├── .github └── workflows │ ├── check_typos.yml │ └── markdown-link-check.yml ├── 3rd_Party_Licenses ├── Amplicon_and_Metagenomics_3rd_Party_Software.md ├── Amplicon_and_Metagenomics_3rd_Party_Software_Licenses │ ├── CAT_LICENSE.pdf │ ├── CheckM_LICENSE.pdf │ ├── DECIPHER_gpl-3.0.pdf │ ├── DESeq2_LICENSE.pdf │ ├── FASTQC_LICENSE.pdf │ ├── GTDBTk_LICENSE.pdf │ ├── HUMAnN_LICENSE.pdf │ ├── KEGGDecoder_LICENSE.pdf │ ├── License_Snakemake_6.7.0_documentation.pdf │ ├── MetaBAT_license.pdf │ ├── MetaPhlAn3_license.pdf │ ├── MultiQC_LICENSE.pdf │ ├── Prodigal_LICENSE.pdf │ ├── R_GPL-2_and_GPL-3_LICENSES.pdf │ ├── The_BIOM_Format_License_biom_format.org.pdf │ ├── VSEARCH_LICENSE.pdf │ ├── bbduk_license.pdf │ ├── bit_LICENSE.pdf │ ├── bowtie2_LICENSE.pdf │ ├── colorbrewer_LICENSE.pdf │ ├── cutadapt_LICENSE.pdf │ ├── dada2_LICENSE.pdf │ ├── dplyr_LICENSE.pdf │ ├── genelab-utils_LICENSE.pdf │ ├── ggrepel_LICENSE.pdf │ ├── kofam_scan_LICENSE.pdf │ ├── kraken2_LICENSE.pdf │ ├── megahit_LICENSE.pdf │ ├── phyloseq_LICENSE.pdf │ ├── samtools_LICENSE.pdf │ ├── tidyverse_LICENSE.pdf │ └── vegan_LICENSE.pdf ├── Methyl-Seq_3rd_Party_Software.md ├── Methyl-Seq_3rd_Party_Software_Licenses │ ├── Bismark_LICENSE.pdf │ ├── FASTQC_LICENSE.pdf │ ├── MethylKit_LICENSE.pdf │ ├── MultiQC_LICENSE.pdf │ ├── Nextflow_LICENSE.pdf │ ├── Qualimap_LICENSE.pdf │ ├── TrimGalore_LICENSE.pdf │ ├── bowtie2_LICENSE.pdf │ ├── cutadapt_LICENSE.pdf │ ├── genomation_LICENSE.pdf │ ├── hisat2_LICENSE.pdf │ ├── samtools_LICENSE.pdf │ └── tidyverse_LICENSE.pdf ├── Microarray_Affymetrix_3rd_Party_Software.md ├── Microarray_Affymetrix_3rd_Party_Software_Licenses │ ├── DT_LICENSE.pdf │ ├── Nextflow_LICENSE.pdf │ ├── PANDAS_LICENSE.pdf │ ├── PYTHON_LICENSE.pdf │ ├── Quarto_LICENSE.pdf │ ├── R-utils_LICENSE.pdf │ ├── R_GPL-2_and_GPL-3_LICENSES.pdf │ ├── Singularity_LICENSE.pdf │ ├── biomaRt_LICENSE.pdf │ ├── dp_tools_LICENSE.pdf │ ├── dplyr_LICENSE.pdf │ ├── glue_LICENSE.pdf │ ├── limma_LICENSE.pdf │ ├── matrixStats_LICENSE.pdf │ ├── oligo_LICENSE.pdf │ ├── statmod_LICENSE.pdf │ ├── stringr_LICENSE.pdf │ └── tibble_LICENSE.pdf ├── Microarray_Agilent_1_Channel_3rd_Party_Software.md ├── Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses │ ├── DT_LICENSE.pdf │ ├── Nextflow_LICENSE.pdf │ ├── PANDAS_LICENSE.pdf │ ├── PYTHON_LICENSE.pdf │ ├── Quarto_LICENSE.pdf │ ├── R-utils_LICENSE.pdf │ ├── R_GPL-2_and_GPL-3_LICENSES.pdf │ ├── Singularity_LICENSE.pdf │ ├── biomaRt_LICENSE.pdf │ ├── dp_tools_LICENSE.pdf │ ├── dplyr_LICENSE.pdf │ ├── ggplot2_LICENSE.pdf │ ├── glue_LICENSE.pdf │ ├── limma_LICENSE.pdf │ ├── matrixStats_LICENSE.pdf │ ├── statmod_LICENSE.pdf │ └── stringr_LICENSE.pdf ├── RNAseq_3rd_Party_Software.md └── RNAseq_3rd_Party_Software_Licenses │ ├── DESeq2_LICENSE.pdf │ ├── FASTQC_LICENSE.pdf │ ├── LOGURU_LICENSE.pdf │ ├── MATPLOTLIB_LICENSE.pdf │ ├── MultiQC_LICENSE.pdf │ ├── NUMPY_LICENSE.pdf │ ├── Nextflow_LICENSE.pdf │ ├── PANDAS_LICENSE.pdf │ ├── PANDERA_LICENSE.pdf │ ├── PYTHON_LICENSE.pdf │ ├── RSEM_LICENSE.pdf │ ├── RSeQC_LICENSE.pdf │ ├── R_GPL-2_and_GPL-3_LICENSES.pdf │ ├── SCIPY_LICENSE.pdf │ ├── SEABORN_LICENSE.pdf │ ├── STAR_LICENSE.pdf │ ├── Singularity_LICENSE.pdf │ ├── TrimGalore_LICENSE.pdf │ ├── cutadapt_LICENSE.pdf │ ├── dp_tools_LICENSE.pdf │ ├── genePredToBed_LICENSE.pdf │ ├── gtfToGenePred_LICENSE.pdf │ ├── jupyter_notebook_LICENSE.pdf │ ├── samtools_LICENSE.pdf │ ├── stringr_LICENSE.pdf │ ├── tidyverse_LICENSE.pdf │ └── tximport_LICENSE.pdf ├── Amplicon ├── 454-and-IonTorrent │ ├── Pipeline_GL-DPPD-7106_Versions │ │ └── GL-DPPD-7106.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── README.md │ │ └── SW_Amp454IonTor │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ └── workflow_code │ │ ├── Snakefile │ │ ├── config.yaml │ │ ├── envs │ │ ├── R.yaml │ │ ├── bbmap.yaml │ │ ├── cutadapt.yaml │ │ ├── qc.yaml │ │ └── vsearch.yaml │ │ └── scripts │ │ └── 454-IonTorrent-R-processing.R ├── Illumina │ ├── GLDS_Processing_Scripts │ │ ├── GLDS-126 │ │ │ └── GLDS_version_2 │ │ │ │ ├── 16S-archaeal-full-R-processing.R │ │ │ │ ├── 16S-archaeal-unique-sample-IDs.txt │ │ │ │ ├── 16S-universal-full-R-processing.R │ │ │ │ ├── 16S-universal-unique-sample-IDs.txt │ │ │ │ ├── README.md │ │ │ │ ├── full-command-line-log.sh │ │ │ │ ├── primers.fa │ │ │ │ └── sample-info.tsv │ │ ├── GLDS-146 │ │ │ └── GLDS_version_2 │ │ │ │ ├── README.md │ │ │ │ ├── full-R-processing.R │ │ │ │ ├── full-command-line-log.sh │ │ │ │ ├── primers.fa │ │ │ │ └── unique-sample-IDs.txt │ │ ├── GLDS-191 │ │ │ └── GLDS_version_3 │ │ │ │ ├── README.md │ │ │ │ ├── full-R-processing.R │ │ │ │ ├── full-command-line-log.sh │ │ │ │ ├── primers.fa │ │ │ │ └── unique-sample-IDs.txt │ │ ├── GLDS-200 │ │ │ └── GLDS_version_2 │ │ │ │ ├── 16S-full-R-processing.R │ │ │ │ ├── 16S-unique-sample-IDs.txt │ │ │ │ ├── ITS-full-R-processing.R │ │ │ │ ├── ITS-unique-sample-IDs.txt │ │ │ │ ├── README.md │ │ │ │ ├── full-command-line-log.sh │ │ │ │ ├── primers.fa │ │ │ │ └── sample-info.tsv │ │ └── GLDS-280 │ │ │ └── GLDS_version_2 │ │ │ ├── Snakefile │ │ │ ├── environment.yml │ │ │ ├── full-R-processing.R │ │ │ ├── primers.fa │ │ │ ├── snakemake-run.log │ │ │ └── unique-sample-IDs.txt │ ├── Pipeline_GL-DPPD-7104_Versions │ │ ├── GL-DPPD-7104-A.md │ │ └── GL-DPPD-7104-B.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── README.md │ │ ├── SW_AmpIllumina-A │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ └── workflow_code │ │ │ ├── Snakefile │ │ │ ├── config.yaml │ │ │ ├── config │ │ │ └── multiqc.config │ │ │ ├── envs │ │ │ ├── R.yaml │ │ │ ├── cutadapt.yaml │ │ │ └── qc.yaml │ │ │ └── scripts │ │ │ ├── Illumina-PE-R-processing.R │ │ │ ├── Illumina-SE-R-processing.R │ │ │ ├── combine-benchmarks.sh │ │ │ └── slurm-status.py │ │ └── SW_AmpIllumina-B │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ └── examples │ │ └── runsheet │ │ ├── README.md │ │ ├── paired_end_runsheet │ │ └── GLDS-487_amplicon_v0_runsheet.csv │ │ └── single_end_runsheet │ │ └── single_end_example.csv ├── README.md └── images │ ├── GL-amplicon-overview.pdf │ └── GL-amplicon-overview.png ├── GeneLab_Reference_Annotations ├── Pipeline_GL-DPPD-7110_Versions │ ├── GL-DPPD-7110-A │ │ ├── GL-DPPD-7110-A.md │ │ └── GL-DPPD-7110-A_annotations.csv │ └── GL-DPPD-7110 │ │ ├── GL-DPPD-7110.md │ │ └── GL-DPPD-7110_annotations.csv ├── README.md └── Workflow_Documentation │ ├── GL_RefAnnotTable-A │ ├── CHANGELOG.md │ ├── README.md │ └── workflow_code │ │ ├── GL-DPPD-7110-A_build-genome-annots-tab.R │ │ ├── bin │ │ └── prepull_singularity.sh │ │ ├── config │ │ └── software │ │ │ └── by_docker_image.config │ │ └── install-org-db.R │ ├── GL_RefAnnotTable │ ├── CHANGELOG.md │ ├── README.md │ └── workflow_code │ │ └── GL-DPPD-7110_build-genome-annots-tab.R │ └── README.md ├── Licenses ├── Amplicon_and_Metagenomics_NOSA_License.pdf ├── Methylation_Sequencing_NOSA_License.pdf ├── Microarray_GPL-3.0_with_Additional_Requirements_License.pdf └── RNA_Sequencing_NOSA_License.pdf ├── Metagenomics ├── Estimate_host_reads_in_raw_data │ ├── Pipeline_GL-DPPD-7109_Versions │ │ └── GL-DPPD-7109.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── README.md │ │ └── SW_MGEstHostReads │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ ├── reference-database-info.md │ │ └── workflow_code │ │ ├── Snakefile │ │ ├── config.yaml │ │ ├── envs │ │ └── kraken2.yaml │ │ ├── example-reads │ │ ├── Sample-1_R1.fastq.gz │ │ └── Sample-1_R2.fastq.gz │ │ └── unique-sample-IDs.txt ├── Illumina │ ├── Pipeline_GL-DPPD-7107_Versions │ │ ├── GL-DPPD-7107-A.md │ │ └── GL-DPPD-7107.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── NF_MGIllumina │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ ├── examples │ │ │ └── runsheet │ │ │ │ ├── README.md │ │ │ │ ├── paired_end_dataset │ │ │ │ └── PE_file.csv │ │ │ │ └── single_end_dataset │ │ │ │ └── SE_file.csv │ │ └── workflow_code │ │ │ ├── bin │ │ │ ├── GL-gen-metagenomics-file-associations-table │ │ │ ├── GL-gen-processed-metagenomics-readme │ │ │ ├── GL-validate-processed-metagenomics-data │ │ │ ├── clean-paths.sh │ │ │ ├── combine-all-gene-tables.py │ │ │ ├── combine-gene-level-coverages-annots-and-tax-per-group.py │ │ │ ├── create_runsheet.sh │ │ │ ├── download-GTDBTK-db.sh │ │ │ ├── format-contig-tax-classifications.sh │ │ │ ├── format-gene-tax-classifications.sh │ │ │ ├── generate-assembly-based-overview-table.sh │ │ │ ├── generate_protocol.sh │ │ │ ├── get_MAGs_estimates_and_taxonomy.sh │ │ │ ├── parse-MAG-annots.py │ │ │ ├── prepull_singularity.sh │ │ │ └── swap-MAG-IDs.py │ │ │ ├── config │ │ │ ├── bbtools_adapters.fa │ │ │ └── multiqc.config │ │ │ ├── envs │ │ │ ├── bit.yaml │ │ │ ├── cat.yaml │ │ │ ├── checkm.yaml │ │ │ ├── genelab.yaml │ │ │ ├── gtdb-tk.yaml │ │ │ ├── humann3.yaml │ │ │ ├── image_def.bit │ │ │ ├── image_def.genelab │ │ │ ├── keggdecoder.yaml │ │ │ ├── kofamscan.yaml │ │ │ ├── mapping.yaml │ │ │ ├── megahit.yaml │ │ │ ├── metabat.yaml │ │ │ ├── prodigal.yaml │ │ │ └── qc.yaml │ │ │ ├── launch.sh │ │ │ ├── launch.slurm │ │ │ ├── main.nf │ │ │ ├── modules │ │ │ ├── assembly.nf │ │ │ ├── assembly_annotation.nf │ │ │ ├── assembly_based_processing.nf │ │ │ ├── binning.nf │ │ │ ├── combine_contig_annotation.nf │ │ │ ├── coverage.nf │ │ │ ├── create_runsheet.nf │ │ │ ├── database_creation.nf │ │ │ ├── genelab.nf │ │ │ ├── quality_assessment.nf │ │ │ ├── read_based_processing.nf │ │ │ ├── read_mapping.nf │ │ │ ├── summarize_MAG.nf │ │ │ ├── summarize_assembly-based_processing.nf │ │ │ ├── summarize_bins.nf │ │ │ └── zip_fasta.nf │ │ │ ├── nextflow.config │ │ │ ├── post_processing.config │ │ │ ├── post_processing.nf │ │ │ └── slurm_submit.slurm │ │ ├── README.md │ │ └── SW_MGIllumina │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ └── workflow_code │ │ ├── Snakefile │ │ ├── config.yaml │ │ ├── config │ │ └── multiqc.config │ │ ├── envs │ │ ├── bit.yaml │ │ ├── cat.yaml │ │ ├── checkm.yaml │ │ ├── gtdb-tk.yaml │ │ ├── humann3.yaml │ │ ├── keggdecoder.yaml │ │ ├── kofamscan.yaml │ │ ├── mapping.yaml │ │ ├── megahit.yaml │ │ ├── metabat.yaml │ │ ├── prodigal.yaml │ │ └── qc.yaml │ │ └── scripts │ │ ├── combine-all-gene-tables.py │ │ ├── combine-benchmarks.sh │ │ ├── combine-gene-level-coverages-annots-and-tax-per-group.py │ │ ├── format-contig-tax-classifications.sh │ │ ├── format-gene-tax-classifications.sh │ │ ├── generate-assembly-based-overview-table.sh │ │ ├── parse-MAG-annots.py │ │ ├── slurm-status.py │ │ └── swap-MAG-IDs.py ├── README.md ├── Remove_human_reads_from_raw_data │ ├── Pipeline_GL-DPPD-7105_Versions │ │ ├── GL-DPPD-7105-A.md │ │ └── GL-DPPD-7105.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── README.md │ │ └── SW_MGRemoveHumanReads-A │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ ├── reference-database-info.md │ │ └── workflow_code │ │ ├── Snakefile │ │ ├── config.yaml │ │ ├── envs │ │ └── kraken2.yaml │ │ ├── example-reads │ │ ├── Sample-1_R1.fastq.gz │ │ └── Sample-1_R2.fastq.gz │ │ └── unique-sample-IDs.txt └── images │ ├── GL-Illumina-metagenomics-overview.pdf │ ├── GL-Illumina-metagenomics-overview.png │ ├── config-ex.png │ └── gitzip-ex.png ├── Methyl-Seq ├── Pipeline_GL-DPPD-7113_Versions │ ├── GL-DPPD-7113.md │ └── images │ │ ├── GL-bisulfite-seq-overview.pdf │ │ └── GL-bisulfite-seq-overview.png ├── README.md ├── Workflow_Documentation │ ├── README.md │ ├── isa_to_runsheet_plugins │ │ ├── dp_tools__methylseq_dna │ │ │ ├── __init__.py │ │ │ ├── checks.py │ │ │ ├── methylSeqDNA_v2.yaml │ │ │ ├── protocol.py │ │ │ └── schemas.py │ │ └── dp_tools__methylseq_rna │ │ │ ├── __init__.py │ │ │ ├── checks.py │ │ │ ├── methylSeqRNA_v1.yaml │ │ │ ├── protocol.py │ │ │ └── schemas.py │ └── runsheet_specification │ │ ├── README.md │ │ ├── paired_end_runsheet │ │ └── OSD-47_methylSeq_v2_runsheet.csv │ │ └── single_end_runsheet │ │ └── OSD-397_methylSeq_v2_runsheet.csv └── images │ ├── GL-methyl-seq-overview.pdf │ └── GL-methyl-seq-overview.png ├── Microarray ├── Affymetrix │ ├── Pipeline_GL-DPPD-7114_Versions │ │ └── GL-DPPD-7114.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── NF_MAAffymetrix │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ └── workflow_code │ │ │ ├── bin │ │ │ ├── Affymetrix.qmd │ │ │ ├── dp_tools__affymetrix │ │ │ │ ├── __init__.py │ │ │ │ ├── checks.py │ │ │ │ ├── config.yaml │ │ │ │ ├── protocol.py │ │ │ │ └── schemas.py │ │ │ ├── generate_md5sum_files.py │ │ │ └── update_curation_table.py │ │ │ ├── config │ │ │ ├── default.config │ │ │ ├── executor │ │ │ │ └── default_slurm.config │ │ │ └── software │ │ │ │ └── by_docker_image.config │ │ │ ├── main.nf │ │ │ ├── modules │ │ │ ├── DUMP_META │ │ │ │ ├── main.nf │ │ │ │ └── resources │ │ │ │ │ └── usr │ │ │ │ │ └── bin │ │ │ │ │ └── reformat_meta.sh │ │ │ ├── GENERATE_MD5SUMS.nf │ │ │ ├── GENERATE_SOFTWARE_TABLE │ │ │ │ ├── main.nf │ │ │ │ └── resources │ │ │ │ │ └── usr │ │ │ │ │ └── bin │ │ │ │ │ └── SoftwareYamlToMarkdownTable.py │ │ │ ├── PARSE_ANNOTATION_TABLE.nf │ │ │ ├── POST_PROCESSING │ │ │ │ └── GENERATE_PROTOCOL │ │ │ │ │ ├── main.nf │ │ │ │ │ └── resources │ │ │ │ │ └── usr │ │ │ │ │ └── bin │ │ │ │ │ └── generate_protocol.sh │ │ │ ├── PROCESS_AFFYMETRIX.nf │ │ │ ├── RUNSHEET_FROM_GLDS.nf │ │ │ ├── RUNSHEET_FROM_ISA.nf │ │ │ ├── UPDATE_ISA_TABLES.nf │ │ │ └── VV_AFFYMETRIX.nf │ │ │ ├── nextflow.config │ │ │ ├── nf-test.config │ │ │ ├── post_processing.nf │ │ │ └── tests │ │ │ ├── assets │ │ │ └── CLEANED_GLDS-428_metadata_GLDS-428-ISA.zip │ │ │ ├── main.GLDS205.nf.test │ │ │ ├── main.GLDS205.nf.test.snap │ │ │ ├── main.GLDS208.nf.test │ │ │ ├── main.GLDS208.nf.test.snap │ │ │ ├── main.GLDS213.nf.test │ │ │ ├── main.GLDS213.nf.test.snap │ │ │ ├── main.GLDS266.nf.test │ │ │ ├── main.GLDS266.nf.test.snap │ │ │ ├── main.GLDS282.nf.test │ │ │ ├── main.GLDS282.nf.test.snap │ │ │ ├── main.GLDS296.nf.test │ │ │ ├── main.GLDS296.nf.test.snap │ │ │ ├── main.GLDS428.nf.test │ │ │ ├── main.GLDS428.nf.test.snap │ │ │ ├── main.GLDS546.nf.test │ │ │ ├── main.GLDS546.nf.test.snap │ │ │ ├── main.GLDS547.nf.test │ │ │ ├── main.GLDS547.nf.test.snap │ │ │ └── nextflow.config │ │ └── README.md ├── Agilent_1-channel │ ├── Pipeline_GL-DPPD-7112_Versions │ │ └── GL-DPPD-7112.md │ ├── README.md │ └── Workflow_Documentation │ │ ├── NF_MAAgilent1ch │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ ├── examples │ │ │ └── runsheet │ │ │ │ ├── GLDS-367_microarray_v0_runsheet.csv │ │ │ │ ├── OSD-548_microarray_v0_runsheet.csv │ │ │ │ └── README.md │ │ └── workflow_code │ │ │ ├── bin │ │ │ ├── Agile1CMP.qmd │ │ │ ├── VV_data_assets.py │ │ │ ├── dp_tools__agilent_1_channel │ │ │ │ ├── __init__.py │ │ │ │ ├── checks.py │ │ │ │ ├── config.yaml │ │ │ │ ├── protocol.py │ │ │ │ └── schemas.py │ │ │ ├── generate_md5sum_files.py │ │ │ └── update_curation_table.py │ │ │ ├── config │ │ │ ├── default.config │ │ │ ├── executor │ │ │ │ └── default_slurm.config │ │ │ └── software │ │ │ │ └── by_docker_image.config │ │ │ ├── main.nf │ │ │ ├── modules │ │ │ ├── AGILE1CH.nf │ │ │ ├── GENERATE_MD5SUMS.nf │ │ │ ├── GENERATE_SOFTWARE_TABLE │ │ │ │ ├── main.nf │ │ │ │ └── resources │ │ │ │ │ └── usr │ │ │ │ │ └── bin │ │ │ │ │ └── SoftwareYamlToMarkdownTable.py │ │ │ ├── PARSE_ANNOTATION_TABLE.nf │ │ │ ├── POST_PROCESSING │ │ │ │ └── GENERATE_PROTOCOL │ │ │ │ │ ├── main.nf │ │ │ │ │ └── resources │ │ │ │ │ └── usr │ │ │ │ │ └── bin │ │ │ │ │ └── generate_protocol.sh │ │ │ ├── RUNSHEET_FROM_GLDS.nf │ │ │ ├── UPDATE_ISA_TABLES.nf │ │ │ └── VV_AGILE1CH.nf │ │ │ ├── nextflow.config │ │ │ ├── nf-test.config │ │ │ ├── post_processing.nf │ │ │ └── tests │ │ │ ├── main.GLDS22.nf.test │ │ │ ├── main.GLDS22.nf.test.snap │ │ │ ├── main.GLDS271.nf.test │ │ │ ├── main.GLDS271.nf.test.snap │ │ │ ├── main.GLDS367.nf.test │ │ │ ├── main.GLDS367.nf.test.snap │ │ │ ├── main.GLDS425.nf.test │ │ │ ├── main.GLDS425.nf.test.snap │ │ │ ├── main.GLDS542.nf.test │ │ │ ├── main.GLDS542.nf.test.snap │ │ │ ├── main.GLDS548.nf.test │ │ │ ├── main.GLDS548.nf.test.snap │ │ │ ├── main.POSTPROCESSING.GLDS542.nf.test │ │ │ ├── modules │ │ │ ├── AGILE1CH.nf.test │ │ │ ├── AGILE1CH.nf.test.snap │ │ │ ├── PARSE_ANNOTATION_TABLE.nf.test │ │ │ ├── PARSE_ANNOTATION_TABLE.nf.test.snap │ │ │ ├── RUNSHEET_FROM_GLDS.nf.test │ │ │ ├── RUNSHEET_FROM_GLDS.nf.test.snap │ │ │ ├── VV_AGILE1CH.nf.test │ │ │ └── VV_AGILE1CH.nf.test.snap │ │ │ └── nextflow.config │ │ └── README.md ├── README.md └── images │ ├── GL-affymetrix-overview.pdf │ ├── GL-affymetrix-overview.png │ ├── GL-agilent_1channel-overview.pdf │ ├── GL-agilent_1channel-overview.png │ ├── GL-microarray-overview.pdf │ └── GL-microarray-overview.png ├── README.md ├── RNAseq ├── GLDS_Processing_Scripts │ ├── GLDS-101 │ │ └── GLDS_version_2 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ └── raw_multiqc.slurm │ │ │ ├── 01-TG_Preproc │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ └── make_Mmus_RL-100_STAR_index.slurm │ │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_RSEM_index.slurm │ │ │ └── rsem_count.slurm │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-101_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ │ ├── README.md │ │ │ └── samples.txt │ ├── GLDS-102 │ │ └── GLDS_version_2 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ └── raw_multiqc.slurm │ │ │ ├── 01-TG_Preproc │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ └── make_Mmus_RL-100_STAR_index.slurm │ │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_RSEM_index.slurm │ │ │ └── rsem_count.slurm │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-102_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ │ ├── README.md │ │ │ └── samples.txt │ ├── GLDS-104 │ │ └── GLDS_version_2 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ └── raw_multiqc.slurm │ │ │ ├── 01-TG_Preproc │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ └── make_Mmus_RL-100_STAR_index.slurm │ │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_RSEM_index.slurm │ │ │ └── rsem_count.slurm │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-104_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ │ ├── README.md │ │ │ └── samples.txt │ ├── GLDS-120 │ │ ├── OSD_version_14 │ │ │ ├── 03-RSEM_Counts │ │ │ │ ├── rsem_count.slurm │ │ │ │ └── samples.txt │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ │ └── organisms.csv │ │ │ ├── Metadata │ │ │ │ └── GLDS-120_metadata.csv │ │ │ ├── README.md │ │ │ └── RSeQC_analyses │ │ │ │ └── 03_infer_experiment │ │ │ │ ├── infer_exp.slurm │ │ │ │ ├── infer_exp_multiqc.slurm │ │ │ │ └── samples.txt │ │ ├── OSD_version_17 │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_runsheet.R │ │ │ │ └── deseq2_normcounts_noERCC_DGE_vis_runsheet.slurm │ │ │ ├── Metadata │ │ │ │ ├── GLDS-120_bulkRNASeq_v1_runsheet.csv │ │ │ │ └── generate_runsheet.slurm │ │ │ └── README.md │ │ └── OSD_versions_2-4 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Athaliana_RL-75_STAR_index.slurm │ │ │ └── samples.txt │ │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Athaliana_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-120_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ │ └── README.md │ ├── GLDS-137 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_RL-150_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-137_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-138 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Bsub168_RL-90_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Bsubtilis-168_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── Create_annot_pkg_with_makeOrgPackageFromNCBI.R │ │ │ ├── GLDS-138_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ ├── org.Bsubtilis.eg.db.tar.gz │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-168 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_w_ERCC_RL-150_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_w_ERCC_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-168_metadata.csv │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-173 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_w_ERCC_RL-150_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_w_ERCC_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-173_metadata.csv │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-208 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Athaliana_RL-150_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Athaliana_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_ISA.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_ISA.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-218 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Athaliana_RL-100_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Athaliana_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-218_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-235 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_w_ERCC_RL-149_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_w_ERCC_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-235_metadata.csv │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-236 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_w_ERCC_RL-149_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_w_ERCC_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-236_metadata.csv │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-245 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_w_ERCC_RL-149_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_w_ERCC_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis_ISA.R │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis_ISA.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-251 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Athaliana_RL-125_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Athaliana_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-251_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-272 │ │ └── README.md │ ├── GLDS-314 │ │ └── GLDS_version_4 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc_GL.slurm │ │ │ ├── raw_multiqc_GL.slurm │ │ │ └── samples.txt │ │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── STAR_counts_table.R │ │ │ ├── STAR_counts_table.slurm │ │ │ ├── align_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 03-RSEM_Counts │ │ │ ├── Quantitate_non-zero_genes_per_sample.R │ │ │ ├── Quantitate_non-zero_genes_per_sample.slurm │ │ │ ├── count_multiqc.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_ISA.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_ISA.slurm │ │ │ └── organisms.csv │ │ │ ├── README.md │ │ │ └── RSeQC_analyses │ │ │ ├── 01_sort_index │ │ │ ├── samples.txt │ │ │ ├── samtools_index.slurm │ │ │ └── samtools_sort.slurm │ │ │ ├── 02_geneBody_coverage │ │ │ ├── genebody_cov.slurm │ │ │ ├── genebody_cov_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 03_infer_experiment │ │ │ ├── infer_exp.slurm │ │ │ ├── infer_exp_multiqc.slurm │ │ │ └── samples.txt │ │ │ └── 05_read_distribution │ │ │ ├── read_dist.slurm │ │ │ ├── read_dist_multiqc.slurm │ │ │ └── samples.txt │ ├── GLDS-37 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Athaliana_RL-100_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Athaliana_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-37_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-379 │ │ └── GLDS_version_3 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.sh │ │ │ └── samples.txt │ │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── STAR_counts_table.R │ │ │ ├── STAR_counts_table.slurm │ │ │ ├── align_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 03-RSEM_Counts │ │ │ ├── Quantitate_non-zero_genes_per_sample.R │ │ │ ├── Quantitate_non-zero_genes_per_sample.slurm │ │ │ ├── count_multiqc.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── deseq2_normcounts_wERCC_DGE_vis_ISA.R │ │ │ └── deseq2_normcounts_wERCC_DGE_vis_ISA.slurm │ │ │ ├── ERCC_Analysis │ │ │ └── GLDS-379_LVR_ERCC_analysis.ipynb │ │ │ ├── README.md │ │ │ └── RSeQC_analyses │ │ │ ├── 01_sort_index │ │ │ ├── samples.txt │ │ │ ├── samtools_index.slurm │ │ │ └── samtools_sort.slurm │ │ │ ├── 02_geneBody_coverage │ │ │ ├── genebody_cov.slurm │ │ │ ├── genebody_cov_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 03_infer_experiment │ │ │ ├── infer_exp.slurm │ │ │ ├── infer_exp_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 04_inner_distance │ │ │ ├── inner_distance.slurm │ │ │ ├── inner_distance_multiqc.slurm │ │ │ └── samples.txt │ │ │ └── 05_read_distribution │ │ │ ├── read_dist.slurm │ │ │ ├── read_dist_multiqc.slurm │ │ │ └── samples.txt │ ├── GLDS-38 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Athaliana_RL-100_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Athaliana_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-38_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-401 │ │ └── GLDS_version_2 │ │ │ ├── 00-RawData │ │ │ ├── raw_fastqc_GL.slurm │ │ │ ├── raw_multiqc_GL.slurm │ │ │ └── samples.txt │ │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── STAR_counts_table.R │ │ │ ├── STAR_counts_table.slurm │ │ │ ├── align_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 03-RSEM_Counts │ │ │ ├── Quantitate_non-zero_genes_per_sample.R │ │ │ ├── Quantitate_non-zero_genes_per_sample.slurm │ │ │ ├── count_multiqc.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_ISA.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis_ISA.slurm │ │ │ └── organisms.csv │ │ │ ├── README.md │ │ │ └── RSeQC_analyses │ │ │ ├── 01_sort_index │ │ │ ├── samples.txt │ │ │ ├── samtools_index.slurm │ │ │ └── samtools_sort.slurm │ │ │ ├── 02_geneBody_coverage │ │ │ ├── genebody_cov.slurm │ │ │ ├── genebody_cov_multiqc.slurm │ │ │ └── samples.txt │ │ │ ├── 03_infer_experiment │ │ │ ├── infer_exp.slurm │ │ │ ├── infer_exp_multiqc.slurm │ │ │ └── samples.txt │ │ │ └── 05_read_distribution │ │ │ ├── read_dist.slurm │ │ │ ├── read_dist_multiqc.slurm │ │ │ └── samples.txt │ ├── GLDS-47 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_RL-50_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-47_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ ├── GLDS-48 │ │ ├── 00-RawData │ │ │ ├── raw_fastqc.slurm │ │ │ ├── raw_multiqc.slurm │ │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ │ ├── samples.txt │ │ │ ├── trim-galore.slurm │ │ │ ├── trimmed_fastqc.slurm │ │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ │ ├── STAR_align.slurm │ │ │ ├── make_Mmus_RL-50_STAR_index.slurm │ │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ │ ├── make_Mmus_RSEM_index.slurm │ │ │ ├── rsem_count.slurm │ │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ │ ├── GLDS-48_metadata.csv │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ │ └── organisms.csv │ │ └── README.md │ └── GLDS-49 │ │ ├── 00-RawData │ │ ├── raw_fastqc.slurm │ │ ├── raw_multiqc.slurm │ │ └── samples.txt │ │ ├── 01-TG_Preproc │ │ ├── samples.txt │ │ ├── trim-galore.slurm │ │ ├── trimmed_fastqc.slurm │ │ └── trimmed_multiqc.slurm │ │ ├── 02-STAR_Alignment │ │ ├── STAR_align.slurm │ │ ├── make_Mmus_RL-50_STAR_index.slurm │ │ └── samples.txt │ │ ├── 03-RSEM_Counts │ │ ├── make_Mmus_RSEM_index.slurm │ │ ├── rsem_count.slurm │ │ └── samples.txt │ │ ├── 04-05-DESeq2_NormCounts_DGE │ │ ├── GLDS-49_metadata.csv │ │ ├── deseq2_normcounts_noERCC_DGE_vis.R │ │ ├── deseq2_normcounts_noERCC_DGE_vis.slurm │ │ └── organisms.csv │ │ └── README.md ├── GeneLab_Reference_and_Annotation_Files │ ├── GL-DPPD-7101-E_ensembl_refs.csv │ └── GLDS_RNAseq_processed_10-2019_to_10-2020.csv ├── Pipeline_GL-DPPD-7101_Versions │ ├── GL-DPPD-7101-A.md │ ├── GL-DPPD-7101-B.md │ ├── GL-DPPD-7101-C.md │ ├── GL-DPPD-7101-D.md │ ├── GL-DPPD-7101-E.md │ └── GL-DPPD-7101-F.md ├── README.md ├── RNAseq_Tool_Install │ ├── GL_RNAseq_mkdir.sh │ ├── GL_genome_index_mkdir.sh │ ├── README.md │ ├── RNAseq_R_tools.yml │ └── RNAseq_fq_to_counts_tools.yml ├── Workflow_Documentation │ ├── NF_RCP-F │ │ ├── CHANGELOG.md │ │ ├── README.md │ │ ├── examples │ │ │ └── runsheet │ │ │ │ ├── README.md │ │ │ │ ├── paired_end_runsheet │ │ │ │ └── GLDS-194_bulkRNASeq_v1.csv │ │ │ │ └── single_end_runsheet │ │ │ │ └── GLDS-48_bulkRNASeq_v1.csv │ │ └── workflow_code │ │ │ ├── assets │ │ │ ├── README.md │ │ │ └── organisms.csv │ │ │ ├── bin │ │ │ ├── Quantitate_non-zero_genes_per_sample.R │ │ │ ├── Quantitate_non-zero_genes_per_sample_STAR.R │ │ │ ├── VV_data_assets.py │ │ │ ├── assess_strandedness.py │ │ │ ├── combined_ercc_analysis.ipynb │ │ │ ├── concat_logs.py │ │ │ ├── create_table_v2.py │ │ │ ├── dge_annotation_R_scripts.zip │ │ │ ├── dge_annotation_R_scripts │ │ │ │ ├── Add_Gene_Annotations.Rmd │ │ │ │ ├── Extend_DGE_Table.Rmd │ │ │ │ ├── Generate_PCA_Table.Rmd │ │ │ │ ├── Perform_DGE.Rmd │ │ │ │ └── dge_annotation_workflow.R │ │ │ ├── dp_tools__NF_RCP │ │ │ │ ├── __init__.py │ │ │ │ ├── checks.py │ │ │ │ ├── config.yaml │ │ │ │ ├── protocol.py │ │ │ │ └── schemas.py │ │ │ ├── filter_to_only_issues.py │ │ │ ├── format_software_versions.py │ │ │ ├── generate_md5sum_files.py │ │ │ ├── generate_publish_to_repo_excel.py │ │ │ ├── get_max_readlength_from_fastqc.py │ │ │ ├── prepull_singularity.sh │ │ │ ├── retrieve_references.py │ │ │ ├── sort_into_subdirectories_by_sample.py │ │ │ └── update_curation_table.py │ │ │ ├── config │ │ │ ├── default.config │ │ │ ├── executor │ │ │ │ ├── cos-hpc-1-node-local.config │ │ │ │ ├── cos-hpc-4-node.config │ │ │ │ ├── default_CI_test.config │ │ │ │ ├── default_local.config │ │ │ │ └── default_slurm.config │ │ │ ├── modules │ │ │ │ └── multiqc.config │ │ │ ├── software │ │ │ │ └── by_docker_image.config │ │ │ └── tests │ │ │ │ ├── test_glds194.config │ │ │ │ ├── test_glds207.config │ │ │ │ ├── test_glds251.config │ │ │ │ ├── test_glds48.config │ │ │ │ ├── test_glds91.config │ │ │ │ └── test_nonGLDS.config │ │ │ ├── main.nf │ │ │ ├── modules │ │ │ ├── DGE_BY_DESEQ2 │ │ │ │ └── main.nf │ │ │ ├── RUNSHEET_FROM_GLDS.nf │ │ │ ├── download.nf │ │ │ ├── fastqc.nf │ │ │ ├── genelab.nf │ │ │ ├── genome.nf │ │ │ ├── quality.nf │ │ │ ├── rseqc.nf │ │ │ └── vv.nf │ │ │ ├── nextflow.config │ │ │ ├── nf-test.config │ │ │ ├── references.nf │ │ │ ├── stage_analysis.nf │ │ │ ├── strandedness.nf │ │ │ ├── test_assets │ │ │ └── CustomAnalysis_bulkRNASeq_v1_runsheet.csv │ │ │ └── tests │ │ │ ├── config │ │ │ └── nftest_modules.yml │ │ │ ├── main.nf.GLDS194.test │ │ │ ├── main.nf.GLDS194.test.snap │ │ │ ├── main.nf.GLDS207.test │ │ │ ├── main.nf.GLDS207.test.snap │ │ │ ├── main.nf.GLDS251.test │ │ │ ├── main.nf.GLDS321.test │ │ │ ├── main.nf.GLDS321.test.snap │ │ │ ├── main.nf.GLDS373.test │ │ │ ├── main.nf.GLDS48.test │ │ │ ├── main.nf.GLDS48.test.snap │ │ │ ├── main.nf.GLDS480.test │ │ │ ├── modules │ │ │ ├── DGE_BY_DESEQ2 │ │ │ │ ├── DGE_BY_DESEQ2.nf.test │ │ │ │ └── DGE_BY_DESEQ2.nf.test.snap │ │ │ ├── genome.quantify_rsem_genes.nf.test │ │ │ ├── genome.quantify_rsem_genes.nf.test.snap │ │ │ ├── genome.quantify_star_genes.nf.test │ │ │ └── genome.quantify_star_genes.nf.test.snap │ │ │ └── nextflow.config │ └── README.md ├── images │ ├── NF_RCP-F_gitzip_rnaseq.png │ ├── NF_RCP-F_rnaseq_workflow.png │ └── RNAseq_pipeline_diagram.png └── organisms.csv ├── Raw_Data_Generation ├── README.md └── UPX_kit_for_bulk_RNAseq │ ├── Pipeline_GL-DPPD-7108_Versions │ └── GL-DPPD-7108.md │ └── README.md ├── images └── NASA_GeneLab_logo-2019.png └── scRNAseq ├── 10X_Chromium_3prime_Data ├── GeneLab_CellType_GeneMarkers │ ├── GL-DPPD-7111_GeneMarker_Files │ │ ├── GL-DPPD-7111_Mmus_Blood_CellType_GeneMarkers.csv │ │ ├── GL-DPPD-7111_Mmus_BoneMarrow_CellType_GeneMarkers.csv │ │ ├── GL-DPPD-7111_Mmus_Brain_CellType_GeneMarkers.csv │ │ ├── GL-DPPD-7111_Mmus_Heart_CellType_GeneMarkers.csv │ │ ├── GL-DPPD-7111_Mmus_Liver_CellType_GeneMarkers.csv │ │ └── GL-DPPD-7111_Mmus_Spleen_CellType_GeneMarkers.csv │ └── GL-DPPD-7111_GeneMarker_Info.csv ├── Pipeline_GL-DPPD-7111_Versions │ └── GL-DPPD-7111.md ├── README.md └── scRNAseq_Tool_Install │ ├── GL_scRNAseq_mkdir.sh │ ├── README.md │ └── scRNAseq_yaml_files │ ├── fastqc.yml │ ├── multiqc.yml │ └── star.yml ├── README.md └── images └── scRNAseq_pipeline_diagram.png /.github/workflows/check_typos.yml: -------------------------------------------------------------------------------- 1 | on: 2 | push: 3 | branches: 4 | - master 5 | pull_request: 6 | branches: 7 | - master 8 | 9 | name: Check typos 10 | jobs: 11 | codespell: 12 | name: Discover typos with codespell 13 | runs-on: ubuntu-latest 14 | strategy: 15 | fail-fast: false 16 | steps: 17 | - uses: actions/checkout@v3 18 | - uses: codespell-project/actions-codespell@master 19 | with: 20 | check_filenames: true 21 | skip: "*.yml,*.cff,*.js,*.lock" 22 | ignore_words_list: RNAseq 23 | -------------------------------------------------------------------------------- /.github/workflows/markdown-link-check.yml: -------------------------------------------------------------------------------- 1 | name: Check Markdown links 2 | 3 | on: push 4 | 5 | jobs: 6 | markdown-link-check: 7 | runs-on: ubuntu-latest 8 | steps: 9 | - uses: actions/checkout@master 10 | - uses: gaurav-nelson/github-action-markdown-link-check@v1 11 | -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/CAT_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/CAT_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/CheckM_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/CheckM_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/DECIPHER_gpl-3.0.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/DECIPHER_gpl-3.0.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/DESeq2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/DESeq2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/FASTQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/FASTQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/GTDBTk_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/GTDBTk_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/HUMAnN_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/HUMAnN_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/KEGGDecoder_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/KEGGDecoder_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/License_Snakemake_6.7.0_documentation.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/License_Snakemake_6.7.0_documentation.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/MetaBAT_license.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/MetaBAT_license.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/MetaPhlAn3_license.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/MetaPhlAn3_license.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/MultiQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/MultiQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/Prodigal_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/Prodigal_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/The_BIOM_Format_License_biom_format.org.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/The_BIOM_Format_License_biom_format.org.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/VSEARCH_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/VSEARCH_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/bbduk_license.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/bbduk_license.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/bit_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/bit_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/bowtie2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/bowtie2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/colorbrewer_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/colorbrewer_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/cutadapt_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/cutadapt_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/dada2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/dada2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/dplyr_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/dplyr_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/genelab-utils_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/genelab-utils_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/ggrepel_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/ggrepel_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/kofam_scan_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/kofam_scan_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/kraken2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/kraken2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/megahit_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/megahit_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/phyloseq_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/phyloseq_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/samtools_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/samtools_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/tidyverse_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/tidyverse_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/vegan_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Amplicon_and_Metagenomics_3rd_Party_Software_Licenses/vegan_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/Bismark_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/Bismark_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/FASTQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/FASTQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/MethylKit_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/MethylKit_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/MultiQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/MultiQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/Qualimap_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/Qualimap_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/TrimGalore_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/TrimGalore_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/bowtie2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/bowtie2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/cutadapt_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/cutadapt_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/genomation_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/genomation_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/hisat2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/hisat2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/samtools_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/samtools_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/tidyverse_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Methyl-Seq_3rd_Party_Software_Licenses/tidyverse_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/DT_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/DT_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/PANDAS_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/PANDAS_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/PYTHON_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/PYTHON_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/Quarto_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/Quarto_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/R-utils_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/R-utils_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/Singularity_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/Singularity_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/biomaRt_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/biomaRt_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/dp_tools_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/dp_tools_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/dplyr_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/dplyr_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/glue_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/glue_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/limma_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/limma_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/matrixStats_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/matrixStats_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/oligo_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/oligo_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/statmod_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/statmod_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/stringr_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/stringr_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/tibble_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Affymetrix_3rd_Party_Software_Licenses/tibble_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/DT_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/DT_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/PANDAS_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/PANDAS_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/PYTHON_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/PYTHON_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/Quarto_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/Quarto_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/R-utils_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/R-utils_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/Singularity_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/Singularity_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/biomaRt_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/biomaRt_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/dp_tools_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/dp_tools_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/dplyr_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/dplyr_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/ggplot2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/ggplot2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/glue_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/glue_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/limma_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/limma_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/matrixStats_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/matrixStats_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/statmod_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/statmod_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/stringr_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/Microarray_Agilent_1_Channel_3rd_Party_Software_Licenses/stringr_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/DESeq2_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/DESeq2_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/FASTQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/FASTQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/LOGURU_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/LOGURU_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/MATPLOTLIB_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/MATPLOTLIB_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/MultiQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/MultiQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/NUMPY_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/NUMPY_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/Nextflow_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/PANDAS_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/PANDAS_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/PANDERA_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/PANDERA_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/PYTHON_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/PYTHON_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/RSEM_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/RSEM_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/RSeQC_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/RSeQC_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/R_GPL-2_and_GPL-3_LICENSES.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/SCIPY_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/SCIPY_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/SEABORN_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/SEABORN_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/STAR_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/STAR_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/Singularity_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/Singularity_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/TrimGalore_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/TrimGalore_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/cutadapt_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/cutadapt_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/dp_tools_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/dp_tools_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/genePredToBed_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/genePredToBed_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/gtfToGenePred_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/gtfToGenePred_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/jupyter_notebook_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/jupyter_notebook_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/samtools_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/samtools_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/stringr_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/stringr_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/tidyverse_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/tidyverse_LICENSE.pdf -------------------------------------------------------------------------------- /3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/tximport_LICENSE.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/3rd_Party_Licenses/RNAseq_3rd_Party_Software_Licenses/tximport_LICENSE.pdf -------------------------------------------------------------------------------- /Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor/CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Workflow change log 2 | 3 | ## [1.0.0](https://github.com/nasa/GeneLab_Data_Processing/tree/SW_Amp454IonTor_1.0.0/Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor) 4 | - original workflow version 5 | -------------------------------------------------------------------------------- /Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor/workflow_code/envs/R.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - r-base=4.1.1 7 | - bioconductor-decipher=2.20.0 8 | - bioconductor-biomformat=1.20.0 9 | -------------------------------------------------------------------------------- /Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor/workflow_code/envs/bbmap.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - bbmap=38.86 7 | -------------------------------------------------------------------------------- /Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor/workflow_code/envs/cutadapt.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - cutadapt=2.3 7 | -------------------------------------------------------------------------------- /Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor/workflow_code/envs/qc.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - fastqc=0.11.9 7 | - multiqc=1.9 8 | - zip=3.0 9 | - python=3.8 10 | -------------------------------------------------------------------------------- /Amplicon/454-and-IonTorrent/Workflow_Documentation/SW_Amp454IonTor/workflow_code/envs/vsearch.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - vsearch=2.15.1 8 | - bit=1.8.37 9 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-126/GLDS_version_2/16S-archaeal-unique-sample-IDs.txt: -------------------------------------------------------------------------------- 1 | 16S_blank_FLT_arch_noINCd_CTRL_YEAR_ArchExtractNC 2 | 16S_dust_FLT_arch_noINCd_DFVS-1_2004_RISS1 3 | 16S_dust_FLT_arch_noINCd_DFVS_2008_RISS3 4 | 16S_dust_FLT_arch_noINCd_VAC_2004_RISS5 5 | 16S_dust_FLT_arch_noINCd_VAC_2008_RISS2 6 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-126/GLDS_version_2/16S-universal-unique-sample-IDs.txt: -------------------------------------------------------------------------------- 1 | 16S_blank_FLT_uni_INCd_CTRL_YEAR_IncubatedNC 2 | 16S_blank_FLT_uni_noINCd_CTRL_YEAR_ExtractionNC 3 | 16S_dust_FLT_uni_INCd_DFVS-1_2004_RISS1 4 | 16S_dust_FLT_uni_INCd_DFVS_2008_RISS3 5 | 16S_dust_FLT_uni_INCd_DFVS-2_2004_RISS4 6 | 16S_dust_FLT_uni_INCd_VAC_2004_RISS5 7 | 16S_dust_FLT_uni_INCd_VAC_2008_RISS2 8 | 16S_dust_FLT_uni_noINCd_DFVS-1_2004_RISS1 9 | 16S_dust_FLT_uni_noINCd_DFVS_2008_RISS3 10 | 16S_dust_FLT_uni_noINCd_VAC_2008_RISS2 11 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-126/GLDS_version_2/primers.fa: -------------------------------------------------------------------------------- 1 | >16S-universal-515F 2 | GTGCCAGCMGCCGCGGTAA 3 | >16S-universal-806R 4 | GGACTACHVGGGTWTCTAAT 5 | >16S-archaeal-349F 6 | GYGCASCAGKCGMGAAW 7 | >16S-archaeal-519R 8 | TTACCGCGGCKGCTG 9 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-146/GLDS_version_2/primers.fa: -------------------------------------------------------------------------------- 1 | >F 2 | GTGYCAGCMGCCGCGGTAA 3 | >R 4 | GGACTACNVGGGTWTCTAAT 5 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-191/GLDS_version_3/primers.fa: -------------------------------------------------------------------------------- 1 | >F 2 | CCTACGGGNGGCWGCAG 3 | >R 4 | GACTACHVGGGTATCTAATCC 5 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-200/GLDS_version_2/16S-unique-sample-IDs.txt: -------------------------------------------------------------------------------- 1 | 16S_AHSFS_SIEVd_106-150um 2 | 16S_AHSFS_SIEVd_150-250um 3 | 16S_AHSFS_SIEVd_250-500um 4 | 16S_AHSFS_SIEVd_75-106um 5 | 16S_AHSFS_SIEVd_blank 6 | 16S_Node3_PAS_blank 7 | 16S_Node3_PAS 8 | Batr_16S 9 | Ecol_16S 10 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-200/GLDS_version_2/ITS-unique-sample-IDs.txt: -------------------------------------------------------------------------------- 1 | ITS_AHSFS_SIEVd_106-150um 2 | ITS_AHSFS_SIEVd_150-250um 3 | ITS_AHSFS_SIEVd_250-500um 4 | ITS_AHSFS_SIEVd_75-106um 5 | ITS_Node3_PAS_blank 6 | ITS_Node3_PAS 7 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-200/GLDS_version_2/primers.fa: -------------------------------------------------------------------------------- 1 | >16S_515F 2 | GTGCCAGCMGCCGCGGTAA 3 | >16S_806R 4 | GGACTACVSGGGTATCTAAT 5 | >ITS1_F 6 | CTTGGTCATTTAGAGGAAGTAA 7 | >ITS2_R 8 | GCTGCGTTCTTCATCGATGC 9 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-280/GLDS_version_2/environment.yml: -------------------------------------------------------------------------------- 1 | name: GL-Illumina-amplicon 2 | channels: 3 | - conda-forge 4 | - bioconda 5 | - defaults 6 | dependencies: 7 | - fastqc=0.11.8 8 | - multiqc=1.7 9 | - cutadapt=2.3 10 | - r-base=3.6.3 11 | - bioconductor-dada2=1.12.1 12 | - bioconductor-decipher=2.12.0 13 | - bioconductor-biomformat=1.12.0 14 | - snakemake=5.5.4 15 | -------------------------------------------------------------------------------- /Amplicon/Illumina/GLDS_Processing_Scripts/GLDS-280/GLDS_version_2/primers.fa: -------------------------------------------------------------------------------- 1 | >V3-V4-341-F 2 | CCTACGGGNGGCWGCAG 3 | >V3-V4-785-R 4 | GACTACHVGGGTATCTAATCC 5 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-A/workflow_code/config/multiqc.config: -------------------------------------------------------------------------------- 1 | extra_fn_clean_exts: 2 | - "_raw" 3 | - "_filtered" 4 | 5 | show_analysis_paths: False 6 | show_analysis_time: False 7 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-A/workflow_code/envs/R.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - r-base=4.1.1 7 | - bioconductor-dada2=1.20.0 8 | - bioconductor-decipher=2.20.0 9 | - bioconductor-biomformat=1.20.0 10 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-A/workflow_code/envs/cutadapt.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - cutadapt=2.3 7 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-A/workflow_code/envs/qc.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - fastqc=0.11.9 7 | - multiqc=1.9 8 | - zip=3.0 9 | - python=3.8 10 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-A/workflow_code/scripts/combine-benchmarks.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | set -e 3 | 4 | ls benchmarks/ > benchmark-filenames.tmp 5 | 6 | head -n 1 benchmarks/$( head -n 1 benchmark-filenames.tmp ) > benchmark-header.tmp 7 | 8 | paste <( printf "process" ) benchmark-header.tmp > building-tab.tmp 9 | 10 | for file in $(cat benchmark-filenames.tmp) 11 | do 12 | 13 | cat <( paste <( echo ${file} | sed 's/-benchmarks.tsv//' ) <( tail -n +2 benchmarks/${file} ) ) >> building-tab.tmp 14 | 15 | done 16 | 17 | mv building-tab.tmp all-benchmarks.tsv 18 | rm -rf benchmark-filenames.tmp benchmark-header.tmp 19 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-A/workflow_code/scripts/slurm-status.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | import subprocess 3 | import sys 4 | 5 | jobid = sys.argv[1] 6 | 7 | # if wanting to use, this should be added to the snakemake call from the root workflow dir: `--cluster-status scripts/slurm-status.py` 8 | 9 | output = str(subprocess.check_output("sacct -j %s --format State --noheader | head -1 | awk '{print $1}'" % jobid, shell=True).strip()) 10 | 11 | running_status=["PENDING", "CONFIGURING", "COMPLETING", "RUNNING", "SUSPENDED"] 12 | if "COMPLETED" in output: 13 | print("success") 14 | elif any(r in output for r in running_status): 15 | print("running") 16 | else: 17 | print("failed") 18 | -------------------------------------------------------------------------------- /Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B/README.md: -------------------------------------------------------------------------------- 1 | # SW_AmpIllumina-B Workflow Information and Usage Instructions 2 | 3 | The SW_AmpIllumina-B workflow is curently under development and will be available soon. 4 | 5 | > A beta version of SW_AmpIllumina-B is available under development branch: [dev2-amplicon-add-runsheet-visualizations](https://github.com/nasa/GeneLab_Data_Processing/tree/dev2-amplicon-add-runsheet-visualizations/Amplicon/Illumina/Workflow_Documentation/SW_AmpIllumina-B) 6 | 7 | -------------------------------------------------------------------------------- /Amplicon/images/GL-amplicon-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Amplicon/images/GL-amplicon-overview.pdf -------------------------------------------------------------------------------- /Amplicon/images/GL-amplicon-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Amplicon/images/GL-amplicon-overview.png -------------------------------------------------------------------------------- /GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/bin/prepull_singularity.sh: -------------------------------------------------------------------------------- 1 | 2 | #!/usr/bin/env bash 3 | 4 | # Addresses issue: https://github.com/nextflow-io/nextflow/issues/1210 5 | 6 | CONFILE=${1:-nextflow.config} 7 | OUTDIR=${2:-./singularity} 8 | 9 | if [ ! -e $CONFILE ]; then 10 | echo "$CONFILE does not exist" 11 | exit 12 | fi 13 | 14 | TMPFILE=`mktemp` 15 | 16 | CURDIR=$(pwd) 17 | 18 | mkdir -p $OUTDIR 19 | 20 | cat ${CONFILE}|grep 'container'|perl -lane 'if ( $_=~/container\s*\=\s*\"(\S+)\"/ ) { $_=~/container\s*\=\s*\"(\S+)\"/; print $1 unless ( $1=~/^\s*$/ or $1=~/\.sif/ or $1=~/\.img/ ) ; }' > $TMPFILE 21 | 22 | cd ${OUTDIR} 23 | 24 | while IFS= read -r line; do 25 | name=$line 26 | name=${name/:/-} 27 | name=${name//\//-} 28 | echo $name 29 | singularity pull ${name}.img docker://$line 30 | done < $TMPFILE 31 | 32 | cd $CURDIR 33 | -------------------------------------------------------------------------------- /GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable-A/workflow_code/config/software/by_docker_image.config: -------------------------------------------------------------------------------- 1 | // Config that specifies containers for nextflow processes 2 | process { 3 | withName: 'GL_REFANNOTTABLE_A' { 4 | container = "quay.io/nasa_genelab/gl-refannottable-a:1.1.0" 5 | } 6 | } 7 | -------------------------------------------------------------------------------- /GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable/CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Workflow change log 2 | 3 | ## [1.0.0](https://github.com/nasa/GeneLab_Data_Processing/tree/GL_RefAnnotTable_1.0.0/GeneLab_Reference_Annotations/Workflow_Documentation/GL_RefAnnotTable) 4 | - original workflow version 5 | -------------------------------------------------------------------------------- /Licenses/Amplicon_and_Metagenomics_NOSA_License.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Licenses/Amplicon_and_Metagenomics_NOSA_License.pdf -------------------------------------------------------------------------------- /Licenses/Methylation_Sequencing_NOSA_License.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Licenses/Methylation_Sequencing_NOSA_License.pdf -------------------------------------------------------------------------------- /Licenses/Microarray_GPL-3.0_with_Additional_Requirements_License.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Licenses/Microarray_GPL-3.0_with_Additional_Requirements_License.pdf -------------------------------------------------------------------------------- /Licenses/RNA_Sequencing_NOSA_License.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Licenses/RNA_Sequencing_NOSA_License.pdf -------------------------------------------------------------------------------- /Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Workflow change log 2 | 3 | ## [1.0.0](https://github.com/nasa/GeneLab_Data_Processing/tree/SW_MGEstHostReads_1.0.0/Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads) 4 | - original workflow version 5 | -------------------------------------------------------------------------------- /Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/workflow_code/envs/kraken2.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - kraken2=2.1.1 7 | -------------------------------------------------------------------------------- /Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/workflow_code/example-reads/Sample-1_R1.fastq.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/workflow_code/example-reads/Sample-1_R1.fastq.gz -------------------------------------------------------------------------------- /Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/workflow_code/example-reads/Sample-1_R2.fastq.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/workflow_code/example-reads/Sample-1_R2.fastq.gz -------------------------------------------------------------------------------- /Metagenomics/Estimate_host_reads_in_raw_data/Workflow_Documentation/SW_MGEstHostReads/workflow_code/unique-sample-IDs.txt: -------------------------------------------------------------------------------- 1 | Sample-1 2 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/bin/download-GTDBTK-db.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | set -e 4 | 5 | echo "Downloading the GTDB-Tk database to ${GTDBTK_DATA_PATH}..." 6 | 7 | # GTDBTK_DB_PATH is defined in build.sh, store the db there 8 | 9 | 10 | DB_URL=$1 11 | TAR_FILE=$(basename ${DB_URL}) 12 | 13 | 14 | downloadFile=true 15 | 16 | while ${downloadFile};do 17 | 18 | wget --timeout=3600 --tries=0 --continue ${DB_URL} -P ${GTDBTK_DATA_PATH} && downloadFile=false 19 | 20 | done 21 | 22 | tar xvzf ${GTDBTK_DATA_PATH}/${TAR_FILE} -C ${GTDBTK_DATA_PATH} --strip 1 23 | rm ${GTDBTK_DATA_PATH}/${TAR_FILE} 24 | 25 | echo "GTDB-Tk database has been successfully downloaded." 26 | 27 | exit 0 28 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/bin/format-contig-tax-classifications.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | awk -F $'\t' ' BEGIN { OFS = FS } { if ( $2 == "classification" ) { print $1,$4,$6,$7,$8,$9,$10,$11,$12 } \ 4 | else if ( $2 == "no taxid assigned" ) { print $1,"NA","NA","NA","NA","NA","NA","NA","NA" } \ 5 | else { n=split($4,lineage,";"); print $1,lineage[n],$6,$7,$8,$9,$10,$11,$12 } } ' ${1} \ 6 | | sed 's/no support/NA/g' | sed 's/superkingdom/domain/' | sed 's/^# contig/contig_ID/' | sed 's/lineage/taxid/' > ${2} 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/bin/format-gene-tax-classifications.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | awk -F $'\t' ' BEGIN { OFS = FS } { if ( $3 == "lineage" ) { print $1,$3,$5,$6,$7,$8,$9,$10,$11 } \ 4 | else if ( $2 == "ORF has no hit to database" || $2 ~ /^no taxid found/ ) { print $1,"NA","NA","NA","NA","NA","NA","NA","NA" } \ 5 | else { n=split($3,lineage,";"); print $1,lineage[n],$5,$6,$7,$8,$9,$10,$11 } } ' ${1} \ 6 | | sed 's/no support/NA/g' | sed 's/superkingdom/domain/' | sed 's/# ORF/gene_ID/' | sed 's/lineage/taxid/' > ${2} 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/bin/prepull_singularity.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Addresses issue: https://github.com/nextflow-io/nextflow/issues/1210 4 | 5 | CONFILE=${1:-nextflow.config} 6 | OUTDIR=${2:-./singularity} 7 | 8 | if [ ! -e $CONFILE ]; then 9 | echo "$CONFILE does not exist" 10 | exit 11 | fi 12 | 13 | TMPFILE=`mktemp` 14 | 15 | CURDIR=$(pwd) 16 | 17 | mkdir -p $OUTDIR 18 | 19 | cat ${CONFILE}|grep 'container'|perl -lane 'if ( $_=~/container\s*\=\s*\"(\S+)\"/ ) { $_=~/container\s*\=\s*\"(\S+)\"/; print $1 unless ( $1=~/^\s*$/ or $1=~/\.sif/ or $1=~/\.img/ ) ; }' > $TMPFILE 20 | 21 | cd ${OUTDIR} 22 | 23 | while IFS= read -r line; do 24 | name=$line 25 | name=${name/:/-} 26 | name=${name//\//-} 27 | echo $name 28 | singularity pull ${name}.img docker://$line 29 | done < $TMPFILE 30 | 31 | cd $CURDIR -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/config/multiqc.config: -------------------------------------------------------------------------------- 1 | extra_fn_clean_exts: 2 | - "_raw" 3 | - "_HRremoved_raw" 4 | - "_filtered" 5 | 6 | show_analysis_paths: False 7 | show_analysis_time: False 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/bit.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - bit=1.8.53 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/cat.yaml: -------------------------------------------------------------------------------- 1 | name: CAT 2 | channels: 3 | - conda-forge 4 | - bioconda 5 | - defaults 6 | dependencies: 7 | - cat=5.2.3 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/checkm.yaml: -------------------------------------------------------------------------------- 1 | name: checkm 2 | channels: 3 | - conda-forge 4 | - bioconda 5 | - defaults 6 | dependencies: 7 | - checkm-genome=1.1.3 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/genelab.yaml: -------------------------------------------------------------------------------- 1 | name: genelab-utils 2 | channels: 3 | - conda-forge 4 | - bioconda 5 | - defaults 6 | - astrobiomike 7 | dependencies: 8 | - genelab-utils==1.3.22=py312_1 -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/gtdb-tk.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - gtdbtk=2.4.0 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/humann3.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - biobakery 6 | dependencies: 7 | - humann=3.9 8 | - metaphlan=4.10 -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/keggdecoder.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | dependencies: 4 | - python=3.6 5 | - pip 6 | - pip: 7 | - KEGGDecoder==1.2.2 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/kofamscan.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - kofamscan=1.3.0 8 | - hmmer=3.3.0 9 | - bit=1.8.53 10 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/mapping.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - bowtie2=2.4.1 7 | - tbb=2020.2 8 | - bbmap=38.86 9 | - samtools=1.2 10 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/megahit.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - megahit=1.2.9 8 | - bit=1.8.53 9 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/metabat.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - metabat2=2.15 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/prodigal.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - prodigal=2.6.3 8 | - bit=1.8.53 9 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/NF_MGIllumina/workflow_code/envs/qc.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - fastqc=0.12.1 7 | - multiqc=1.19 8 | - bbmap=38.86 9 | - zip=3.0 10 | - python=3.8 11 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/config/multiqc.config: -------------------------------------------------------------------------------- 1 | extra_fn_clean_exts: 2 | - "_raw" 3 | - "_HRremoved_raw" 4 | - "_filtered" 5 | 6 | show_analysis_paths: False 7 | show_analysis_time: False 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/bit.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - bit=1.8.53 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/cat.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - cat=5.2.2 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/checkm.yaml: -------------------------------------------------------------------------------- 1 | name: checkm 2 | channels: 3 | - conda-forge 4 | - bioconda 5 | - defaults 6 | dependencies: 7 | - checkm-genome=1.1.3 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/gtdb-tk.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - gtdbtk=1.5.0 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/humann3.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - biobakery 6 | dependencies: 7 | - humann=3.6 8 | - metaphlan=4.0.1 9 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/keggdecoder.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | dependencies: 4 | - python=3.6 5 | - pip 6 | - pip: 7 | - KEGGDecoder==1.2.2 8 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/kofamscan.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - kofamscan=1.3.0 8 | - hmmer=3.3.0 9 | - bit=1.8.53 10 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/mapping.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - bowtie2=2.3.5.1 7 | - tbb=2020.2 8 | - bbmap=38.86 9 | - samtools=1.9 10 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/megahit.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - megahit=1.2.9 8 | - bit=1.8.53 9 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/metabat.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - metabat2=2.15 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/prodigal.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | - astrobiomike 6 | dependencies: 7 | - prodigal=2.6.3 8 | - bit=1.8.53 9 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/envs/qc.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - fastqc=0.11.9 7 | - multiqc=1.11 8 | - bbmap=38.86 9 | - zip=3.0 10 | - python=3.8 11 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/scripts/combine-benchmarks.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | set -e 3 | 4 | ls benchmarks/ > benchmark-filenames.tmp 5 | 6 | head -n 1 benchmarks/$( head -n 1 benchmark-filenames.tmp ) > benchmark-header.tmp 7 | 8 | paste <( printf "process" ) benchmark-header.tmp > building-tab.tmp 9 | 10 | for file in $(cat benchmark-filenames.tmp) 11 | do 12 | 13 | cat <( paste <( echo ${file} | sed 's/-benchmarks.tsv//' ) <( tail -n +2 benchmarks/${file} ) ) >> building-tab.tmp 14 | 15 | done 16 | 17 | mv building-tab.tmp all-benchmarks.tsv 18 | rm -rf benchmark-filenames.tmp benchmark-header.tmp 19 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/scripts/format-contig-tax-classifications.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | awk -F $'\t' ' BEGIN { OFS = FS } { if ( $2 == "classification" ) { print $1,$4,$6,$7,$8,$9,$10,$11,$12 } \ 4 | else if ( $2 == "no taxid assigned" ) { print $1,"NA","NA","NA","NA","NA","NA","NA","NA" } \ 5 | else { n=split($4,lineage,";"); print $1,lineage[n],$6,$7,$8,$9,$10,$11,$12 } } ' ${1} \ 6 | | sed 's/no support/NA/g' | sed 's/superkingdom/domain/' | sed 's/^# contig/contig_ID/' | sed 's/lineage/taxid/' > ${2} 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/scripts/format-gene-tax-classifications.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | awk -F $'\t' ' BEGIN { OFS = FS } { if ( $3 == "lineage" ) { print $1,$3,$5,$6,$7,$8,$9,$10,$11 } \ 4 | else if ( $2 == "ORF has no hit to database" || $2 ~ /^no taxid found/ ) { print $1,"NA","NA","NA","NA","NA","NA","NA","NA" } \ 5 | else { n=split($3,lineage,";"); print $1,lineage[n],$5,$6,$7,$8,$9,$10,$11 } } ' ${1} \ 6 | | sed 's/no support/NA/g' | sed 's/superkingdom/domain/' | sed 's/# ORF/gene_ID/' | sed 's/lineage/taxid/' > ${2} 7 | -------------------------------------------------------------------------------- /Metagenomics/Illumina/Workflow_Documentation/SW_MGIllumina/workflow_code/scripts/slurm-status.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | import subprocess 3 | import sys 4 | 5 | jobid = sys.argv[1] 6 | 7 | # if wanting to use, this should be added to the snakemake call from the root workflow dir: `--cluster-status scripts/slurm-status.py` 8 | 9 | output = str(subprocess.check_output("sacct -j %s --format State --noheader | head -1 | awk '{print $1}'" % jobid, shell=True).strip()) 10 | 11 | running_status=["PENDING", "CONFIGURING", "COMPLETING", "RUNNING", "SUSPENDED"] 12 | if "COMPLETED" in output: 13 | print("success") 14 | elif any(r in output for r in running_status): 15 | print("running") 16 | else: 17 | print("failed") 18 | -------------------------------------------------------------------------------- /Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Workflow change log 2 | 3 | ## [1.0.0](https://github.com/nasa/GeneLab_Data_Processing/tree/SW_MGRemoveHumanReads-A_1.0.0/Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A) 4 | - original workflow version 5 | -------------------------------------------------------------------------------- /Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/workflow_code/envs/kraken2.yaml: -------------------------------------------------------------------------------- 1 | channels: 2 | - conda-forge 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - kraken2=2.1.1 7 | -------------------------------------------------------------------------------- /Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/workflow_code/example-reads/Sample-1_R1.fastq.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/workflow_code/example-reads/Sample-1_R1.fastq.gz -------------------------------------------------------------------------------- /Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/workflow_code/example-reads/Sample-1_R2.fastq.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/workflow_code/example-reads/Sample-1_R2.fastq.gz -------------------------------------------------------------------------------- /Metagenomics/Remove_human_reads_from_raw_data/Workflow_Documentation/SW_MGRemoveHumanReads-A/workflow_code/unique-sample-IDs.txt: -------------------------------------------------------------------------------- 1 | Sample-1 2 | -------------------------------------------------------------------------------- /Metagenomics/images/GL-Illumina-metagenomics-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/images/GL-Illumina-metagenomics-overview.pdf -------------------------------------------------------------------------------- /Metagenomics/images/GL-Illumina-metagenomics-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/images/GL-Illumina-metagenomics-overview.png -------------------------------------------------------------------------------- /Metagenomics/images/config-ex.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/images/config-ex.png -------------------------------------------------------------------------------- /Metagenomics/images/gitzip-ex.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Metagenomics/images/gitzip-ex.png -------------------------------------------------------------------------------- /Methyl-Seq/Pipeline_GL-DPPD-7113_Versions/images/GL-bisulfite-seq-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Methyl-Seq/Pipeline_GL-DPPD-7113_Versions/images/GL-bisulfite-seq-overview.pdf -------------------------------------------------------------------------------- /Methyl-Seq/Pipeline_GL-DPPD-7113_Versions/images/GL-bisulfite-seq-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Methyl-Seq/Pipeline_GL-DPPD-7113_Versions/images/GL-bisulfite-seq-overview.png -------------------------------------------------------------------------------- /Methyl-Seq/Workflow_Documentation/README.md: -------------------------------------------------------------------------------- 1 | coming soon... 2 | -------------------------------------------------------------------------------- /Methyl-Seq/Workflow_Documentation/isa_to_runsheet_plugins/dp_tools__methylseq_dna/__init__.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | # Import for access at the module level 4 | from . import checks 5 | from . import protocol 6 | from . import schemas 7 | 8 | # Set config path 9 | config = Path(__file__).parent / "methylSeqDNA_v2.yaml" 10 | -------------------------------------------------------------------------------- /Methyl-Seq/Workflow_Documentation/isa_to_runsheet_plugins/dp_tools__methylseq_rna/__init__.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | # Import for access at the module level 4 | from . import checks 5 | from . import protocol 6 | from . import schemas 7 | 8 | # Set config path 9 | config = Path(__file__).parent / "methylSeqRNA_v1.yaml" 10 | -------------------------------------------------------------------------------- /Methyl-Seq/images/GL-methyl-seq-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Methyl-Seq/images/GL-methyl-seq-overview.pdf -------------------------------------------------------------------------------- /Methyl-Seq/images/GL-methyl-seq-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Methyl-Seq/images/GL-methyl-seq-overview.png -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/bin/dp_tools__affymetrix/__init__.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | # Import for access at the module level 4 | from . import checks 5 | from . import protocol 6 | from . import schemas 7 | 8 | # Set config path 9 | config = Path(__file__).parent / "config.yaml" -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/config/software/by_docker_image.config: -------------------------------------------------------------------------------- 1 | process { 2 | withName: 'PROCESS_AFFYMETRIX' { 3 | container = "quay.io/j_81/gl_images:NF_AffyMP-A_1.0.0-RC7" 4 | } 5 | withName: 'RUNSHEET_FROM_GLDS|RUNSHEET_FROM_ISA|VV_AFFYMETRIX|GENERATE_MD5SUMS|UPDATE_ISA_TABLES|GENERATE_SOFTWARE_TABLE' { 6 | container = "quay.io/j_81/dp_tools:1.3.4" 7 | } 8 | } 9 | -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/modules/DUMP_META/main.nf: -------------------------------------------------------------------------------- 1 | process DUMP_META { 2 | publishDir "${ params.resultsDir }/GeneLab", 3 | mode: params.publish_dir_mode 4 | 5 | input: 6 | val(meta) 7 | 8 | output: 9 | path("meta.sh") 10 | 11 | script: 12 | """ 13 | # Write the meta file 14 | reformat_meta.sh '${ meta }' > meta.sh 15 | """ 16 | } -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/modules/GENERATE_MD5SUMS.nf: -------------------------------------------------------------------------------- 1 | process GENERATE_MD5SUMS { 2 | // Generates tabular data indicating genelab standard publishing files, md5sum generation, and tool version table formatting 3 | tag "${ params.gldsAccession }" 4 | publishDir "${ params.resultsDir }/GeneLab", 5 | mode: params.publish_dir_mode 6 | 7 | input: 8 | path(data_dir) 9 | path(runsheet) 10 | path(dp_tools__affymetrix) 11 | 12 | output: 13 | path("*md5sum*") 14 | path("Missing_md5sum_files_GLmicroarray.txt"), optional: true 15 | 16 | script: 17 | """ 18 | generate_md5sum_files.py --root-path ${ data_dir } \\ 19 | --runsheet-path ${ runsheet } \\ 20 | --plug-in-dir ${ dp_tools__affymetrix } 21 | """ 22 | } -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/modules/GENERATE_SOFTWARE_TABLE/main.nf: -------------------------------------------------------------------------------- 1 | process GENERATE_SOFTWARE_TABLE { 2 | publishDir "${ params.resultsDir }/GeneLab", 3 | pattern: "software_versions_GLmicroarray.md", 4 | mode: params.publish_dir_mode 5 | 6 | input: 7 | path("software_versions.yaml") 8 | 9 | output: 10 | path("software_versions_GLmicroarray.md") 11 | 12 | script: 13 | """ 14 | SoftwareYamlToMarkdownTable.py software_versions.yaml 15 | """ 16 | } -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/modules/POST_PROCESSING/GENERATE_PROTOCOL/main.nf: -------------------------------------------------------------------------------- 1 | process GENERATE_PROTOCOL { 2 | tag "${ params.gldsAccession }" 3 | publishDir "${ params.resultsDir }/GeneLab", 4 | mode: params.publish_dir_mode 5 | 6 | input: 7 | path("software_versions_GLmicroarray.md") 8 | path("meta.sh") 9 | 10 | output: 11 | path("PROTOCOL_GLmicroarray.txt") 12 | 13 | script: 14 | """ 15 | generate_protocol.sh 16 | """ 17 | } -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/modules/RUNSHEET_FROM_ISA.nf: -------------------------------------------------------------------------------- 1 | process RUNSHEET_FROM_ISA { 2 | // Generates Runsheet using a path to an ISA archive 3 | tag "${ gldsAccession }" 4 | publishDir "${ params.resultsDir }/Metadata", 5 | pattern: "*.zip", 6 | mode: params.publish_dir_mode 7 | 8 | input: 9 | val(osdAccession) 10 | val(gldsAccession) 11 | path(isaArchive) 12 | path("dp_tools__agilent_1_channel") 13 | 14 | output: 15 | path("${ osdAccession }_microarray_v?_runsheet.csv"), emit: runsheet 16 | 17 | script: 18 | """ 19 | dpt-isa-to-runsheet --accession ${ osdAccession } \ 20 | --plugin-dir dp_tools__agilent_1_channel \ 21 | --isa-archive ${ isaArchive } 22 | """ 23 | } -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/nf-test.config: -------------------------------------------------------------------------------- 1 | config { 2 | 3 | testsDir "tests" 4 | workDir "/tmp/.nf-test" 5 | configFile "nextflow.config" 6 | configFile "tests/nextflow.config" 7 | profile "docker" 8 | 9 | } 10 | -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/tests/assets/CLEANED_GLDS-428_metadata_GLDS-428-ISA.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/tests/assets/CLEANED_GLDS-428_metadata_GLDS-428-ISA.zip -------------------------------------------------------------------------------- /Microarray/Affymetrix/Workflow_Documentation/NF_MAAffymetrix/workflow_code/tests/nextflow.config: -------------------------------------------------------------------------------- 1 | params { 2 | resultsDir = params.outputDir 3 | } -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/bin/dp_tools__agilent_1_channel/__init__.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | # Import for access at the module level 4 | from . import checks 5 | from . import protocol 6 | from . import schemas 7 | 8 | # Set config path 9 | config = Path(__file__).parent / "config.yaml" -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/config/software/by_docker_image.config: -------------------------------------------------------------------------------- 1 | // Config that specifies packaged conda yml files for each process 2 | process { 3 | withName: 'AGILE1CH' { 4 | container = "quay.io/j_81/gl_images:NF_AffyMP-A_1.0.0-RC7" 5 | } 6 | withName: 'RUNSHEET_FROM_GLDS|VV_AGILE1CH|GENERATE_MD5SUMS|UPDATE_ISA_TABLES|GENERATE_SOFTWARE_TABLE' { 7 | container = "quay.io/j_81/dp_tools:1.3.1" 8 | } 9 | } 10 | -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/modules/GENERATE_MD5SUMS.nf: -------------------------------------------------------------------------------- 1 | process GENERATE_MD5SUMS { 2 | // Generates tabular data indicating genelab standard publishing files, md5sum generation, and tool version table formatting 3 | tag "${ params.gldsAccession }" 4 | publishDir "${ params.outputDir }/${ params.gldsAccession }/GeneLab", 5 | mode: params.publish_dir_mode 6 | 7 | input: 8 | path(data_dir) 9 | path(runsheet) 10 | path(dp_tools__agilent_1_channel) 11 | 12 | output: 13 | path("*md5sum*") 14 | path("Missing_md5sum_files.txt"), optional: true 15 | 16 | script: 17 | """ 18 | generate_md5sum_files.py --root-path ${ data_dir } \\ 19 | --runsheet-path ${ runsheet } \\ 20 | --plug-in-dir ${ dp_tools__agilent_1_channel } 21 | """ 22 | } -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/modules/GENERATE_SOFTWARE_TABLE/main.nf: -------------------------------------------------------------------------------- 1 | process GENERATE_SOFTWARE_TABLE { 2 | publishDir "${ params.outputDir }/${ params.gldsAccession }/GeneLab", 3 | pattern: "software_versions_GLmicroarray.md", 4 | mode: params.publish_dir_mode 5 | 6 | input: 7 | path("software_versions.yaml") 8 | val(filename) 9 | 10 | output: 11 | path("software_versions_GLmicroarray.md") 12 | 13 | script: 14 | """ 15 | SoftwareYamlToMarkdownTable.py software_versions.yaml \"$filename\" 16 | """ 17 | } -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/modules/POST_PROCESSING/GENERATE_PROTOCOL/main.nf: -------------------------------------------------------------------------------- 1 | process GENERATE_PROTOCOL { 2 | tag "${ params.gldsAccession }" 3 | publishDir "${ params.outputDir }/${ params.gldsAccession }/GeneLab", 4 | mode: params.publish_dir_mode 5 | 6 | input: 7 | path("software_versions_GLmicroarray.md") 8 | val(organism) 9 | 10 | output: 11 | path("PROTOCOL_GLmicroarray.txt") 12 | 13 | script: 14 | """ 15 | generate_protocol.sh $workflow.manifest.version \"$organism\" 16 | """ 17 | } -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/nf-test.config: -------------------------------------------------------------------------------- 1 | config { 2 | 3 | testsDir "tests" 4 | workDir "/tmp/.nf-test" 5 | configFile "nextflow.config" 6 | profile "docker" 7 | 8 | } 9 | -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/tests/main.POSTPROCESSING.GLDS542.nf.test: -------------------------------------------------------------------------------- 1 | nextflow_pipeline { 2 | 3 | name "Test Workflow post_processing.nf" 4 | script "post_processing.nf" 5 | 6 | test("GLDS-542: Should run without failures") { 7 | 8 | when { 9 | params { 10 | // define parameters here. Example: 11 | osdAccession = "OSD-542" 12 | gldsAccession = "GLDS-542" 13 | outputDir = file("/tmp/.nf-test/tests/f8e4a2468b9782955384329fe1207804/output") 14 | } 15 | } 16 | 17 | then { 18 | assert workflow.success 19 | } 20 | 21 | } 22 | 23 | } 24 | -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/tests/modules/PARSE_ANNOTATION_TABLE.nf.test.snap: -------------------------------------------------------------------------------- 1 | { 2 | "Should run without failures": { 3 | "content": [ 4 | { 5 | "reference_version_and_source": [ 6 | [ 7 | "107", 8 | "ensembl" 9 | ] 10 | ], 11 | "annotations_db_url": [ 12 | "https://figshare.com/ndownloader/files/36597120" 13 | ] 14 | } 15 | ], 16 | "timestamp": "2023-01-18T00:23:45+0000" 17 | } 18 | } -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/tests/modules/RUNSHEET_FROM_GLDS.nf.test.snap: -------------------------------------------------------------------------------- 1 | { 2 | "GLDS-367: Should run without failures": { 3 | "content": [ 4 | { 5 | "runsheet": [ 6 | "OSD-367_microarray_v0_runsheet.csv:md5,6b066905180d502a70e4ad9fc094433d" 7 | ], 8 | "isaArchive": [ 9 | "GLDS-367_metadata_GLDS-367-ISA.zip:md5,130bb4f9fded2750631cfed98c173c06" 10 | ] 11 | } 12 | ], 13 | "timestamp": "2023-02-15T00:16:07+0000" 14 | } 15 | } -------------------------------------------------------------------------------- /Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/tests/nextflow.config: -------------------------------------------------------------------------------- 1 | /* 2 | ======================================================================================== 3 | Nextflow config file for running tests 4 | ======================================================================================== 5 | */ 6 | -------------------------------------------------------------------------------- /Microarray/images/GL-affymetrix-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/images/GL-affymetrix-overview.pdf -------------------------------------------------------------------------------- /Microarray/images/GL-affymetrix-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/images/GL-affymetrix-overview.png -------------------------------------------------------------------------------- /Microarray/images/GL-agilent_1channel-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/images/GL-agilent_1channel-overview.pdf -------------------------------------------------------------------------------- /Microarray/images/GL-agilent_1channel-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/images/GL-agilent_1channel-overview.png -------------------------------------------------------------------------------- /Microarray/images/GL-microarray-overview.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/images/GL-microarray-overview.pdf -------------------------------------------------------------------------------- /Microarray/images/GL-microarray-overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/Microarray/images/GL-microarray-overview.png -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-101/GLDS_version_2/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-101/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/GLDS-101_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6J_GST_FLT_Rep1_M23,FLT 3 | Mmus_C57-6J_GST_FLT_Rep2_M24,FLT 4 | Mmus_C57-6J_GST_FLT_Rep3_M25,FLT 5 | Mmus_C57-6J_GST_FLT_Rep4_M26,FLT 6 | Mmus_C57-6J_GST_FLT_Rep5_M27,FLT 7 | Mmus_C57-6J_GST_FLT_Rep6_M28,FLT 8 | Mmus_C57-6J_GST_GC_Rep1_M33,GC 9 | Mmus_C57-6J_GST_GC_Rep2_M34,GC 10 | Mmus_C57-6J_GST_GC_Rep3_M35,GC 11 | Mmus_C57-6J_GST_GC_Rep4_M36,GC 12 | Mmus_C57-6J_GST_GC_Rep5_M37,GC 13 | Mmus_C57-6J_GST_GC_Rep6_M38,GC 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-101/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-101_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-user=user@nasa.gov 8 | #SBATCH --mail-type=END 9 | 10 | start=$(date +%s) 11 | echo "start time: $start" 12 | echo $HOSTNAME 13 | 14 | /Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 15 | 16 | end=$(date +%s) 17 | echo "end time: $end" 18 | runtime_s=$(echo $(( end - start ))) 19 | echo "total run time(s): $runtime_s" 20 | sec_per_min=60 21 | sec_per_hr=3600 22 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 23 | echo "total run time(m): $runtime_m" 24 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 25 | echo "total run time(h): $runtime_h" 26 | 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-101/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-101/GLDS_version_2/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_GST_FLT_Rep1_M23 2 | Mmus_C57-6J_GST_FLT_Rep2_M24 3 | Mmus_C57-6J_GST_FLT_Rep3_M25 4 | Mmus_C57-6J_GST_FLT_Rep4_M26 5 | Mmus_C57-6J_GST_FLT_Rep5_M27 6 | Mmus_C57-6J_GST_FLT_Rep6_M28 7 | Mmus_C57-6J_GST_GC_Rep1_M33 8 | Mmus_C57-6J_GST_GC_Rep2_M34 9 | Mmus_C57-6J_GST_GC_Rep3_M35 10 | Mmus_C57-6J_GST_GC_Rep4_M36 11 | Mmus_C57-6J_GST_GC_Rep5_M37 12 | Mmus_C57-6J_GST_GC_Rep6_M38 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-102/GLDS_version_2/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-102/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/GLDS-102_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6J_KDN_FLT_Rep1_M23,FLT 3 | Mmus_C57-6J_KDN_FLT_Rep2_M24,FLT 4 | Mmus_C57-6J_KDN_FLT_Rep3_M25,FLT 5 | Mmus_C57-6J_KDN_FLT_Rep4_M26,FLT 6 | Mmus_C57-6J_KDN_FLT_Rep5_M27,FLT 7 | Mmus_C57-6J_KDN_FLT_Rep6_M28,FLT 8 | Mmus_C57-6J_KDN_GC_Rep1_M33,GC 9 | Mmus_C57-6J_KDN_GC_Rep2_M34,GC 10 | Mmus_C57-6J_KDN_GC_Rep3_M35,GC 11 | Mmus_C57-6J_KDN_GC_Rep4_M36,GC 12 | Mmus_C57-6J_KDN_GC_Rep5_M37,GC 13 | Mmus_C57-6J_KDN_GC_Rep6_M38,GC 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-102/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-102_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-user=user@nasa.gov 8 | #SBATCH --mail-type=END 9 | 10 | start=$(date +%s) 11 | echo "start time: $start" 12 | echo $HOSTNAME 13 | 14 | /Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 15 | 16 | end=$(date +%s) 17 | echo "end time: $end" 18 | runtime_s=$(echo $(( end - start ))) 19 | echo "total run time(s): $runtime_s" 20 | sec_per_min=60 21 | sec_per_hr=3600 22 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 23 | echo "total run time(m): $runtime_m" 24 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 25 | echo "total run time(h): $runtime_h" 26 | 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-102/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-102/GLDS_version_2/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_KDN_FLT_Rep1_M23 2 | Mmus_C57-6J_KDN_FLT_Rep2_M24 3 | Mmus_C57-6J_KDN_FLT_Rep3_M25 4 | Mmus_C57-6J_KDN_FLT_Rep4_M26 5 | Mmus_C57-6J_KDN_FLT_Rep5_M27 6 | Mmus_C57-6J_KDN_FLT_Rep6_M28 7 | Mmus_C57-6J_KDN_GC_Rep1_M33 8 | Mmus_C57-6J_KDN_GC_Rep2_M34 9 | Mmus_C57-6J_KDN_GC_Rep3_M35 10 | Mmus_C57-6J_KDN_GC_Rep4_M36 11 | Mmus_C57-6J_KDN_GC_Rep5_M37 12 | Mmus_C57-6J_KDN_GC_Rep6_M38 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-104/GLDS_version_2/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-104/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/GLDS-104_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6J_SLS_FLT_Rep1_M23,FLT 3 | Mmus_C57-6J_SLS_FLT_Rep2_M24,FLT 4 | Mmus_C57-6J_SLS_FLT_Rep3_M25,FLT 5 | Mmus_C57-6J_SLS_FLT_Rep4_M26,FLT 6 | Mmus_C57-6J_SLS_FLT_Rep5_M27,FLT 7 | Mmus_C57-6J_SLS_FLT_Rep6_M28,FLT 8 | Mmus_C57-6J_SLS_GC_Rep1_M33,GC 9 | Mmus_C57-6J_SLS_GC_Rep2_M34,GC 10 | Mmus_C57-6J_SLS_GC_Rep3_M35,GC 11 | Mmus_C57-6J_SLS_GC_Rep4_M36,GC 12 | Mmus_C57-6J_SLS_GC_Rep5_M37,GC 13 | Mmus_C57-6J_SLS_GC_Rep6_M38,GC 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-104/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-104_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-user=user@nasa.gov 8 | #SBATCH --mail-type=END 9 | 10 | start=$(date +%s) 11 | echo "start time: $start" 12 | echo $HOSTNAME 13 | 14 | /Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 15 | 16 | end=$(date +%s) 17 | echo "end time: $end" 18 | runtime_s=$(echo $(( end - start ))) 19 | echo "total run time(s): $runtime_s" 20 | sec_per_min=60 21 | sec_per_hr=3600 22 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 23 | echo "total run time(m): $runtime_m" 24 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 25 | echo "total run time(h): $runtime_h" 26 | 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-104/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-104/GLDS_version_2/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_SLS_FLT_Rep1_M23 2 | Mmus_C57-6J_SLS_FLT_Rep2_M24 3 | Mmus_C57-6J_SLS_FLT_Rep3_M25 4 | Mmus_C57-6J_SLS_FLT_Rep4_M26 5 | Mmus_C57-6J_SLS_FLT_Rep5_M27 6 | Mmus_C57-6J_SLS_FLT_Rep6_M28 7 | Mmus_C57-6J_SLS_GC_Rep1_M33 8 | Mmus_C57-6J_SLS_GC_Rep2_M34 9 | Mmus_C57-6J_SLS_GC_Rep3_M35 10 | Mmus_C57-6J_SLS_GC_Rep4_M36 11 | Mmus_C57-6J_SLS_GC_Rep5_M37 12 | Mmus_C57-6J_SLS_GC_Rep6_M38 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-120/OSD_version_14/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-120/OSD_versions_2-4/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-120_raw_multiqc_report" 4 | #SBATCH --output=GLDS-120_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-120/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-120/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-120/OSD_versions_2-4/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-120_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 13 | 14 | end=$(date +%s) 15 | echo "end time: $end" 16 | runtime_s=$(echo $(( end - start ))) 17 | echo "total run time(s): $runtime_s" 18 | sec_per_min=60 19 | sec_per_hr=3600 20 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 21 | echo "total run time(m): $runtime_m" 22 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 23 | echo "total run time(h): $runtime_h" 24 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-120/OSD_versions_2-4/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-137_raw_multiqc_report" 4 | #SBATCH --output=GLDS-137_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-137/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-137/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_BAL-TAL_LVR_BSL_Rep1_B1 2 | Mmus_BAL-TAL_LVR_BSL_Rep2_B2 3 | Mmus_BAL-TAL_LVR_BSL_Rep3_B3 4 | Mmus_BAL-TAL_LVR_BSL_Rep4_B4 5 | Mmus_BAL-TAL_LVR_BSL_Rep5_B6 6 | Mmus_BAL-TAL_LVR_BSL_Rep6_B7 7 | Mmus_BAL-TAL_LVR_FLT_Rep1_F1 8 | Mmus_BAL-TAL_LVR_FLT_Rep2_F2 9 | Mmus_BAL-TAL_LVR_FLT_Rep3_F3 10 | Mmus_BAL-TAL_LVR_FLT_Rep4_F4 11 | Mmus_BAL-TAL_LVR_FLT_Rep5_F5 12 | Mmus_BAL-TAL_LVR_FLT_Rep6_F6 13 | Mmus_BAL-TAL_LVR_GC_Rep1_G1 14 | Mmus_BAL-TAL_LVR_GC_Rep2_G2 15 | Mmus_BAL-TAL_LVR_GC_Rep3_G3 16 | Mmus_BAL-TAL_LVR_GC_Rep4_G5 17 | Mmus_BAL-TAL_LVR_GC_Rep5_G6 18 | Mmus_BAL-TAL_LVR_GC_Rep6_G7 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_BAL-TAL_LVR_BSL_Rep1_B1 2 | Mmus_BAL-TAL_LVR_BSL_Rep2_B2 3 | Mmus_BAL-TAL_LVR_BSL_Rep3_B3 4 | Mmus_BAL-TAL_LVR_BSL_Rep4_B4 5 | Mmus_BAL-TAL_LVR_BSL_Rep5_B6 6 | Mmus_BAL-TAL_LVR_BSL_Rep6_B7 7 | Mmus_BAL-TAL_LVR_FLT_Rep1_F1 8 | Mmus_BAL-TAL_LVR_FLT_Rep2_F2 9 | Mmus_BAL-TAL_LVR_FLT_Rep3_F3 10 | Mmus_BAL-TAL_LVR_FLT_Rep4_F4 11 | Mmus_BAL-TAL_LVR_FLT_Rep5_F5 12 | Mmus_BAL-TAL_LVR_FLT_Rep6_F6 13 | Mmus_BAL-TAL_LVR_GC_Rep1_G1 14 | Mmus_BAL-TAL_LVR_GC_Rep2_G2 15 | Mmus_BAL-TAL_LVR_GC_Rep3_G3 16 | Mmus_BAL-TAL_LVR_GC_Rep4_G5 17 | Mmus_BAL-TAL_LVR_GC_Rep5_G6 18 | Mmus_BAL-TAL_LVR_GC_Rep6_G7 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_BAL-TAL_LVR_BSL_Rep1_B1 2 | Mmus_BAL-TAL_LVR_BSL_Rep2_B2 3 | Mmus_BAL-TAL_LVR_BSL_Rep3_B3 4 | Mmus_BAL-TAL_LVR_BSL_Rep4_B4 5 | Mmus_BAL-TAL_LVR_BSL_Rep5_B6 6 | Mmus_BAL-TAL_LVR_BSL_Rep6_B7 7 | Mmus_BAL-TAL_LVR_FLT_Rep1_F1 8 | Mmus_BAL-TAL_LVR_FLT_Rep2_F2 9 | Mmus_BAL-TAL_LVR_FLT_Rep3_F3 10 | Mmus_BAL-TAL_LVR_FLT_Rep4_F4 11 | Mmus_BAL-TAL_LVR_FLT_Rep5_F5 12 | Mmus_BAL-TAL_LVR_FLT_Rep6_F6 13 | Mmus_BAL-TAL_LVR_GC_Rep1_G1 14 | Mmus_BAL-TAL_LVR_GC_Rep2_G2 15 | Mmus_BAL-TAL_LVR_GC_Rep3_G3 16 | Mmus_BAL-TAL_LVR_GC_Rep4_G5 17 | Mmus_BAL-TAL_LVR_GC_Rep5_G6 18 | Mmus_BAL-TAL_LVR_GC_Rep6_G7 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_BAL-TAL_LVR_BSL_Rep1_B1 2 | Mmus_BAL-TAL_LVR_BSL_Rep2_B2 3 | Mmus_BAL-TAL_LVR_BSL_Rep3_B3 4 | Mmus_BAL-TAL_LVR_BSL_Rep4_B4 5 | Mmus_BAL-TAL_LVR_BSL_Rep5_B6 6 | Mmus_BAL-TAL_LVR_BSL_Rep6_B7 7 | Mmus_BAL-TAL_LVR_FLT_Rep1_F1 8 | Mmus_BAL-TAL_LVR_FLT_Rep2_F2 9 | Mmus_BAL-TAL_LVR_FLT_Rep3_F3 10 | Mmus_BAL-TAL_LVR_FLT_Rep4_F4 11 | Mmus_BAL-TAL_LVR_FLT_Rep5_F5 12 | Mmus_BAL-TAL_LVR_FLT_Rep6_F6 13 | Mmus_BAL-TAL_LVR_GC_Rep1_G1 14 | Mmus_BAL-TAL_LVR_GC_Rep2_G2 15 | Mmus_BAL-TAL_LVR_GC_Rep3_G3 16 | Mmus_BAL-TAL_LVR_GC_Rep4_G5 17 | Mmus_BAL-TAL_LVR_GC_Rep5_G6 18 | Mmus_BAL-TAL_LVR_GC_Rep6_G7 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/04-05-DESeq2_NormCounts_DGE/GLDS-137_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_BAL-TAL_LVR_BSL_Rep1_B1,BSL 3 | Mmus_BAL-TAL_LVR_BSL_Rep2_B2,BSL 4 | Mmus_BAL-TAL_LVR_BSL_Rep3_B3,BSL 5 | Mmus_BAL-TAL_LVR_BSL_Rep4_B4,BSL 6 | Mmus_BAL-TAL_LVR_BSL_Rep5_B6,BSL 7 | Mmus_BAL-TAL_LVR_BSL_Rep6_B7,BSL 8 | Mmus_BAL-TAL_LVR_FLT_Rep1_F1,FLT 9 | Mmus_BAL-TAL_LVR_FLT_Rep2_F2,FLT 10 | Mmus_BAL-TAL_LVR_FLT_Rep3_F3,FLT 11 | Mmus_BAL-TAL_LVR_FLT_Rep4_F4,FLT 12 | Mmus_BAL-TAL_LVR_FLT_Rep5_F5,FLT 13 | Mmus_BAL-TAL_LVR_FLT_Rep6_F6,FLT 14 | Mmus_BAL-TAL_LVR_GC_Rep1_G1,GC 15 | Mmus_BAL-TAL_LVR_GC_Rep2_G2,GC 16 | Mmus_BAL-TAL_LVR_GC_Rep3_G3,GC 17 | Mmus_BAL-TAL_LVR_GC_Rep4_G5,GC 18 | Mmus_BAL-TAL_LVR_GC_Rep5_G6,GC 19 | Mmus_BAL-TAL_LVR_GC_Rep6_G7,GC 20 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-137_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-137/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-138_raw_multiqc_report" 4 | #SBATCH --output=GLDS-138_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-138/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-138/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Bsub_168_cells_FLT_Rep1_BS-A1 2 | Bsub_168_cells_FLT_Rep2_BS-A2 3 | Bsub_168_cells_FLT_Rep3_BS-A3 4 | Bsub_168_cells_FLT_Rep4_BS-A4 5 | Bsub_168_cells_FLT_Rep5_BS-A5 6 | Bsub_168_cells_FLT_Rep6_BS-C1 7 | Bsub_168_cells_FLT_Rep7_BS-C2 8 | Bsub_168_cells_FLT_Rep8_BS-C3 9 | Bsub_168_cells_FLT_Rep9_BS-C4 10 | Bsub_168_cells_GC_Rep1_BS-A1 11 | Bsub_168_cells_GC_Rep2_BS-A2 12 | Bsub_168_cells_GC_Rep3_BS-A3 13 | Bsub_168_cells_GC_Rep4_BS-A4 14 | Bsub_168_cells_GC_Rep5_BS-A5 15 | Bsub_168_cells_GC_Rep6_BS-C1 16 | Bsub_168_cells_GC_Rep7_BS-C2 17 | Bsub_168_cells_GC_Rep8_BS-C3 18 | Bsub_168_cells_GC_Rep9_BS-C4 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Bsub_168_cells_FLT_Rep1_BS-A1 2 | Bsub_168_cells_FLT_Rep2_BS-A2 3 | Bsub_168_cells_FLT_Rep3_BS-A3 4 | Bsub_168_cells_FLT_Rep4_BS-A4 5 | Bsub_168_cells_FLT_Rep5_BS-A5 6 | Bsub_168_cells_FLT_Rep6_BS-C1 7 | Bsub_168_cells_FLT_Rep7_BS-C2 8 | Bsub_168_cells_FLT_Rep8_BS-C3 9 | Bsub_168_cells_FLT_Rep9_BS-C4 10 | Bsub_168_cells_GC_Rep1_BS-A1 11 | Bsub_168_cells_GC_Rep2_BS-A2 12 | Bsub_168_cells_GC_Rep3_BS-A3 13 | Bsub_168_cells_GC_Rep4_BS-A4 14 | Bsub_168_cells_GC_Rep5_BS-A5 15 | Bsub_168_cells_GC_Rep6_BS-C1 16 | Bsub_168_cells_GC_Rep7_BS-C2 17 | Bsub_168_cells_GC_Rep8_BS-C3 18 | Bsub_168_cells_GC_Rep9_BS-C4 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Bsub_168_cells_FLT_Rep1_BS-A1 2 | Bsub_168_cells_FLT_Rep2_BS-A2 3 | Bsub_168_cells_FLT_Rep3_BS-A3 4 | Bsub_168_cells_FLT_Rep4_BS-A4 5 | Bsub_168_cells_FLT_Rep5_BS-A5 6 | Bsub_168_cells_FLT_Rep6_BS-C1 7 | Bsub_168_cells_FLT_Rep7_BS-C2 8 | Bsub_168_cells_FLT_Rep8_BS-C3 9 | Bsub_168_cells_FLT_Rep9_BS-C4 10 | Bsub_168_cells_GC_Rep1_BS-A1 11 | Bsub_168_cells_GC_Rep2_BS-A2 12 | Bsub_168_cells_GC_Rep3_BS-A3 13 | Bsub_168_cells_GC_Rep4_BS-A4 14 | Bsub_168_cells_GC_Rep5_BS-A5 15 | Bsub_168_cells_GC_Rep6_BS-C1 16 | Bsub_168_cells_GC_Rep7_BS-C2 17 | Bsub_168_cells_GC_Rep8_BS-C3 18 | Bsub_168_cells_GC_Rep9_BS-C4 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Bsub_168_cells_FLT_Rep1_BS-A1 2 | Bsub_168_cells_FLT_Rep2_BS-A2 3 | Bsub_168_cells_FLT_Rep3_BS-A3 4 | Bsub_168_cells_FLT_Rep4_BS-A4 5 | Bsub_168_cells_FLT_Rep5_BS-A5 6 | Bsub_168_cells_FLT_Rep6_BS-C1 7 | Bsub_168_cells_FLT_Rep7_BS-C2 8 | Bsub_168_cells_FLT_Rep8_BS-C3 9 | Bsub_168_cells_FLT_Rep9_BS-C4 10 | Bsub_168_cells_GC_Rep1_BS-A1 11 | Bsub_168_cells_GC_Rep2_BS-A2 12 | Bsub_168_cells_GC_Rep3_BS-A3 13 | Bsub_168_cells_GC_Rep4_BS-A4 14 | Bsub_168_cells_GC_Rep5_BS-A5 15 | Bsub_168_cells_GC_Rep6_BS-C1 16 | Bsub_168_cells_GC_Rep7_BS-C2 17 | Bsub_168_cells_GC_Rep8_BS-C3 18 | Bsub_168_cells_GC_Rep9_BS-C4 19 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/04-05-DESeq2_NormCounts_DGE/GLDS-138_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Bsub_168_cells_FLT_Rep1_BS-A1,FLT 3 | Bsub_168_cells_FLT_Rep2_BS-A2,FLT 4 | Bsub_168_cells_FLT_Rep3_BS-A3,FLT 5 | Bsub_168_cells_FLT_Rep4_BS-A4,FLT 6 | Bsub_168_cells_FLT_Rep5_BS-A5,FLT 7 | Bsub_168_cells_FLT_Rep6_BS-C1,FLT 8 | Bsub_168_cells_FLT_Rep7_BS-C2,FLT 9 | Bsub_168_cells_FLT_Rep8_BS-C3,FLT 10 | Bsub_168_cells_FLT_Rep9_BS-C4,FLT 11 | Bsub_168_cells_GC_Rep1_BS-A1,GC 12 | Bsub_168_cells_GC_Rep2_BS-A2,GC 13 | Bsub_168_cells_GC_Rep3_BS-A3,GC 14 | Bsub_168_cells_GC_Rep4_BS-A4,GC 15 | Bsub_168_cells_GC_Rep5_BS-A5,GC 16 | Bsub_168_cells_GC_Rep6_BS-C1,GC 17 | Bsub_168_cells_GC_Rep7_BS-C2,GC 18 | Bsub_168_cells_GC_Rep8_BS-C3,GC 19 | Bsub_168_cells_GC_Rep9_BS-C4,GC 20 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=14000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/04-05-DESeq2_NormCounts_DGE/org.Bsubtilis.eg.db.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/RNAseq/GLDS_Processing_Scripts/GLDS-138/04-05-DESeq2_NormCounts_DGE/org.Bsubtilis.eg.db.tar.gz -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-138/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | ORYLA,Oryzias latipes,8090,org.Olatipes.eg.db 7 | SQUID,Euprymna scolopes,, 8 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 9 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 10 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 11 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 12 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 13 | BACSU,Bacillus subtilis (strain 168),224308,org.Bsubtilis.eg.db 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-168/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-168_raw_multiqc_report" 4 | #SBATCH --output=GLDS-168_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-168/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-168/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-168/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_wERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="deseq2_normcounts_wERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_wERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_wERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-168/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-173_raw_multiqc_report" 4 | #SBATCH --output=GLDS-173_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-173/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-173/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6CR_LVR_FLT_Rep1_F58 2 | Mmus_C57-6CR_LVR_FLT_Rep2_F64 3 | Mmus_C57-6CR_LVR_GC_Rep1_G40 4 | Mmus_C57-6CR_LVR_GC_Rep2_G44 5 | Mmus_C57-6CR_LVR_VIV_Rep1_V14 6 | Mmus_C57-6CR_LVR_VIV_Rep2_V9 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6CR_LVR_FLT_Rep1_F58 2 | Mmus_C57-6CR_LVR_FLT_Rep2_F64 3 | Mmus_C57-6CR_LVR_GC_Rep1_G40 4 | Mmus_C57-6CR_LVR_GC_Rep2_G44 5 | Mmus_C57-6CR_LVR_VIV_Rep1_V14 6 | Mmus_C57-6CR_LVR_VIV_Rep2_V9 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6CR_LVR_FLT_Rep1_F58 2 | Mmus_C57-6CR_LVR_FLT_Rep2_F64 3 | Mmus_C57-6CR_LVR_GC_Rep1_G40 4 | Mmus_C57-6CR_LVR_GC_Rep2_G44 5 | Mmus_C57-6CR_LVR_VIV_Rep1_V14 6 | Mmus_C57-6CR_LVR_VIV_Rep2_V9 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6CR_LVR_FLT_Rep1_F58 2 | Mmus_C57-6CR_LVR_FLT_Rep2_F64 3 | Mmus_C57-6CR_LVR_GC_Rep1_G40 4 | Mmus_C57-6CR_LVR_GC_Rep2_G44 5 | Mmus_C57-6CR_LVR_VIV_Rep1_V14 6 | Mmus_C57-6CR_LVR_VIV_Rep2_V9 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/04-05-DESeq2_NormCounts_DGE/GLDS-173_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6CR_LVR_FLT_Rep1_F58,FLT 3 | Mmus_C57-6CR_LVR_FLT_Rep2_F64,FLT 4 | Mmus_C57-6CR_LVR_GC_Rep1_G40,GC 5 | Mmus_C57-6CR_LVR_GC_Rep2_G44,GC 6 | Mmus_C57-6CR_LVR_VIV_Rep1_V14,VIV 7 | Mmus_C57-6CR_LVR_VIV_Rep2_V9,VIV 8 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_wERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="deseq2_normcounts_wERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_wERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_wERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-173/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-208_raw_multiqc_report" 4 | #SBATCH --output=GLDS-208_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-208/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-208/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Col-0_Root_Zone-II_Rep1_SRR7287373-6 2 | Atha_Col-0_Root_Zone-II_Rep2_SRR7287377-80 3 | Atha_Col-0_Root_Zone-II_Rep3_SRR7287381-4 4 | Atha_Col-0_Root_Zone-I_Rep1_SRR7287361-4 5 | Atha_Col-0_Root_Zone-I_Rep2_SRR7287365-8 6 | Atha_Col-0_Root_Zone-I_Rep3_SRR7287369-72 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Col-0_Root_Zone-II_Rep1_SRR7287373-6 2 | Atha_Col-0_Root_Zone-II_Rep2_SRR7287377-80 3 | Atha_Col-0_Root_Zone-II_Rep3_SRR7287381-4 4 | Atha_Col-0_Root_Zone-I_Rep1_SRR7287361-4 5 | Atha_Col-0_Root_Zone-I_Rep2_SRR7287365-8 6 | Atha_Col-0_Root_Zone-I_Rep3_SRR7287369-72 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/01-TG_Preproc/trimmed_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-208_trimmed_multiqc_report" 4 | #SBATCH --output=GLDS-208_trimmed_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-208/01-TG_Preproc/FastQC_Reports 13 | out_dir=/path/to/GLDS-208/01-TG_Preproc/FastQC_Reports/trimmed_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Col-0_Root_Zone-II_Rep1_SRR7287373-6 2 | Atha_Col-0_Root_Zone-II_Rep2_SRR7287377-80 3 | Atha_Col-0_Root_Zone-II_Rep3_SRR7287381-4 4 | Atha_Col-0_Root_Zone-I_Rep1_SRR7287361-4 5 | Atha_Col-0_Root_Zone-I_Rep2_SRR7287365-8 6 | Atha_Col-0_Root_Zone-I_Rep3_SRR7287369-72 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Col-0_Root_Zone-II_Rep1_SRR7287373-6 2 | Atha_Col-0_Root_Zone-II_Rep2_SRR7287377-80 3 | Atha_Col-0_Root_Zone-II_Rep3_SRR7287381-4 4 | Atha_Col-0_Root_Zone-I_Rep1_SRR7287361-4 5 | Atha_Col-0_Root_Zone-I_Rep2_SRR7287365-8 6 | Atha_Col-0_Root_Zone-I_Rep3_SRR7287369-72 7 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis_ISA.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-208_deseq2_normcounts_noERCC_DGE_vis_ISA" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis_ISA.out 5 | #SBATCH --mem=40000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | Rscript --save deseq2_normcounts_noERCC_DGE_vis_ISA.R 13 | 14 | end=$(date +%s) 15 | echo "end time: $end" 16 | runtime_s=$(echo $(( end - start ))) 17 | echo "total run time(s): $runtime_s" 18 | sec_per_min=60 19 | sec_per_hr=3600 20 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 21 | echo "total run time(m): $runtime_m" 22 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 23 | echo "total run time(h): $runtime_h" 24 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-208/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-218_raw_multiqc_report" 4 | #SBATCH --output=GLDS-218_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-218/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-218/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ws_leaf_FLT_Rep1_GSM2516803 2 | Atha_Ws_leaf_FLT_Rep2_GSM2516804 3 | Atha_Ws_leaf_FLT_Rep3_GSM2516805 4 | Atha_Ws_leaf_GC_Rep1_GSM2516800 5 | Atha_Ws_leaf_GC_Rep2_GSM2516801 6 | Atha_Ws_leaf_GC_Rep3_GSM2516802 7 | Atha_Ws_root_FLT_Rep1_GSM2516797 8 | Atha_Ws_root_FLT_Rep2_GSM2516798 9 | Atha_Ws_root_FLT_Rep3_GSM2516799 10 | Atha_Ws_root_GC_Rep1_GSM2516794 11 | Atha_Ws_root_GC_Rep2_GSM2516795 12 | Atha_Ws_root_GC_Rep3_GSM2516796 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ws_leaf_FLT_Rep1_GSM2516803 2 | Atha_Ws_leaf_FLT_Rep2_GSM2516804 3 | Atha_Ws_leaf_FLT_Rep3_GSM2516805 4 | Atha_Ws_leaf_GC_Rep1_GSM2516800 5 | Atha_Ws_leaf_GC_Rep2_GSM2516801 6 | Atha_Ws_leaf_GC_Rep3_GSM2516802 7 | Atha_Ws_root_FLT_Rep1_GSM2516797 8 | Atha_Ws_root_FLT_Rep2_GSM2516798 9 | Atha_Ws_root_FLT_Rep3_GSM2516799 10 | Atha_Ws_root_GC_Rep1_GSM2516794 11 | Atha_Ws_root_GC_Rep2_GSM2516795 12 | Atha_Ws_root_GC_Rep3_GSM2516796 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/01-TG_Preproc/trimmed_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-218_trimmed_multiqc_report" 4 | #SBATCH --output=GLDS-218_trimmed_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-218/01-TG_Preproc/FastQC_Reports 13 | out_dir=/path/to/GLDS-218/01-TG_Preproc/FastQC_Reports/trimmed_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ws_leaf_FLT_Rep1_GSM2516803 2 | Atha_Ws_leaf_FLT_Rep2_GSM2516804 3 | Atha_Ws_leaf_FLT_Rep3_GSM2516805 4 | Atha_Ws_leaf_GC_Rep1_GSM2516800 5 | Atha_Ws_leaf_GC_Rep2_GSM2516801 6 | Atha_Ws_leaf_GC_Rep3_GSM2516802 7 | Atha_Ws_root_FLT_Rep1_GSM2516797 8 | Atha_Ws_root_FLT_Rep2_GSM2516798 9 | Atha_Ws_root_FLT_Rep3_GSM2516799 10 | Atha_Ws_root_GC_Rep1_GSM2516794 11 | Atha_Ws_root_GC_Rep2_GSM2516795 12 | Atha_Ws_root_GC_Rep3_GSM2516796 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ws_leaf_FLT_Rep1_GSM2516803 2 | Atha_Ws_leaf_FLT_Rep2_GSM2516804 3 | Atha_Ws_leaf_FLT_Rep3_GSM2516805 4 | Atha_Ws_leaf_GC_Rep1_GSM2516800 5 | Atha_Ws_leaf_GC_Rep2_GSM2516801 6 | Atha_Ws_leaf_GC_Rep3_GSM2516802 7 | Atha_Ws_root_FLT_Rep1_GSM2516797 8 | Atha_Ws_root_FLT_Rep2_GSM2516798 9 | Atha_Ws_root_FLT_Rep3_GSM2516799 10 | Atha_Ws_root_GC_Rep1_GSM2516794 11 | Atha_Ws_root_GC_Rep2_GSM2516795 12 | Atha_Ws_root_GC_Rep3_GSM2516796 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/04-05-DESeq2_NormCounts_DGE/GLDS-218_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Atha_Ws_leaf_FLT_Rep1_GSM2516803,leaf_FLT 3 | Atha_Ws_leaf_FLT_Rep2_GSM2516804,leaf_FLT 4 | Atha_Ws_leaf_FLT_Rep3_GSM2516805,leaf_FLT 5 | Atha_Ws_leaf_GC_Rep1_GSM2516800,leaf_GC 6 | Atha_Ws_leaf_GC_Rep2_GSM2516801,leaf_GC 7 | Atha_Ws_leaf_GC_Rep3_GSM2516802,leaf_GC 8 | Atha_Ws_root_FLT_Rep1_GSM2516797,root_FLT 9 | Atha_Ws_root_FLT_Rep2_GSM2516798,root_FLT 10 | Atha_Ws_root_FLT_Rep3_GSM2516799,root_FLT 11 | Atha_Ws_root_GC_Rep1_GSM2516794,root_GC 12 | Atha_Ws_root_GC_Rep2_GSM2516795,root_GC 13 | Atha_Ws_root_GC_Rep3_GSM2516796,root_GC 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=20000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 13 | 14 | end=$(date +%s) 15 | echo "end time: $end" 16 | runtime_s=$(echo $(( end - start ))) 17 | echo "total run time(s): $runtime_s" 18 | sec_per_min=60 19 | sec_per_hr=3600 20 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 21 | echo "total run time(m): $runtime_m" 22 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 23 | echo "total run time(h): $runtime_h" 24 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-218/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | ORYLA,Oryzias latipes,8090,org.Olatipes.eg.db 7 | SQUID,Euprymna scolopes,, 8 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 9 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 10 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 11 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 12 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 13 | BACSU,Bacillus subtilis (strain 168),224308,MeSH.Bsu.168.eg.db 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-235/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-235_raw_multiqc_report" 4 | #SBATCH --output=GLDS-235_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-235/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-235/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-235/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_wERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-235_deseq2_normcounts_wERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_wERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_wERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-235/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-236/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-236_raw_multiqc_report" 4 | #SBATCH --output=GLDS-236_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-236/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-236/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-236/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_wERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-236_deseq2_normcounts_wERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_wERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_wERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-236/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-245/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-245_raw_multiqc_report" 4 | #SBATCH --output=GLDS-245_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-245/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-245/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-245/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_wERCC_DGE_vis_ISA.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-245_deseq2_normcounts_wERCC_DGE_vis_ISA" 4 | #SBATCH --output=deseq2_normcounts_wERCC_DGE_vis_ISA.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_wERCC_DGE_vis_ISA.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-245/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-251_raw_multiqc_report" 4 | #SBATCH --output=GLDS-251_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-251/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-251/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ler-0_sl_FLT_0.09G_Rep1_Sample-131 2 | Atha_Ler-0_sl_FLT_0.09G_Rep2_Sample-136 3 | Atha_Ler-0_sl_FLT_0.09G_Rep3_Sample-139 4 | Atha_Ler-0_sl_FLT_0.18G_Rep1_Sample-135 5 | Atha_Ler-0_sl_FLT_0.18G_Rep2_Sample-151 6 | Atha_Ler-0_sl_FLT_0.18G_Rep3_Sample-156 7 | Atha_Ler-0_sl_FLT_0.36G_Rep1_Sample-154 8 | Atha_Ler-0_sl_FLT_0.36G_Rep2_Sample-160 9 | Atha_Ler-0_sl_FLT_0.36G_Rep3_Sample-211 10 | Atha_Ler-0_sl_FLT_0.57G_Rep1_Sample-171 11 | Atha_Ler-0_sl_FLT_0.57G_Rep2_Sample-176 12 | Atha_Ler-0_sl_FLT_0.57G_Rep3_Sample-214 13 | Atha_Ler-0_sl_FLT_0.57G_Rep4_Sample-231 14 | Atha_Ler-0_sl_FLT_1G_Rep1_Sample-175 15 | Atha_Ler-0_sl_FLT_1G_Rep2_Sample-179 16 | Atha_Ler-0_sl_FLT_1G_Rep3_Sample-235 17 | Atha_Ler-0_sl_FLT_uG_Rep1_Sample-111 18 | Atha_Ler-0_sl_FLT_uG_Rep2_Sample-114 19 | Atha_Ler-0_sl_FLT_uG_Rep3_Sample-116 20 | Atha_Ler-0_sl_FLT_uG_Rep4_Sample-120 21 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ler-0_sl_FLT_0.09G_Rep1_Sample-131 2 | Atha_Ler-0_sl_FLT_0.09G_Rep2_Sample-136 3 | Atha_Ler-0_sl_FLT_0.09G_Rep3_Sample-139 4 | Atha_Ler-0_sl_FLT_0.18G_Rep1_Sample-135 5 | Atha_Ler-0_sl_FLT_0.18G_Rep2_Sample-151 6 | Atha_Ler-0_sl_FLT_0.18G_Rep3_Sample-156 7 | Atha_Ler-0_sl_FLT_0.36G_Rep1_Sample-154 8 | Atha_Ler-0_sl_FLT_0.36G_Rep2_Sample-160 9 | Atha_Ler-0_sl_FLT_0.36G_Rep3_Sample-211 10 | Atha_Ler-0_sl_FLT_0.57G_Rep1_Sample-171 11 | Atha_Ler-0_sl_FLT_0.57G_Rep2_Sample-176 12 | Atha_Ler-0_sl_FLT_0.57G_Rep3_Sample-214 13 | Atha_Ler-0_sl_FLT_0.57G_Rep4_Sample-231 14 | Atha_Ler-0_sl_FLT_1G_Rep1_Sample-175 15 | Atha_Ler-0_sl_FLT_1G_Rep2_Sample-179 16 | Atha_Ler-0_sl_FLT_1G_Rep3_Sample-235 17 | Atha_Ler-0_sl_FLT_uG_Rep1_Sample-111 18 | Atha_Ler-0_sl_FLT_uG_Rep2_Sample-114 19 | Atha_Ler-0_sl_FLT_uG_Rep3_Sample-116 20 | Atha_Ler-0_sl_FLT_uG_Rep4_Sample-120 21 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/01-TG_Preproc/trimmed_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-251_trimmed_multiqc_report" 4 | #SBATCH --output=GLDS-251_trimmed_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-251/01-TG_Preproc/FastQC_Reports 13 | out_dir=/path/to/GLDS-251/01-TG_Preproc/FastQC_Reports/trimmed_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ler-0_sl_FLT_0.09G_Rep1_Sample-131 2 | Atha_Ler-0_sl_FLT_0.09G_Rep2_Sample-136 3 | Atha_Ler-0_sl_FLT_0.09G_Rep3_Sample-139 4 | Atha_Ler-0_sl_FLT_0.18G_Rep1_Sample-135 5 | Atha_Ler-0_sl_FLT_0.18G_Rep2_Sample-151 6 | Atha_Ler-0_sl_FLT_0.18G_Rep3_Sample-156 7 | Atha_Ler-0_sl_FLT_0.36G_Rep1_Sample-154 8 | Atha_Ler-0_sl_FLT_0.36G_Rep2_Sample-160 9 | Atha_Ler-0_sl_FLT_0.36G_Rep3_Sample-211 10 | Atha_Ler-0_sl_FLT_0.57G_Rep1_Sample-171 11 | Atha_Ler-0_sl_FLT_0.57G_Rep2_Sample-176 12 | Atha_Ler-0_sl_FLT_0.57G_Rep3_Sample-214 13 | Atha_Ler-0_sl_FLT_0.57G_Rep4_Sample-231 14 | Atha_Ler-0_sl_FLT_1G_Rep1_Sample-175 15 | Atha_Ler-0_sl_FLT_1G_Rep2_Sample-179 16 | Atha_Ler-0_sl_FLT_1G_Rep3_Sample-235 17 | Atha_Ler-0_sl_FLT_uG_Rep1_Sample-111 18 | Atha_Ler-0_sl_FLT_uG_Rep2_Sample-114 19 | Atha_Ler-0_sl_FLT_uG_Rep3_Sample-116 20 | Atha_Ler-0_sl_FLT_uG_Rep4_Sample-120 21 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_Ler-0_sl_FLT_0.09G_Rep1_Sample-131 2 | Atha_Ler-0_sl_FLT_0.09G_Rep2_Sample-136 3 | Atha_Ler-0_sl_FLT_0.09G_Rep3_Sample-139 4 | Atha_Ler-0_sl_FLT_0.18G_Rep1_Sample-135 5 | Atha_Ler-0_sl_FLT_0.18G_Rep2_Sample-151 6 | Atha_Ler-0_sl_FLT_0.18G_Rep3_Sample-156 7 | Atha_Ler-0_sl_FLT_0.36G_Rep1_Sample-154 8 | Atha_Ler-0_sl_FLT_0.36G_Rep2_Sample-160 9 | Atha_Ler-0_sl_FLT_0.36G_Rep3_Sample-211 10 | Atha_Ler-0_sl_FLT_0.57G_Rep1_Sample-171 11 | Atha_Ler-0_sl_FLT_0.57G_Rep2_Sample-176 12 | Atha_Ler-0_sl_FLT_0.57G_Rep3_Sample-214 13 | Atha_Ler-0_sl_FLT_0.57G_Rep4_Sample-231 14 | Atha_Ler-0_sl_FLT_1G_Rep1_Sample-175 15 | Atha_Ler-0_sl_FLT_1G_Rep2_Sample-179 16 | Atha_Ler-0_sl_FLT_1G_Rep3_Sample-235 17 | Atha_Ler-0_sl_FLT_uG_Rep1_Sample-111 18 | Atha_Ler-0_sl_FLT_uG_Rep2_Sample-114 19 | Atha_Ler-0_sl_FLT_uG_Rep3_Sample-116 20 | Atha_Ler-0_sl_FLT_uG_Rep4_Sample-120 21 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=20000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 13 | 14 | end=$(date +%s) 15 | echo "end time: $end" 16 | runtime_s=$(echo $(( end - start ))) 17 | echo "total run time(s): $runtime_s" 18 | sec_per_min=60 19 | sec_per_hr=3600 20 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 21 | echo "total run time(m): $runtime_m" 22 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 23 | echo "total run time(h): $runtime_h" 24 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-251/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/RSeQC_analyses/01_sort_index/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/RSeQC_analyses/02_geneBody_coverage/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/RSeQC_analyses/03_infer_experiment/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-314/GLDS_version_4/RSeQC_analyses/05_read_distribution/samples.txt: -------------------------------------------------------------------------------- 1 | 05G4_WT_RED_Col0_03g_Rep1 2 | 06H4_WT_RED_Col0_03g_Rep2 3 | 07A5_WT_RED_Col0_03g_Rep3 4 | 13I4_WT_DARK_Col0_03g_Rep1 5 | 14J4_WT_DARK_Col0_03g_Rep2 6 | 15A7_WT_DARK_Col0_03g_Rep3 7 | 21H5_WT_RED_Col0_1g_Rep1 8 | 22A6_WT_RED_Col0_1g_Rep2 9 | 23B6_WT_RED_Col0_1g_Rep3 10 | 30H7_WT_DARK_Col0_1g_Rep1 11 | 31A8_WT_DARK_Col0_1g_Rep2 12 | 32B8_WT_DARK_Col0_1g_Rep3 13 | JBA1_WT_DARK_Col0_0g_Rep1 14 | JBA3_WT_RED_Col0_0g_Rep2 15 | JBB1_WT_DARK_Col0_0g_Rep2 16 | JBB3_WT_RED_Col0_0g_Rep3 17 | JBH2_WT_RED_Col0_0g_Rep1 18 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-37/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-37_raw_multiqc_report" 4 | #SBATCH --output=GLDS-37_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-37/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-37/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-37/01-TG_Preproc/trimmed_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-37_trimmed_multiqc_report" 4 | #SBATCH --output=GLDS-37_trimmed_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-37/01-TG_Preproc/FastQC_Reports 13 | out_dir=/path/to/GLDS-37/01-TG_Preproc/FastQC_Reports/trimmed_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-37/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-37_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 13 | 14 | end=$(date +%s) 15 | echo "end time: $end" 16 | runtime_s=$(echo $(( end - start ))) 17 | echo "total run time(s): $runtime_s" 18 | sec_per_min=60 19 | sec_per_hr=3600 20 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 21 | echo "total run time(m): $runtime_m" 22 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 23 | echo "total run time(h): $runtime_h" 24 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-37/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-38_raw_multiqc_report" 4 | #SBATCH --output=GLDS-38_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-38/00-RawData/FastQC_Reports 13 | out_dir=/path/to/GLDS-38/00-RawData/FastQC_Reports/raw_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_WT-Col-0_sl_FLT_Rep1_G1S1 2 | Atha_WT-Col-0_sl_FLT_Rep2_G1S2 3 | Atha_WT-Col-0_sl_FLT_Rep3_G1S3 4 | Atha_WT-Col-0_sl_GC_Rep1_G2S1 5 | Atha_WT-Col-0_sl_GC_Rep2_G2S2 6 | Atha_WT-Col-0_sl_GC_Rep3_G2S3 7 | Atha_WT-Col-0_sl_LN2_Rep1_n2-1 8 | Atha_WT-Col-0_sl_LN2_Rep2_n2-2 9 | Atha_WT-Col-0_sl_LN2_Rep3_n2-3 10 | Atha_WT-Col-0_sl_RNAlat_Rep1_rl1 11 | Atha_WT-Col-0_sl_RNAlat_Rep2_rl2 12 | Atha_WT-Col-0_sl_RNAlat_Rep3_rl3 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_WT-Col-0_sl_FLT_Rep1_G1S1 2 | Atha_WT-Col-0_sl_FLT_Rep2_G1S2 3 | Atha_WT-Col-0_sl_FLT_Rep3_G1S3 4 | Atha_WT-Col-0_sl_GC_Rep1_G2S1 5 | Atha_WT-Col-0_sl_GC_Rep2_G2S2 6 | Atha_WT-Col-0_sl_GC_Rep3_G2S3 7 | Atha_WT-Col-0_sl_LN2_Rep1_n2-1 8 | Atha_WT-Col-0_sl_LN2_Rep2_n2-2 9 | Atha_WT-Col-0_sl_LN2_Rep3_n2-3 10 | Atha_WT-Col-0_sl_RNAlat_Rep1_rl1 11 | Atha_WT-Col-0_sl_RNAlat_Rep2_rl2 12 | Atha_WT-Col-0_sl_RNAlat_Rep3_rl3 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/01-TG_Preproc/trimmed_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-38_trimmed_multiqc_report" 4 | #SBATCH --output=GLDS-38_trimmed_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | in_dir=/path/to/GLDS-38/01-TG_Preproc/FastQC_Reports 13 | out_dir=/path/to/GLDS-38/01-TG_Preproc/FastQC_Reports/trimmed_multiqc_report 14 | 15 | call="multiqc -o $out_dir $in_dir/" 16 | 17 | echo $call 18 | eval $call 19 | 20 | end=$(date +%s) 21 | echo "end time: $end" 22 | runtime_s=$(echo $(( end - start ))) 23 | echo "total run time(s): $runtime_s" 24 | sec_per_min=60 25 | sec_per_hr=3600 26 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 27 | echo "total run time(m): $runtime_m" 28 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 29 | echo "total run time(h): $runtime_h" 30 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_WT-Col-0_sl_FLT_Rep1_G1S1 2 | Atha_WT-Col-0_sl_FLT_Rep2_G1S2 3 | Atha_WT-Col-0_sl_FLT_Rep3_G1S3 4 | Atha_WT-Col-0_sl_GC_Rep1_G2S1 5 | Atha_WT-Col-0_sl_GC_Rep2_G2S2 6 | Atha_WT-Col-0_sl_GC_Rep3_G2S3 7 | Atha_WT-Col-0_sl_LN2_Rep1_n2-1 8 | Atha_WT-Col-0_sl_LN2_Rep2_n2-2 9 | Atha_WT-Col-0_sl_LN2_Rep3_n2-3 10 | Atha_WT-Col-0_sl_RNAlat_Rep1_rl1 11 | Atha_WT-Col-0_sl_RNAlat_Rep2_rl2 12 | Atha_WT-Col-0_sl_RNAlat_Rep3_rl3 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Atha_WT-Col-0_sl_FLT_Rep1_G1S1 2 | Atha_WT-Col-0_sl_FLT_Rep2_G1S2 3 | Atha_WT-Col-0_sl_FLT_Rep3_G1S3 4 | Atha_WT-Col-0_sl_GC_Rep1_G2S1 5 | Atha_WT-Col-0_sl_GC_Rep2_G2S2 6 | Atha_WT-Col-0_sl_GC_Rep3_G2S3 7 | Atha_WT-Col-0_sl_LN2_Rep1_n2-1 8 | Atha_WT-Col-0_sl_LN2_Rep2_n2-2 9 | Atha_WT-Col-0_sl_LN2_Rep3_n2-3 10 | Atha_WT-Col-0_sl_RNAlat_Rep1_rl1 11 | Atha_WT-Col-0_sl_RNAlat_Rep2_rl2 12 | Atha_WT-Col-0_sl_RNAlat_Rep3_rl3 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/04-05-DESeq2_NormCounts_DGE/GLDS-38_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Atha_WT-Col-0_sl_FLT_Rep1_G1S1,FLT 3 | Atha_WT-Col-0_sl_FLT_Rep2_G1S2,FLT 4 | Atha_WT-Col-0_sl_FLT_Rep3_G1S3,FLT 5 | Atha_WT-Col-0_sl_GC_Rep1_G2S1,GC 6 | Atha_WT-Col-0_sl_GC_Rep2_G2S2,GC 7 | Atha_WT-Col-0_sl_GC_Rep3_G2S3,GC 8 | Atha_WT-Col-0_sl_LN2_Rep1_n2-1,LN2 9 | Atha_WT-Col-0_sl_LN2_Rep2_n2-2,LN2 10 | Atha_WT-Col-0_sl_LN2_Rep3_n2-3,LN2 11 | Atha_WT-Col-0_sl_RNAlat_Rep1_rl1,RNAlat 12 | Atha_WT-Col-0_sl_RNAlat_Rep2_rl2,RNAlat 13 | Atha_WT-Col-0_sl_RNAlat_Rep3_rl3,RNAlat 14 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-38_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | 8 | start=$(date +%s) 9 | echo "start time: $start" 10 | echo $HOSTNAME 11 | 12 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 13 | 14 | end=$(date +%s) 15 | echo "end time: $end" 16 | runtime_s=$(echo $(( end - start ))) 17 | echo "total run time(s): $runtime_s" 18 | sec_per_min=60 19 | sec_per_hr=3600 20 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 21 | echo "total run time(m): $runtime_m" 22 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 23 | echo "total run time(h): $runtime_h" 24 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-38/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/RSeQC_analyses/01_sort_index/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/RSeQC_analyses/02_geneBody_coverage/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/RSeQC_analyses/03_infer_experiment/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-401/GLDS_version_2/RSeQC_analyses/05_read_distribution/samples.txt: -------------------------------------------------------------------------------- 1 | GSM5398358 2 | GSM5398359 3 | GSM5398360 4 | GSM5398361 5 | GSM5398362 6 | GSM5398363 7 | GSM5398364 8 | GSM5398365 9 | GSM5398366 10 | GSM5398367 11 | GSM5398368 12 | GSM5398369 13 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-47_raw_multiqc_report" 4 | #SBATCH --output=GLDS-47_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-47/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-47/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6T_LVR_BSL_Rep1_B1 2 | Mmus_C57-6T_LVR_BSL_Rep2_B2 3 | Mmus_C57-6T_LVR_BSL_Rep3_B3 4 | Mmus_C57-6T_LVR_FLT_Rep1_F1 5 | Mmus_C57-6T_LVR_FLT_Rep2_F2 6 | Mmus_C57-6T_LVR_FLT_Rep3_F4 7 | Mmus_C57-6T_LVR_GC_Rep1_G2 8 | Mmus_C57-6T_LVR_GC_Rep2_G3 9 | Mmus_C57-6T_LVR_GC_Rep3_G5 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6T_LVR_BSL_Rep1_B1 2 | Mmus_C57-6T_LVR_BSL_Rep2_B2 3 | Mmus_C57-6T_LVR_BSL_Rep3_B3 4 | Mmus_C57-6T_LVR_FLT_Rep1_F1 5 | Mmus_C57-6T_LVR_FLT_Rep2_F2 6 | Mmus_C57-6T_LVR_FLT_Rep3_F4 7 | Mmus_C57-6T_LVR_GC_Rep1_G2 8 | Mmus_C57-6T_LVR_GC_Rep2_G3 9 | Mmus_C57-6T_LVR_GC_Rep3_G5 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6T_LVR_BSL_Rep1_B1 2 | Mmus_C57-6T_LVR_BSL_Rep2_B2 3 | Mmus_C57-6T_LVR_BSL_Rep3_B3 4 | Mmus_C57-6T_LVR_FLT_Rep1_F1 5 | Mmus_C57-6T_LVR_FLT_Rep2_F2 6 | Mmus_C57-6T_LVR_FLT_Rep3_F4 7 | Mmus_C57-6T_LVR_GC_Rep1_G2 8 | Mmus_C57-6T_LVR_GC_Rep2_G3 9 | Mmus_C57-6T_LVR_GC_Rep3_G5 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6T_LVR_BSL_Rep1_B1 2 | Mmus_C57-6T_LVR_BSL_Rep2_B2 3 | Mmus_C57-6T_LVR_BSL_Rep3_B3 4 | Mmus_C57-6T_LVR_FLT_Rep1_F1 5 | Mmus_C57-6T_LVR_FLT_Rep2_F2 6 | Mmus_C57-6T_LVR_FLT_Rep3_F4 7 | Mmus_C57-6T_LVR_GC_Rep1_G2 8 | Mmus_C57-6T_LVR_GC_Rep2_G3 9 | Mmus_C57-6T_LVR_GC_Rep3_G5 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/04-05-DESeq2_NormCounts_DGE/GLDS-47_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6T_LVR_BSL_Rep1_B1,BSL 3 | Mmus_C57-6T_LVR_BSL_Rep2_B2,BSL 4 | Mmus_C57-6T_LVR_BSL_Rep3_B3,BSL 5 | Mmus_C57-6T_LVR_FLT_Rep1_F1,FLT 6 | Mmus_C57-6T_LVR_FLT_Rep2_F2,FLT 7 | Mmus_C57-6T_LVR_FLT_Rep3_F4,FLT 8 | Mmus_C57-6T_LVR_GC_Rep1_G2,GC 9 | Mmus_C57-6T_LVR_GC_Rep2_G3,GC 10 | Mmus_C57-6T_LVR_GC_Rep3_G5,GC 11 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-47_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-47/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-48_raw_multiqc_report" 4 | #SBATCH --output=GLDS-48_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-48/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-48/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_FLT_C_Rep1_M25 2 | Mmus_C57-6J_LVR_FLT_C_Rep2_M26 3 | Mmus_C57-6J_LVR_FLT_C_Rep3_M27 4 | Mmus_C57-6J_LVR_FLT_C_Rep4_M28 5 | Mmus_C57-6J_LVR_FLT_C_Rep5_M30 6 | Mmus_C57-6J_LVR_FLT_I_Rep1_M21 7 | Mmus_C57-6J_LVR_FLT_I_Rep2_M22 8 | Mmus_C57-6J_LVR_GC_C_Rep1_M36 9 | Mmus_C57-6J_LVR_GC_C_Rep2_M37 10 | Mmus_C57-6J_LVR_GC_C_Rep3_M38 11 | Mmus_C57-6J_LVR_GC_C_Rep4_M39 12 | Mmus_C57-6J_LVR_GC_C_Rep5_M40 13 | Mmus_C57-6J_LVR_GC_I_Rep1_M31 14 | Mmus_C57-6J_LVR_GC_I_Rep2_M32 15 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_FLT_C_Rep1_M25 2 | Mmus_C57-6J_LVR_FLT_C_Rep2_M26 3 | Mmus_C57-6J_LVR_FLT_C_Rep3_M27 4 | Mmus_C57-6J_LVR_FLT_C_Rep4_M28 5 | Mmus_C57-6J_LVR_FLT_C_Rep5_M30 6 | Mmus_C57-6J_LVR_FLT_I_Rep1_M21 7 | Mmus_C57-6J_LVR_FLT_I_Rep2_M22 8 | Mmus_C57-6J_LVR_GC_C_Rep1_M36 9 | Mmus_C57-6J_LVR_GC_C_Rep2_M37 10 | Mmus_C57-6J_LVR_GC_C_Rep3_M38 11 | Mmus_C57-6J_LVR_GC_C_Rep4_M39 12 | Mmus_C57-6J_LVR_GC_C_Rep5_M40 13 | Mmus_C57-6J_LVR_GC_I_Rep1_M31 14 | Mmus_C57-6J_LVR_GC_I_Rep2_M32 15 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_FLT_C_Rep1_M25 2 | Mmus_C57-6J_LVR_FLT_C_Rep2_M26 3 | Mmus_C57-6J_LVR_FLT_C_Rep3_M27 4 | Mmus_C57-6J_LVR_FLT_C_Rep4_M28 5 | Mmus_C57-6J_LVR_FLT_C_Rep5_M30 6 | Mmus_C57-6J_LVR_FLT_I_Rep1_M21 7 | Mmus_C57-6J_LVR_FLT_I_Rep2_M22 8 | Mmus_C57-6J_LVR_GC_C_Rep1_M36 9 | Mmus_C57-6J_LVR_GC_C_Rep2_M37 10 | Mmus_C57-6J_LVR_GC_C_Rep3_M38 11 | Mmus_C57-6J_LVR_GC_C_Rep4_M39 12 | Mmus_C57-6J_LVR_GC_C_Rep5_M40 13 | Mmus_C57-6J_LVR_GC_I_Rep1_M31 14 | Mmus_C57-6J_LVR_GC_I_Rep2_M32 15 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_FLT_C_Rep1_M25 2 | Mmus_C57-6J_LVR_FLT_C_Rep2_M26 3 | Mmus_C57-6J_LVR_FLT_C_Rep3_M27 4 | Mmus_C57-6J_LVR_FLT_C_Rep4_M28 5 | Mmus_C57-6J_LVR_FLT_C_Rep5_M30 6 | Mmus_C57-6J_LVR_FLT_I_Rep1_M21 7 | Mmus_C57-6J_LVR_FLT_I_Rep2_M22 8 | Mmus_C57-6J_LVR_GC_C_Rep1_M36 9 | Mmus_C57-6J_LVR_GC_C_Rep2_M37 10 | Mmus_C57-6J_LVR_GC_C_Rep3_M38 11 | Mmus_C57-6J_LVR_GC_C_Rep4_M39 12 | Mmus_C57-6J_LVR_GC_C_Rep5_M40 13 | Mmus_C57-6J_LVR_GC_I_Rep1_M31 14 | Mmus_C57-6J_LVR_GC_I_Rep2_M32 15 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/04-05-DESeq2_NormCounts_DGE/GLDS-48_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6J_LVR_FLT_C_Rep1_M25,FLT_C 3 | Mmus_C57-6J_LVR_FLT_C_Rep2_M26,FLT_C 4 | Mmus_C57-6J_LVR_FLT_C_Rep3_M27,FLT_C 5 | Mmus_C57-6J_LVR_FLT_C_Rep4_M28,FLT_C 6 | Mmus_C57-6J_LVR_FLT_C_Rep5_M30,FLT_C 7 | Mmus_C57-6J_LVR_FLT_I_Rep1_M21,FLT_I 8 | Mmus_C57-6J_LVR_FLT_I_Rep2_M22,FLT_I 9 | Mmus_C57-6J_LVR_GC_C_Rep1_M36,GC_C 10 | Mmus_C57-6J_LVR_GC_C_Rep2_M37,GC_C 11 | Mmus_C57-6J_LVR_GC_C_Rep3_M38,GC_C 12 | Mmus_C57-6J_LVR_GC_C_Rep4_M39,GC_C 13 | Mmus_C57-6J_LVR_GC_C_Rep5_M40,GC_C 14 | Mmus_C57-6J_LVR_GC_I_Rep1_M31,GC_I 15 | Mmus_C57-6J_LVR_GC_I_Rep2_M32,GC_I 16 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-48_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-48/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/00-RawData/raw_multiqc.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-49_raw_multiqc_report" 4 | #SBATCH --output=GLDS-49_raw_multiqc_report.out 5 | #SBATCH --mem=16000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | in_dir=/path/to/GLDS-49/00-RawData/FastQC_Reports 14 | out_dir=/path/to/GLDS-49/00-RawData/FastQC_Reports/raw_multiqc_report 15 | 16 | call="multiqc -o $out_dir $in_dir/" 17 | 18 | echo $call 19 | eval $call 20 | 21 | end=$(date +%s) 22 | echo "end time: $end" 23 | runtime_s=$(echo $(( end - start ))) 24 | echo "total run time(s): $runtime_s" 25 | sec_per_min=60 26 | sec_per_hr=3600 27 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 28 | echo "total run time(m): $runtime_m" 29 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 30 | echo "total run time(h): $runtime_h" 31 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/00-RawData/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_DI_1y_Rep1 2 | Mmus_C57-6J_LVR_DI_1y_Rep2 3 | Mmus_C57-6J_LVR_DI_1y_Rep3 4 | Mmus_C57-6J_LVR_LN2_1y_Rep1 5 | Mmus_C57-6J_LVR_LN2_1y_Rep2 6 | Mmus_C57-6J_LVR_LN2_1y_Rep3 7 | Mmus_C57-6J_LVR_LN2_3d_Rep1 8 | Mmus_C57-6J_LVR_LN2_3d_Rep2 9 | Mmus_C57-6J_LVR_LN2_3d_Rep3 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/01-TG_Preproc/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_DI_1y_Rep1 2 | Mmus_C57-6J_LVR_DI_1y_Rep2 3 | Mmus_C57-6J_LVR_DI_1y_Rep3 4 | Mmus_C57-6J_LVR_LN2_1y_Rep1 5 | Mmus_C57-6J_LVR_LN2_1y_Rep2 6 | Mmus_C57-6J_LVR_LN2_1y_Rep3 7 | Mmus_C57-6J_LVR_LN2_3d_Rep1 8 | Mmus_C57-6J_LVR_LN2_3d_Rep2 9 | Mmus_C57-6J_LVR_LN2_3d_Rep3 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/02-STAR_Alignment/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_DI_1y_Rep1 2 | Mmus_C57-6J_LVR_DI_1y_Rep2 3 | Mmus_C57-6J_LVR_DI_1y_Rep3 4 | Mmus_C57-6J_LVR_LN2_1y_Rep1 5 | Mmus_C57-6J_LVR_LN2_1y_Rep2 6 | Mmus_C57-6J_LVR_LN2_1y_Rep3 7 | Mmus_C57-6J_LVR_LN2_3d_Rep1 8 | Mmus_C57-6J_LVR_LN2_3d_Rep2 9 | Mmus_C57-6J_LVR_LN2_3d_Rep3 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/03-RSEM_Counts/make_Mmus_RSEM_index.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="make_Mmus_RSEM_index" 4 | #SBATCH --output=make_Mmus_RSEM_index.out 5 | #SBATCH --mem=60000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | rsem-prepare-reference --gtf /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.96.gtf \ 14 | /path/to/Genomes/Mus_musculus/Mus_musculus.GRCm38.dna.toplevel.fa \ 15 | /path/to/RSEM_Indices/Mus_musculus/Mmus 16 | 17 | end=$(date +%s) 18 | echo "end time: $end" 19 | runtime_s=$(echo $(( end - start ))) 20 | echo "total run time(s): $runtime_s" 21 | sec_per_min=60 22 | sec_per_hr=3600 23 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 24 | echo "total run time(m): $runtime_m" 25 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 26 | echo "total run time(h): $runtime_h" 27 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/03-RSEM_Counts/samples.txt: -------------------------------------------------------------------------------- 1 | Mmus_C57-6J_LVR_DI_1y_Rep1 2 | Mmus_C57-6J_LVR_DI_1y_Rep2 3 | Mmus_C57-6J_LVR_DI_1y_Rep3 4 | Mmus_C57-6J_LVR_LN2_1y_Rep1 5 | Mmus_C57-6J_LVR_LN2_1y_Rep2 6 | Mmus_C57-6J_LVR_LN2_1y_Rep3 7 | Mmus_C57-6J_LVR_LN2_3d_Rep1 8 | Mmus_C57-6J_LVR_LN2_3d_Rep2 9 | Mmus_C57-6J_LVR_LN2_3d_Rep3 10 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/04-05-DESeq2_NormCounts_DGE/GLDS-49_metadata.csv: -------------------------------------------------------------------------------- 1 | sample,condition 2 | Mmus_C57-6J_LVR_DI_1y_Rep1,DI_1y 3 | Mmus_C57-6J_LVR_DI_1y_Rep2,DI_1y 4 | Mmus_C57-6J_LVR_DI_1y_Rep3,DI_1y 5 | Mmus_C57-6J_LVR_LN2_1y_Rep1,LN2_1y 6 | Mmus_C57-6J_LVR_LN2_1y_Rep2,LN2_1y 7 | Mmus_C57-6J_LVR_LN2_1y_Rep3,LN2_1y 8 | Mmus_C57-6J_LVR_LN2_3d_Rep1,LN2_3d 9 | Mmus_C57-6J_LVR_LN2_3d_Rep2,LN2_3d 10 | Mmus_C57-6J_LVR_LN2_3d_Rep3,LN2_3d 11 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/04-05-DESeq2_NormCounts_DGE/deseq2_normcounts_noERCC_DGE_vis.slurm: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # 3 | #SBATCH --job-name="GLDS-49_deseq2_normcounts_noERCC_DGE_vis" 4 | #SBATCH --output=deseq2_normcounts_noERCC_DGE_vis.out 5 | #SBATCH --mem=40000 6 | # 7 | #SBATCH --mail-type=END 8 | 9 | start=$(date +%s) 10 | echo "start time: $start" 11 | echo $HOSTNAME 12 | 13 | Rscript --save deseq2_normcounts_noERCC_DGE_vis.R 14 | 15 | end=$(date +%s) 16 | echo "end time: $end" 17 | runtime_s=$(echo $(( end - start ))) 18 | echo "total run time(s): $runtime_s" 19 | sec_per_min=60 20 | sec_per_hr=3600 21 | runtime_m=$(echo "scale=2; $runtime_s / $sec_per_min;" | bc) 22 | echo "total run time(m): $runtime_m" 23 | runtime_h=$(echo "scale=2; $runtime_s / $sec_per_hr;" | bc) 24 | echo "total run time(h): $runtime_h" 25 | -------------------------------------------------------------------------------- /RNAseq/GLDS_Processing_Scripts/GLDS-49/04-05-DESeq2_NormCounts_DGE/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/RNAseq_Tool_Install/GL_genome_index_mkdir.sh: -------------------------------------------------------------------------------- 1 | mkdir ./Genomes 2 | mkdir ./Genomes/Mus_musculus 3 | mkdir ./Genomes/Arabidopsis_thaliana 4 | mkdir ./Genomes/Bacillus_subtilis 5 | mkdir ./Genomes/Brassica_rapa 6 | mkdir ./Genomes/Drosophila_melanogaster 7 | mkdir ./Genomes/ERCC 8 | mkdir ./Genomes/Escherichia_coli 9 | mkdir ./Genomes/Homo_sapiens 10 | mkdir ./Genomes/Mycobacterium_marinum 11 | mkdir ./Genomes/Oryzias_latipes 12 | mkdir ./Genomes/Staphylococcus_aures 13 | mkdir ./Genomes/Streptococcus_mutans 14 | 15 | mkdir ./STAR_Indices 16 | mkdir ./STAR_Indices/STAR_index_scripts 17 | 18 | mkdir ./RSEM_Indices 19 | mkdir ./RSEM_Indices/RSEM_index_scripts 20 | -------------------------------------------------------------------------------- /RNAseq/RNAseq_Tool_Install/RNAseq_R_tools.yml: -------------------------------------------------------------------------------- 1 | name: RNAseq_R_tools 2 | channels: 3 | - bioconda 4 | - conda-forge 5 | 6 | dependencies: 7 | - r-base=4.0.3 8 | - r-tidyverse 9 | - bioconductor-deseq2 10 | - libopenblas=0.3.7 11 | - bioconductor-tximport 12 | - bioconductor-stringdb 13 | - bioconductor-panther.db 14 | - bioconductor-org.hs.eg.db 15 | - bioconductor-org.mm.eg.db 16 | - bioconductor-org.dm.eg.db 17 | - bioconductor-org.ce.eg.db 18 | - bioconductor-org.at.tair.db 19 | - bioconductor-org.eck12.eg.db 20 | - bioconductor-org.sc.sgd.db 21 | - bioconductor-risa 22 | -------------------------------------------------------------------------------- /RNAseq/RNAseq_Tool_Install/RNAseq_fq_to_counts_tools.yml: -------------------------------------------------------------------------------- 1 | name: RNAseq_fq_to_counts 2 | channels: 3 | - conda-forge 4 | - bioconda 5 | 6 | dependencies: 7 | - python 8 | - bcftools 9 | - fastqc 10 | - multiqc 11 | - qualimap 12 | - rsem 13 | - rseqc 14 | - samtools 15 | - star 16 | - trim-galore 17 | - umi_tools 18 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/assets/README.md: -------------------------------------------------------------------------------- 1 | # Description and Sources of Asset Files 2 | 3 | 1. organisms.csv 4 | 5 | - Source: Created in house. 6 | - Description: Details the organisms processed in GeneLab, associated taxon ID and annotation databases. 7 | - Useage in Workflow: Used to retrieve the correct taxon ID and annotation database during the annotation addition step. -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/assets/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/bin/concat_logs.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python 2 | # Concatenate V&V logs 3 | 4 | from pathlib import Path 5 | 6 | logs = sorted(list(Path.cwd().glob("VV_in.tsv*"))) 7 | 8 | OUTPUT_FN = Path("VV_log_final_GLbulkRNAseq.tsv") 9 | 10 | for i, log in enumerate(logs): 11 | with open(log, "r") as in_f: 12 | if i == 0: # first file 13 | contents = in_f.read() 14 | else: 15 | contents += "".join(in_f.readlines()[1:]) # skip header 16 | 17 | with open(OUTPUT_FN, "w") as out_f: 18 | out_f.write(contents) 19 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/bin/dge_annotation_R_scripts.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/bin/dge_annotation_R_scripts.zip -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/bin/dp_tools__NF_RCP/__init__.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | # Import for access at the module level 4 | from . import checks 5 | from . import protocol 6 | from . import schemas 7 | 8 | # Set config path 9 | config = Path(__file__).parent / "config.yaml" -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/bin/filter_to_only_issues.py: -------------------------------------------------------------------------------- 1 | #! /usr/bin/env python 2 | import pandas as pd 3 | 4 | INPUT_FN="VV_log_final_GLbulkRNAseq.tsv" 5 | OUTPUT_FN="VV_log_final_only_issues_GLbulkRNAseq.tsv" 6 | 7 | df = pd.read_csv(INPUT_FN, sep="\t") 8 | 9 | df_filtered = df.loc[~df["code"].isin(["FlagCode.GREEN"])] 10 | df_filtered.to_csv(OUTPUT_FN, sep="\t", index=False) -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/bin/prepull_singularity.sh: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env bash 2 | 3 | # Addresses issue: https://github.com/nextflow-io/nextflow/issues/1210 4 | 5 | CONFILE=${1:-nextflow.config} 6 | OUTDIR=${2:-./singularity} 7 | 8 | if [ ! -e $CONFILE ]; then 9 | echo "$CONFILE does not exist" 10 | exit 11 | fi 12 | 13 | TMPFILE=`mktemp` 14 | 15 | CURDIR=$(pwd) 16 | 17 | mkdir -p $OUTDIR 18 | 19 | cat ${CONFILE}|grep 'container'|perl -lane 'if ( $_=~/container\s*\=\s*\"(\S+)\"/ ) { $_=~/container\s*\=\s*\"(\S+)\"/; print $1 unless ( $1=~/^\s*$/ or $1=~/\.sif/ or $1=~/\.img/ ) ; }' > $TMPFILE 20 | 21 | cd ${OUTDIR} 22 | 23 | while IFS= read -r line; do 24 | name=$line 25 | name=${name/:/-} 26 | name=${name//\//-} 27 | echo $name 28 | singularity pull ${name}.img docker://$line 29 | done < $TMPFILE 30 | 31 | cd $CURDIR -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/executor/cos-hpc-1-node-local.config: -------------------------------------------------------------------------------- 1 | /* Submitted as a full 1 node sbatch with 28 cpus. 2 | * Everything runs as local executor. Only the inital Nextflow program 3 | * needs to be launched using slurm (ideally by sbatch) 4 | */ 5 | process { 6 | executor='local' 7 | 8 | withLabel: networkBound { 9 | executor = 'local' 10 | maxForks = 1 11 | } 12 | 13 | withLabel: cpuBound { 14 | cpus=16 15 | } 16 | 17 | withLabel: maxCPU { 18 | cpus=28 19 | } 20 | 21 | withName: COUNT_ALIGNED { 22 | cpus=9 // Assessed to be near full speed in this case 23 | } 24 | 25 | } 26 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/executor/cos-hpc-4-node.config: -------------------------------------------------------------------------------- 1 | /* Submitted as a small sbatch with 4 reserved cpus for nextflow process 2 | * and very quick processes. Also has ability to submit additional 3 | * sbatch jobs for longer running, more cpus needed processes. 4 | * This particular profile is designed to occupy no more than 112 cpus total 5 | */ 6 | process { 7 | executor='slurm' 8 | 9 | withLabel: networkBound { 10 | executor = 'local' 11 | maxForks = 1 12 | } 13 | 14 | withLabel: cpuBound { 15 | cpus=16 16 | 17 | } 18 | 19 | withLabel: maxCPU { 20 | cpus=28 21 | } 22 | 23 | withName: COUNT_ALIGNED { 24 | cpus=9 // Assessed to be near full speed in this case 25 | } 26 | 27 | } 28 | 29 | executor { 30 | $local { 31 | cpus = 4 32 | } 33 | 34 | $slurm { 35 | queueSize = 12 36 | } 37 | 38 | } 39 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/executor/default_CI_test.config: -------------------------------------------------------------------------------- 1 | // Everything is local, no time limits 2 | // Not expected to working for production runs due to high RAM needs for processes like building indexes 3 | 4 | process { 5 | executor='local' 6 | 7 | withLabel: big_mem { 8 | memory = 4.GB 9 | } 10 | withLabel: maxCPU { 11 | cpus = 2 12 | } 13 | 14 | // time='20m' 15 | 16 | } 17 | 18 | params { 19 | max_flag_code = 81 // HALT flag codes do not halt the workflow but should be manually assessed 20 | } 21 | 22 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/executor/default_local.config: -------------------------------------------------------------------------------- 1 | // Everything is local, no time limits 2 | // Not expected to working for production runs due to high RAM needs for processes like building indexes 3 | 4 | process { 5 | executor='local' 6 | 7 | withLabel: big_mem { 8 | memory = 8.GB 9 | } 10 | withLabel: maxCPU { 11 | cpus = 3 12 | } 13 | 14 | // time='20m' 15 | } 16 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/modules/multiqc.config: -------------------------------------------------------------------------------- 1 | module_order: 2 | - fastqc: 3 | - cutadapt 4 | - star 5 | - rseqc 6 | - rsem 7 | 8 | extra_fn_clean_exts: 9 | - '.read_distribution_out' 10 | - '.infer_experiment_out' 11 | - '.geneBodyCoverage.txt' 12 | 13 | use_filename_as_sample_name: 14 | - rseqc/gene_body_coverage 15 | 16 | show_analysis_paths: False 17 | show_analysis_time: False 18 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/tests/test_glds194.config: -------------------------------------------------------------------------------- 1 | // Should be loaded by every RNASeq process. 2 | params { 3 | /* 4 | Parameters that MUST be supplied 5 | */ 6 | gldsAccession = 'GLDS-194' // GeneLab Data Accession Number, e.g. GLDS-104 7 | use_dummy_gene_counts = true // Use random gene counts for Deseq2, this addresses an issue where low/zero gene counts causes DGE analysis to fail 8 | 9 | /* 10 | DEBUG parameters, should NOT be overwritten for production processing runs 11 | */ 12 | genomeSubsample = 19 // Subsamples the reference fasta and gtf to a single sequence (often representing a single chromosome) 13 | truncateTo = 300 // Subsamples the raw reads files to the specified number of reads for EACH raw reads file. 14 | 15 | } 16 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/tests/test_glds207.config: -------------------------------------------------------------------------------- 1 | // Should be loaded by every RNASeq process. 2 | params { 3 | /* 4 | Parameters that MUST be supplied 5 | */ 6 | gldsAccession = 'GLDS-207' // GeneLab Data Accession Number, e.g. GLDS-104 7 | use_dummy_gene_counts = true // Use random gene counts for Deseq2, this addresses an issue where low/zero gene counts causes DGE analysis to fail 8 | 9 | truncateTo = 100 // Subsamples the raw reads files to the specified number of reads for EACH raw reads file. 10 | 11 | } 12 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/tests/test_glds251.config: -------------------------------------------------------------------------------- 1 | // Should be loaded by every RNASeq process. 2 | params { 3 | /* 4 | Parameters that MUST be supplied 5 | */ 6 | gldsAccession = 'GLDS-251' // GeneLab Data Accession Number, e.g. GLDS-104 7 | use_dummy_gene_counts = true // Use random gene counts for Deseq2, this addresses an issue where low/zero gene counts causes DGE analysis to fail 8 | 9 | genomeSubsample = 5 // Subsamples the reference fasta and gtf to a single sequence (often representing a single chromosome) 10 | truncateTo = 300 // Subsamples the raw reads files to the specified number of reads for EACH raw reads file. 11 | 12 | } 13 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/tests/test_glds48.config: -------------------------------------------------------------------------------- 1 | // Should be loaded by every RNASeq process. 2 | params { 3 | /* 4 | Parameters that MUST be supplied 5 | */ 6 | gldsAccession = 'GLDS-48' // GeneLab Data Accession Number, e.g. GLDS-104 7 | use_dummy_gene_counts = true // Use random gene counts for Deseq2, this addresses an issue where low/zero gene counts causes DGE analysis to fail 8 | 9 | /* 10 | DEBUG parameters, should NOT be overwritten for production processing runs 11 | */ 12 | genomeSubsample = 19 // Subsamples the reference fasta and gtf to a single sequence (often representing a single chromosome) 13 | truncateTo = 600 // Subsamples the raw reads files to the specified number of reads for EACH raw reads file. 14 | 15 | } 16 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/config/tests/test_glds91.config: -------------------------------------------------------------------------------- 1 | // Should be loaded by every RNASeq process. 2 | params { 3 | /* 4 | Parameters that MUST be supplied 5 | */ 6 | gldsAccession = 'GLDS-91' // GeneLab Data Accession Number, e.g. GLDS-104 7 | use_dummy_gene_counts = true // Use random gene counts for Deseq2, this addresses an issue where low/zero gene counts causes DGE analysis to fail 8 | 9 | /* 10 | DEBUG parameters, should NOT be overwritten for production processing runs 11 | */ 12 | genomeSubsample = 21 // Subsamples the reference fasta and gtf to a single sequence (often representing a single chromosome) 13 | truncateTo = 600 // Subsamples the raw reads files to the specified number of reads for EACH raw reads file. 14 | 15 | } 16 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/modules/fastqc.nf: -------------------------------------------------------------------------------- 1 | /* Processes dealing with fastQC files 2 | */ 3 | 4 | process GET_MAX_READ_LENGTH { 5 | // Returns max read length based on all supplied fastqc data files 6 | input: 7 | path(fastqc_datazip) 8 | 9 | output: 10 | env(RESULT), emit: length 11 | 12 | script: 13 | """ 14 | # unzip fastqc datazip 15 | unzip ${ fastqc_datazip } 16 | 17 | RESULT=\$(get_max_readlength_from_fastqc.py "${ fastqc_datazip.baseName }/fastqc_data.txt") 18 | """ 19 | } 20 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/nf-test.config: -------------------------------------------------------------------------------- 1 | config { 2 | testsDir "tests" 3 | workDir "/tmp/.nf-test" 4 | configFile "nextflow.config" 5 | profile "docker,test" 6 | } 7 | -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/tests/config/nftest_modules.yml: -------------------------------------------------------------------------------- 1 | DGE_BY_DESEQ2: 2 | - RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/modules/DGE_BY_DESEQ2/** 3 | - RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/tests/modules/DGE_BY_DESEQ2/** -------------------------------------------------------------------------------- /RNAseq/Workflow_Documentation/NF_RCP-F/workflow_code/tests/nextflow.config: -------------------------------------------------------------------------------- 1 | /* 2 | ======================================================================================== 3 | Nextflow config file for running tests 4 | ======================================================================================== 5 | */ 6 | -------------------------------------------------------------------------------- /RNAseq/images/NF_RCP-F_gitzip_rnaseq.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/RNAseq/images/NF_RCP-F_gitzip_rnaseq.png -------------------------------------------------------------------------------- /RNAseq/images/NF_RCP-F_rnaseq_workflow.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/RNAseq/images/NF_RCP-F_rnaseq_workflow.png -------------------------------------------------------------------------------- /RNAseq/images/RNAseq_pipeline_diagram.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/RNAseq/images/RNAseq_pipeline_diagram.png -------------------------------------------------------------------------------- /RNAseq/organisms.csv: -------------------------------------------------------------------------------- 1 | name,species,taxon,annotations 2 | HUMAN,Homo sapiens,9606,org.Hs.eg.db 3 | MOUSE,Mus musculus,10090,org.Mm.eg.db 4 | RAT,Rattus norvegicus,10116,org.Rn.eg.db 5 | ZEBRAFISH,Danio rerio,7955,org.Dr.eg.db 6 | FLY,Drosophila melanogaster,7227,org.Dm.eg.db 7 | WORM,Caenorhabditis elegans,6239,org.Ce.eg.db 8 | YEAST,Saccharomyces cerevisiae (strain ATCC 204508 / S288c),559292,org.Sc.sgd.db 9 | ARABIDOPSIS,Arabidopsis thaliana,3702,org.At.tair.db 10 | ECOLI,Escherichia coli (strain K12),83333,org.EcK12.eg.db 11 | BACSU,Bacillus subtilis (strain 168),224308, 12 | -------------------------------------------------------------------------------- /Raw_Data_Generation/README.md: -------------------------------------------------------------------------------- 1 | # GeneLab pipelines for generating raw data 2 | 3 | ## About 4 | [NASA GeneLab](https://genelab.nasa.gov/) has created standard pipelines for generating raw sequence data from libraries created [in-house](https://genelab.nasa.gov/genelab-sequencing-services/omics_data) using different library preparation methods/kits and sequenced on Illumina's NovaSeq instrument. Click on a library preparation method/kit below for more details. 5 | 6 | --- 7 | 8 | ## Select a library preparation method/kit for more info: 9 | 10 | * [UPX kit for bulk RNAseq](UPX_kit_for_bulk_RNAseq) 11 | -------------------------------------------------------------------------------- /images/NASA_GeneLab_logo-2019.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/images/NASA_GeneLab_logo-2019.png -------------------------------------------------------------------------------- /scRNAseq/10X_Chromium_3prime_Data/scRNAseq_Tool_Install/GL_scRNAseq_mkdir.sh: -------------------------------------------------------------------------------- 1 | mkdir 00-RawData 01-TG_Preproc 02-STAR_Alignment 2 | 3 | mkdir 00-RawData/Fastq 4 | mkdir 00-RawData/FastQC_Reports 5 | mkdir 00-RawData/FastQC_Reports/raw_multiqc_report 6 | 7 | mkdir 02-STAR_Alignment/align_multiqc_report 8 | -------------------------------------------------------------------------------- /scRNAseq/10X_Chromium_3prime_Data/scRNAseq_Tool_Install/scRNAseq_yaml_files/fastqc.yml: -------------------------------------------------------------------------------- 1 | name: fastqc 2 | channels: 3 | - bioconda 4 | - defaults 5 | dependencies: 6 | - fastqc=0.11.9 7 | -------------------------------------------------------------------------------- /scRNAseq/10X_Chromium_3prime_Data/scRNAseq_Tool_Install/scRNAseq_yaml_files/multiqc.yml: -------------------------------------------------------------------------------- 1 | name: multiqc 2 | channels: 3 | - bioconda 4 | - conda-forge 5 | - defaults 6 | dependencies: 7 | - python=3.10.2 8 | - multiqc=1.12 9 | -------------------------------------------------------------------------------- /scRNAseq/10X_Chromium_3prime_Data/scRNAseq_Tool_Install/scRNAseq_yaml_files/star.yml: -------------------------------------------------------------------------------- 1 | name: star 2 | channels: 3 | - bioconda 4 | - conda-forge 5 | - defaults 6 | dependencies: 7 | - python=3.10 8 | - star=2.7.10a 9 | -------------------------------------------------------------------------------- /scRNAseq/README.md: -------------------------------------------------------------------------------- 1 | # GeneLab bioinformatics processing pipelines for single cell RNA-sequencing data 2 | 3 | --- 4 | 5 | ## Available Data Types 6 | 7 | * [10X Chromium 3' Data](10X_Chromium_3prime_Data) 8 | -------------------------------------------------------------------------------- /scRNAseq/images/scRNAseq_pipeline_diagram.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nasa/GeneLab_Data_Processing/296943b32dfd84f5f754cdc5eba6ce2d659af12e/scRNAseq/images/scRNAseq_pipeline_diagram.png --------------------------------------------------------------------------------