├── .gitignore ├── Analysis_scripts ├── Figure1_and_Figure2.Rmd ├── Figure3_and_feature_char.Rmd ├── Figure4_and_supp_boxplots.Rmd ├── Figure5_and_genera_consistency.Rmd ├── Supplemental_Discriminatory_Analysis.Rmd ├── Supplemental_FP_Analysis.Rmd ├── Supplemental_chimera_plot.R ├── Supplemental_top_feature_consistency.Rmd ├── calc_aitchison_permanova.R ├── calc_bray_curt_permanova.R ├── consistency_analysis │ ├── consistency_functions.R │ ├── prep_diarrhea_consistency.R │ └── prep_obesity_consistency.R ├── outlier_Wilcoxon_CLR_investigating.R ├── parse_percent_chimeras.R └── process_FDR_sim_data.Rmd ├── Config.sh ├── Display_items ├── Main_figures │ ├── Figure1.pdf │ ├── Figure1.png │ ├── Figure2.pdf │ ├── Figure2.png │ ├── Figure3.pdf │ ├── Figure3.png │ ├── Figure4.pdf │ ├── Figure4.png │ ├── Figure5.pdf │ └── Figure5.png ├── Misc_figures │ ├── AUROC_heatmap_UNFILT.pdf │ ├── AUROC_heatmap_UNFILT.png │ ├── Figure2A_Corrplot_Unfilt_raw.pdf │ ├── Figure2B_Corrplot_Filt_raw.pdf │ ├── Figure4_old_heat.pdf │ ├── Figure4_old_heat.png │ ├── OLD_Figure4_FDR_heatmaps_raw.pdf │ ├── Supp_Fig4_UNFILT.pdf │ ├── Supp_Fig4_UNFILT.png │ └── Total_Number_of_hits.pdf ├── Supp_figures │ ├── Supp_Fig1.pdf │ ├── Supp_Fig1.png │ ├── Supp_Fig2.pdf │ ├── Supp_Fig3.pdf │ ├── Supp_Fig3.png │ ├── Supp_Fig4.pdf │ ├── Supp_Fig4.png │ ├── Supp_Fig5.pdf │ ├── Supp_Fig5.png │ ├── Supp_Fig6.pdf │ ├── Supp_Fig6.png │ ├── Supp_Fig7.pdf │ ├── Supp_Fig7.png │ ├── Supp_Fig8.pdf │ └── Supp_Fig8.png └── Tables │ ├── Supp_table1.tsv │ ├── Supplemental Data 1.xlsx │ ├── Table1_and_additional_details.xlsx │ └── Table2_diarrhea_consistency.tsv ├── LICENSE ├── Misc_datafiles ├── ASV_filt_nums.txt ├── ASV_nonfilt_nums.txt ├── Expected_MALL_output │ └── No_filt_Results │ │ ├── ANCOM_out │ │ └── Ancom_res.tsv │ │ ├── Aldex_out │ │ └── Aldex_res.tsv │ │ ├── Corncob_out │ │ └── Corncob_results.tsv │ │ ├── Deseq2_out │ │ └── Deseq2_results.tsv │ │ ├── Lefse_out │ │ ├── Lefse_results.tsv │ │ ├── lefse_format_file.tsv │ │ └── lefse_formatted.lefse │ │ ├── Limma_voom_TMMwsp │ │ └── limma_voom_tmmwsp_res.tsv │ │ ├── Maaslin2_out │ │ ├── all_results.tsv │ │ ├── maaslin2.log │ │ ├── residuals.rds │ │ └── significant_results.tsv │ │ ├── Maaslin2_rare_out │ │ ├── all_results.tsv │ │ ├── maaslin2.log │ │ ├── residuals.rds │ │ └── significant_results.tsv │ │ ├── Wilcoxon_CLR_out │ │ └── Wil_CLR_results.tsv │ │ ├── Wilcoxon_rare_out │ │ └── Wil_rare_results.tsv │ │ ├── edgeR_out │ │ └── edgeR_res.tsv │ │ ├── fixed_non_rare_tables │ │ └── MALL_ASVs_table.tsv │ │ ├── fixed_rare_tables │ │ └── MALL_ASVs_table.tsv │ │ ├── limma_voom_tmm_out │ │ ├── Ref_choosing.txt │ │ └── limma_voom_tmm_res.tsv │ │ ├── metagenomeSeq_out │ │ └── mgSeq_res.tsv │ │ ├── t_test_rare_out │ │ └── t_test_res.tsv │ │ └── time_file.txt ├── aitchison_permanova_results.tsv ├── bray_permanova_results.tsv ├── consistency_analysis_RDS_out │ ├── diarrhea_combined_overlap.rds │ ├── diarrhea_outputs_binary_clean_combined.rds │ ├── obesity_combined_overlap.rds │ └── obesity_outputs_binary_clean_combined.rds ├── mapfiles │ ├── dataset_name_mapping.csv │ ├── diarrhea_lefse_misformatted_ids.txt │ └── tool_name_mapping.csv └── uchime_ref_chimera_parsing │ ├── uchime_ref_chimera_filenames.tsv │ └── uchime_ref_chimera_percents.tsv ├── Pipeline_scripts ├── Ancom2_Script │ └── ancom_v2.1.R ├── False_Discovery_Analysis │ ├── Generate_Random_data_splits │ │ ├── ArcticFreshwaters_split.sh │ │ ├── Blueberry_splits.sh │ │ ├── Generate_ALL_splits.sh │ │ ├── Generate_Random_Splits.sh │ │ ├── Generate_splits.R │ │ ├── Ji_WTP_DS_split.sh │ │ ├── Ob_goodrich_generate_rand_splits.sh │ │ ├── Office_splits.sh │ │ ├── cdi_schubert_splits.sh │ │ ├── hiv_noguerajulian_splits.sh │ │ └── sw_sed_splits.sh │ └── Run_scripts │ │ ├── run_JI_WTP_DS_filt.sh │ │ ├── run_JI_WTP_DS_unfilt.sh │ │ ├── run_all_FP_datasets_filt.sh │ │ ├── run_all_FP_datasets_unfilt.sh │ │ ├── run_arcticfresh_filt.sh │ │ ├── run_arcticfresh_unfilt.sh │ │ ├── run_blueberry_filt.sh │ │ ├── run_blueberry_unfilt.sh │ │ ├── run_goodrich_filt.sh │ │ ├── run_goodrich_unfilt.sh │ │ ├── run_hiv_noguera_filt.sh │ │ ├── run_hiv_noguera_unfilt.sh │ │ ├── run_office_FD_test_filt.sh │ │ ├── run_office_FD_test_unfilt.sh │ │ ├── run_schubert_filt.sh │ │ ├── run_schubert_unfilt.sh │ │ ├── run_sw_sed_filt.sh │ │ └── run_sw_sed_unfilt.sh ├── Run_scripts │ ├── FP_runs │ │ ├── run_JI_WTP_DS_filt.sh │ │ ├── run_JI_WTP_DS_unfilt.sh │ │ ├── run_JI_WTP_DS_unfilt_EXT.sh │ │ ├── run_arcticfresh_filt.sh │ │ ├── run_arcticfresh_unfilt.sh │ │ ├── run_arcticfresh_unfilt_EXT.sh │ │ ├── run_blueberry_filt.sh │ │ ├── run_blueberry_unfilt.sh │ │ ├── run_blueberry_unfilt_EXT.sh │ │ ├── run_goodrich_filt.sh │ │ ├── run_goodrich_unfilt.sh │ │ ├── run_goodrich_unfilt_EXT.sh │ │ ├── run_hiv_noguera_filt.sh │ │ ├── run_hiv_noguera_unfilt.sh │ │ ├── run_hiv_noguera_unfilt_EXT.sh │ │ ├── run_office_FD_test_filt.sh │ │ ├── run_office_FD_test_unfilt.sh │ │ ├── run_office_FD_test_unfilt_EXT.sh │ │ ├── run_schubert_filt.sh │ │ ├── run_schubert_unfilt.sh │ │ ├── run_schubert_unfilt_EXT.sh │ │ ├── run_sw_sed_filt.sh │ │ ├── run_sw_sed_unfilt.sh │ │ └── run_sw_sed_unfilt_EXT.sh │ ├── input_parameters │ │ ├── Diarrhea │ │ │ ├── filt_input │ │ │ │ ├── Genus_input.txt │ │ │ │ ├── combined_input.txt │ │ │ │ ├── metadata_input.txt │ │ │ │ ├── output_files.txt │ │ │ │ └── sort_combined.txt │ │ │ └── nonfilt_input │ │ │ │ ├── combined_input.txt │ │ │ │ ├── genus_table.txt │ │ │ │ ├── metadata_input.txt │ │ │ │ ├── output.txt │ │ │ │ ├── rare_tables.tsv │ │ │ │ └── sort_combined_input.txt │ │ ├── Obesity │ │ │ ├── filt_input │ │ │ │ ├── ASV_table_input.txt │ │ │ │ ├── combined_input.txt │ │ │ │ ├── metadata_input.txt │ │ │ │ ├── output.txt │ │ │ │ └── sort_combined_input.txt │ │ │ └── nonfilt_input │ │ │ │ ├── ASV_rare_table.txt │ │ │ │ ├── ASV_table_input.txt │ │ │ │ ├── combined_input.txt │ │ │ │ ├── metadata_input.txt │ │ │ │ ├── output.txt │ │ │ │ └── sort_combined_input.txt │ │ ├── sorted_combined_input.txt │ │ ├── sorted_input.tsv │ │ ├── subset_run_filt.txt │ │ └── subset_run_no_filt.txt │ ├── run_0.1_filt_datasets.sh │ ├── run_0.1_filt_datasets_corncob.sh │ ├── run_FP_unfilt_EXT.sh │ ├── run_FP_unfilt_EXT_sl.sh │ ├── run_all_FP_datasets_filt.sh │ ├── run_all_FP_datasets_unfilt.sh │ ├── run_all_tools.sh │ ├── run_diarrhea_filt.sh │ ├── run_diarrhea_nonfilt.sh │ ├── run_no_filt_datasets.sh │ ├── run_no_filt_datasets_corncob.sh │ ├── run_obesity_filt.sh │ └── run_obesity_nofilt.sh └── Tool_scripts │ ├── Filter_samples_and_features.R │ ├── Filter_samples_of_non_rare_table.R │ ├── Format_lefse.R │ ├── Run_ANCOM.R │ ├── Run_Aldex2.R │ ├── Run_Corncob.R │ ├── Run_DESeq2.R │ ├── Run_Limma_Voom_TMM.R │ ├── Run_Limma_Voom_TMMwsp.R │ ├── Run_Maaslin2.R │ ├── Run_Wilcox_CLR.R │ ├── Run_Wilcox_rare.R │ ├── Run_edgeR.R │ ├── Run_metagenomeSeq.R │ └── Run_t_test_rare.R ├── Plotting_data ├── Main_Figures │ ├── Figure1A_dataset_characteristics.csv.gz │ ├── Figure1A_feat_count.csv.gz │ ├── Figure1B_dataset_characteristics.csv.gz │ ├── Figure1B_feat_count.csv.gz │ ├── Figure2A_pval.csv.gz │ ├── Figure2A_rho.csv.gz │ ├── Figure2B_pval.csv.gz │ ├── Figure2B_rho.csv.gz │ ├── Figure3A.csv │ ├── Figure3A.csv.gz │ ├── Figure3B.csv │ ├── Figure3B.csv.gz │ ├── Figure3C_bin_dist.csv │ ├── Figure3C_bin_dist.csv.gz │ ├── Figure3D_bin_dist.csv │ ├── Figure3D_bin_dist.csv.gz │ ├── Figure4A_boxplots.csv.gz │ ├── Figure4B_boxplots.csv.gz │ ├── Figure5_and_Table2_genera_diarrhea_expected_consistency.csv.gz │ └── Figure5_and_Table2_genera_diarrhea_observed_consistency.csv.gz ├── Supp_figures │ ├── FDR_Read_depth.csv │ ├── SuppTable1_genera_obesity_expected_consistency.csv.gz │ ├── SuppTable1_genera_obesity_observed_consistency.csv.gz │ ├── Supp_Fig1AB_mean_RA_sig_hits.csv.gz │ ├── Supp_Fig1C_unfilt_total_hits.csv │ ├── Supp_Fig1C_unfilt_total_hits.csv.gz │ ├── Supp_Fig1D_filt_total_hits.csv │ ├── Supp_Fig1D_filt_total_hits.csv.gz │ ├── Supp_Fig2A_chimera_percents.csv.gz │ ├── Supp_Fig2B_chimera_spearman.csv.gz │ ├── Supp_Fig3A.csv.gz │ ├── Supp_Fig3B.csv.gz │ ├── Supp_Fig4_CLR_07.csv.gz │ ├── Supp_Fig4_CLR_09.csv.gz │ ├── Supp_Fig4_RA_07.csv.gz │ ├── Supp_Fig4_RA_09.csv.gz │ ├── Supp_Fig5A_filt.csv.gz │ ├── Supp_Fig5B_unfilt.csv.gz │ └── Supp_Fig8_data.csv.gz └── source_data_all.xlsx └── README.md /.gitignore: -------------------------------------------------------------------------------- 1 | Data/ 2 | Analysis_scripts/*files 3 | Analysis_scripts/*html 4 | Pipeline_scripts/Run_scripts/LEFSE_stuff/ 5 | Pipeline_scripts/Run_scripts/OLD_STUFF/ 6 | Pipeline_scripts/Run_scripts/FP_runs/EXT_2/ 7 | -------------------------------------------------------------------------------- /Analysis_scripts/calc_aitchison_permanova.R: -------------------------------------------------------------------------------- 1 | # Separate code to compute PERMANOVA on Aichison's distance between the two sample groups for each tested dataset in Fig 1. 2 | 3 | rm(list = ls(all.names = TRUE)) 4 | 5 | library(parallelDist) 6 | library(vegan) 7 | 8 | pseudocount_and_clr <- function(in_df, pseudocount = 1) { 9 | # Adds pseudocount to all samples and applies centred log-ratio transformation. 10 | # Note that this functions assumes that columns are samples and rows are features. 11 | 12 | return(as.data.frame(apply(in_df + pseudocount, 13 | 2, 14 | function(x){log(x) - mean(log(x))}))) 15 | } 16 | 17 | # Read in ASV tables (unfiltered and filtered as well as rarefied or not for each). 18 | unfilt_study_tab <- readRDS("/home/jacob/GitHub_Repos/Hackathon_testing/Data/unfilt_study_tab_21_04_07.RDS") 19 | filt_study_tab <- readRDS("/home/jacob/GitHub_Repos/Hackathon_testing/Data/filt_study_tab_21_04_07.RDS") 20 | 21 | # Read in sample groups for each dataset. 22 | meta_tables <- list() 23 | for (study in names(filt_study_tab$nonrare)) { 24 | 25 | # The metadata table files have various file naming schemes so there are a few to try: 26 | meta_path1 <- paste("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/", study, "/", study, "_meta.tsv", sep = "") 27 | meta_path2 <- paste("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/", study, "/", study, "_metadata.tsv", sep = "") 28 | meta_path3 <- paste("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/", study, "/", study, "_metadata.csv", sep = "") 29 | 30 | if (file.exists(meta_path1)) { 31 | meta_tables[[study]] <- read.table(file = meta_path1, header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 32 | } else if (file.exists(meta_path2)) { 33 | meta_tables[[study]] <- read.table(file = meta_path2, header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 34 | } else if (file.exists(meta_path3)) { 35 | meta_tables[[study]] <- read.table(file = meta_path3, header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 36 | } else { 37 | print(study) 38 | stop("Metadata file not found.") 39 | } 40 | } 41 | 42 | 43 | 44 | PERMANOVA_output <- data.frame(matrix(NA, nrow = 38, ncol = 9)) 45 | rownames(PERMANOVA_output) <- names(filt_study_tab$nonrare) 46 | colnames(PERMANOVA_output) <- c("dataset", 47 | "filt_nonrare_R2", "filt_nonrare_P", "filt_rare_R2", "filt_rare_P", 48 | "unfilt_nonrare_R2", "unfilt_nonrare_P", "unfilt_rare_R2", "unfilt_rare_P") 49 | PERMANOVA_output$dataset <- names(filt_study_tab$nonrare) 50 | 51 | num_threads <- 30 52 | 53 | for (study in names(filt_study_tab$nonrare)) { 54 | 55 | message("Running ", study, " dataset") 56 | 57 | unfilt_nonrare_samples <- colnames(unfilt_study_tab$nonrare[[study]])[which(colnames(unfilt_study_tab$nonrare[[study]]) %in% rownames(meta_tables[[study]]))] 58 | unfilt_nonrare_ASV_aitchison <- parallelDist(x = t(pseudocount_and_clr(unfilt_study_tab$nonrare[[study]][, unfilt_nonrare_samples])), method = "euclidean", threads = num_threads) 59 | unfilt_nonrare_ASV_aitchison_formula <- as.formula(unfilt_nonrare_ASV_aitchison ~ meta_tables[[study]][unfilt_nonrare_samples, 1]) 60 | unfilt_nonrare_ASV_aitchison_permanova <- data.frame(adonis(formula = unfilt_nonrare_ASV_aitchison_formula, permutations = 999)$aov.tab) 61 | PERMANOVA_output[study, c("unfilt_nonrare_R2", "unfilt_nonrare_P")] <- as.numeric(unfilt_nonrare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 62 | 63 | unfilt_rare_samples <- colnames(unfilt_study_tab$rare[[study]])[which(colnames(unfilt_study_tab$rare[[study]]) %in% rownames(meta_tables[[study]]))] 64 | unfilt_rare_ASV_aitchison <- parallelDist(x = t(pseudocount_and_clr(unfilt_study_tab$rare[[study]][, unfilt_rare_samples])), method = "euclidean", threads = num_threads) 65 | unfilt_rare_ASV_aitchison_formula <- as.formula(unfilt_rare_ASV_aitchison ~ meta_tables[[study]][unfilt_rare_samples, 1]) 66 | unfilt_rare_ASV_aitchison_permanova <- data.frame(adonis(formula = unfilt_rare_ASV_aitchison_formula, permutations = 999)$aov.tab) 67 | PERMANOVA_output[study, c("unfilt_rare_R2", "unfilt_rare_P")] <- as.numeric(unfilt_rare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 68 | 69 | filt_nonrare_samples <- colnames(filt_study_tab$nonrare[[study]])[which(colnames(filt_study_tab$nonrare[[study]]) %in% rownames(meta_tables[[study]]))] 70 | filt_nonrare_ASV_aitchison <- parallelDist(x = t(pseudocount_and_clr(filt_study_tab$nonrare[[study]][, filt_nonrare_samples])), method = "euclidean", threads = num_threads) 71 | filt_nonrare_ASV_aitchison_formula <- as.formula(filt_nonrare_ASV_aitchison ~ meta_tables[[study]][filt_nonrare_samples, 1]) 72 | filt_nonrare_ASV_aitchison_permanova <- data.frame(adonis(formula = filt_nonrare_ASV_aitchison_formula, permutations = 999)$aov.tab) 73 | PERMANOVA_output[study, c("filt_nonrare_R2", "filt_nonrare_P")] <- as.numeric(filt_nonrare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 74 | 75 | filt_rare_samples <- colnames(filt_study_tab$rare[[study]])[which(colnames(filt_study_tab$rare[[study]]) %in% rownames(meta_tables[[study]]))] 76 | filt_rare_ASV_aitchison <- parallelDist(x = t(pseudocount_and_clr(filt_study_tab$rare[[study]][, filt_rare_samples])), method = "euclidean", threads = num_threads) 77 | filt_rare_ASV_aitchison_formula <- as.formula(filt_rare_ASV_aitchison ~ meta_tables[[study]][filt_rare_samples, 1]) 78 | filt_rare_ASV_aitchison_permanova <- data.frame(adonis(formula = filt_rare_ASV_aitchison_formula, permutations = 999)$aov.tab) 79 | PERMANOVA_output[study, c("filt_rare_R2", "filt_rare_P")] <- as.numeric(filt_rare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 80 | 81 | } 82 | 83 | write.table(x = PERMANOVA_output, 84 | file = "/home/gavin/github_repos/hackathon/Comparison_of_DA_microbiome_methods/Misc_datafiles/aitchison_permanova_results.tsv", 85 | row.names = FALSE, col.names = TRUE, quote = FALSE, sep = "\t") 86 | -------------------------------------------------------------------------------- /Analysis_scripts/calc_bray_curt_permanova.R: -------------------------------------------------------------------------------- 1 | # Separate code to compute PERMANOVA on Aichison's distance between the two sample groups for each tested dataset in Fig 1. 2 | 3 | rm(list = ls(all.names = TRUE)) 4 | 5 | library(parallelDist) 6 | library(vegan) 7 | 8 | 9 | # Read in ASV tables (unfiltered and filtered as well as rarefied or not for each). 10 | unfilt_study_tab <- readRDS("/home/jacob/GitHub_Repos/Hackathon_testing/Data/unfilt_study_tab_21_04_07.RDS") 11 | filt_study_tab <- readRDS("/home/jacob/GitHub_Repos/Hackathon_testing/Data/filt_study_tab_21_04_07.RDS") 12 | 13 | # Read in sample groups for each dataset. 14 | meta_tables <- list() 15 | for (study in names(filt_study_tab$nonrare)) { 16 | 17 | # The metadata table files have various file naming schemes so there are a few to try: 18 | meta_path1 <- paste("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/", study, "/", study, "_meta.tsv", sep = "") 19 | meta_path2 <- paste("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/", study, "/", study, "_metadata.tsv", sep = "") 20 | meta_path3 <- paste("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/", study, "/", study, "_metadata.csv", sep = "") 21 | 22 | if (file.exists(meta_path1)) { 23 | meta_tables[[study]] <- read.table(file = meta_path1, header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 24 | } else if (file.exists(meta_path2)) { 25 | meta_tables[[study]] <- read.table(file = meta_path2, header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 26 | } else if (file.exists(meta_path3)) { 27 | meta_tables[[study]] <- read.table(file = meta_path3, header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 28 | } else { 29 | print(study) 30 | stop("Metadata file not found.") 31 | } 32 | } 33 | 34 | 35 | 36 | PERMANOVA_output <- data.frame(matrix(NA, nrow = 38, ncol = 9)) 37 | rownames(PERMANOVA_output) <- names(filt_study_tab$nonrare) 38 | colnames(PERMANOVA_output) <- c("dataset", 39 | "filt_nonrare_R2", "filt_nonrare_P", "filt_rare_R2", "filt_rare_P", 40 | "unfilt_nonrare_R2", "unfilt_nonrare_P", "unfilt_rare_R2", "unfilt_rare_P") 41 | PERMANOVA_output$dataset <- names(filt_study_tab$nonrare) 42 | 43 | num_threads <- 30 44 | 45 | for (study in names(filt_study_tab$nonrare)) { 46 | 47 | message("Running ", study, " dataset") 48 | 49 | unfilt_nonrare_samples <- colnames(unfilt_study_tab$nonrare[[study]])[which(colnames(unfilt_study_tab$nonrare[[study]]) %in% rownames(meta_tables[[study]]))] 50 | unfilt_nonrare_ASV_aitchison <- parallelDist(x = t(unfilt_study_tab$nonrare[[study]][, unfilt_nonrare_samples]), method = "bray", threads = num_threads) 51 | unfilt_nonrare_ASV_aitchison_formula <- as.formula(unfilt_nonrare_ASV_aitchison ~ meta_tables[[study]][unfilt_nonrare_samples, 1]) 52 | unfilt_nonrare_ASV_aitchison_permanova <- data.frame(adonis(formula = unfilt_nonrare_ASV_aitchison_formula, permutations = 999)$aov.tab) 53 | PERMANOVA_output[study, c("unfilt_nonrare_R2", "unfilt_nonrare_P")] <- as.numeric(unfilt_nonrare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 54 | 55 | unfilt_rare_samples <- colnames(unfilt_study_tab$rare[[study]])[which(colnames(unfilt_study_tab$rare[[study]]) %in% rownames(meta_tables[[study]]))] 56 | unfilt_rare_ASV_aitchison <- parallelDist(x = t(unfilt_study_tab$rare[[study]][, unfilt_rare_samples]), method = "bray", threads = num_threads) 57 | unfilt_rare_ASV_aitchison_formula <- as.formula(unfilt_rare_ASV_aitchison ~ meta_tables[[study]][unfilt_rare_samples, 1]) 58 | unfilt_rare_ASV_aitchison_permanova <- data.frame(adonis(formula = unfilt_rare_ASV_aitchison_formula, permutations = 999)$aov.tab) 59 | PERMANOVA_output[study, c("unfilt_rare_R2", "unfilt_rare_P")] <- as.numeric(unfilt_rare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 60 | 61 | filt_nonrare_samples <- colnames(filt_study_tab$nonrare[[study]])[which(colnames(filt_study_tab$nonrare[[study]]) %in% rownames(meta_tables[[study]]))] 62 | filt_nonrare_ASV_aitchison <- parallelDist(x = t(filt_study_tab$nonrare[[study]][, filt_nonrare_samples]), method = "bray", threads = num_threads) 63 | filt_nonrare_ASV_aitchison_formula <- as.formula(filt_nonrare_ASV_aitchison ~ meta_tables[[study]][filt_nonrare_samples, 1]) 64 | filt_nonrare_ASV_aitchison_permanova <- data.frame(adonis(formula = filt_nonrare_ASV_aitchison_formula, permutations = 999)$aov.tab) 65 | PERMANOVA_output[study, c("filt_nonrare_R2", "filt_nonrare_P")] <- as.numeric(filt_nonrare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 66 | 67 | filt_rare_samples <- colnames(filt_study_tab$rare[[study]])[which(colnames(filt_study_tab$rare[[study]]) %in% rownames(meta_tables[[study]]))] 68 | filt_rare_ASV_aitchison <- parallelDist(x = t(filt_study_tab$rare[[study]][, filt_rare_samples]), method = "bray", threads = num_threads) 69 | filt_rare_ASV_aitchison_formula <- as.formula(filt_rare_ASV_aitchison ~ meta_tables[[study]][filt_rare_samples, 1]) 70 | filt_rare_ASV_aitchison_permanova <- data.frame(adonis(formula = filt_rare_ASV_aitchison_formula, permutations = 999)$aov.tab) 71 | PERMANOVA_output[study, c("filt_rare_R2", "filt_rare_P")] <- as.numeric(filt_rare_ASV_aitchison_permanova[1, c("R2", "Pr..F.")]) 72 | 73 | } 74 | 75 | write.table(x = PERMANOVA_output, 76 | file = "/home/jacob/GitHub_Repos/Clean_Hackathon/Misc_datafiles/bray_permanova_results.tsv", 77 | row.names = FALSE, col.names = TRUE, quote = FALSE, sep = "\t") 78 | -------------------------------------------------------------------------------- /Analysis_scripts/outlier_Wilcoxon_CLR_investigating.R: -------------------------------------------------------------------------------- 1 | ### Code to investigate major outliers in unfiltered Wilcoxon CLR FDR analysis. 2 | ### Written by Gavin 3 | 4 | rm(list = ls(all.names = TRUE)) 5 | 6 | setwd("/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon/Studies/") 7 | 8 | # Taken from https://stackoverflow.com/questions/2602583/geometric-mean-is-there-a-built-in 9 | geometric_mean_w_pseudocount = function(x, na.rm = TRUE){ 10 | exp(sum(log(x + 1), na.rm = na.rm) / length(x)) 11 | } 12 | 13 | datasets_w_outliers <- c("Office", "ArcticFreshwaters", "cdi_schubert", "Blueberry") 14 | 15 | wilcoxon_clr_fdr_summary <- list() 16 | 17 | for (dataset in datasets_w_outliers) { 18 | 19 | wilcoxon_clr_fdr_summary[[dataset]] <- data.frame(matrix(NA, nrow = 100, ncol = 4)) 20 | 21 | colnames(wilcoxon_clr_fdr_summary[[dataset]]) <- c("num_sig", "prop_sig", "mean_gm_ratio", "mean_depth_ratio") 22 | 23 | abun_tab_nonrare_path <- paste(dataset, 24 | "/No_filt_Results/fixed_non_rare_tables/", 25 | dataset, 26 | "_ASVs_table.tsv", 27 | sep = "") 28 | 29 | abun_tab_nonrare <- read.table(abun_tab_nonrare_path, 30 | header = TRUE, sep = "\t", row.names = 1, 31 | stringsAsFactors = FALSE, 32 | comment.char = "", check.names = FALSE) 33 | 34 | abun_dataset_geometric_means <- sapply(abun_tab_nonrare, geometric_mean_w_pseudocount) 35 | abun_dataset_colSums <- colSums(abun_tab_nonrare) 36 | 37 | # The files containing the groupings are actually misnamed - they are sorted alphabetically rather than numerically. 38 | path_to_groupings = paste(dataset, "/False_Discovery_Testing/nonfilt_tabs/", sep = "") 39 | files_to_read <- list.files(path = path_to_groupings, pattern = "*.tsv$", full.names = TRUE) 40 | files_to_read_ext <- list.files(path = path_to_groupings, pattern = "*.tsvext", full.names = TRUE) 41 | files_to_read <- c(files_to_read, files_to_read_ext) 42 | 43 | for (rep_num in 1:100) { 44 | 45 | rep_num_as.char <- as.character(rep_num) 46 | 47 | if (rep_num <= 10) { 48 | wilcoxon_clr_rep_out_path <- paste(dataset, 49 | "False_Discovery_Testing/results_nonfilt", 50 | rep_num_as.char, 51 | "Wilcoxon_CLR_out/Wil_CLR_results.tsv", 52 | sep = "/") 53 | } else { 54 | wilcoxon_clr_rep_out_path <- paste(dataset, 55 | "False_Discovery_Testing/results_nonfilt_ext", 56 | as.character(rep_num - 10), 57 | "Wilcoxon_CLR_out/Wil_CLR_results.tsv", 58 | sep = "/") 59 | } 60 | 61 | wilcoxon_clr_rep_out <- read.table(wilcoxon_clr_rep_out_path, 62 | header = TRUE, sep = "\t", row.names = 1) 63 | 64 | wilcoxon_clr_rep_out$fdr <- p.adjust(wilcoxon_clr_rep_out$x, "fdr") 65 | 66 | rep_num_sig <- length(which(wilcoxon_clr_rep_out$fdr < 0.05)) 67 | rep_prop_sig <- rep_num_sig / nrow(wilcoxon_clr_rep_out) 68 | 69 | rep_ran_groups <- read.table(files_to_read[rep_num], header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 70 | rep_ran_group1 <- rownames(rep_ran_groups)[which(rep_ran_groups[, 1] == "ran1")] 71 | rep_ran_group2 <- rownames(rep_ran_groups)[which(rep_ran_groups[, 1] == "ran2")] 72 | 73 | rep_ran_group1_mean_gm <- mean(abun_dataset_geometric_means[rep_ran_group1]) 74 | rep_ran_group2_mean_gm <- mean(abun_dataset_geometric_means[rep_ran_group2]) 75 | 76 | rep_ran_group1_mean_depth <- mean(abun_dataset_colSums[rep_ran_group1]) 77 | rep_ran_group2_mean_depth <- mean(abun_dataset_colSums[rep_ran_group2]) 78 | 79 | if (rep_ran_group1_mean_gm >= rep_ran_group2_mean_gm) { 80 | mean_gm_ratio <- rep_ran_group1_mean_gm / rep_ran_group2_mean_gm 81 | } else if (rep_ran_group1_mean_gm < rep_ran_group2_mean_gm) { 82 | mean_gm_ratio <- rep_ran_group2_mean_gm / rep_ran_group1_mean_gm 83 | } 84 | 85 | if (rep_ran_group1_mean_depth >= rep_ran_group2_mean_depth) { 86 | mean_depth_ratio <- rep_ran_group1_mean_depth / rep_ran_group2_mean_depth 87 | } else if (rep_ran_group1_mean_depth < rep_ran_group2_mean_depth) { 88 | mean_depth_ratio <- rep_ran_group2_mean_depth / rep_ran_group1_mean_depth 89 | } 90 | 91 | wilcoxon_clr_fdr_summary[[dataset]][rep_num, ] <- c(rep_num_sig, rep_prop_sig, mean_gm_ratio, mean_depth_ratio) 92 | 93 | } 94 | 95 | } 96 | 97 | wilcoxon_clr_fdr_summary$ArcticFreshwaters$above_30 <- FALSE 98 | wilcoxon_clr_fdr_summary$Office$above_30 <- FALSE 99 | wilcoxon_clr_fdr_summary$cdi_schubert$above_30 <- FALSE 100 | wilcoxon_clr_fdr_summary$Blueberry$above_30 <- FALSE 101 | 102 | # Note that I needed to use a lower cut-off to get the same sample numbers as shown in the existing supp figure - I'm thinking that 30% wasn't the cut-off used? 103 | wilcoxon_clr_fdr_summary$ArcticFreshwaters$above_30[which(wilcoxon_clr_fdr_summary$ArcticFreshwaters$prop_sig > 0.2)] <- TRUE 104 | wilcoxon_clr_fdr_summary$Office$above_30[which(wilcoxon_clr_fdr_summary$Office$prop_sig > 0.2)] <- TRUE 105 | wilcoxon_clr_fdr_summary$cdi_schubert$above_30[which(wilcoxon_clr_fdr_summary$cdi_schubert$prop_sig > 0.2)] <- TRUE 106 | wilcoxon_clr_fdr_summary$Blueberry$above_30[which(wilcoxon_clr_fdr_summary$Blueberry$prop_sig > 0.2)] <- TRUE 107 | 108 | # Take a look at ratios of depth vs geometric means 109 | par(mfrow = c(2, 2)) 110 | plot(wilcoxon_clr_fdr_summary$ArcticFreshwaters$mean_depth_ratio, wilcoxon_clr_fdr_summary$ArcticFreshwaters$mean_gm_ratio, col = as.factor(wilcoxon_clr_fdr_summary$ArcticFreshwaters$above_30)) 111 | plot(wilcoxon_clr_fdr_summary$Office$mean_depth_ratio, wilcoxon_clr_fdr_summary$Office$mean_gm_ratio, col = as.factor(wilcoxon_clr_fdr_summary$Office$above_30)) 112 | plot(wilcoxon_clr_fdr_summary$cdi_schubert$mean_depth_ratio, wilcoxon_clr_fdr_summary$cdi_schubert$mean_gm_ratio, col = as.factor(wilcoxon_clr_fdr_summary$cdi_schubert$above_30)) 113 | plot(wilcoxon_clr_fdr_summary$Blueberry$mean_depth_ratio, wilcoxon_clr_fdr_summary$Blueberry$mean_gm_ratio, col = as.factor(wilcoxon_clr_fdr_summary$Blueberry$above_30)) 114 | 115 | ### Used these plots as evidence for statements regarding that outliers tend to have the most extreme geometric means as well. 116 | -------------------------------------------------------------------------------- /Analysis_scripts/parse_percent_chimeras.R: -------------------------------------------------------------------------------- 1 | # Separate code to parse percent chimeras from each dataset. 2 | 3 | rm(list = ls(all.names = TRUE)) 4 | 5 | library(seqinr) 6 | 7 | setwd("/home/gavin/github_repos/hackathon/Comparison_of_DA_microbiome_methods/Misc_datafiles/uchime_ref_chimera_parsing/") 8 | 9 | # Read in ASV tables (unfiltered and filtered as well as rarefied or not for each). 10 | unfilt_study_tab <- readRDS("/home/jacob/GitHub_Repos/Hackathon_testing/Data/unfilt_study_tab_21_04_07.RDS") 11 | filt_study_tab <- readRDS("/home/jacob/GitHub_Repos/Hackathon_testing/Data/filt_study_tab_21_04_07.RDS") 12 | 13 | # Read in mapping of datasets to UCHIME ref (implemented in VSEARCH) non-chimera output FASTAs. 14 | uchime_ref_info <- read.table("uchime_ref_chimera_filenames.txt", header = TRUE, sep = "\t", row.names = 1, stringsAsFactors = FALSE) 15 | 16 | chimeras <- list() 17 | 18 | for (study in rownames(uchime_ref_info)) { 19 | 20 | chimera_fastafile <- paste("/home/gavin/projects/hackathon/chimera_testing/uchime_ref_out", uchime_ref_info[study, "file"], sep = "/") 21 | 22 | chimeras[[study]] <- names(seqinr::read.fasta(file = chimera_fastafile, seqtype = "DNA")) 23 | 24 | } 25 | 26 | percent_chimeras <- data.frame(matrix(NA, nrow = 38, ncol = 4)) 27 | rownames(percent_chimeras) <- names(unfilt_study_tab$rare) 28 | colnames(percent_chimeras) <- c("filt_rare", "filt_nonrare", "unfilt_rare", "unfilt_nonrare") 29 | 30 | 31 | for (study in rownames(uchime_ref_info)) { 32 | 33 | for (rare_set in c("rare", "nonrare")) { 34 | 35 | filt_ASVs <- rownames(filt_study_tab[[rare_set]][[study]]) 36 | unfilt_ASVs <- rownames(unfilt_study_tab[[rare_set]][[study]]) 37 | 38 | colout <- paste(c("filt", "unfilt"), "_", rare_set, sep = "") 39 | 40 | percent_chimeras[study, colout] <- c((length(which(filt_ASVs %in% chimeras[[study]])) / length(filt_ASVs)) * 100, 41 | (length(which(unfilt_ASVs %in% chimeras[[study]])) / length(unfilt_ASVs)) * 100) 42 | 43 | } 44 | } 45 | 46 | write.table(x = percent_chimeras, 47 | file = "uchime_ref_chimera_percents.tsv", 48 | row.names = TRUE, col.names = NA, quote = FALSE, sep = "\t") 49 | -------------------------------------------------------------------------------- /Config.sh: -------------------------------------------------------------------------------- 1 | DATA_DIR="/home/jacob/projects/HACKATHON_ANCOM_FIX_21_03_13/Hackathon" 2 | ANCOM_DIR="/home/jacob/GitHub_Repos/Clean_Hackathon/Pipeline_scripts/Ancom2_Script" 3 | TOOL_DIR="/home/jacob/GitHub_Repos/Clean_Hackathon/Pipeline_scripts/Tool_scripts/" 4 | -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure1.pdf -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure1.png -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure2.pdf -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure2.png -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure3.pdf -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure3.png -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure4.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure4.pdf -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure4.png -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure5.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure5.pdf -------------------------------------------------------------------------------- /Display_items/Main_figures/Figure5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Main_figures/Figure5.png -------------------------------------------------------------------------------- /Display_items/Misc_figures/AUROC_heatmap_UNFILT.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/AUROC_heatmap_UNFILT.pdf -------------------------------------------------------------------------------- /Display_items/Misc_figures/AUROC_heatmap_UNFILT.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/AUROC_heatmap_UNFILT.png -------------------------------------------------------------------------------- /Display_items/Misc_figures/Figure2A_Corrplot_Unfilt_raw.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Figure2A_Corrplot_Unfilt_raw.pdf -------------------------------------------------------------------------------- /Display_items/Misc_figures/Figure2B_Corrplot_Filt_raw.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Figure2B_Corrplot_Filt_raw.pdf -------------------------------------------------------------------------------- /Display_items/Misc_figures/Figure4_old_heat.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Figure4_old_heat.pdf -------------------------------------------------------------------------------- /Display_items/Misc_figures/Figure4_old_heat.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Figure4_old_heat.png -------------------------------------------------------------------------------- /Display_items/Misc_figures/OLD_Figure4_FDR_heatmaps_raw.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/OLD_Figure4_FDR_heatmaps_raw.pdf -------------------------------------------------------------------------------- /Display_items/Misc_figures/Supp_Fig4_UNFILT.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Supp_Fig4_UNFILT.pdf -------------------------------------------------------------------------------- /Display_items/Misc_figures/Supp_Fig4_UNFILT.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Supp_Fig4_UNFILT.png -------------------------------------------------------------------------------- /Display_items/Misc_figures/Total_Number_of_hits.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Misc_figures/Total_Number_of_hits.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig1.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig1.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig1.png -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig2.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig2.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig3.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig3.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig3.png -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig4.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig4.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig4.png -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig5.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig5.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig5.png -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig6.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig6.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig6.png -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig7.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig7.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig7.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig7.png -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig8.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig8.pdf -------------------------------------------------------------------------------- /Display_items/Supp_figures/Supp_Fig8.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Supp_figures/Supp_Fig8.png -------------------------------------------------------------------------------- /Display_items/Tables/Supp_table1.tsv: -------------------------------------------------------------------------------- 1 | Tool No. sig. genera Max overlap Mean exp. Mean obs. Fold diff. P 2 | MaAsLin2 (rare) 8 2 1.019 1.25 1.227 0.003 3 | MaAsLin2 20 3 1.071 1.25 1.167 0.004 4 | t-test (rare) 6 2 1.012 1.167 1.153 0.015 5 | ALDEx2 24 3 1.064 1.167 1.097 0.025 6 | limma voom (TMMwsp) 34 3 1.127 1.235 1.096 0.036 7 | corncob 34 3 1.136 1.206 1.062 0.135 8 | LEfSe 51 3 1.215 1.275 1.049 0.151 9 | limma voom (TMM) 44 3 1.164 1.205 1.035 0.207 10 | Wilcoxon (rare) 22 2 1.062 1.091 1.027 0.249 11 | edgeR 68 3 1.327 1.338 1.008 0.415 12 | Wilcoxon (CLR) 47 3 1.167 1.17 1.003 0.449 13 | DESeq2 40 2 1.123 1.125 1.002 0.465 14 | metagenomeSeq 4 1 1.009 1 0.991 0.028 15 | ANCOM-II 8 1 1.015 1 0.985 0.105 16 | -------------------------------------------------------------------------------- /Display_items/Tables/Supplemental Data 1.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Tables/Supplemental Data 1.xlsx -------------------------------------------------------------------------------- /Display_items/Tables/Table1_and_additional_details.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Display_items/Tables/Table1_and_additional_details.xlsx -------------------------------------------------------------------------------- /Display_items/Tables/Table2_diarrhea_consistency.tsv: -------------------------------------------------------------------------------- 1 | Tool No. sig. genera Max overlap Mean exp. Mean obs. Fold diff. P 2 | ALDEx2 57 3 1.141 1.544 1.353 < 0.001 3 | limma voom (TMM) 76 4 1.22 1.618 1.326 < 0.001 4 | MaAsLin2 (rare) 74 3 1.204 1.595 1.325 < 0.001 5 | ANCOM-II 15 3 1.033 1.333 1.29 < 0.001 6 | MaAsLin2 79 3 1.215 1.557 1.281 < 0.001 7 | Wilcoxon (rare) 88 4 1.269 1.625 1.281 < 0.001 8 | metagenomeSeq 66 3 1.164 1.485 1.276 < 0.001 9 | Wilcoxon (CLR) 82 3 1.22 1.549 1.27 < 0.001 10 | limma voom (TMMwsp) 85 4 1.239 1.565 1.263 < 0.001 11 | t-test (rare) 62 3 1.145 1.403 1.225 < 0.001 12 | corncob 87 5 1.275 1.552 1.217 < 0.001 13 | DESeq2 82 4 1.246 1.512 1.213 < 0.001 14 | LEfSe 119 5 1.408 1.613 1.146 < 0.001 15 | edgeR 138 5 1.509 1.667 1.105 0.002 16 | -------------------------------------------------------------------------------- /Misc_datafiles/ASV_filt_nums.txt: -------------------------------------------------------------------------------- 1 | 3436 ArcticFireSoils/Fix_Results_0.1/fixed_non_rare_tables/ArcticFireSoils_ASVs_table.tsv 2 | 345 ArcticFreshwaters/Fix_Results_0.1/fixed_non_rare_tables/ArcticFreshwaters_ASVs_table.tsv 3 | 4548 ArcticTransects/Fix_Results_0.1/fixed_non_rare_tables/ArcticTransects_ASVs_table.tsv 4 | 677 art_scher/Fix_Results_0.1/fixed_non_rare_tables/art_scher_ASVs_table.tsv 5 | 1041 asd_son/Fix_Results_0.1/fixed_non_rare_tables/asd_son_ASVs_table.tsv 6 | 295 BISCUIT/Fix_Results_0.1/fixed_non_rare_tables/BISCUIT_ASVs_table.tsv 7 | 3255 Blueberry/Fix_Results_0.1/fixed_non_rare_tables/Blueberry_ASVs_table.tsv 8 | 600 cdi_schubert/Fix_Results_0.1/fixed_non_rare_tables/cdi_schubert_ASVs_table.tsv 9 | 460 cdi_vincent/Fix_Results_0.1/fixed_non_rare_tables/cdi_vincent_ASVs_table.tsv 10 | 530 Chemerin/Fix_Results_0.1/fixed_non_rare_tables/Chemerin_ASVs_table.tsv 11 | 1202 crc_baxter/Fix_Results_0.1/fixed_non_rare_tables/crc_baxter_ASVs_table.tsv 12 | 11406 crc_zeller/Fix_Results_0.1/fixed_non_rare_tables/crc_zeller_ASVs_table.tsv 13 | 226 edd_singh/Fix_Results_0.1/fixed_non_rare_tables/edd_singh_ASVs_table.tsv 14 | 713 Exercise/Fix_Results_0.1/fixed_non_rare_tables/Exercise_ASVs_table.tsv 15 | 686 glass_plastic_oberbeckmann/Fix_Results_0.1/fixed_non_rare_tables/glass_plastic_oberbeckmann_ASVs_table.tsv 16 | 7258 GWMC_ASIA_NA/Fix_Results_0.1/fixed_non_rare_tables/GWMC_ASIA_NA_ASVs_table.tsv 17 | 7093 GWMC_HOT_COLD/Fix_Results_0.1/fixed_non_rare_tables/GWMC_HOT_COLD_ASVs_table.tsv 18 | 623 hiv_dinh/Fix_Results_0.1/fixed_non_rare_tables/hiv_dinh_ASVs_table.tsv 19 | 709 hiv_lozupone/Fix_Results_0.1/fixed_non_rare_tables/hiv_lozupone_ASVs_table.tsv 20 | 3093 hiv_noguerajulian/Fix_Results_0.1/fixed_non_rare_tables/hiv_noguerajulian_ASVs_table.tsv 21 | 2872 ibd_gevers/Fix_Results_0.1/fixed_non_rare_tables/ibd_gevers_ASVs_table.tsv 22 | 1016 ibd_papa/Fix_Results_0.1/fixed_non_rare_tables/ibd_papa_ASVs_table.tsv 23 | 257 Ji_WTP_DS/Fix_Results_0.1/fixed_non_rare_tables/Ji_WTP_DS_ASVs_table.tsv 24 | 282 MALL/Fix_Results_0.1/fixed_non_rare_tables/MALL_ASVs_table.tsv 25 | 4288 ob_goodrich/Fix_Results_0.1/fixed_non_rare_tables/ob_goodrich_ASVs_table.tsv 26 | 602 ob_ross/Fix_Results_0.1/fixed_non_rare_tables/ob_ross_ASVs_table.tsv 27 | 1597 ob_turnbaugh/Fix_Results_0.1/fixed_non_rare_tables/ob_turnbaugh_ASVs_table.tsv 28 | 1439 ob_zhu/Fix_Results_0.1/fixed_non_rare_tables/ob_zhu_ASVs_table.tsv 29 | 186 Office/Fix_Results_0.1/fixed_non_rare_tables/Office_ASVs_table.tsv 30 | 639 par_scheperjans/Fix_Results_0.1/fixed_non_rare_tables/par_scheperjans_ASVs_table.tsv 31 | 2769 sed_plastic_hoellein/Fix_Results_0.1/fixed_non_rare_tables/sed_plastic_hoellein_ASVs_table.tsv 32 | 1293 sed_plastic_rosato/Fix_Results_0.1/fixed_non_rare_tables/sed_plastic_rosato_ASVs_table.tsv 33 | 1991 seston_plastic_mccormick/Fix_Results_0.1/fixed_non_rare_tables/seston_plastic_mccormick_ASVs_table.tsv 34 | 4799 sw_plastic_frere/Fix_Results_0.1/fixed_non_rare_tables/sw_plastic_frere_ASVs_table.tsv 35 | 2247 sw_sed_detender/Fix_Results_0.1/fixed_non_rare_tables/sw_sed_detender_ASVs_table.tsv 36 | 570 t1d_alkanani/Fix_Results_0.1/fixed_non_rare_tables/t1d_alkanani_ASVs_table.tsv 37 | 398 t1d_mejialeon/Fix_Results_0.1/fixed_non_rare_tables/t1d_mejialeon_ASVs_table.tsv 38 | 826 wood_plastic_kesy/Fix_Results_0.1/fixed_non_rare_tables/wood_plastic_kesy_ASVs_table.tsv 39 | -------------------------------------------------------------------------------- /Misc_datafiles/ASV_nonfilt_nums.txt: -------------------------------------------------------------------------------- 1 | 37234 ArcticFireSoils/No_filt_Results/fixed_non_rare_tables/ArcticFireSoils_ASVs_table.tsv 2 | 168729 ArcticFreshwaters/No_filt_Results/fixed_non_rare_tables/ArcticFreshwaters_ASVs_table.tsv 3 | 116792 ArcticTransects/No_filt_Results/fixed_non_rare_tables/ArcticTransects_ASVs_table.tsv 4 | 1846 art_scher/No_filt_Results/fixed_non_rare_tables/art_scher_ASVs_table.tsv 5 | 2924 asd_son/No_filt_Results/fixed_non_rare_tables/asd_son_ASVs_table.tsv 6 | 1128 BISCUIT/No_filt_Results/fixed_non_rare_tables/BISCUIT_ASVs_table.tsv 7 | 8246 Blueberry/No_filt_Results/fixed_non_rare_tables/Blueberry_ASVs_table.tsv 8 | 3347 cdi_schubert/No_filt_Results/fixed_non_rare_tables/cdi_schubert_ASVs_table.tsv 9 | 761 cdi_vincent/No_filt_Results/fixed_non_rare_tables/cdi_vincent_ASVs_table.tsv 10 | 1420 Chemerin/No_filt_Results/fixed_non_rare_tables/Chemerin_ASVs_table.tsv 11 | 18414 crc_baxter/No_filt_Results/fixed_non_rare_tables/crc_baxter_ASVs_table.tsv 12 | 40086 crc_zeller/No_filt_Results/fixed_non_rare_tables/crc_zeller_ASVs_table.tsv 13 | 1323 edd_singh/No_filt_Results/fixed_non_rare_tables/edd_singh_ASVs_table.tsv 14 | 1314 Exercise/No_filt_Results/fixed_non_rare_tables/Exercise_ASVs_table.tsv 15 | 1987 glass_plastic_oberbeckmann/No_filt_Results/fixed_non_rare_tables/glass_plastic_oberbeckmann_ASVs_table.tsv 16 | 89066 GWMC_ASIA_NA/No_filt_Results/fixed_non_rare_tables/GWMC_ASIA_NA_ASVs_table.tsv 17 | 92127 GWMC_HOT_COLD/No_filt_Results/fixed_non_rare_tables/GWMC_HOT_COLD_ASVs_table.tsv 18 | 1263 hiv_dinh/No_filt_Results/fixed_non_rare_tables/hiv_dinh_ASVs_table.tsv 19 | 1157 hiv_lozupone/No_filt_Results/fixed_non_rare_tables/hiv_lozupone_ASVs_table.tsv 20 | 14598 hiv_noguerajulian/No_filt_Results/fixed_non_rare_tables/hiv_noguerajulian_ASVs_table.tsv 21 | 10120 ibd_gevers/No_filt_Results/fixed_non_rare_tables/ibd_gevers_ASVs_table.tsv 22 | 2574 ibd_papa/No_filt_Results/fixed_non_rare_tables/ibd_papa_ASVs_table.tsv 23 | 3765 Ji_WTP_DS/No_filt_Results/fixed_non_rare_tables/Ji_WTP_DS_ASVs_table.tsv 24 | 1054 MALL/No_filt_Results/fixed_non_rare_tables/MALL_ASVs_table.tsv 25 | 55965 ob_goodrich/No_filt_Results/fixed_non_rare_tables/ob_goodrich_ASVs_table.tsv 26 | 1204 ob_ross/No_filt_Results/fixed_non_rare_tables/ob_ross_ASVs_table.tsv 27 | 6112 ob_turnbaugh/No_filt_Results/fixed_non_rare_tables/ob_turnbaugh_ASVs_table.tsv 28 | 3314 ob_zhu/No_filt_Results/fixed_non_rare_tables/ob_zhu_ASVs_table.tsv 29 | 3857 ob_zupancic/No_filt_Results/fixed_non_rare_tables/ob_zupancic_ASVs_table.tsv 30 | 74923 Office/No_filt_Results/fixed_non_rare_tables/Office_ASVs_table.tsv 31 | 2911 par_scheperjans/No_filt_Results/fixed_non_rare_tables/par_scheperjans_ASVs_table.tsv 32 | 7266 sed_plastic_hoellein/No_filt_Results/fixed_non_rare_tables/sed_plastic_hoellein_ASVs_table.tsv 33 | 1725 sed_plastic_rosato/No_filt_Results/fixed_non_rare_tables/sed_plastic_rosato_ASVs_table.tsv 34 | 9286 seston_plastic_mccormick/No_filt_Results/fixed_non_rare_tables/seston_plastic_mccormick_ASVs_table.tsv 35 | 19936 sw_plastic_frere/No_filt_Results/fixed_non_rare_tables/sw_plastic_frere_ASVs_table.tsv 36 | 10750 sw_sed_detender/No_filt_Results/fixed_non_rare_tables/sw_sed_detender_ASVs_table.tsv 37 | 83349 t1d_alkanani/No_filt_Results/fixed_non_rare_tables/t1d_alkanani_ASVs_table.tsv 38 | 572 t1d_mejialeon/No_filt_Results/fixed_non_rare_tables/t1d_mejialeon_ASVs_table.tsv 39 | 3210 wood_plastic_kesy/No_filt_Results/fixed_non_rare_tables/wood_plastic_kesy_ASVs_table.tsv 40 | -------------------------------------------------------------------------------- /Misc_datafiles/Expected_MALL_output/No_filt_Results/Maaslin2_out/residuals.rds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Misc_datafiles/Expected_MALL_output/No_filt_Results/Maaslin2_out/residuals.rds -------------------------------------------------------------------------------- /Misc_datafiles/Expected_MALL_output/No_filt_Results/Maaslin2_out/significant_results.tsv: -------------------------------------------------------------------------------- 1 | metadata feature value coef stderr N N.not.0 pval qval 2 | -------------------------------------------------------------------------------- /Misc_datafiles/Expected_MALL_output/No_filt_Results/Maaslin2_rare_out/residuals.rds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Misc_datafiles/Expected_MALL_output/No_filt_Results/Maaslin2_rare_out/residuals.rds -------------------------------------------------------------------------------- /Misc_datafiles/Expected_MALL_output/No_filt_Results/Maaslin2_rare_out/significant_results.tsv: -------------------------------------------------------------------------------- 1 | metadata feature value coef stderr N N.not.0 pval qval 2 | -------------------------------------------------------------------------------- /Misc_datafiles/Expected_MALL_output/No_filt_Results/limma_voom_tmm_out/Ref_choosing.txt: -------------------------------------------------------------------------------- 1 | Used max square root read depth to determine reference sample 2 | -------------------------------------------------------------------------------- /Misc_datafiles/Expected_MALL_output/No_filt_Results/time_file.txt: -------------------------------------------------------------------------------- 1 | Filtering took 0 seconds 2 | Aldex2 took 40 seconds 3 | Deseq2 took 16 seconds 4 | Lefse took 13 seconds 5 | Corncob took 51 seconds 6 | Wilcoxon rare took 2 seconds 7 | Wilcoxon CLR took 2 seconds 8 | Maaslin2 rare took 6 seconds 9 | Maaslin2 took 6 seconds 10 | Ancom2 took 580 seconds 11 | metagenomeSeq took 8 seconds 12 | edgeR took 7 seconds 13 | t test rare took 1 seconds 14 | Limma_voom_tmm took 2 seconds 15 | Limma_voom_TMMwsp took 1 seconds 16 | -------------------------------------------------------------------------------- /Misc_datafiles/aitchison_permanova_results.tsv: -------------------------------------------------------------------------------- 1 | dataset filt_nonrare_R2 filt_nonrare_P filt_rare_R2 filt_rare_P unfilt_nonrare_R2 unfilt_nonrare_P unfilt_rare_R2 unfilt_rare_P 2 | ArcticFireSoils 0.0696659963457443 0.001 0.0688600113258021 0.001 0.0542323195067593 0.001 0.0550757134646529 0.001 3 | ArcticFreshwaters 0.0405820504645526 0.001 0.0363953085956932 0.001 0.0502799463570677 0.001 0.0504909980060341 0.001 4 | ArcticTransects 0.114453368766791 0.001 0.0912421942522724 0.001 0.0687747984673482 0.001 0.0569505530217616 0.001 5 | art_scher 0.0264215838181628 0.103 0.0279898976875674 0.049 0.0191558400778249 0.045 0.0206054315940519 0.02 6 | asd_son 0.00973376364571379 0.939 0.00955744261502291 0.952 0.00869260971347566 0.905 0.00862310853453559 0.931 7 | BISCUIT 0.0356368212959645 0.053 0.0368513711909307 0.035 0.0315558558761565 0.055 0.0322196272722851 0.05 8 | Blueberry 0.0430503334549609 0.003 0.0434201165143512 0.001 0.0340809556081408 0.007 0.0341482894423532 0.002 9 | cdi_schubert 0.104582541742789 0.001 0.103174196252833 0.001 0.0883539564282318 0.001 0.0833398723977644 0.001 10 | cdi_vincent 0.0524387774936984 0.002 0.0585776506027014 0.002 0.0439697975615856 0.002 0.0502835057121468 0.001 11 | Chemerin 0.431141476424867 0.001 0.428686128591787 0.001 0.367475271256685 0.001 0.376077050615621 0.001 12 | crc_baxter 0.00652191745654173 0.003 0.00625126513275595 0.005 0.0055765718073815 0.003 0.00564526935581744 0.003 13 | crc_zeller 0.0185197060991465 0.001 0.0171402101553203 0.001 0.0163081745890095 0.001 0.0156203622979426 0.001 14 | edd_singh 0.0711019462728914 0.001 0.0699810048001066 0.001 0.0608740763961222 0.001 0.0589073038909859 0.001 15 | Exercise 0.0179936756213328 0.039 0.0176292820420758 0.044 0.0174263465050254 0.031 0.0174080319949745 0.031 16 | glass_plastic_oberbeckmann 0.0885059627297402 0.002 0.0871745849248641 0.006 0.075732347035947 0.003 0.0807851312295007 0.002 17 | GWMC_ASIA_NA 0.0674603629148846 0.001 0.0659804933722939 0.001 0.05394252312387 0.001 0.052586984757971 0.001 18 | GWMC_HOT_COLD 0.0262420613133043 0.001 0.0256458743321881 0.001 0.0218820845319328 0.001 0.0216192854368454 0.001 19 | hiv_dinh 0.0472191349308132 0.365 0.0504000975504559 0.246 0.0346830390485636 0.437 0.0389113300145299 0.171 20 | hiv_lozupone 0.0634896981436903 0.093 0.0639318628750018 0.038 0.060723774609126 0.053 0.0701932722924571 0.005 21 | hiv_noguerajulian 0.0179940301753056 0.001 0.0160390388935053 0.001 0.0149218759182206 0.001 0.0148919856837446 0.001 22 | ibd_gevers 0.0187338461457287 0.002 0.017702902922383 0.002 0.0149578304895623 0.001 0.0135320487590814 0.001 23 | ibd_papa 0.0748332988846814 0.185 0.0716422170108597 0.239 0.0608473718284121 0.05 0.0576487000814562 0.047 24 | Ji_WTP_DS 0.315499442135693 0.001 0.312719524275217 0.001 0.252316295920156 0.001 0.25828174892952 0.001 25 | MALL 0.102178680562977 0.001 0.098440028547477 0.001 0.0732203266918138 0.001 0.0740838459997038 0.001 26 | ob_goodrich 0.00597913360766927 0.001 0.00582601661747585 0.001 0.00448856604165553 0.001 0.00481872395166033 0.001 27 | ob_ross 0.0199826499287357 0.677 0.0207673957419119 0.576 0.0185682894609536 0.634 0.0179379423666287 0.754 28 | ob_turnbaugh 0.0441659858515161 0.001 0.0406018931215271 0.001 0.0260430642537702 0.001 0.0204564006567571 0.001 29 | ob_zhu 0.0790279278571828 0.001 0.0745749547788973 0.002 0.0627735887772468 0.002 0.0594163144109 0.001 30 | Office 0.00943658926456931 0.001 0.0103017107149803 0.001 0.00327291734097775 0.001 0.0038051998499933 0.001 31 | par_scheperjans 0.0319529957827855 0.739 0.0312989817633516 0.817 0.0116310509030206 0.009 0.0116752020126558 0.011 32 | sed_plastic_hoellein 0.0988349546676057 0.005 0.0909266147413382 0.003 0.0960070521610969 0.002 0.0889588771898027 0.001 33 | sed_plastic_rosato 0.212548085683567 0.001 0.208454740929283 0.001 0.195400963026763 0.001 0.19977823397974 0.001 34 | seston_plastic_mccormick 0.0767979477771775 0.001 0.0762327125086603 0.001 0.0708130130257204 0.001 0.070002727958991 0.001 35 | sw_plastic_frere 0.146934355134702 0.001 0.170294760515622 0.001 0.0975763278489827 0.001 0.140586375883642 0.001 36 | sw_sed_detender 0.311131297024804 0.001 0.316494438833168 0.001 0.233368291916124 0.001 0.256049793952969 0.001 37 | t1d_alkanani 0.136120580660059 0.031 0.133970455768121 0.027 0.0138413204515799 0.08 0.0142518645726207 0.002 38 | t1d_mejialeon 0.0888557538984517 0.001 0.0883037823917124 0.001 0.0663230678240696 0.003 0.0623055239681937 0.007 39 | wood_plastic_kesy 0.0363915516983625 0.005 0.0389304152972254 0.002 0.0413541034229947 0.002 0.0386437419800718 0.003 40 | -------------------------------------------------------------------------------- /Misc_datafiles/bray_permanova_results.tsv: -------------------------------------------------------------------------------- 1 | dataset filt_nonrare_R2 filt_nonrare_P filt_rare_R2 filt_rare_P unfilt_nonrare_R2 unfilt_nonrare_P unfilt_rare_R2 unfilt_rare_P 2 | ArcticFireSoils 0.116430851040547 0.001 0.118777400655713 0.001 0.107601933181985 0.001 0.110623366393566 0.001 3 | ArcticFreshwaters 0.0306144557443891 0.001 0.0327187537138362 0.001 0.0557225905105872 0.001 0.0554134639088689 0.001 4 | ArcticTransects 0.0979264658820938 0.001 0.104210174168245 0.001 0.072541572653433 0.001 0.0699574948379634 0.001 5 | art_scher 0.0293679032724185 0.151 0.033881342084829 0.063 0.0239472881464801 0.028 0.025226486695914 0.031 6 | asd_son 0.00903991486063062 0.874 0.0085094858452797 0.906 0.00854818981481689 0.762 0.00830043644019556 0.822 7 | BISCUIT 0.034316738852871 0.211 0.0320188550727848 0.329 0.0313535814184384 0.203 0.0296793892759467 0.267 8 | Blueberry 0.0530782651231991 0.003 0.05422671446061 0.002 0.0429866738259712 0.001 0.0432588729130845 0.001 9 | cdi_schubert 0.107964496513486 0.001 0.113210897497602 0.001 0.092686728162187 0.001 0.0956652261719034 0.001 10 | cdi_vincent 0.0671715708351409 0.002 0.0604357872192049 0.008 0.0532292988955698 0.001 0.0475304835433114 0.006 11 | Chemerin 0.422069937034238 0.001 0.450822994281947 0.001 0.39843613296692 0.001 0.426821102288684 0.001 12 | crc_baxter 0.00559127673014292 0.07 0.00649815611421106 0.016 0.00489919609710061 0.088 0.00568167286951534 0.025 13 | crc_zeller 0.0200389260246195 0.001 0.0203915915094094 0.001 0.0190927176794497 0.001 0.0193202369195699 0.001 14 | edd_singh 0.0959002187722125 0.001 0.103790332401906 0.001 0.0734872585154947 0.001 0.0802380403989765 0.001 15 | Exercise 0.0165383766026926 0.129 0.018697082361532 0.073 0.0170586885725996 0.106 0.0207080291912292 0.04 16 | glass_plastic_oberbeckmann 0.0805474418368185 0.004 0.0793734441526137 0.004 0.0784808575910739 0.004 0.0781870997116278 0.003 17 | GWMC_ASIA_NA 0.0638369810080224 0.001 0.0663551002501294 0.001 0.055698357643091 0.001 0.0574630918379047 0.001 18 | GWMC_HOT_COLD 0.0253009009796941 0.001 0.0263941325355094 0.001 0.0226881690940975 0.001 0.0235370257608044 0.001 19 | hiv_dinh 0.0479358205301399 0.358 0.0365808699887769 0.737 0.0401520795920137 0.206 0.0358141000401257 0.357 20 | hiv_lozupone 0.0559897959939816 0.143 0.0701575011263694 0.07 0.0596378396769087 0.068 0.0720234249877082 0.024 21 | hiv_noguerajulian 0.0117599085985723 0.007 0.0147649589663225 0.003 0.0107734475528079 0.011 0.0145971316463098 0.001 22 | ibd_gevers 0.0159465944925995 0.001 0.0175993756048021 0.001 0.0132626671952414 0.003 0.0140370826511317 0.003 23 | ibd_papa 0.0693333505841738 0.316 0.0722723939736976 0.229 0.0544291085297718 0.109 0.0553025749662446 0.09 24 | Ji_WTP_DS 0.259543620863993 0.001 0.262747131701576 0.001 0.24188749808027 0.001 0.245332163398253 0.001 25 | MALL 0.0863571720617086 0.001 0.0860956148488012 0.001 0.0719247347954552 0.001 0.0736524723141514 0.001 26 | ob_goodrich 0.00680033244961309 0.001 0.00696166437183179 0.001 0.0060967693517676 0.001 0.00634742011048468 0.001 27 | ob_ross 0.0180865476823261 0.754 0.0197898206534867 0.581 0.0150991545551047 0.901 0.0163224944946619 0.794 28 | ob_turnbaugh 0.035858528458453 0.022 0.0391372210269653 0.01 0.0242662221095587 0.001 0.0206472068762274 0.013 29 | ob_zhu 0.0674261338979812 0.001 0.0699134711047738 0.002 0.0555311499642529 0.003 0.0567603845063669 0.001 30 | Office 0.0118643899440962 0.001 0.0136125541369809 0.001 0.00590165992607382 0.001 0.00572839189365014 0.001 31 | par_scheperjans 0.0306335608629616 0.709 0.0312092327207969 0.716 0.012360994791374 0.008 0.0122265239708879 0.016 32 | sed_plastic_hoellein 0.109032788302582 0.002 0.100507172113011 0.004 0.104917144662532 0.002 0.0988455580196773 0.002 33 | sed_plastic_rosato 0.178868801445473 0.001 0.184765545735814 0.001 0.177332988091263 0.001 0.182730241015584 0.001 34 | seston_plastic_mccormick 0.108100178985157 0.001 0.109354049572423 0.001 0.0966740040815368 0.001 0.0952864225338249 0.001 35 | sw_plastic_frere 0.220359303341093 0.001 0.21528897530646 0.001 0.201046585286705 0.001 0.192316573759398 0.001 36 | sw_sed_detender 0.317035586647081 0.001 0.352922528933158 0.001 0.286975851836558 0.001 0.313845961035455 0.001 37 | t1d_alkanani 0.106900168960632 0.141 0.138442141089384 0.046 0.0175741463857884 0.004 0.0160637014093064 0.001 38 | t1d_mejialeon 0.16706485066504 0.001 0.172699171191831 0.001 0.121402016139151 0.002 0.118439423787597 0.002 39 | wood_plastic_kesy 0.0579138052214306 0.001 0.0549819136995836 0.005 0.0570852092203069 0.001 0.0518989767690092 0.001 40 | -------------------------------------------------------------------------------- /Misc_datafiles/consistency_analysis_RDS_out/diarrhea_combined_overlap.rds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Misc_datafiles/consistency_analysis_RDS_out/diarrhea_combined_overlap.rds -------------------------------------------------------------------------------- /Misc_datafiles/consistency_analysis_RDS_out/diarrhea_outputs_binary_clean_combined.rds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Misc_datafiles/consistency_analysis_RDS_out/diarrhea_outputs_binary_clean_combined.rds -------------------------------------------------------------------------------- /Misc_datafiles/consistency_analysis_RDS_out/obesity_combined_overlap.rds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Misc_datafiles/consistency_analysis_RDS_out/obesity_combined_overlap.rds -------------------------------------------------------------------------------- /Misc_datafiles/consistency_analysis_RDS_out/obesity_outputs_binary_clean_combined.rds: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Misc_datafiles/consistency_analysis_RDS_out/obesity_outputs_binary_clean_combined.rds -------------------------------------------------------------------------------- /Misc_datafiles/mapfiles/dataset_name_mapping.csv: -------------------------------------------------------------------------------- 1 | raw,clean 2 | Chemerin,Mouse - Facilities 3 | Blueberry,Soil - Blueberry 4 | MALL,Human - ALL 5 | Exercise,Mouse - Exercised 6 | BISCUIT,Human - CD (1) 7 | Office,Built - Office 8 | art_scher,Human - RA 9 | asd_son,Human - ASD 10 | cdi_schubert,Human - C. diff (1) 11 | cdi_vincent,Human - C. diff (2) 12 | crc_baxter,Human - CC (1) 13 | crc_zeller,Human - CC (2) 14 | edd_singh,Human - Inf. 15 | hiv_dinh,Human - HIV (1) 16 | hiv_lozupone,Human - HIV (2) 17 | hiv_noguerajulian,Human - HIV (3) 18 | ibd_gevers,Human - CD (2) 19 | ibd_papa,Human - IBD 20 | ob_goodrich,Human - OB (1) 21 | ob_ross,Human - OB (2) 22 | ob_turnbaugh,Human - OB (3) 23 | ob_zhu,Human - OB (4) 24 | par_scheperjans,Human - Par. 25 | t1d_alkanani,Human - T1D (1) 26 | t1d_mejialeon,Human - T1D (2) 27 | GWMC_ASIA_NA,WWSR - Continents 28 | GWMC_HOT_COLD,WWSR - Temp. 29 | sw_sed_detender,Marine - Sediment 30 | sw_plastic_frere,Marine - Plastic (1) 31 | sed_plastic_hoellein,Marine - Plastic (2) 32 | wood_plastic_kesy,Marine - Plastic (3) 33 | seston_plastic_mccormick,River - Plastic 34 | glass_plastic_oberbeckmann,Marine - Plastic (4) 35 | sed_plastic_rosato,Marine - Plastic (5) 36 | ArcticTransects,Soil - Arctic 37 | ArcticFireSoils,Soil - Fires 38 | ArcticFreshwaters,Freshwater - Arctic 39 | Ji_WTP_DS,Freshwater - Treat. -------------------------------------------------------------------------------- /Misc_datafiles/mapfiles/diarrhea_lefse_misformatted_ids.txt: -------------------------------------------------------------------------------- 1 | raw fixed 2 | _Ruminococcus_gnavusgroup [Ruminococcus] gnavus group 3 | _Ruminococcus_torquesgroup [Ruminococcus] torques group 4 | LachnospiraceaeNK4A136group Lachnospiraceae NK4A136 group 5 | UCG_003 UCG_003 6 | UCG_002 UCG_002 7 | ErysipelotrichaceaeUCG_003 Erysipelotrichaceae UCG_003 8 | _Eubacterium_eligensgroup [Eubacterium] eligens group 9 | LachnospiraceaeUCG_004 Lachnospiraceae UCG_004 10 | _Eubacterium_halliigroup [Eubacterium] hallii group 11 | Clostridiumsensustricto1 Clostridium sensu stricto 1 12 | NA NA 13 | Prevotella2 Prevotella 2 14 | Prevotella9 Prevotella 9 15 | Prevotella7 Prevotella 7 16 | Coprococcus1 Coprococcus 1 17 | Coprococcus2 Coprococcus 2 18 | CoriobacteriaceaeUCG_002 Coriobacteriaceae UCG_002 19 | ErysipelotrichaceaeUCG_003 Erysipelotrichaceae UCG_003 20 | ErysipelotrichaceaeUCG_006 Erysipelotrichaceae UCG_006 21 | ErysipelotrichaceaeUCG_004 Erysipelotrichaceae UCG_004 22 | _Eubacterium_oxidoreducensgroup [Eubacterium] oxidoreducens group 23 | LachnospiraceaeUCG_005 Lachnospiraceae UCG_005 24 | LachnospiraceaeND3007group Lachnospiraceae ND3007 group 25 | LachnospiraceaeUCG_004 Lachnospiraceae UCG_004 26 | FamilyXIIIAD3011group Family XIIIAD3011 group 27 | LachnospiraceaeUCG_007 Lachnospiraceae UCG_007 28 | LachnospiraceaeUCG_001 Lachnospiraceae UCG_001 29 | LachnospiraceaeUCG_003 Lachnospiraceae UCG_003 30 | Clostridiumsensustricto1 Clostridium sensu stricto 1 31 | LachnospiraceaeUCG_008 Lachnospiraceae UCG_008 32 | Ruminococcus1 Ruminococcus 1 33 | Ruminococcus2 Ruminococcus 2 34 | LachnospiraceaeUCG_010 Lachnospiraceae UCG_010 35 | FamilyXIIIUCG_001 Family XIIIUCG_001 36 | ChristensenellaceaeR_7group Christensenellaceae R_7 group 37 | _Eubacterium_ruminantiumgroup [Eubacterium] ruminantium group 38 | PrevotellaceaeNK3B31group Prevotellaceae NK3B31 group 39 | RuminococcaceaeUCG_014 Ruminococcaceae UCG_014 40 | RuminococcaceaeUCG_013 Ruminococcaceae UCG_013 41 | RuminococcaceaeUCG_010 Ruminococcaceae UCG_010 42 | _Eubacterium_brachygroup [Eubacterium] brachy group 43 | RuminococcaceaeNK4A214group Ruminococcaceae NK4A214 group 44 | RikenellaceaeRC9gutgroup Rikenellaceae RC9 gut group 45 | RuminococcaceaeUCG_011 Ruminococcaceae UCG_011 46 | DefluviitaleaceaeUCG_011 Defluviitaleaceae UCG_011 47 | RuminococcaceaeUCG_009 Ruminococcaceae UCG_009 48 | RuminococcaceaeUCG_005 Ruminococcaceae UCG_005 49 | RuminococcaceaeUCG_004 Ruminococcaceae UCG_004 50 | RuminococcaceaeUCG_007 Ruminococcaceae UCG_007 51 | RuminococcaceaeUCG_003 Ruminococcaceae UCG_003 52 | RuminococcaceaeUCG_002 Ruminococcaceae UCG_002 53 | LachnospiraceaeNK4A136group Lachnospiraceae NK4A136 group 54 | _Eubacterium_coprostanoligenesgroup [Eubacterium] coprostanoligenes group 55 | _Eubacterium_nodatumgroup [Eubacterium] nodatum group 56 | LachnospiraceaeNC2004group Lachnospiraceae NC2004 group 57 | Tyzzerella3 Tyzzerella 3 58 | Corynebacterium1 Corynebacterium 1 59 | CandidatusSoleaferrea Candidatus Soleaferrea 60 | _Eubacterium_halliigroup [Eubacterium] halliigroup 61 | CandidatusSaccharimonas Candidatus Saccharimonas 62 | RuminococcaceaeV9D2013group Ruminococcaceae V9D2013 group 63 | Escherichia_Shigella Escherichia_Shigella 64 | LachnospiraceaeFCS020group Lachnospiraceae FCS020 group 65 | Ruminiclostridium9 Ruminiclostridium 9 66 | Ruminiclostridium6 Ruminiclostridium 6 67 | Ruminiclostridium5 Ruminiclostridium 5 68 | Ruminiclostridium1 Ruminiclostridium 1 69 | _Eubacterium_ventriosumgroup [Eubacterium] ventriosum group 70 | _Ruminococcus_gauvreauiigroup [Ruminococcus] gauvreauii group -------------------------------------------------------------------------------- /Misc_datafiles/mapfiles/tool_name_mapping.csv: -------------------------------------------------------------------------------- 1 | raw,clean 2 | aldex2,ALDEx2 3 | ancom,ANCOM-II 4 | corncob,corncob 5 | deseq2,DESeq2 6 | edger,edgeR 7 | lefse,LEfSe 8 | limma_voom_TMM,limma voom (TMM) 9 | limma_voom_TMMwsp,limma voom (TMMwsp) 10 | maaslin2,MaAsLin2 11 | maaslin2rare,MaAsLin2 (rare) 12 | metagenomeSeq,metagenomeSeq 13 | ttestrare,t-test (rare) 14 | wilcoxonclr,Wilcoxon (CLR) 15 | wilcoxonrare,Wilcoxon (rare) 16 | -------------------------------------------------------------------------------- /Misc_datafiles/uchime_ref_chimera_parsing/uchime_ref_chimera_filenames.tsv: -------------------------------------------------------------------------------- 1 | dataset file percent_chimeras 2 | crc_zeller crc_zeller.otu_seqs.100.passed.fasta 33.8 3 | ob_goodrich ob_goodrich.otu_seqs.100.passed.fasta 18.3 4 | Blueberry Blueberry_ASVs.fasta 14 5 | ArcticFireSoils ArcticFireSoils.fa 13.7 6 | Chemerin Chemerin_ASVs.fasta 13.2 7 | GWMC_ASIA_NA GWMC_ASIA_NA.fasta 12.5 8 | GWMC_HOT_COLD GWMC_HOT_COLD_ASVs.fasta 12.5 9 | Office Office_ASVs.fasta 10.2 10 | hiv_noguerajulian hiv_noguerajulian.otu_seqs.100.passed.fasta 9 11 | t1d_mejialeon t1d_mejialeon.otu_seqs.100.passed.fasta 8.8 12 | ArcticTransects ArcticTransects.fa 8.3 13 | t1d_alkanani t1d_alkanani.otu_seqs.100.passed.fasta 8 14 | cdi_schubert cdi_schubert.otu_seqs.100.passed.fasta 7.7 15 | crc_baxter crc_baxter.otu_seqs.100.passed.fasta 7.5 16 | Exercise Exercise_ASVs.fasta 6.9 17 | sw_plastic_frere sw_plastic_frere_ASVs.fasta 6.5 18 | sed_plastic_rosato sed_plastic_rosato_ASVs.fasta 5.8 19 | asd_son asd_son.otu_seqs.100.passed.fasta 5.5 20 | sw_sed_detender sw_sed_detender_ASVs.fasta 5 21 | ob_zhu ob_zhu.otu_seqs.100.passed.fasta 4.8 22 | ArcticFreshwaters ArcticFreshwaters.fa 4.4 23 | hiv_lozupone hiv_lozupone.otu_seqs.100.passed.fasta 4.1 24 | edd_singh edd_singh.otu_seqs.100.passed.fasta 4 25 | hiv_dinh hiv_dinh.otu_seqs.100.passed.fasta 4 26 | ibd_gevers ibd_gevers.otu_seqs.100.passed.fasta 3.8 27 | par_scheperjans par_scheperjans.otu_seqs.100.passed.fasta 2.8 28 | wood_plastic_kesy wood_plastic_kesy_ASVs.fasta 2.6 29 | BISCUIT BISCUIT_ASVs.fasta 2.3 30 | seston_plastic_mccormick seston_plastic_mccormick_ASVs.fasta 2.3 31 | sed_plastic_hoellein sed_plastic_hoellein_ASVs.fasta 2 32 | glass_plastic_oberbeckmann glass_plastic_oberbeckmann_ASVs.fasta 1.5 33 | MALL MALL_ASVs.fasta 1.5 34 | ibd_papa ibd_papa.otu_seqs.100.passed.fasta 0.9 35 | Ji_WTP_DS Ji_WTP_DS.fa 0.9 36 | cdi_vincent cdi_vincent.otu_seqs.100.passed.fasta 0.5 37 | ob_turnbaugh ob_turnbaugh.otu_seqs.100.passed.fasta 0.5 38 | art_scher art_scher.otu_seqs.100.passed.fasta 0.3 39 | ob_ross ob_ross.otu_seqs.100.passed.fasta 0.2 -------------------------------------------------------------------------------- /Misc_datafiles/uchime_ref_chimera_parsing/uchime_ref_chimera_percents.tsv: -------------------------------------------------------------------------------- 1 | filt_rare filt_nonrare unfilt_rare unfilt_nonrare 2 | ArcticFireSoils 5.58951965065502 5.58951965065502 12.9589632829374 13.6572395455644 3 | ArcticFreshwaters 0.290697674418605 0.290697674418605 3.65536831677163 4.47880612583566 4 | ArcticTransects 0.593798108643061 0.593798108643061 4.25511150148831 8.23864852599944 5 | art_scher 0.29673590504451 0.29585798816568 0.273672687465791 0.2710027100271 6 | asd_son 4.42307692307692 4.42307692307692 5.54414784394251 5.54225111187136 7 | BISCUIT 1.70068027210884 1.70068027210884 2.24416517055655 2.21827861579414 8 | Blueberry 13.3066994468347 13.3066994468347 13.9645114244045 13.9599757428745 9 | cdi_schubert 8.18030050083473 8.18030050083473 7.65983112183353 7.68081291093843 10 | cdi_vincent 0.873362445414847 0.871459694989107 0.535475234270415 0.526315789473684 11 | Chemerin 2.83553875236295 2.83553875236295 13.0681818181818 13.2487667371388 12 | crc_baxter 3.33333333333333 3.33055786844296 6.98107584562658 7.50556671916581 13 | crc_zeller 28.7494515138218 28.72424375274 33.4877599368255 33.7757265810153 14 | edd_singh 4.88888888888889 4.88888888888889 4.02124430955994 4.00907715582451 15 | Exercise 4.07303370786517 4.07303370786517 6.89655172413793 6.93069306930693 16 | glass_plastic_oberbeckmann 0.875912408759124 0.875912408759124 1.54781647318961 1.46022155085599 17 | GWMC_ASIA_NA 9.42538238941711 9.42538238941711 9.26129909469554 12.4246336944928 18 | GWMC_HOT_COLD 9.23575860124083 9.23575860124083 9.14192190787936 12.1246987821028 19 | hiv_dinh 4.66237942122186 4.66237942122186 4.05083399523431 4.04120443740095 20 | hiv_lozupone 2.0260492040521 2.11864406779661 4.10958904109589 4.1522491349481 21 | hiv_noguerajulian 6.20713305898491 6.30659767141009 8.36927500513452 9.00870041789409 22 | ibd_gevers 1.46443514644351 1.46290491118077 3.41534309145645 3.75531178970254 23 | ibd_papa 0.493583415597236 0.492125984251969 0.906225374310481 0.893898173338515 24 | Ji_WTP_DS 0.78125 0.78125 0.705645161290323 0.664187035069075 25 | MALL 0.355871886120996 0.355871886120996 1.55339805825243 1.51946818613485 26 | ob_goodrich 9.9370188943317 9.9370188943317 17.960681186775 18.3189193052677 27 | ob_ross 0.166389351081531 0.166389351081531 0.250417362270451 0.249376558603491 28 | ob_turnbaugh 0.877742946708464 0.87719298245614 0.52382561676242 0.540009818360334 29 | ob_zhu 4.28973277074543 4.3115438108484 4.56235214599527 4.7087232115907 30 | Office 0 0 7.75471875293455 9.12282106724327 31 | par_scheperjans 1.25588697017268 1.22511485451761 2.79021701687909 2.78350515463918 32 | sed_plastic_hoellein 1.40949554896142 1.3728323699422 1.8900675024108 2.00963523743978 33 | sed_plastic_rosato 5.33751962323391 5.3405572755418 5.50568521843208 5.80046403712297 34 | seston_plastic_mccormick 1.00755667506297 1.00502512562814 2.22355769230769 2.34787291330102 35 | sw_plastic_frere 6.44347626691126 6.60691954981242 6.69335886500131 6.53122648607976 36 | sw_sed_detender 4.1780199818347 4.1406945681211 4.64820570782707 5.023723137036 37 | t1d_alkanani 10.0175746924429 9.33125972006221 7.65069203372256 7.97859576714498 38 | t1d_mejialeon 7.55667506297229 7.55667506297229 8.7719298245614 8.75656742556918 39 | wood_plastic_kesy 1.60493827160494 1.57575757575758 3.04321363359708 2.55531318167653 40 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/ArcticFreshwaters_split.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | 4 | source ../../../Config.sh 5 | echo $DATA_DIR 6 | 7 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing 8 | 9 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/ArcticFreshwaters/No_filt_Results/fixed_non_rare_tables/ArcticFreshwaters_ASVs_table.tsv -R $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table_rare.tsv -G $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_meta.tsv -O $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/ 10 | 11 | 12 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Blueberry_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | echo $DATA_DIR 6 | 7 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing 8 | 9 | 10 | 11 | 12 | 13 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/Blueberry/No_filt_Results/fixed_non_rare_tables/Blueberry_ASVs_table.tsv -R $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table_rare.tsv -G $DATA_DIR/Studies/Blueberry/Blueberry_metadata.tsv -O $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/ 14 | 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Generate_ALL_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | 4 | 5 | ./ArcticFreshwaters_split.sh 6 | ./Blueberry_splits.sh 7 | ./cdi_schubert_splits.sh 8 | ./hiv_noguerajulian_splits.sh 9 | ./Ji_WTP_DS_split.sh 10 | ./Ob_goodrich_generate_rand_splits.sh 11 | ./Office_splits.sh 12 | ./sw_sed_splits.sh 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Generate_Random_Splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | ASV_table_Path= 4 | Output_Path= 5 | Rar_ASV_table_Path= 6 | Filt_ASV_table= 7 | Filt_Rar_ASV_table= 8 | Groupings_Path= 9 | 10 | ## loop that accepts arguments from command line 11 | while [ "$1" != "" ]; do 12 | case $1 in 13 | -A | --ASV_table ) 14 | shift 15 | ASV_table_Path=$1 16 | ;; 17 | -R | --rar_ASV_table ) 18 | shift 19 | Rar_ASV_table_Path=$1 20 | ;; 21 | -G | --Groupings ) 22 | shift 23 | Groupings_Path=$1 24 | ;; 25 | -O | --output ) 26 | shift 27 | Output_Path=$1 28 | ;; 29 | * ) 30 | echo "argument not recognized" 31 | exit 1 32 | esac 33 | shift 34 | done 35 | 36 | ### deal with nonfilt samples first 37 | mkdir $Output_Path/nonfilt_tabs 38 | nonfilt_out=$Output_Path/nonfilt_tabs 39 | ## Rscript that takes in ASV table, Groupings table, Rar table and generates 100 new random grouping files 40 | ## along with a single ASV and rar ASV table that comes from samples of the largest grouping 41 | Rscript Generate_splits.R $ASV_table_Path $Groupings_Path $Rar_ASV_table_Path $nonfilt_out 42 | 43 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Generate_splits.R: -------------------------------------------------------------------------------- 1 | ### script that will take 2 | 3 | args <- commandArgs(trailingOnly = TRUE) 4 | #test if there is an argument supply 5 | if (length(args) <= 2) { 6 | stop("At least three arguments must be supplied", call.=FALSE) 7 | } 8 | 9 | con <- file(args[1]) 10 | file_1_line1 <- readLines(con,n=1) 11 | close(con) 12 | 13 | if(grepl("Constructed from biom file", file_1_line1)){ 14 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 15 | comment.char = "", quote="", check.names = F) 16 | }else{ 17 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 18 | comment.char = "", quote="", check.names = F) 19 | } 20 | 21 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 22 | 23 | # read in rarified table 24 | con2 <- file(args[3]) 25 | file_2_line1 <- readLines(con2, n=1) 26 | close(con2) 27 | 28 | if(grepl("Constructed from biom file", file_2_line1)){ 29 | Rar_ASV_table <- read.table(args[3], sep="\t", skip=1, header=T, row.names = 1, 30 | comment.char = "", quote="", check.names = F) 31 | }else{ 32 | Rar_ASV_table <- read.table(args[3], sep="\t", header=T, row.names = 1, 33 | comment.char = "", quote="", check.names = F) 34 | } 35 | 36 | ### filter rar_asv table so it matches the grouping file. 37 | 38 | sample_num <- length(colnames(Rar_ASV_table)) 39 | grouping_num <- length(rownames(groupings)) 40 | 41 | #check if the same number of samples are being input. 42 | if(sample_num != grouping_num){ 43 | message("The number of samples in the ASV table and the groupings table are unequal") 44 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 45 | } 46 | 47 | #check if order of samples match up. 48 | if(identical(colnames(Rar_ASV_table), rownames(groupings))==T){ 49 | message("Groupings and ASV table are in the same order") 50 | }else{ 51 | rows_to_keep <- intersect(colnames(Rar_ASV_table), rownames(groupings)) 52 | groupings <- groupings[rows_to_keep,,drop=F] 53 | Rar_ASV_table <- Rar_ASV_table[,rows_to_keep] 54 | if(identical(colnames(Rar_ASV_table), rownames(groupings))==T){ 55 | message("Groupings table was re-arrange to be in the same order as the ASV table") 56 | message("A total of ", sample_num-length(colnames(Rar_ASV_table)), " from the Rar_ASV_table") 57 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 58 | }else{ 59 | stop("Unable to match samples between the ASV table and groupings table") 60 | } 61 | } 62 | 63 | # match ASV table to rarified table. 64 | sort_ASV_table <- ASV_table[,colnames(Rar_ASV_table)] 65 | 66 | ### okay now to the meat 67 | 68 | ### first we will find which grouping has the largest number of samples 69 | 70 | variable <- names(which.max(table(groupings[1]))) 71 | 72 | filt_groupings <- groupings[which(groupings[1]==variable),,drop=FALSE] 73 | filt_ASV_table <- sort_ASV_table[,rownames(filt_groupings)] 74 | filt_Rar_ASV_table <- Rar_ASV_table[,rownames(filt_groupings)] 75 | 76 | ## we need to export those tables and now we need to generate 100 random groupings 77 | 78 | write_random_grpings <- function(grp_file, num_tabs){ 79 | ### calulate number of samples to be choosen to be grp "ran1" 80 | n <- round(length(rownames(filt_groupings))/2) 81 | 82 | for(i in 1:num_tabs){ 83 | temp_groupings <- filt_groupings[,,drop=F] 84 | samps_choosen <- sample(c(1:length(rownames(filt_groupings))), n) 85 | temp_groupings[1] <- "ran2" 86 | temp_groupings[samps_choosen,] <- "ran1" 87 | tab_name <- paste(args[[4]], "/random_table_",i,".tsv",sep="") 88 | if(i > 10){ 89 | tab_name <- paste(tab_name, "ext", sep="") 90 | } 91 | write.table(temp_groupings, file=tab_name, quote=FALSE, sep="\t", col.names = NA) 92 | } 93 | 94 | } 95 | 96 | write_random_grpings(filt_groupings, 100) 97 | 98 | 99 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Ji_WTP_DS_split.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing 6 | 7 | 8 | 9 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/Ji_WTP_DS/No_filt_Results/fixed_non_rare_tables/Ji_WTP_DS_ASVs_table.tsv -R $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table_rare.tsv -G $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_metadata.csv -O $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/ 10 | 11 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Ob_goodrich_generate_rand_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing 6 | 7 | 8 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/ob_goodrich/No_filt_Results/fixed_non_rare_tables/ob_goodrich_ASVs_table.tsv -R $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table_rare.tsv -G $DATA_DIR/Studies/ob_goodrich/ob_goodrich_metadata.tsv -O $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/ 9 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/Office_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | 4 | source ../../../Config.sh 5 | 6 | 7 | echo $DATA_DIR 8 | 9 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing 10 | 11 | 12 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/Office/No_filt_Results/fixed_non_rare_tables/Office_ASVs_table.tsv -R $DATA_DIR/Studies/Office/Office_ASVs_table_rare.tsv -G $DATA_DIR/Studies/Office/Office_metadata.tsv -O $DATA_DIR/Studies/Office/False_Discovery_Testing/ 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/cdi_schubert_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing 6 | 7 | 8 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/cdi_schubert/No_filt_Results/fixed_non_rare_tables/cdi_schubert_ASVs_table.tsv -R $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table_rare.tsv -G $DATA_DIR/Studies/cdi_schubert/cdi_schubert_metadata.tsv -O $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/ 9 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/hiv_noguerajulian_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing 6 | 7 | 8 | 9 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv -R $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table_rare.tsv -G $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_metadata.tsv -O $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/ 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Generate_Random_data_splits/sw_sed_splits.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing 6 | 7 | 8 | ./Generate_Random_Splits.sh -A $DATA_DIR/Studies/sw_sed_detender/No_filt_Results/fixed_non_rare_tables/sw_sed_detender_ASVs_table.tsv -R $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table_rare.tsv -G $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_metadata.tsv -O $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/ 9 | 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_JI_WTP_DS_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | 14 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_filt/{#} -D 35880 -F 0.1" ::: $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/nonfilt_tabs/*.tsv 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_JI_WTP_DS_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 5 "../../run_all_tools.sh -A $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_all_FP_datasets_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/logs/ 6 | 7 | ## arcticfresh 8 | 9 | ./run_arcticfresh_filt.sh 2> $DATA_DIR/logs/arctic_filt.log 10 | 11 | ## blueberry 12 | ./run_blueberry_filt.sh 2> $DATA_DIR/logs/blueberry_filt.log 13 | 14 | ## goodrich 15 | ./run_goodrich_filt.sh 2> $DATA_DIR/logs/goodrich_filt.log 16 | 17 | ## hiv_nog 18 | ./run_hiv_noguera_filt.sh 2> $DATA_DIR/logs/hiv_nog_filt.log 19 | 20 | ## JI_WTP 21 | ./run_JI_WTP_DS_filt.sh 2> $DATA_DIR/logs/Ji_WTP_filt.log 22 | 23 | ## Office 24 | ./run_office_FD_test_filt.sh 2> $DATA_DIR/logs/office_filt.log 25 | 26 | ## schubert 27 | ./run_schubert_filt.sh 2> $DATA_DIR/logs/schubert_filt.log 28 | 29 | ## sw_sed 30 | ./run_sw_sed_filt.sh 2> $DATA_DIR/logs/sw_sed_filt.log 31 | 32 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_all_FP_datasets_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/logs 6 | 7 | ## arcticfresh 8 | 9 | ./run_arcticfresh_unfilt.sh 2> $DATA_DIR/logs/artic_unfilt.log 10 | 11 | ## blueberry 12 | ./run_blueberry_unfilt.sh 2> $DATA_DIR/logs/blueberry_unfilt.log 13 | 14 | ## goodrich 15 | ./run_goodrich_unfilt.sh 2> $DATA_DIR/logs/goodrich_unfilt.log 16 | 17 | ## hiv_nog 18 | ./run_hiv_noguera_unfilt.sh 2> $DATA_DIR/logs/hiv_nog_unfilt.log 19 | 20 | ## JI_WTP 21 | ./run_JI_WTP_DS_unfilt.sh 2> $DATA_DIR/logs/Ji_WTP_unfilt.log 22 | 23 | ## Office 24 | ./run_office_FD_test_unfilt.sh 2> $DATA_DIR/logs/office_unfilt.log 25 | 26 | ## schubert 27 | ./run_schubert_unfilt.sh 2> $DATA_DIR/logs/schubert_unfilt.log 28 | 29 | ## sw_sed 30 | ./run_sw_sed_unfilt.sh 2> $DATA_DIR/logs/sw_sed_unfilt.log 31 | 32 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_arcticfresh_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | 14 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_filt/{#} -D 2000 -F 0.1" ::: $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/nonfilt_tabs/*.tsv 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_arcticfresh_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | 14 | parallel -j 5 "../../run_all_tools.sh -A $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table_rare.tsv -O $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/nonfilt_tabs/*.tsv 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_blueberry_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_filt/{#} -D 5215 -F 0.1" ::: $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_blueberry_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_goodrich_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_filt/{#} -D 3433 -F 0.1" ::: $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_goodrich_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt 6 | for i in {1..10} 7 | do 8 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt/$i 9 | done 10 | 11 | 12 | parallel -j 5 "../../run_all_tools.sh -A $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table_rare.tsv -O $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_hiv_noguera_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_filt/{#} -D 2012 -F 0.1" ::: $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_hiv_noguera_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table_rare.tsv -O $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_office_FD_test_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/Office/Office_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/Office/False_Discovery_Testing/results_filt/{#} -D 2000 -F 0.1" ::: $DATA_DIR/Studies/Office/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_office_FD_test_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/Office/Office_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Office/Office_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/Office/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_schubert_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_filt/{#} -D 2010 -F 0.1" ::: $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_schubert_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table_rare.tsv -O $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_sw_sed_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "../../run_all_tools.sh -A $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_filt/{#} -D 2000 -F 0.1" ::: $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/False_Discovery_Analysis/Run_scripts/run_sw_sed_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 5 "../../run_all_tools.sh -A $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table_rare.tsv -O $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_JI_WTP_DS_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | 14 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_filt/{#} -D 35880 -F 0.1 --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/nonfilt_tabs/*.tsv* 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_JI_WTP_DS_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 5 "./run_all_tools.sh -A $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_JI_WTP_DS_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | 13 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/Ji_WTP_DS/False_Discovery_Testing/nonfilt_tabs/*.tsvext 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_arcticfresh_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | 6 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_filt 7 | 8 | for i in {1..100} 9 | do 10 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_filt/$i 11 | done 12 | 13 | 14 | 15 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_filt/{#} -D 2000 -F 0.1 --DESEQ2_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --MAASLIN_RARE_SKIP T --MAASLIN_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ANCOM_SKIP T --CORNCOB_SKIP T --ALDEX_SKIP T" ::: $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/nonfilt_tabs/*.tsv* 16 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_arcticfresh_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | 14 | parallel -j 5 "./run_all_tools.sh -A $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table_rare.tsv -O $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/nonfilt_tabs/*.tsv 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_arcticfresh_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | 13 | 14 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table_rare.tsv -O $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/ArcticFreshwaters/False_Discovery_Testing/nonfilt_tabs/*.tsvext 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_blueberry_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_filt/{#} -D 5215 -F 0.1 --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/nonfilt_tabs/*.tsv* 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_blueberry_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "./run_all_tools.sh -A $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_blueberry_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | 13 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Blueberry/Blueberry_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/Blueberry/False_Discovery_Testing/nonfilt_tabs/*.tsvext 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_goodrich_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_filt/{#} -D 3433 -F 0.1" ::: $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/nonfilt_tabs/*.tsv* 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_goodrich_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt 6 | for i in {1..10} 7 | do 8 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt/$i 9 | done 10 | 11 | 12 | parallel -j 5 "./run_all_tools.sh -A $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table_rare.tsv -O $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_goodrich_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt_ext 6 | for i in {1..90} 7 | do 8 | mkdir $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt_ext/$i 9 | done 10 | 11 | 12 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/ob_goodrich/ob_goodrich_ASVs_table_rare.tsv -O $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/ob_goodrich/False_Discovery_Testing/nonfilt_tabs/*.tsvext 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_hiv_noguera_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_filt/{#} -D 2012 -F 0.1 --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/nonfilt_tabs/*.tsv* 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_hiv_noguera_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 10 "./run_all_tools.sh -A $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table_rare.tsv -O $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_hiv_noguera_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | 13 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table_rare.tsv -O $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/hiv_noguerajulian/False_Discovery_Testing/nonfilt_tabs/*.tsvext 14 | 15 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_office_FD_test_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/Office/Office_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/Office/False_Discovery_Testing/results_filt/{#} -D 2000 -F 0.1 --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/Office/False_Discovery_Testing/nonfilt_tabs/*.tsv* 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_office_FD_test_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | parallel -j 5 "./run_all_tools.sh -A $DATA_DIR/Studies/Office/Office_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Office/Office_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/Office/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_office_FD_test_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/Office/Office_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/Office/Office_ASVs_table_rare.tsv -O $DATA_DIR/Studies/Office/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/Office/False_Discovery_Testing/nonfilt_tabs/*.tsvext 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_schubert_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_filt/{#} -D 2010 -F 0.1 --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/nonfilt_tabs/*.tsv* 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_schubert_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | parallel -j 10 "./run_all_tools.sh -A $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table_rare.tsv -O $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/nonfilt_tabs/*.tsv 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_schubert_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/cdi_schubert/cdi_schubert_ASVs_table_rare.tsv -O $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/cdi_schubert/False_Discovery_Testing/nonfilt_tabs/*.tsvext 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_sw_sed_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_filt 6 | 7 | for i in {1..100} 8 | do 9 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_filt/$i 10 | done 11 | 12 | 13 | parallel -j 25 "./run_all_tools.sh -A $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table.tsv -G {1} -O $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_filt/{#} -D 2000 -F 0.1 --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/nonfilt_tabs/*.tsv* 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_sw_sed_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt 6 | 7 | for i in {1..10} 8 | do 9 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt/$i 10 | done 11 | 12 | 13 | parallel -j 5 "./run_all_tools.sh -A $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table_rare.tsv -O $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt/{#}" ::: $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/nonfilt_tabs/*.tsv 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/FP_runs/run_sw_sed_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt_ext 6 | 7 | for i in {1..90} 8 | do 9 | mkdir $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt_ext/$i 10 | done 11 | 12 | 13 | parallel -j 45 "./run_all_tools.sh -A $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table.tsv -G {1} -R $DATA_DIR/Studies/sw_sed_detender/sw_sed_detender_ASVs_table_rare.tsv -O $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/results_nonfilt_ext/{#} --ALDEX_SKIP T --CORNCOB_SKIP T --ANCOM_SKIP T" ::: $DATA_DIR/Studies/sw_sed_detender/False_Discovery_Testing/nonfilt_tabs/*.tsvext 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/filt_input/Genus_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus.tsv 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/filt_input/combined_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_metadata.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_metadata.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_metadata.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_metadata.tsv 10 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_metadata.tsv 11 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/Genus_filt 12 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/Genus_filt 13 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/Genus_filt 14 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/Genus_filt 15 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/Genus_filt 16 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/filt_input/metadata_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_metadata.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_metadata.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_metadata.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_metadata.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_metadata.tsv 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/filt_input/output_files.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/Genus_filt 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/Genus_filt 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/Genus_filt 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/Genus_filt 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/Genus_filt 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/filt_input/sort_combined.txt: -------------------------------------------------------------------------------- 1 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table.tsv 2 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_metadata.tsv 3 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/Genus_filt 4 | 2010 5 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table.tsv 6 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_metadata.tsv 7 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/Genus_filt 8 | 2027 9 | /Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus.tsv 10 | /Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_metadata.tsv 11 | /Testing_Bias_robustness/Diarrhea/dia_schneider/Genus_filt 12 | 10219 13 | /Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table.tsv 14 | /Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_metadata.tsv 15 | /Testing_Bias_robustness/Diarrhea/edd_singh/Genus_filt 16 | 2006 17 | /Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus.tsv 18 | /Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_metadata.tsv 19 | /Testing_Bias_robustness/Diarrhea/GEMS1/Genus_filt 20 | 2017 21 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/nonfilt_input/combined_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_metadata.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_metadata.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_metadata.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_metadata.tsv 10 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_metadata.tsv 11 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/Genus_no_filt 12 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/Genus_no_filt 13 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/Genus_no_filt 14 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/Genus_no_filt 15 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/Genus_no_filt 16 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table_rare.tsv 17 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table_rare.tsv 18 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus_rare.tsv 19 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table_rare.tsv 20 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus_rare.tsv 21 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/nonfilt_input/genus_table.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus.tsv 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/nonfilt_input/metadata_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_metadata.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_metadata.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_metadata.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_metadata.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_metadata.tsv 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/nonfilt_input/output.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/Genus_no_filt 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/Genus_no_filt 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/Genus_no_filt 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/Genus_no_filt 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/Genus_no_filt 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/nonfilt_input/rare_tables.tsv: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table_rare.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table_rare.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus_rare.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table_rare.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus_rare.tsv 6 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Diarrhea/nonfilt_input/sort_combined_input.txt: -------------------------------------------------------------------------------- 1 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table_rare.tsv 2 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_genus_table.tsv 3 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/cdi_schubert_metadata.tsv 4 | /Testing_Bias_robustness/Diarrhea/cdi_schubert/Genus_no_filt 5 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table_rare.tsv 6 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_genus_table.tsv 7 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/cdi_vincent_metadata.tsv 8 | /Testing_Bias_robustness/Diarrhea/cdi_vincent/Genus_no_filt 9 | /Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus_rare.tsv 10 | /Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_genus.tsv 11 | /Testing_Bias_robustness/Diarrhea/dia_schneider/dia_schneider_metadata.tsv 12 | /Testing_Bias_robustness/Diarrhea/dia_schneider/Genus_no_filt 13 | /Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table_rare.tsv 14 | /Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_genus_table.tsv 15 | /Testing_Bias_robustness/Diarrhea/edd_singh/edd_singh_metadata.tsv 16 | /Testing_Bias_robustness/Diarrhea/edd_singh/Genus_no_filt 17 | /Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus_rare.tsv 18 | /Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_genus.tsv 19 | /Testing_Bias_robustness/Diarrhea/GEMS1/GEMS1_metadata.tsv 20 | /Testing_Bias_robustness/Diarrhea/GEMS1/Genus_no_filt 21 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/filt_input/ASV_table_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata.tsv 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/filt_input/combined_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata.tsv 10 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_metadata.tsv 11 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_metadata.tsv 12 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_metadata.tsv 13 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_metadata.tsv 14 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_metadata.tsv 15 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/baxter_groupings.txt 16 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/HMP_groupings.txt 17 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/schubert_groupings.txt 18 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/zeevi_groupings.txt 19 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/Genus_filt 20 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/Genus_filt 21 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/Genus_filt 22 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/Genus_filt 23 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/Genus_filt 24 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/Genus_filt 25 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/Genus_filt 26 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/Genus_filt 27 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/Genus_filt 28 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/filt_input/metadata_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_metadata.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_metadata.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_metadata.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_metadata.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_metadata.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/baxter_groupings.txt 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/HMP_groupings.txt 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/schubert_groupings.txt 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/zeevi_groupings.txt 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/filt_input/output.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/Genus_filt 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/Genus_filt 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/Genus_filt 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/Genus_filt 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/Genus_filt 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/Genus_filt 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/Genus_filt 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/Genus_filt 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/Genus_filt 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/filt_input/sort_combined_input.txt: -------------------------------------------------------------------------------- 1 | /Testing_Bias_robustness/Obesity/baxter/Genus_filt 2 | /Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata.tsv 3 | /Testing_Bias_robustness/Obesity/baxter/baxter_groupings.txt 4 | 10600 5 | /Testing_Bias_robustness/Obesity/goodrich/Genus_filt 6 | /Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table.tsv 7 | /Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_metadata.tsv 8 | 3433 9 | /Testing_Bias_robustness/Obesity/HMP/Genus_filt 10 | /Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata.tsv 11 | /Testing_Bias_robustness/Obesity/HMP/HMP_groupings.txt 12 | 2000 13 | /Testing_Bias_robustness/Obesity/ross/Genus_filt 14 | /Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table.tsv 15 | /Testing_Bias_robustness/Obesity/ross/ob_ross_metadata.tsv 16 | 2017 17 | /Testing_Bias_robustness/Obesity/schubert/Genus_filt 18 | /Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata.tsv 19 | /Testing_Bias_robustness/Obesity/schubert/schubert_groupings.txt 20 | 2000 21 | /Testing_Bias_robustness/Obesity/turnbaugh/Genus_filt 22 | /Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table.tsv 23 | /Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_metadata.tsv 24 | 2008 25 | /Testing_Bias_robustness/Obesity/zeevi/Genus_filt 26 | /Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata.tsv 27 | /Testing_Bias_robustness/Obesity/zeevi/zeevi_groupings.txt 28 | 2000 29 | /Testing_Bias_robustness/Obesity/zhu/Genus_filt 30 | /Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table.tsv 31 | /Testing_Bias_robustness/Obesity/zhu/ob_zhu_metadata.tsv 32 | 2196 33 | /Testing_Bias_robustness/Obesity/zupancic/Genus_filt 34 | /Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table.tsv 35 | /Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_metadata.tsv 36 | 2055 37 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/nonfilt_input/ASV_rare_table.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata_rare.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table_rare.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata_rare.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table_rare.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata_rare.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table_rare.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata_rare.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table_rare.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table_rare.tsv 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/nonfilt_input/ASV_table_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata.tsv 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/nonfilt_input/combined_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata.tsv 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata.tsv 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata.tsv 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata.tsv 10 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata_rare.tsv 11 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table_rare.tsv 12 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata_rare.tsv 13 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table_rare.tsv 14 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata_rare.tsv 15 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table_rare.tsv 16 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata_rare.tsv 17 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table_rare.tsv 18 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table_rare.tsv 19 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_metadata.tsv 20 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_metadata.tsv 21 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_metadata.tsv 22 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_metadata.tsv 23 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_metadata.tsv 24 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/baxter_groupings.txt 25 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/HMP_groupings.txt 26 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/schubert_groupings.txt 27 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/zeevi_groupings.txt 28 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/Genus_filt 29 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/Genus_filt 30 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/Genus_filt 31 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/Genus_filt 32 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/Genus_filt 33 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/Genus_filt 34 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/Genus_filt 35 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/Genus_filt 36 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/Genus_filt 37 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/nonfilt_input/metadata_input.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_metadata.tsv 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/ob_ross_metadata.tsv 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_metadata.tsv 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/ob_zhu_metadata.tsv 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_metadata.tsv 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/baxter_groupings.txt 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/HMP_groupings.txt 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/schubert_groupings.txt 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/zeevi_groupings.txt 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/nonfilt_input/output.txt: -------------------------------------------------------------------------------- 1 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/baxter/Genus_filt 2 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/goodrich/Genus_filt 3 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/HMP/Genus_filt 4 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/ross/Genus_filt 5 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/schubert/Genus_filt 6 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/turnbaugh/Genus_filt 7 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zeevi/Genus_filt 8 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zhu/Genus_filt 9 | /home/jacob/projects/Hackathon/Testing_Bias_robustness/Obesity/zupancic/Genus_filt 10 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/Obesity/nonfilt_input/sort_combined_input.txt: -------------------------------------------------------------------------------- 1 | /Testing_Bias_robustness/Obesity/baxter/Genus_no_filt 2 | /Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata_rare.tsv 3 | /Testing_Bias_robustness/Obesity/baxter/obesity_baxter_genera_metadata.tsv 4 | /Testing_Bias_robustness/Obesity/baxter/baxter_groupings.txt 5 | /Testing_Bias_robustness/Obesity/goodrich/Genus_no_filt 6 | /Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table_rare.tsv 7 | /Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_genus_table.tsv 8 | /Testing_Bias_robustness/Obesity/goodrich/ob_goodrich_metadata.tsv 9 | /Testing_Bias_robustness/Obesity/HMP/Genus_no_filt 10 | /Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata_rare.tsv 11 | /Testing_Bias_robustness/Obesity/HMP/obesity_HMP_genera_metadata.tsv 12 | /Testing_Bias_robustness/Obesity/HMP/HMP_groupings.txt 13 | /Testing_Bias_robustness/Obesity/ross/Genus_no_filt 14 | /Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table_rare.tsv 15 | /Testing_Bias_robustness/Obesity/ross/ob_ross_genus_table.tsv 16 | /Testing_Bias_robustness/Obesity/ross/ob_ross_metadata.tsv 17 | /Testing_Bias_robustness/Obesity/schubert/Genus_no_filt 18 | /Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata_rare.tsv 19 | /Testing_Bias_robustness/Obesity/schubert/obesity_schubert_genera_metadata.tsv 20 | /Testing_Bias_robustness/Obesity/schubert/schubert_groupings.txt 21 | /Testing_Bias_robustness/Obesity/turnbaugh/Genus_no_filt 22 | /Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table_rare.tsv 23 | /Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_genus_table.tsv 24 | /Testing_Bias_robustness/Obesity/turnbaugh/ob_turnbaugh_metadata.tsv 25 | /Testing_Bias_robustness/Obesity/zeevi/Genus_no_filt 26 | /Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata_rare.tsv 27 | /Testing_Bias_robustness/Obesity/zeevi/obesity_zeevi_genera_metadata.tsv 28 | /Testing_Bias_robustness/Obesity/zeevi/zeevi_groupings.txt 29 | /Testing_Bias_robustness/Obesity/zhu/Genus_no_filt 30 | /Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table_rare.tsv 31 | /Testing_Bias_robustness/Obesity/zhu/ob_zhu_genus_table.tsv 32 | /Testing_Bias_robustness/Obesity/zhu/ob_zhu_metadata.tsv 33 | /Testing_Bias_robustness/Obesity/zupancic/Genus_no_filt 34 | /Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table_rare.tsv 35 | /Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_genus_table.tsv 36 | /Testing_Bias_robustness/Obesity/zupancic/ob_zupancic_metadata.tsv 37 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/sorted_combined_input.txt: -------------------------------------------------------------------------------- 1 | /Studies/ArcticFireSoils/ArcticFireSoils_ASVs_table.tsv 2 | /Studies/ArcticFireSoils/ArcticFireSoils_meta.tsv 3 | /Studies/ArcticFireSoils/Fix_Results_0.1 4 | 45300 5 | /Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv 6 | /Studies/ArcticFreshwaters/ArcticFreshwaters_meta.tsv 7 | /Studies/ArcticFreshwaters/Fix_Results_0.1 8 | 2000 9 | /Studies/ArcticTransects/ArcticTransects_ASVs_table.tsv 10 | /Studies/ArcticTransects/ArcticTransects_meta.tsv 11 | /Studies/ArcticTransects/Fix_Results_0.1 12 | 2000 13 | /Studies/art_scher/art_scher_ASVs_table.tsv 14 | /Studies/art_scher/art_scher_metadata.tsv 15 | /Studies/art_scher/Fix_Results_0.1 16 | 2024 17 | /Studies/asd_son/asd_son_ASVs_table.tsv 18 | /Studies/asd_son/asd_son_metadata.tsv 19 | /Studies/asd_son/Fix_Results_0.1 20 | 2529 21 | /Studies/BISCUIT/BISCUIT_ASVs_table.tsv 22 | /Studies/BISCUIT/BISCUIT_metadata.tsv 23 | /Studies/BISCUIT/Fix_Results_0.1 24 | 2098 25 | /Studies/Blueberry/Blueberry_ASVs_table.tsv 26 | /Studies/Blueberry/Blueberry_metadata.tsv 27 | /Studies/Blueberry/Fix_Results_0.1 28 | 5215 29 | /Studies/cdi_schubert/cdi_schubert_ASVs_table.tsv 30 | /Studies/cdi_schubert/cdi_schubert_metadata.tsv 31 | /Studies/cdi_schubert/Fix_Results_0.1 32 | 2010 33 | /Studies/cdi_vincent/cdi_vincent_ASVs_table.tsv 34 | /Studies/cdi_vincent/cdi_vincent_metadata.tsv 35 | /Studies/cdi_vincent/Fix_Results_0.1 36 | 2027 37 | /Studies/Chemerin/Chemerin_ASVs_table.tsv 38 | /Studies/Chemerin/Chemerin_metadata.tsv 39 | /Studies/Chemerin/Fix_Results_0.1 40 | 2456 41 | /Studies/crc_baxter/crc_baxter_ASVs_table.tsv 42 | /Studies/crc_baxter/crc_baxter_metadata.tsv 43 | /Studies/crc_baxter/Fix_Results_0.1 44 | 2021 45 | /Studies/crc_zeller/crc_zeller_ASVs_table.tsv 46 | /Studies/crc_zeller/crc_zeller_metadata.tsv 47 | /Studies/crc_zeller/Fix_Results_0.1 48 | 28042 49 | /Studies/edd_singh/edd_singh_ASVs_table.tsv 50 | /Studies/edd_singh/edd_singh_metadata.tsv 51 | /Studies/edd_singh/Fix_Results_0.1 52 | 2006 53 | /Studies/Exercise/Exercise_ASVs_table.tsv 54 | /Studies/Exercise/Exercise_metadata.tsv 55 | /Studies/Exercise/Fix_Results_0.1 56 | 2184 57 | /Studies/glass_plastic_oberbeckmann/glass_plastic_oberbeckmann_ASVs_table.tsv 58 | /Studies/glass_plastic_oberbeckmann/glass_plastic_oberbeckmann_metadata.tsv 59 | /Studies/glass_plastic_oberbeckmann/Fix_Results_0.1 60 | 2000 61 | /Studies/GWMC_ASIA_NA/GWMC_ASIA_NA_ASVs_table.tsv 62 | /Studies/GWMC_ASIA_NA/GWMC_ASIA_NA_metadata.csv 63 | /Studies/GWMC_ASIA_NA/Fix_Results_0.1 64 | 25600 65 | /Studies/GWMC_HOT_COLD/GWMC_HOT_COLD_ASVs_table.tsv 66 | /Studies/GWMC_HOT_COLD/GWMC_HOT_COLD_metadata.csv 67 | /Studies/GWMC_HOT_COLD/Fix_Results_0.1 68 | 25600 69 | /Studies/hiv_dinh/hiv_dinh_ASVs_table.tsv 70 | /Studies/hiv_dinh/hiv_dinh_metadata.tsv 71 | /Studies/hiv_dinh/Fix_Results_0.1 72 | 2170 73 | /Studies/hiv_lozupone/hiv_lozupone_ASVs_table.tsv 74 | /Studies/hiv_lozupone/hiv_lozupone_metadata.tsv 75 | /Studies/hiv_lozupone/Fix_Results_0.1 76 | 2220 77 | /Studies/hiv_noguerajulian/hiv_noguerajulian_ASVs_table.tsv 78 | /Studies/hiv_noguerajulian/hiv_noguerajulian_metadata.tsv 79 | /Studies/hiv_noguerajulian/Fix_Results_0.1 80 | 2012 81 | /Studies/ibd_gevers/ibd_gevers_ASVs_table.tsv 82 | /Studies/ibd_gevers/ibd_gevers_metadata.tsv 83 | /Studies/ibd_gevers/Fix_Results_0.1 84 | 2071 85 | /Studies/ibd_papa/ibd_papa_ASVs_table.tsv 86 | /Studies/ibd_papa/ibd_papa_metadata.tsv 87 | /Studies/ibd_papa/Fix_Results_0.1 88 | 2089 89 | /Studies/Ji_WTP_DS/Ji_WTP_DS_ASVs_table.tsv 90 | /Studies/Ji_WTP_DS/Ji_WTP_DS_metadata.csv 91 | /Studies/Ji_WTP_DS/Fix_Results_0.1 92 | 35880 93 | /Studies/MALL/MALL_ASVs_table.tsv 94 | /Studies/MALL/MALL_metadata.tsv 95 | /Studies/MALL/Fix_Results_0.1 96 | 2085 97 | /Studies/ob_goodrich/ob_goodrich_ASVs_table.tsv 98 | /Studies/ob_goodrich/ob_goodrich_metadata.tsv 99 | /Studies/ob_goodrich/Fix_Results_0.1 100 | 3433 101 | /Studies/ob_ross/ob_ross_ASVs_table.tsv 102 | /Studies/ob_ross/ob_ross_metadata.tsv 103 | /Studies/ob_ross/Fix_Results_0.1 104 | 2017 105 | /Studies/ob_turnbaugh/ob_turnbaugh_ASVs_table.tsv 106 | /Studies/ob_turnbaugh/ob_turnbaugh_metadata.tsv 107 | /Studies/ob_turnbaugh/Fix_Results_0.1 108 | 2008 109 | /Studies/ob_zhu/ob_zhu_ASVs_table.tsv 110 | /Studies/ob_zhu/ob_zhu_metadata.tsv 111 | /Studies/ob_zhu/Fix_Results_0.1 112 | 2196 113 | /Studies/ob_zupancic/ob_zupancic_ASVs_table.tsv 114 | /Studies/ob_zupancic/ob_zupancic_metadata.tsv 115 | /Studies/ob_zupancic/Fix_Results_0.1 116 | 2055 117 | /Studies/Office/Office_ASVs_table.tsv 118 | /Studies/Office/Office_metadata.tsv 119 | /Studies/Office/Fix_Results_0.1 120 | 2000 121 | /Studies/par_scheperjans/par_scheperjans_ASVs_table.tsv 122 | /Studies/par_scheperjans/par_scheperjans_metadata.tsv 123 | /Studies/par_scheperjans/Fix_Results_0.1 124 | 2023 125 | /Studies/sed_plastic_hoellein/sed_plastic_hoellein_ASVs_table.tsv 126 | /Studies/sed_plastic_hoellein/sed_plastic_hoellein_metadata.tsv 127 | /Studies/sed_plastic_hoellein/Fix_Results_0.1 128 | 2000 129 | /Studies/sed_plastic_rosato/sed_plastic_rosato_ASVs_table.tsv 130 | /Studies/sed_plastic_rosato/sed_plastic_rosato_metadata.tsv 131 | /Studies/sed_plastic_rosato/Fix_Results_0.1 132 | 2000 133 | /Studies/seston_plastic_mccormick/seston_plastic_mccormick_ASVs_table.tsv 134 | /Studies/seston_plastic_mccormick/seston_plastic_mccormick_metadata.tsv 135 | /Studies/seston_plastic_mccormick/Fix_Results_0.1 136 | 2000 137 | /Studies/sw_plastic_frere/sw_plastic_frere_ASVs_table.tsv 138 | /Studies/sw_plastic_frere/sw_plastic_frere_metadata.tsv 139 | /Studies/sw_plastic_frere/Fix_Results_0.1 140 | 2000 141 | /Studies/sw_sed_detender/sw_sed_detender_ASVs_table.tsv 142 | /Studies/sw_sed_detender/sw_sed_detender_metadata.tsv 143 | /Studies/sw_sed_detender/Fix_Results_0.1 144 | 2000 145 | /Studies/t1d_alkanani/t1d_alkanani_ASVs_table.tsv 146 | /Studies/t1d_alkanani/t1d_alkanani_metadata.tsv 147 | /Studies/t1d_alkanani/Fix_Results_0.1 148 | 2060 149 | /Studies/t1d_mejialeon/t1d_mejialeon_ASVs_table.tsv 150 | /Studies/t1d_mejialeon/t1d_mejialeon_metadata.tsv 151 | /Studies/t1d_mejialeon/Fix_Results_0.1 152 | 2202 153 | /Studies/wood_plastic_kesy/wood_plastic_kesy_ASVs_table.tsv 154 | /Studies/wood_plastic_kesy/wood_plastic_kesy_metadata.tsv 155 | /Studies/wood_plastic_kesy/Fix_Results_0.1 156 | 2000 157 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/subset_run_filt.txt: -------------------------------------------------------------------------------- 1 | /Studies/ArcticFireSoils/ArcticFireSoils_ASVs_table.tsv 2 | /Studies/ArcticFireSoils/ArcticFireSoils_meta.tsv 3 | /Studies/ArcticFireSoils/Fix_Results_0.1 4 | 45300 5 | /Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv 6 | /Studies/ArcticFreshwaters/ArcticFreshwaters_meta.tsv 7 | /Studies/ArcticFreshwaters/Fix_Results_0.1 8 | 2000 9 | /Studies/ArcticTransects/ArcticTransects_ASVs_table.tsv 10 | /Studies/ArcticTransects/ArcticTransects_meta.tsv 11 | /Studies/ArcticTransects/Fix_Results_0.1 12 | 2000 13 | /Studies/Office/Office_ASVs_table.tsv 14 | /Studies/Office/Office_metadata.tsv 15 | /Studies/Office/Fix_Results_0.1 16 | 2000 17 | 18 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/input_parameters/subset_run_no_filt.txt: -------------------------------------------------------------------------------- 1 | /Studies/ArcticFireSoils/ArcticFireSoils_ASVs_table_rare.tsv 2 | /Studies/ArcticFireSoils/ArcticFireSoils_ASVs_table.tsv 3 | /Studies/ArcticFireSoils/ArcticFireSoils_meta.tsv 4 | /Studies/ArcticFireSoils/No_filt_Results 5 | /Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table_rare.tsv 6 | /Studies/ArcticFreshwaters/ArcticFreshwaters_ASVs_table.tsv 7 | /Studies/ArcticFreshwaters/ArcticFreshwaters_meta.tsv 8 | /Studies/ArcticFreshwaters/No_filt_Results 9 | /Studies/ArcticTransects/ArcticTransects_ASVs_table_rare.tsv 10 | /Studies/ArcticTransects/ArcticTransects_ASVs_table.tsv 11 | /Studies/ArcticTransects/ArcticTransects_meta.tsv 12 | /Studies/ArcticTransects/No_filt_Results 13 | /Studies/Office/Office_ASVs_table_rare.tsv 14 | /Studies/Office/Office_ASVs_table.tsv 15 | /Studies/Office/Office_metadata.tsv 16 | /Studies/Office/No_filt_Results 17 | 18 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_0.1_filt_datasets.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | export DATA_DIR 6 | 7 | find "$DATA_DIR/Studies" -maxdepth 1 -mindepth 1 -type d | while read dir; 8 | do mkdir $dir/Fix_Results_0.1; 9 | done 10 | 11 | parallel --env $DATA_DIR -j 38 -N4 "./run_all_tools.sh -A $DATA_DIR{1} -G $DATA_DIR{2} -O $DATA_DIR{3} -D {4} -F 0.1" :::: <(cat input_parameters/sorted_combined_input.txt) 12 | 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_0.1_filt_datasets_corncob.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | export DATA_DIR 6 | 7 | find "$DATA_DIR/Studies" -maxdepth 1 -mindepth 1 -type d | while read dir; 8 | do mkdir $dir/Fix_Results_0.1; 9 | done 10 | 11 | parallel --env $DATA_DIR -j 38 -N4 "./run_all_tools.sh -A $DATA_DIR{1} -G $DATA_DIR{2} -O $DATA_DIR{3} -D {4} -F 0.1 --ALDEX_SKIP T --ANCOM_SKIP T --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --MAASLIN_RARE_SKIP T --MAASLIN_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T" :::: <(cat input_parameters/sorted_combined_input.txt) 12 | 13 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_FP_unfilt_EXT.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/logs 6 | 7 | ## arcticfresh 8 | 9 | FP_runs/run_arcticfresh_unfilt_EXT.sh 2> $DATA_DIR/logs/artic_unfilt_EXT.log 10 | 11 | ## blueberry 12 | FP_runs/run_blueberry_unfilt_EXT.sh 2> $DATA_DIR/logs/blueberry_unfilt_EXT.log 13 | 14 | ## goodrich 15 | FP_runs/run_goodrich_unfilt_EXT.sh 2> $DATA_DIR/logs/goodrich_unfilt_EXT.log 16 | 17 | ## hiv_nog 18 | FP_runs/run_hiv_noguera_unfilt_EXT.sh 2> $DATA_DIR/logs/hiv_nog_unfilt_EXT.log 19 | 20 | ## JI_WTP 21 | FP_runs/run_JI_WTP_DS_unfilt_EXT.sh 2> $DATA_DIR/logs/Ji_WTP_unfilt_EXT.log 22 | 23 | ## Office 24 | FP_runs/run_office_FD_test_unfilt_EXT.sh 2> $DATA_DIR/logs/office_unfilt_EXT.log 25 | 26 | ## schubert 27 | FP_runs/run_schubert_unfilt_EXT.sh 2> $DATA_DIR/logs/schubert_unfilt_EXT.log 28 | 29 | ## sw_sed 30 | FP_runs/run_sw_sed_unfilt_EXT.sh 2> $DATA_DIR/logs/sw_sed_unfilt_EXT.log 31 | 32 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_FP_unfilt_EXT_sl.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/logs 6 | 7 | ## arcticfresh 8 | 9 | FP_runs/run_arcticfresh_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/artic_unfilt_EXT_sl.log 10 | 11 | ## blueberry 12 | FP_runs/run_blueberry_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/blueberry_unfilt_EXT_sl.log 13 | 14 | ## goodrich 15 | FP_runs/run_goodrich_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/goodrich_unfilt_EXT_sl.log 16 | 17 | ## hiv_nog 18 | FP_runs/run_hiv_noguera_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/hiv_nog_unfilt_EXT_sl.log 19 | 20 | ## JI_WTP 21 | FP_runs/run_JI_WTP_DS_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/Ji_WTP_unfilt_EXT_sl.log 22 | 23 | ## Office 24 | FP_runs/run_office_FD_test_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/office_unfilt_EXT_sl.log 25 | 26 | ## schubert 27 | FP_runs/run_schubert_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/schubert_unfilt_EXT_sl.log 28 | 29 | ## sw_sed 30 | FP_runs/run_sw_sed_unfilt_EXT_sl.sh 2> $DATA_DIR/logs/sw_sed_unfilt_EXT_sl.log 31 | 32 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_all_FP_datasets_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/logs/ 6 | 7 | ## arcticfresh 8 | 9 | FP_runs/run_arcticfresh_filt.sh 2> $DATA_DIR/logs/arctic_filt.log 10 | 11 | ## blueberry 12 | FP_runs/run_blueberry_filt.sh 2> $DATA_DIR/logs/blueberry_filt.log 13 | 14 | ## goodrich 15 | FP_runs/run_goodrich_filt.sh 2> $DATA_DIR/logs/goodrich_filt.log 16 | 17 | ## hiv_nog 18 | FP_runs/run_hiv_noguera_filt.sh 2> $DATA_DIR/logs/hiv_nog_filt.log 19 | 20 | ## JI_WTP 21 | FP_runs/run_JI_WTP_DS_filt.sh 2> $DATA_DIR/logs/Ji_WTP_filt.log 22 | 23 | ## Office 24 | FP_runs/run_office_FD_test_filt.sh 2> $DATA_DIR/logs/office_filt.log 25 | 26 | ## schubert 27 | FP_runs/run_schubert_filt.sh 2> $DATA_DIR/logs/schubert_filt.log 28 | 29 | ## sw_sed 30 | FP_runs/run_sw_sed_filt.sh 2> $DATA_DIR/logs/sw_sed_filt.log 31 | 32 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_all_FP_datasets_unfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | 5 | mkdir $DATA_DIR/logs 6 | 7 | ## arcticfresh 8 | 9 | FP_runs/run_arcticfresh_unfilt.sh 2> $DATA_DIR/logs/artic_unfilt.log 10 | 11 | ## blueberry 12 | FP_runs/run_blueberry_unfilt.sh 2> $DATA_DIR/logs/blueberry_unfilt.log 13 | 14 | ## goodrich 15 | FP_runs/run_goodrich_unfilt.sh 2> $DATA_DIR/logs/goodrich_unfilt.log 16 | 17 | ## hiv_nog 18 | FP_runs/run_hiv_noguera_unfilt.sh 2> $DATA_DIR/logs/hiv_nog_unfilt.log 19 | 20 | ## JI_WTP 21 | FP_runs/run_JI_WTP_DS_unfilt.sh 2> $DATA_DIR/logs/Ji_WTP_unfilt.log 22 | 23 | ## Office 24 | FP_runs/run_office_FD_test_unfilt.sh 2> $DATA_DIR/logs/office_unfilt.log 25 | 26 | ## schubert 27 | FP_runs/run_schubert_unfilt.sh 2> $DATA_DIR/logs/schubert_unfilt.log 28 | 29 | ## sw_sed 30 | FP_runs/run_sw_sed_unfilt.sh 2> $DATA_DIR/logs/sw_sed_unfilt.log 31 | 32 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_diarrhea_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | 6 | find "$DATA_DIR/Testing_Bias_robustness/Diarrhea" -maxdepth 1 -mindepth 1 -type d | while read dir; 7 | do mkdir $dir/Genus_filt; 8 | done 9 | 10 | parallel -j 5 -N4 "./run_all_tools.sh -A $DATA_DIR{1} -G $DATA_DIR{2} -O $DATA_DIR{3} -D {4} -F 0.1" :::: <(cat input_parameters/Diarrhea/filt_input/sort_combined.txt) 11 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_diarrhea_nonfilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | 6 | find "$DATA_DIR/Testing_Bias_robustness/Diarrhea" -maxdepth 1 -mindepth 1 -type d | while read dir; 7 | do mkdir $dir/Genus_no_filt; 8 | done 9 | 10 | 11 | parallel -j 5 -N4 "./run_all_tools.sh -A $DATA_DIR{2} -G $DATA_DIR{3} -O $DATA_DIR{4} -R $DATA_DIR{1}" :::: <(cat input_parameters/Diarrhea/nonfilt_input/sort_combined_input.txt) 12 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_no_filt_datasets.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | export DATA_DIR 6 | 7 | find "$DATA_DIR/Studies" -maxdepth 1 -mindepth 1 -type d | while read dir; 8 | do mkdir $dir/No_filt_Results; 9 | done 10 | 11 | 12 | parallel --env $DATA_DIR -j 9 -N4 "./run_all_tools.sh -A $DATA_DIR{2} -G $DATA_DIR{3} -O $DATA_DIR{4} -R $DATA_DIR{1}" :::: <(cat input_parameters/sorted_input.tsv) 13 | 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_no_filt_datasets_corncob.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | export DATA_DIR 6 | 7 | find "$DATA_DIR/Studies" -maxdepth 1 -mindepth 1 -type d | while read dir; 8 | do mkdir $dir/No_filt_Results; 9 | done 10 | 11 | 12 | parallel --env $DATA_DIR -j 9 -N4 "./run_all_tools.sh -A $DATA_DIR{2} -G $DATA_DIR{3} -O $DATA_DIR{4} -R $DATA_DIR{1} --ALDEX_SKIP T --ANCOM_SKIP T --DESEQ2_SKIP T --LEFSE_SKIP T --WILCOX_RARE_SKIP T --WILCOX_CLR_SKIP T --MAASLIN_RARE_SKIP T --MAASLIN_SKIP T --METAGENOME_SKIP T --EDGER_SKIP T --TTEST_RARE_SKIP T --LIMMA_TMM_SKIP T --LIMMA_TMMWSP_SKIP T" :::: <(cat input_parameters/sorted_input.tsv) 13 | 14 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_obesity_filt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | 6 | 7 | find "$DATA_DIR/Testing_Bias_robustness/Obesity" -maxdepth 1 -mindepth 1 -type d | while read dir; 8 | do mkdir $dir/Genus_filt; 9 | done 10 | 11 | parallel -j 9 -N4 "./run_all_tools.sh -A $DATA_DIR{2} -G $DATA_DIR{3} -O $DATA_DIR{1} -D {4} -F 0.1" :::: <(cat input_parameters/Obesity/filt_input/sort_combined_input.txt) 12 | -------------------------------------------------------------------------------- /Pipeline_scripts/Run_scripts/run_obesity_nofilt.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | source ../../Config.sh 4 | echo $DATA_DIR 5 | 6 | find "$DATA_DIR/Testing_Bias_robustness/Obesity" -maxdepth 1 -mindepth 1 -type d | while read dir; 7 | do mkdir $dir/Genus_no_filt; 8 | done 9 | 10 | 11 | parallel -j 9 -N4 "./run_all_tools.sh -A $DATA_DIR{3} -G $DATA_DIR{4} -O $DATA_DIR{1} -R $DATA_DIR{2}" :::: <(cat input_parameters/Obesity/nonfilt_input/sort_combined_input.txt) 12 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Filter_samples_and_features.R: -------------------------------------------------------------------------------- 1 | #### Check if rarified and non-rarified tables contain the same samples and if they don't create a table that does 2 | remove_rare_features <- function( table , cutoff_pro) { 3 | if(cutoff_pro==0){ 4 | message("No filtering will be done due to cutoff_pro set to 0") 5 | return(table) 6 | } 7 | row2keep <- c() 8 | cutoff <- ceiling( cutoff_pro * ncol(table) ) 9 | for ( i in 1:nrow(table) ) { 10 | row_nonzero <- length( which( table[ i , ] > 0 ) ) 11 | if ( row_nonzero > cutoff ) { 12 | row2keep <- c( row2keep , i) 13 | } 14 | } 15 | return( table [ row2keep , , drop=F ]) 16 | } 17 | 18 | 19 | args <- commandArgs(trailingOnly = TRUE) 20 | #test if there is an argument supply 21 | if (length(args) <= 4) { 22 | stop("At least five arguments must be supplied", call.=FALSE) 23 | } 24 | 25 | ### check if we need to skip first line of file 26 | con <- file(args[1]) 27 | file_1_line1 <- readLines(con,n=1) 28 | close(con) 29 | 30 | if(grepl("Constructed from biom file", file_1_line1)){ 31 | ASV_table_1 <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 32 | comment.char = "", quote="", check.names = F) 33 | }else{ 34 | ASV_table_1 <- read.table(args[1], sep="\t", header=T, row.names = 1, 35 | comment.char = "", quote="", check.names = F) 36 | } 37 | 38 | 39 | if("taxonomy" %in% colnames(ASV_table_1)){ 40 | ASV_table_1 <- subset(ASV_table_1, select=-c(taxonomy)) 41 | } 42 | 43 | 44 | 45 | ### loaded in the tables now we need to filter the ASVS that are found in less than X filter level 46 | ASV_table_1 <- remove_rare_features(ASV_table_1, as.numeric(args[[2]])) 47 | 48 | 49 | ### rarify table based on depth 50 | set.seed(199) 51 | ASV_table_2 <- data.frame(t(GUniFrac::Rarefy(t(ASV_table_1), depth=as.numeric(args[[5]]))$otu.tab.rff), check.rows = F, 52 | check.names = F) 53 | 54 | ## read in the metadata 55 | groupings <- read.table(args[6], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 56 | # in some cases metadata will be smaller than the ASV table so we take intersect 57 | samps_keep <- intersect(colnames(ASV_table_2), rownames(groupings)) 58 | ASV_table_2 <- ASV_table_2[,samps_keep] 59 | ## this makes it so we only keep samples in the table we are interested in comparing 60 | 61 | 62 | ### we need to remove rows (ASVs) that have a sum of 0 across all samples 63 | remove_rows <- which(rowSums(ASV_table_2)==0) 64 | 65 | if(length(remove_rows) != 0){ 66 | ASV_table_2 <- ASV_table_2[-remove_rows,] 67 | } 68 | 69 | 70 | ### write out tables and make sure that the samples in them agree 71 | if(!identical(colnames(ASV_table_1), colnames(ASV_table_2))){ 72 | 73 | if(length(colnames(ASV_table_1)) > length(colnames(ASV_table_2))){ 74 | 75 | message("There are more samples in the non-rarified table. These samples will be fitlered out before running differential abundance calculations") 76 | ASV_table_1 <- ASV_table_1[, colnames(ASV_table_2)] 77 | 78 | #fix issue 1 by making sure there are no rowSums equal to 0 in the non-rare table. 79 | remove_rows_zero <- which(rowSums(ASV_table_1)==0) 80 | if(length(remove_rows_zero) != 0){ 81 | ASV_table_1 <- ASV_table_1[-remove_rows_zero,] 82 | } 83 | write.table(ASV_table_1, sep="\t", quote=F, file=args[[3]]) 84 | write.table(ASV_table_2, sep="\t", quote=F, file=args[[4]]) 85 | } 86 | else{ 87 | 88 | "The samples do not match in the rarified and non-rarified tables please check the input files" 89 | } 90 | }else{ 91 | "Samples between tables agree, no sample filter required, returning feature filtered tables" 92 | 93 | #fix issue 1 by making sure there are no rowSums equal to 0 in the non-rare table. 94 | remove_rows_zero <- which(rowSums(ASV_table_1)==0) 95 | if(length(remove_rows_zero) != 0){ 96 | ASV_table_1 <- ASV_table_1[-remove_rows_zero,] 97 | } 98 | write.table(ASV_table_1, sep="\t", quote=F, file=args[[3]]) 99 | write.table(ASV_table_2, sep="\t", quote=F, file = args[[4]]) 100 | } 101 | ### filer ASV_table_1 to be the same 102 | 103 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Filter_samples_of_non_rare_table.R: -------------------------------------------------------------------------------- 1 | #### Check if rarified and non-rarified tables contain the same samples and if they don't create a table that does 2 | 3 | 4 | 5 | args <- commandArgs(trailingOnly = TRUE) 6 | #test if there is an argument supply 7 | if (length(args) <= 2) { 8 | stop("At least three arguments must be supplied", call.=FALSE) 9 | } 10 | 11 | ### check if we need to skip first line of file 12 | con <- file(args[1]) 13 | file_1_line1 <- readLines(con,n=1) 14 | close(con) 15 | 16 | if(grepl("Constructed from biom file", file_1_line1)){ 17 | ASV_table_1 <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 18 | comment.char = "", quote="", check.names = F) 19 | }else{ 20 | ASV_table_1 <- read.table(args[1], sep="\t", header=T, row.names = 1, 21 | comment.char = "", quote="", check.names = F) 22 | } 23 | if("taxonomy" %in% colnames(ASV_table_1)){ 24 | ASV_table_1 <- subset(ASV_table_1, select=-c(taxonomy)) 25 | } 26 | 27 | 28 | con2 <- file(args[[2]]) 29 | file_2_line1 <- readLines(con2, n=1) 30 | close(con2) 31 | 32 | if(grepl("Constructed from biom file", file_2_line1)){ 33 | ASV_table_2 <- read.table(args[2], sep="\t", skip=1, header=T, row.names = 1, 34 | comment.char = "", quote="", check.names = F) 35 | }else{ 36 | ASV_table_2 <- read.table(args[2], sep="\t", header=T, row.names = 1, 37 | comment.char = "", quote="", check.names = F) 38 | } 39 | 40 | if("taxonomy" %in% colnames(ASV_table_2)){ 41 | ASV_table_2 <- subset(ASV_table_2, select=-c(taxonomy)) 42 | } 43 | 44 | 45 | ## in this set up we read both tables in 46 | ## we then need to first double check the ASV_table_2 against the metadata 47 | ## techiically to run the unfiltered data we could just input 0 into 48 | ## the remove_rare_features.... this would centralize the way the pipeline is run 49 | ## and we can output a fixed ASV table easily... the only issue would be that 50 | ## we would need to include a seed to make it reproducible... 51 | ## hmmm 52 | 53 | ## I think for now to save time we will just continue as is but we can discuss 54 | ## this in the feature. 55 | 56 | ## read in the metadata 57 | groupings <- read.table(args[4], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 58 | # in some cases metadata will be smaller than the ASV table so we take intersect 59 | samps_keep <- intersect(colnames(ASV_table_2), rownames(groupings)) 60 | ASV_table_2 <- ASV_table_2[,samps_keep] 61 | ## this makes it so we only keep samples in the table we are interested in comparing 62 | 63 | ### we need to remove rows (ASVs) that have a sum of 0 across all samples 64 | remove_rows <- which(rowSums(ASV_table_2)==0) 65 | 66 | if(length(remove_rows) != 0){ 67 | ASV_table_2 <- ASV_table_2[-remove_rows,] 68 | } 69 | 70 | 71 | 72 | if(!identical(colnames(ASV_table_1), colnames(ASV_table_2))){ 73 | 74 | if(length(colnames(ASV_table_1)) > length(colnames(ASV_table_2))){ 75 | 76 | message("There are more samples in the non-rarified table. These samples will be fitlered out before running differential abundance calculations") 77 | ASV_table_1 <- ASV_table_1[, colnames(ASV_table_2)] 78 | 79 | #fix issue 1 by making sure there are no rowSums equal to 0 in the non-rare table. 80 | remove_rows_zero <- which(rowSums(ASV_table_1)==0) 81 | if(length(remove_rows_zero) != 0){ 82 | ASV_table_1 <- ASV_table_1[-remove_rows_zero,] 83 | } 84 | write.table(ASV_table_1, sep="\t", quote=F, file=args[[3]]) 85 | write.table(ASV_table_2, sep="\t", quote=F, file=args[[5]]) 86 | } 87 | else{ 88 | 89 | "The samples do not match in the rarified and non-rarified tables please check the input files" 90 | } 91 | }else{ 92 | "Samples between tables agree, no filtering required" 93 | #fix issue 1 by making sure there are no rowSums equal to 0 in the non-rare table. 94 | remove_rows_zero <- which(rowSums(ASV_table_1)==0) 95 | if(length(remove_rows_zero) != 0){ 96 | ASV_table_1 <- ASV_table_1[-remove_rows_zero,] 97 | } 98 | write.table(ASV_table_1, sep="\t", quote=F, file=args[[3]]) 99 | write.table(ASV_table_2, sep="\t", quote=F, file=args[[5]]) 100 | } 101 | ### filer ASV_table_1 to be the same 102 | 103 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Format_lefse.R: -------------------------------------------------------------------------------- 1 | #### Format_Lefse 2 | 3 | 4 | 5 | args <- commandArgs(trailingOnly = TRUE) 6 | #test if there is an argument supply 7 | if (length(args) <= 2) { 8 | stop("At least three arguments must be supplied", call.=FALSE) 9 | } 10 | 11 | 12 | con <- file(args[1]) 13 | file_1_line1 <- readLines(con,n=1) 14 | close(con) 15 | 16 | if(grepl("Constructed from biom file", file_1_line1)){ 17 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 18 | comment.char = "", quote="", check.names = F) 19 | }else{ 20 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 21 | comment.char = "", quote="", check.names = F) 22 | } 23 | 24 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 25 | 26 | #number of samples 27 | sample_num <- length(colnames(ASV_table)) 28 | grouping_num <- length(rownames(groupings)) 29 | 30 | #check if the same number of samples are being input. 31 | if(sample_num != grouping_num){ 32 | message("The number of samples in the ASV table and the groupings table are unequal") 33 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 34 | } 35 | 36 | #check if order of samples match up. 37 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 38 | message("Groupings and ASV table are in the same order") 39 | }else{ 40 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 41 | groupings <- groupings[rows_to_keep,,drop=F] 42 | ASV_table <- ASV_table[,rows_to_keep] 43 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 44 | message("Groupings table was re-arrange to be in the same order as the ASV table") 45 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 46 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 47 | }else{ 48 | stop("Unable to match samples between the ASV table and groupings table") 49 | } 50 | } 51 | 52 | 53 | flip_ASV_table <- data.frame(t(ASV_table), check.names = F) 54 | 55 | if(all.equal(rownames(flip_ASV_table), rownames(groupings)) == F){ 56 | stop("Error: Samples do not match up!!! at merging of metadata and ASV table") 57 | } 58 | 59 | 60 | 61 | flip_ASV_table <- cbind(groupings[,1], flip_ASV_table) 62 | colnames(flip_ASV_table)[1] <- "Groupings" 63 | flip_ASV_table <- cbind(rownames(groupings), flip_ASV_table) 64 | colnames(flip_ASV_table)[1] <- "id" 65 | 66 | ret_tab <- data.frame(t(flip_ASV_table), check.names = F) 67 | 68 | write.table(ret_tab, file=args[3], quote=FALSE, sep="\t", col.names = F) 69 | 70 | message("Lefse formatted table written") 71 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_ANCOM.R: -------------------------------------------------------------------------------- 1 | 2 | deps = c("exactRankTests", "nlme", "dplyr", "ggplot2", "compositions") 3 | for (dep in deps){ 4 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 5 | install.packages(dep) 6 | } 7 | library(dep, character.only = TRUE) 8 | } 9 | 10 | #args[4] will contain path for the ancom code 11 | 12 | 13 | args <- commandArgs(trailingOnly = TRUE) 14 | 15 | if (length(args) <= 3) { 16 | stop("At least three arguments must be supplied", call.=FALSE) 17 | } 18 | 19 | source(args[[4]]) 20 | 21 | con <- file(args[1]) 22 | file_1_line1 <- readLines(con,n=1) 23 | close(con) 24 | 25 | if(grepl("Constructed from biom file", file_1_line1)){ 26 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 27 | comment.char = "", quote="", check.names = F) 28 | }else{ 29 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 30 | comment.char = "", quote="", check.names = F) 31 | } 32 | 33 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 34 | 35 | #number of samples 36 | sample_num <- length(colnames(ASV_table)) 37 | grouping_num <- length(rownames(groupings)) 38 | 39 | if(sample_num != grouping_num){ 40 | message("The number of samples in the ASV table and the groupings table are unequal") 41 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 42 | } 43 | 44 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 45 | message("Groupings and ASV table are in the same order") 46 | }else{ 47 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 48 | groupings <- groupings[rows_to_keep,,drop=F] 49 | ASV_table <- ASV_table[,rows_to_keep] 50 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 51 | message("Groupings table was re-arrange to be in the same order as the ASV table") 52 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 53 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 54 | }else{ 55 | stop("Unable to match samples between the ASV table and groupings table") 56 | } 57 | } 58 | 59 | groupings$Sample <- rownames(groupings) 60 | 61 | prepro <- feature_table_pre_process(feature_table = ASV_table, meta_data = groupings, sample_var = 'Sample', 62 | group_var = NULL, out_cut = 0.05, zero_cut = 0.90, 63 | lib_cut = 1000, neg_lb=FALSE) 64 | 65 | feature_table <- prepro$feature_table 66 | metadata <- prepro$meta_data 67 | struc_zero <- prepro$structure_zeros 68 | 69 | #run ancom 70 | main_var <- colnames(groupings)[1] 71 | p_adj_method = "BH" 72 | alpha=0.05 73 | adj_formula=NULL 74 | rand_formula=NULL 75 | res <- ANCOM(feature_table = feature_table, meta_data = metadata, struc_zero = struc_zero, main_var = main_var, p_adj_method = p_adj_method, 76 | alpha=alpha, adj_formula = adj_formula, rand_formula = rand_formula) 77 | 78 | 79 | write.table(res$out, file=args[3], quote=FALSE, sep="\t", col.names = NA) 80 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Aldex2.R: -------------------------------------------------------------------------------- 1 | #### Script to Run ALDEX2 differential abundance 2 | 3 | 4 | deps = c("ALDEx2") 5 | for (dep in deps){ 6 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 7 | if (!requireNamespace("BiocManager", quietly = TRUE)) 8 | install.packages("BiocManager") 9 | 10 | BiocManager::install("ALDEx2") 11 | } 12 | library(dep, character.only = TRUE) 13 | } 14 | 15 | library(ALDEx2) 16 | 17 | args <- commandArgs(trailingOnly = TRUE) 18 | 19 | 20 | 21 | #test if there is an argument supply 22 | if (length(args) <= 2) { 23 | stop("At least three arguments must be supplied", call.=FALSE) 24 | } 25 | 26 | con <- file(args[1]) 27 | file_1_line1 <- readLines(con,n=1) 28 | close(con) 29 | 30 | if(grepl("Constructed from biom file", file_1_line1)){ 31 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 32 | comment.char = "", quote="", check.names = F) 33 | }else{ 34 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 35 | comment.char = "", quote="", check.names = F) 36 | } 37 | 38 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 39 | 40 | #number of samples 41 | sample_num <- length(colnames(ASV_table)) 42 | grouping_num <- length(rownames(groupings)) 43 | 44 | #check if the same number of samples are being input. 45 | if(sample_num != grouping_num){ 46 | message("The number of samples in the ASV table and the groupings table are unequal") 47 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 48 | } 49 | 50 | #check if order of samples match up. 51 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 52 | message("Groupings and ASV table are in the same order") 53 | }else{ 54 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 55 | groupings <- groupings[rows_to_keep,,drop=F] 56 | ASV_table <- ASV_table[,rows_to_keep] 57 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 58 | message("Groupings table was re-arrange to be in the same order as the ASV table") 59 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 60 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 61 | }else{ 62 | stop("Unable to match samples between the ASV table and groupings table") 63 | } 64 | } 65 | 66 | results <- aldex(reads=ASV_table, conditions = groupings[,1], mc.samples = 128, test="t", effect=TRUE, 67 | include.sample.summary = FALSE, verbose=T, denom="all") 68 | 69 | write.table(results, file=args[3], quote=FALSE, sep='\t', col.names = NA) 70 | 71 | 72 | message("Results table saved to ", args[3]) 73 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Corncob.R: -------------------------------------------------------------------------------- 1 | #### Run Corncob 2 | 3 | library(corncob) 4 | library(phyloseq) 5 | 6 | #install corncob if its not installed. 7 | deps = c("corncob") 8 | for (dep in deps){ 9 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 10 | if(dep=="corncob"){ 11 | devtools::install_github("bryandmartin/corncob") 12 | } 13 | else 14 | if (!requireNamespace("BiocManager", quietly = TRUE)) 15 | install.packages("BiocManager") 16 | 17 | BiocManager::install("phyloseq") 18 | } 19 | library(dep, character.only = TRUE) 20 | } 21 | 22 | 23 | 24 | 25 | args <- commandArgs(trailingOnly = TRUE) 26 | 27 | if (length(args) <= 2) { 28 | stop("At least three arguments must be supplied", call.=FALSE) 29 | } 30 | 31 | con <- file(args[1]) 32 | file_1_line1 <- readLines(con,n=1) 33 | close(con) 34 | 35 | if(grepl("Constructed from biom file", file_1_line1)){ 36 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 37 | comment.char = "", quote="", check.names = F) 38 | }else{ 39 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 40 | comment.char = "", quote="", check.names = F) 41 | } 42 | 43 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 44 | 45 | #number of samples 46 | sample_num <- length(colnames(ASV_table)) 47 | grouping_num <- length(rownames(groupings)) 48 | 49 | #check if the same number of samples are being input. 50 | if(sample_num != grouping_num){ 51 | message("The number of samples in the ASV table and the groupings table are unequal") 52 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 53 | } 54 | 55 | #check if order of samples match up. 56 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 57 | message("Groupings and ASV table are in the same order") 58 | }else{ 59 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 60 | groupings <- groupings[rows_to_keep,,drop=F] 61 | ASV_table <- ASV_table[,rows_to_keep] 62 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 63 | message("Groupings table was re-arrange to be in the same order as the ASV table") 64 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 65 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 66 | }else{ 67 | stop("Unable to match samples between the ASV table and groupings table") 68 | } 69 | } 70 | 71 | #run corncob 72 | #put data into phyloseq object. 73 | colnames(groupings) 74 | colnames(groupings)[1] <- "places" 75 | 76 | OTU <- phyloseq::otu_table(ASV_table, taxa_are_rows = T) 77 | sampledata <- phyloseq::sample_data(groupings, errorIfNULL = T) 78 | phylo <- phyloseq::merge_phyloseq(OTU, sampledata) 79 | 80 | my_formula <- as.formula(paste("~","places",sep=" ", collapse = "")) 81 | my_formula 82 | results <- corncob::differentialTest(formula= my_formula, 83 | phi.formula = my_formula, 84 | phi.formula_null = my_formula, 85 | formula_null = ~ 1, 86 | test="Wald", data=phylo, 87 | boot=F, 88 | fdr_cutoff = 0.05) 89 | 90 | 91 | write.table(results$p_fdr, file=args[[3]], sep="\t", col.names = NA, quote=F) 92 | write.table(results$p, file=paste0(args[[3]], "_uncor", sep=""), sep="\t", col.names = NA, quote=F) 93 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_DESeq2.R: -------------------------------------------------------------------------------- 1 | #Run_DeSeq2 2 | 3 | deps = c("DESeq2") 4 | for (dep in deps){ 5 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 6 | if (!requireNamespace("BiocManager", quietly = TRUE)) 7 | install.packages("BiocManager") 8 | 9 | BiocManager::install("DESeq2") 10 | } 11 | library(dep, character.only = TRUE) 12 | } 13 | 14 | library(DESeq2) 15 | 16 | 17 | args <- commandArgs(trailingOnly = TRUE) 18 | #test if there is an argument supply 19 | if (length(args) <= 2) { 20 | stop("At least three arguments must be supplied", call.=FALSE) 21 | } 22 | 23 | con <- file(args[1]) 24 | file_1_line1 <- readLines(con,n=1) 25 | close(con) 26 | 27 | if(grepl("Constructed from biom file", file_1_line1)){ 28 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 29 | comment.char = "", quote="", check.names = F) 30 | }else{ 31 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 32 | comment.char = "", quote="", check.names = F) 33 | } 34 | 35 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 36 | 37 | #number of samples 38 | sample_num <- length(colnames(ASV_table)) 39 | grouping_num <- length(rownames(groupings)) 40 | 41 | #check if the same number of samples are being input. 42 | if(sample_num != grouping_num){ 43 | message("The number of samples in the ASV table and the groupings table are unequal") 44 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 45 | } 46 | 47 | #check if order of samples match up. 48 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 49 | message("Groupings and ASV table are in the same order") 50 | }else{ 51 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 52 | groupings <- groupings[rows_to_keep,,drop=F] 53 | ASV_table <- ASV_table[,rows_to_keep] 54 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 55 | message("Groupings table was re-arrange to be in the same order as the ASV table") 56 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 57 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 58 | }else{ 59 | stop("Unable to match samples between the ASV table and groupings table") 60 | } 61 | } 62 | 63 | colnames(groupings)[1] <- "Groupings" 64 | #Run Deseq2 65 | 66 | dds <- DESeq2::DESeqDataSetFromMatrix(countData = ASV_table, 67 | colData=groupings, 68 | design = ~ Groupings) 69 | dds_res <- DESeq2::DESeq(dds, sfType = "poscounts") 70 | 71 | res <- results(dds_res, tidy=T, format="DataFrame") 72 | 73 | rownames(res) <- res$row 74 | res <- res[,-1] 75 | 76 | write.table(res, file=args[3], quote=FALSE, sep="\t", col.names = NA) 77 | 78 | message("Results written to ", args[3]) 79 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Limma_Voom_TMM.R: -------------------------------------------------------------------------------- 1 | 2 | deps = c("edgeR") 3 | for (dep in deps){ 4 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 5 | if (!requireNamespace("BiocManager", quietly = TRUE)) 6 | install.packages("BiocManager") 7 | 8 | BiocManager::install(deps) 9 | } 10 | library(dep, character.only = TRUE) 11 | } 12 | 13 | 14 | args <- commandArgs(trailingOnly = TRUE) 15 | #test if there is an argument supply 16 | if (length(args) <= 2) { 17 | stop("At least three arguments must be supplied", call.=FALSE) 18 | } 19 | 20 | con <- file(args[1]) 21 | file_1_line1 <- readLines(con,n=1) 22 | close(con) 23 | 24 | if(grepl("Constructed from biom file", file_1_line1)){ 25 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 26 | comment.char = "", quote="", check.names = F) 27 | }else{ 28 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 29 | comment.char = "", quote="", check.names = F) 30 | } 31 | 32 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 33 | 34 | #number of samples 35 | sample_num <- length(colnames(ASV_table)) 36 | grouping_num <- length(rownames(groupings)) 37 | 38 | #check if the same number of samples are being input. 39 | if(sample_num != grouping_num){ 40 | message("The number of samples in the ASV table and the groupings table are unequal") 41 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 42 | } 43 | 44 | #check if order of samples match up. 45 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 46 | message("Groupings and ASV table are in the same order") 47 | }else{ 48 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 49 | groupings <- groupings[rows_to_keep,,drop=F] 50 | ASV_table <- ASV_table[,rows_to_keep] 51 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 52 | message("Groupings table was re-arrange to be in the same order as the ASV table") 53 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 54 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 55 | }else{ 56 | stop("Unable to match samples between the ASV table and groupings table") 57 | } 58 | } 59 | 60 | DGE_LIST <- DGEList(ASV_table) 61 | ### do normalization 62 | ### Reference sample will be the sample with the highest read depth 63 | 64 | ### check if upper quartile method works for selecting reference 65 | Upper_Quartile_norm_test <- calcNormFactors(DGE_LIST, method="upperquartile") 66 | 67 | summary_upper_quartile <- summary(Upper_Quartile_norm_test$samples$norm.factors)[3] 68 | if(is.na(summary_upper_quartile) | is.infinite(summary_upper_quartile)){ 69 | message("Upper Quartile reference selection failed will use find sample with largest sqrt(read_depth) to use as reference") 70 | Ref_col <- which.max(colSums(sqrt(ASV_table))) 71 | DGE_LIST_Norm <- calcNormFactors(DGE_LIST, method = "TMM", refColumn = Ref_col) 72 | fileConn<-file(args[[4]]) 73 | writeLines(c("Used max square root read depth to determine reference sample"), fileConn) 74 | close(fileConn) 75 | 76 | }else{ 77 | DGE_LIST_Norm <- calcNormFactors(DGE_LIST, method="TMM") 78 | } 79 | 80 | ## make matrix for testing 81 | colnames(groupings) <- c("comparison") 82 | mm <- model.matrix(~comparison, groupings) 83 | 84 | voomvoom <- voom(DGE_LIST_Norm, mm, plot=F) 85 | 86 | fit <- lmFit(voomvoom,mm) 87 | fit <- eBayes(fit) 88 | res <- topTable(fit, coef=2, n=nrow(DGE_LIST_Norm), sort.by="none") 89 | write.table(res, file=args[3], quote=F, sep="\t", col.names = NA) 90 | 91 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Limma_Voom_TMMwsp.R: -------------------------------------------------------------------------------- 1 | 2 | deps = c("edgeR") 3 | for (dep in deps){ 4 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 5 | if (!requireNamespace("BiocManager", quietly = TRUE)) 6 | install.packages("BiocManager") 7 | 8 | BiocManager::install(deps) 9 | } 10 | library(dep, character.only = TRUE) 11 | } 12 | 13 | 14 | args <- commandArgs(trailingOnly = TRUE) 15 | #test if there is an argument supply 16 | if (length(args) <= 2) { 17 | stop("At least three arguments must be supplied", call.=FALSE) 18 | } 19 | 20 | con <- file(args[1]) 21 | file_1_line1 <- readLines(con,n=1) 22 | close(con) 23 | 24 | if(grepl("Constructed from biom file", file_1_line1)){ 25 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 26 | comment.char = "", quote="", check.names = F) 27 | }else{ 28 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 29 | comment.char = "", quote="", check.names = F) 30 | } 31 | 32 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 33 | 34 | #number of samples 35 | sample_num <- length(colnames(ASV_table)) 36 | grouping_num <- length(rownames(groupings)) 37 | 38 | #check if the same number of samples are being input. 39 | if(sample_num != grouping_num){ 40 | message("The number of samples in the ASV table and the groupings table are unequal") 41 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 42 | } 43 | 44 | #check if order of samples match up. 45 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 46 | message("Groupings and ASV table are in the same order") 47 | }else{ 48 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 49 | groupings <- groupings[rows_to_keep,,drop=F] 50 | ASV_table <- ASV_table[,rows_to_keep] 51 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 52 | message("Groupings table was re-arrange to be in the same order as the ASV table") 53 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 54 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 55 | }else{ 56 | stop("Unable to match samples between the ASV table and groupings table") 57 | } 58 | } 59 | 60 | DGE_LIST <- DGEList(ASV_table) 61 | ### do normalization 62 | ### Reference sample will be the sample with the highest read depth 63 | 64 | ### check if upper quartile method works for selecting reference 65 | Upper_Quartile_norm_test <- calcNormFactors(DGE_LIST, method="upperquartile") 66 | 67 | summary_upper_quartile <- summary(Upper_Quartile_norm_test$samples$norm.factors)[3] 68 | if(is.na(summary_upper_quartile) | is.infinite(summary_upper_quartile)){ 69 | message("Upper Quartile reference selection failed will use find sample with largest sqrt(read_depth) to use as reference") 70 | Ref_col <- which.max(colSums(sqrt(ASV_table))) 71 | DGE_LIST_Norm <- calcNormFactors(DGE_LIST, method = "TMMwsp", refColumn = Ref_col) 72 | fileConn<-file(args[[4]]) 73 | writeLines(c("Used max square root read depth to determine reference sample"), fileConn) 74 | close(fileConn) 75 | }else{ 76 | DGE_LIST_Norm <- calcNormFactors(DGE_LIST, method="TMMwsp") 77 | } 78 | 79 | ## make matrix for testing 80 | colnames(groupings) <- c("comparison") 81 | mm <- model.matrix(~comparison, groupings) 82 | 83 | voomvoom <- voom(DGE_LIST_Norm, mm, plot=F) 84 | 85 | fit <- lmFit(voomvoom,mm) 86 | fit <- eBayes(fit) 87 | res <- topTable(fit, coef=2, n=nrow(DGE_LIST_Norm), sort.by="none") 88 | write.table(res, file=args[3], quote=F, sep="\t", col.names = NA) 89 | 90 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Maaslin2.R: -------------------------------------------------------------------------------- 1 | if(!requireNamespace("BiocManager", quietly = TRUE)) 2 | install.packages("BiocManager") 3 | #BiocManager::install("Maaslin2") 4 | 5 | args <- commandArgs(trailingOnly = TRUE) 6 | 7 | if (length(args) <= 2) { 8 | stop("At least three arguments must be supplied", call.=FALSE) 9 | } 10 | 11 | 12 | 13 | con <- file(args[1]) 14 | file_1_line1 <- readLines(con,n=1) 15 | close(con) 16 | 17 | if(grepl("Constructed from biom file", file_1_line1)){ 18 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 19 | comment.char = "", quote="", check.names = F) 20 | }else{ 21 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 22 | comment.char = "", quote="", check.names = F) 23 | } 24 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 25 | 26 | #number of samples 27 | sample_num <- length(colnames(ASV_table)) 28 | grouping_num <- length(rownames(groupings)) 29 | 30 | if(sample_num != grouping_num){ 31 | message("The number of samples in the ASV table and the groupings table are unequal") 32 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 33 | } 34 | 35 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 36 | message("Groupings and ASV table are in the same order") 37 | }else{ 38 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 39 | groupings <- groupings[rows_to_keep,,drop=F] 40 | ASV_table <- ASV_table[,rows_to_keep] 41 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 42 | message("Groupings table was re-arrange to be in the same order as the ASV table") 43 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 44 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 45 | }else{ 46 | stop("Unable to match samples between the ASV table and groupings table") 47 | } 48 | } 49 | 50 | 51 | 52 | library(Maaslin2) 53 | 54 | 55 | 56 | ASV_table <- data.frame(t(ASV_table), check.rows = F, check.names = F, stringsAsFactors = F) 57 | 58 | 59 | fit_data <- Maaslin2( 60 | ASV_table, groupings,args[3], transform = "AST", 61 | fixed_effects = c(colnames(groupings[1])), 62 | standardize = FALSE, plot_heatmap = F, plot_scatter = F) 63 | 64 | 65 | 66 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Wilcox_CLR.R: -------------------------------------------------------------------------------- 1 | args <- commandArgs(trailingOnly = TRUE) 2 | 3 | if (length(args) <= 2) { 4 | stop("At least three arguments must be supplied", call.=FALSE) 5 | } 6 | 7 | con <- file(args[1]) 8 | file_1_line1 <- readLines(con,n=1) 9 | close(con) 10 | 11 | if(grepl("Constructed from biom file", file_1_line1)){ 12 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 13 | comment.char = "", quote="", check.names = F) 14 | }else{ 15 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 16 | comment.char = "", quote="", check.names = F) 17 | } 18 | 19 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 20 | 21 | #number of samples 22 | sample_num <- length(colnames(ASV_table)) 23 | grouping_num <- length(rownames(groupings)) 24 | 25 | if(sample_num != grouping_num){ 26 | message("The number of samples in the ASV table and the groupings table are unequal") 27 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 28 | } 29 | 30 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 31 | message("Groupings and ASV table are in the same order") 32 | }else{ 33 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 34 | groupings <- groupings[rows_to_keep,,drop=F] 35 | ASV_table <- ASV_table[,rows_to_keep] 36 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 37 | message("Groupings table was re-arrange to be in the same order as the ASV table") 38 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 39 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 40 | }else{ 41 | stop("Unable to match samples between the ASV table and groupings table") 42 | } 43 | } 44 | 45 | 46 | colnames(groupings) 47 | colnames(groupings)[1] <- "places" 48 | 49 | 50 | #add pseudo count 51 | CLR_table <- data.frame(apply(ASV_table + 1, 2, function(x){log(x) - mean(log(x))})) 52 | ## get clr table 53 | 54 | 55 | 56 | #apply wilcox test to rarified table 57 | pvals <- apply(CLR_table, 1, function(x) wilcox.test(x ~ groupings[,1], exact=F)$p.value) 58 | 59 | write.table(pvals, file=args[[3]], sep="\t", col.names = NA, quote=F) 60 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_Wilcox_rare.R: -------------------------------------------------------------------------------- 1 | args <- commandArgs(trailingOnly = TRUE) 2 | 3 | if (length(args) <= 2) { 4 | stop("At least three arguments must be supplied", call.=FALSE) 5 | } 6 | 7 | con <- file(args[1]) 8 | file_1_line1 <- readLines(con,n=1) 9 | close(con) 10 | 11 | if(grepl("Constructed from biom file", file_1_line1)){ 12 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 13 | comment.char = "", quote="", check.names = F) 14 | }else{ 15 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 16 | comment.char = "", quote="", check.names = F) 17 | } 18 | 19 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 20 | 21 | #number of samples 22 | sample_num <- length(colnames(ASV_table)) 23 | grouping_num <- length(rownames(groupings)) 24 | 25 | if(sample_num != grouping_num){ 26 | message("The number of samples in the ASV table and the groupings table are unequal") 27 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 28 | } 29 | 30 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 31 | message("Groupings and ASV table are in the same order") 32 | }else{ 33 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 34 | groupings <- groupings[rows_to_keep,,drop=F] 35 | ASV_table <- ASV_table[,rows_to_keep] 36 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 37 | message("Groupings table was re-arrange to be in the same order as the ASV table") 38 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 39 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 40 | }else{ 41 | stop("Unable to match samples between the ASV table and groupings table") 42 | } 43 | } 44 | 45 | 46 | colnames(groupings) 47 | colnames(groupings)[1] <- "places" 48 | 49 | #apply wilcox test to rarified table 50 | pvals <- apply(ASV_table, 1, function(x) wilcox.test(x ~ groupings[,1], exact=F)$p.value) 51 | 52 | write.table(pvals, file=args[[3]], sep="\t", col.names = NA, quote=F) 53 | 54 | 55 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_edgeR.R: -------------------------------------------------------------------------------- 1 | 2 | deps = c("edgeR", "phyloseq") 3 | for (dep in deps){ 4 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 5 | if (!requireNamespace("BiocManager", quietly = TRUE)) 6 | install.packages("BiocManager") 7 | 8 | BiocManager::install(deps) 9 | } 10 | library(dep, character.only = TRUE) 11 | } 12 | 13 | ### Taken from phyloseq authors at: https://joey711.github.io/phyloseq-extensions/edgeR.html 14 | phyloseq_to_edgeR = function(physeq, group, method="RLE", ...){ 15 | require("edgeR") 16 | require("phyloseq") 17 | # Enforce orientation. 18 | if( !taxa_are_rows(physeq) ){ physeq <- t(physeq) } 19 | x = as(otu_table(physeq), "matrix") 20 | # Add one to protect against overflow, log(0) issues. 21 | x = x + 1 22 | # Check `group` argument 23 | if( identical(all.equal(length(group), 1), TRUE) & nsamples(physeq) > 1 ){ 24 | # Assume that group was a sample variable name (must be categorical) 25 | group = get_variable(physeq, group) 26 | } 27 | # Define gene annotations (`genes`) as tax_table 28 | taxonomy = tax_table(physeq, errorIfNULL=FALSE) 29 | if( !is.null(taxonomy) ){ 30 | taxonomy = data.frame(as(taxonomy, "matrix")) 31 | } 32 | # Now turn into a DGEList 33 | y = DGEList(counts=x, group=group, genes=taxonomy, remove.zeros = TRUE, ...) 34 | # Calculate the normalization factors 35 | z = calcNormFactors(y, method=method) 36 | # Check for division by zero inside `calcNormFactors` 37 | if( !all(is.finite(z$samples$norm.factors)) ){ 38 | stop("Something wrong with edgeR::calcNormFactors on this data, 39 | non-finite $norm.factors, consider changing `method` argument") 40 | } 41 | # Estimate dispersions 42 | return(estimateTagwiseDisp(estimateCommonDisp(z))) 43 | } 44 | 45 | 46 | args <- commandArgs(trailingOnly = TRUE) 47 | #test if there is an argument supply 48 | if (length(args) <= 2) { 49 | stop("At least three arguments must be supplied", call.=FALSE) 50 | } 51 | 52 | con <- file(args[1]) 53 | file_1_line1 <- readLines(con,n=1) 54 | close(con) 55 | 56 | if(grepl("Constructed from biom file", file_1_line1)){ 57 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 58 | comment.char = "", quote="", check.names = F) 59 | }else{ 60 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 61 | comment.char = "", quote="", check.names = F) 62 | } 63 | 64 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 65 | 66 | #number of samples 67 | sample_num <- length(colnames(ASV_table)) 68 | grouping_num <- length(rownames(groupings)) 69 | 70 | #check if the same number of samples are being input. 71 | if(sample_num != grouping_num){ 72 | message("The number of samples in the ASV table and the groupings table are unequal") 73 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 74 | } 75 | 76 | #check if order of samples match up. 77 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 78 | message("Groupings and ASV table are in the same order") 79 | }else{ 80 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 81 | groupings <- groupings[rows_to_keep,,drop=F] 82 | ASV_table <- ASV_table[,rows_to_keep] 83 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 84 | message("Groupings table was re-arrange to be in the same order as the ASV table") 85 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 86 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 87 | }else{ 88 | stop("Unable to match samples between the ASV table and groupings table") 89 | } 90 | } 91 | 92 | OTU <- phyloseq::otu_table(ASV_table, taxa_are_rows = T) 93 | sampledata <- phyloseq::sample_data(groupings, errorIfNULL = T) 94 | phylo <- phyloseq::merge_phyloseq(OTU, sampledata) 95 | 96 | test <- phyloseq_to_edgeR(physeq = phylo, group=colnames(groupings)[1]) 97 | 98 | et = exactTest(test) 99 | 100 | tt = topTags(et, n=nrow(test$table), adjust.method="fdr", sort.by="PValue") 101 | res <- tt@.Data[[1]] 102 | 103 | write.table(res, file=args[3], quote=F, sep="\t", col.names = NA) 104 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_metagenomeSeq.R: -------------------------------------------------------------------------------- 1 | deps = c("metagenomeSeq") 2 | for (dep in deps){ 3 | if (dep %in% installed.packages()[,"Package"] == FALSE){ 4 | if (!requireNamespace("BiocManager", quietly = TRUE)) 5 | install.packages("BiocManager") 6 | 7 | BiocManager::install(deps) 8 | } 9 | library(dep, character.only = TRUE) 10 | } 11 | 12 | args <- commandArgs(trailingOnly = TRUE) 13 | #test if there is an argument supply 14 | if (length(args) <= 2) { 15 | stop("At least three arguments must be supplied", call.=FALSE) 16 | } 17 | 18 | con <- file(args[1]) 19 | file_1_line1 <- readLines(con,n=1) 20 | close(con) 21 | 22 | if(grepl("Constructed from biom file", file_1_line1)){ 23 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 24 | comment.char = "", quote="", check.names = F) 25 | }else{ 26 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 27 | comment.char = "", quote="", check.names = F) 28 | } 29 | 30 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 31 | 32 | #number of samples 33 | sample_num <- length(colnames(ASV_table)) 34 | grouping_num <- length(rownames(groupings)) 35 | 36 | #check if the same number of samples are being input. 37 | if(sample_num != grouping_num){ 38 | message("The number of samples in the ASV table and the groupings table are unequal") 39 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 40 | } 41 | 42 | #check if order of samples match up. 43 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 44 | message("Groupings and ASV table are in the same order") 45 | }else{ 46 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 47 | groupings <- groupings[rows_to_keep,,drop=F] 48 | ASV_table <- ASV_table[,rows_to_keep] 49 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 50 | message("Groupings table was re-arrange to be in the same order as the ASV table") 51 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 52 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 53 | }else{ 54 | stop("Unable to match samples between the ASV table and groupings table") 55 | } 56 | } 57 | 58 | data_list <- list() 59 | data_list[["counts"]] <- ASV_table 60 | data_list[["taxa"]] <- rownames(ASV_table) 61 | 62 | pheno <- AnnotatedDataFrame(groupings) 63 | pheno 64 | counts <- AnnotatedDataFrame(ASV_table) 65 | feature_data <- data.frame("ASV"=rownames(ASV_table), 66 | "ASV2"=rownames(ASV_table)) 67 | feature_data <- AnnotatedDataFrame(feature_data) 68 | rownames(feature_data) <- feature_data@data$ASV 69 | 70 | 71 | test_obj <- newMRexperiment(counts = data_list$counts, phenoData = pheno, featureData = feature_data) 72 | 73 | p <- cumNormStat(test_obj, pFlag = T) 74 | p 75 | 76 | test_obj_norm <- cumNorm(test_obj, p=p) 77 | 78 | fromula <- as.formula(paste(~1, colnames(groupings)[1], sep=" + ")) 79 | pd <- pData(test_obj_norm) 80 | mod <- model.matrix(fromula, data=pd) 81 | regres <- fitFeatureModel(test_obj_norm, mod) 82 | 83 | res_table <- MRfulltable(regres, number = length(rownames(ASV_table))) 84 | 85 | write.table(res_table, file=args[3], quote=F, sep="\t", col.names = NA) 86 | -------------------------------------------------------------------------------- /Pipeline_scripts/Tool_scripts/Run_t_test_rare.R: -------------------------------------------------------------------------------- 1 | ### Run T Test on rarified 2 | 3 | args <- commandArgs(trailingOnly = TRUE) 4 | 5 | if (length(args) <= 2) { 6 | stop("At least three arguments must be supplied", call.=FALSE) 7 | } 8 | 9 | con <- file(args[1]) 10 | file_1_line1 <- readLines(con,n=1) 11 | close(con) 12 | 13 | if(grepl("Constructed from biom file", file_1_line1)){ 14 | ASV_table <- read.table(args[1], sep="\t", skip=1, header=T, row.names = 1, 15 | comment.char = "", quote="", check.names = F) 16 | }else{ 17 | ASV_table <- read.table(args[1], sep="\t", header=T, row.names = 1, 18 | comment.char = "", quote="", check.names = F) 19 | } 20 | 21 | groupings <- read.table(args[2], sep="\t", row.names = 1, header=T, comment.char = "", quote="", check.names = F) 22 | 23 | #number of samples 24 | sample_num <- length(colnames(ASV_table)) 25 | grouping_num <- length(rownames(groupings)) 26 | 27 | if(sample_num != grouping_num){ 28 | message("The number of samples in the ASV table and the groupings table are unequal") 29 | message("Will remove any samples that are not found in either the ASV table or the groupings table") 30 | } 31 | 32 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 33 | message("Groupings and ASV table are in the same order") 34 | }else{ 35 | rows_to_keep <- intersect(colnames(ASV_table), rownames(groupings)) 36 | groupings <- groupings[rows_to_keep,,drop=F] 37 | ASV_table <- ASV_table[,rows_to_keep] 38 | if(identical(colnames(ASV_table), rownames(groupings))==T){ 39 | message("Groupings table was re-arrange to be in the same order as the ASV table") 40 | message("A total of ", sample_num-length(colnames(ASV_table)), " from the ASV_table") 41 | message("A total of ", grouping_num-length(rownames(groupings)), " from the groupings table") 42 | }else{ 43 | stop("Unable to match samples between the ASV table and groupings table") 44 | } 45 | } 46 | 47 | 48 | colnames(groupings) 49 | colnames(groupings)[1] <- "places" 50 | 51 | #apply wilcox test to rarified table 52 | pvals <- apply(ASV_table, 1, function(x) t.test(x ~ groupings[,1], exact=F)$p.value) 53 | 54 | write.table(pvals, file=args[[3]], sep="\t", col.names = NA, quote=F) -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure1A_dataset_characteristics.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure1A_dataset_characteristics.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure1A_feat_count.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure1A_feat_count.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure1B_dataset_characteristics.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure1B_dataset_characteristics.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure1B_feat_count.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure1B_feat_count.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure2A_pval.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure2A_pval.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure2A_rho.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure2A_rho.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure2B_pval.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure2B_pval.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure2B_rho.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure2B_rho.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure3A.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure3A.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure3B.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure3B.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure3C_bin_dist.csv: -------------------------------------------------------------------------------- 1 | ,aldex2,ancom,corncob,deseq2,edger,lefse,maaslin2,maaslin2rare,metagenomeSeq,ttestrare,wilcoxonclr,wilcoxonrare,limma_voom_TMM,limma_voom_TMMwsp 2 | aldex2,0,0.56644236665469,0.745131501223102,0.614701185069592,0.832741977551749,0.818303747074172,0.546943426496013,0.552974067072378,0.555682090324239,0.420005248779981,0.437514243404141,0.470462499238449,0.597781988292204,0.66116578690561 3 | ancom,0.56644236665469,0,0.8801541224026,0.72993094536142,0.910602822612425,0.907833473211493,0.72669163947444,0.689784012056017,0.732071097354326,0.695046490174855,0.697788395213535,0.678506681813045,0.730195305617189,0.775801012850457 4 | corncob,0.745131501223102,0.8801541224026,0,0.586494337438286,0.683887656572352,0.70448279726898,0.617930570475687,0.690145189471252,0.690526537968124,0.720470847081201,0.754766542623133,0.68115113085584,0.694058855462005,0.721513103613238 5 | deseq2,0.614701185069592,0.72993094536142,0.586494337438286,0,0.668474158758828,0.703728447570593,0.558744485696551,0.612701313437676,0.585376984870146,0.59501375255464,0.622352544863456,0.566061337472152,0.515518259162959,0.596298594401607 6 | edger,0.832741977551749,0.910602822612425,0.683887656572352,0.668474158758828,0,0.628162407454164,0.678363257275674,0.730012801548318,0.748299881297888,0.791228774468688,0.759046220983591,0.740097165020143,0.717649377243772,0.711588142452006 7 | lefse,0.818303747074172,0.907833473211493,0.70448279726898,0.703728447570593,0.628162407454164,0,0.641925547350571,0.681215299250273,0.770273485725538,0.788409134485466,0.805628684099772,0.663100692313187,0.722249016147594,0.71285346815356 8 | maaslin2,0.546943426496013,0.72669163947444,0.617930570475687,0.558744485696551,0.678363257275674,0.641925547350571,0,0.364432340709725,0.473180422533302,0.545068400964515,0.562248185328094,0.421942952046726,0.546874143420896,0.6001431462315 9 | maaslin2rare,0.552974067072378,0.689784012056017,0.690145189471252,0.612701313437676,0.730012801548318,0.681215299250273,0.364432340709725,0,0.525363077134347,0.493937745807014,0.638458529595223,0.293741810425531,0.600398054723438,0.670695908920837 10 | metagenomeSeq,0.555682090324239,0.732071097354326,0.690526537968124,0.585376984870146,0.748299881297888,0.770273485725538,0.473180422533302,0.525363077134347,0,0.58378492659003,0.564734870961196,0.521055632852722,0.616307437067414,0.612092206754896 11 | ttestrare,0.420005248779981,0.695046490174855,0.720470847081201,0.59501375255464,0.791228774468688,0.788409134485466,0.545068400964515,0.493937745807014,0.58378492659003,0,0.563560628672513,0.433386106220806,0.605292814005304,0.650907754657017 12 | wilcoxonclr,0.437514243404141,0.697788395213535,0.754766542623133,0.622352544863456,0.759046220983591,0.805628684099772,0.562248185328094,0.638458529595223,0.564734870961196,0.563560628672513,0,0.516154955127817,0.593648040614449,0.565802663322598 13 | wilcoxonrare,0.470462499238449,0.678506681813045,0.68115113085584,0.566061337472152,0.740097165020143,0.663100692313187,0.421942952046726,0.293741810425531,0.521055632852722,0.433386106220806,0.516154955127817,0,0.541509521683186,0.615978283453356 14 | limma_voom_TMM,0.597781988292204,0.730195305617189,0.694058855462005,0.515518259162959,0.717649377243772,0.722249016147594,0.546874143420896,0.600398054723438,0.616307437067414,0.605292814005304,0.593648040614449,0.541509521683186,0,0.604392514004987 15 | limma_voom_TMMwsp,0.66116578690561,0.775801012850457,0.721513103613238,0.596298594401607,0.711588142452006,0.71285346815356,0.6001431462315,0.670695908920837,0.612092206754896,0.650907754657017,0.565802663322598,0.615978283453356,0.604392514004987,0 16 | -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure3C_bin_dist.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure3C_bin_dist.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure3D_bin_dist.csv: -------------------------------------------------------------------------------- 1 | ,aldex2,ancom,corncob,deseq2,edger,lefse,maaslin2,maaslin2rare,metagenomeSeq,ttestrare,wilcoxonclr,wilcoxonrare,limma_voom_TMM,limma_voom_TMMwsp 2 | aldex2,0,0.653610719334591,0.82171359417884,0.687588348191493,0.935881887528599,0.930639920227192,0.548451561472352,0.492793824801729,0.627973346324009,0.467961636605744,0.528014131512653,0.441310268283626,0.776366292322526,0.763182036891239 3 | ancom,0.653610719334591,0,0.855799840746741,0.751785723923155,0.924271845824767,0.900457391145133,0.753879953202304,0.783031487026739,0.758323561763372,0.727503313578546,0.764207230455937,0.712776488298929,0.75572080954558,0.811838180276034 4 | corncob,0.82171359417884,0.855799840746741,0,0.680550006822091,0.766383773826462,0.77494816987935,0.67308241407998,0.714978086906774,0.75200011526435,0.803567403264554,0.83440863404433,0.733116586126448,0.823601128240069,0.798099597646478 5 | deseq2,0.687588348191493,0.751785723923155,0.680550006822091,0,0.784211682181846,0.770167961066634,0.686375701061746,0.710839651048982,0.709983790046811,0.726502904750098,0.729101925770524,0.674182059878054,0.711065192431327,0.734547614751356 6 | edger,0.935881887528599,0.924271845824767,0.766383773826462,0.784211682181846,0,0.743054554629589,0.846770476320111,0.862903024494911,0.869122866333991,0.923843743660702,0.929891945454522,0.86100355800756,0.908621732022603,0.92037967587121 7 | lefse,0.930639920227192,0.900457391145133,0.77494816987935,0.770167961066634,0.743054554629589,0,0.778966196383895,0.812591474857621,0.850427013571048,0.922512893338888,0.917235518145743,0.799953145602077,0.877361725577742,0.885193599309762 8 | maaslin2,0.548451561472352,0.753879953202304,0.67308241407998,0.686375701061746,0.846770476320111,0.778966196383895,0,0.354434935541916,0.506205164903192,0.581666277215011,0.659231590397181,0.389105840512882,0.80778615607143,0.71139370115085 9 | maaslin2rare,0.492793824801729,0.783031487026739,0.714978086906774,0.710839651048982,0.862903024494911,0.812591474857621,0.354434935541916,0,0.55843538182183,0.498122302567054,0.670665319600018,0.249637516347325,0.798109054542588,0.759276617288047 10 | metagenomeSeq,0.627973346324009,0.758323561763372,0.75200011526435,0.709983790046811,0.869122866333991,0.850427013571048,0.506205164903192,0.55843538182183,0,0.621884291854078,0.696150050660727,0.533943116368689,0.783856317885264,0.737895184336967 11 | ttestrare,0.467961636605744,0.727503313578546,0.803567403264554,0.726502904750098,0.923843743660702,0.922512893338888,0.581666277215011,0.498122302567054,0.621884291854078,0,0.610996085540271,0.484944900572226,0.794464707808094,0.781706757489883 12 | wilcoxonclr,0.528014131512653,0.764207230455937,0.83440863404433,0.729101925770524,0.929891945454522,0.917235518145743,0.659231590397181,0.670665319600018,0.696150050660727,0.610996085540271,0,0.616081150579817,0.658743289873298,0.477892685293326 13 | wilcoxonrare,0.441310268283626,0.712776488298929,0.733116586126448,0.674182059878054,0.86100355800756,0.799953145602077,0.389105840512882,0.249637516347325,0.533943116368689,0.484944900572226,0.616081150579817,0,0.759870397232091,0.721211397881617 14 | limma_voom_TMM,0.776366292322526,0.75572080954558,0.823601128240069,0.711065192431327,0.908621732022603,0.877361725577742,0.80778615607143,0.798109054542588,0.783856317885264,0.794464707808094,0.658743289873298,0.759870397232091,0,0.619710504920165 15 | limma_voom_TMMwsp,0.763182036891239,0.811838180276034,0.798099597646478,0.734547614751356,0.92037967587121,0.885193599309762,0.71139370115085,0.759276617288047,0.737895184336967,0.781706757489883,0.477892685293326,0.721211397881617,0.619710504920165,0 16 | -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure3D_bin_dist.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure3D_bin_dist.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure4A_boxplots.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure4A_boxplots.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure4B_boxplots.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure4B_boxplots.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure5_and_Table2_genera_diarrhea_expected_consistency.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure5_and_Table2_genera_diarrhea_expected_consistency.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Main_Figures/Figure5_and_Table2_genera_diarrhea_observed_consistency.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Main_Figures/Figure5_and_Table2_genera_diarrhea_observed_consistency.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/SuppTable1_genera_obesity_expected_consistency.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/SuppTable1_genera_obesity_expected_consistency.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/SuppTable1_genera_obesity_observed_consistency.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/SuppTable1_genera_obesity_observed_consistency.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig1AB_mean_RA_sig_hits.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig1AB_mean_RA_sig_hits.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig1C_unfilt_total_hits.csv: -------------------------------------------------------------------------------- 1 | ,value,Tool,Tool_rename,Filt 2 | aldex2,7429,aldex2,ALDEx2,Unfiltered 3 | ancom,4365,ancom,ANCOM-II,Unfiltered 4 | corncob,38257,corncob,corncob,Unfiltered 5 | deseq2,17653,deseq2,DESeq2,Unfiltered 6 | edger,56066,edger,edgeR,Unfiltered 7 | lefse,78314,lefse,LEfSe,Unfiltered 8 | maaslin2,49979,maaslin2,MaAsLin2,Unfiltered 9 | maaslin2rare,39115,maaslin2rare,MaAsLin2 (rare),Unfiltered 10 | metagenomeSeq,43482,metagenomeSeq,metagenomeSeq,Unfiltered 11 | ttestrare,29264,ttestrare,t-test (rare),Unfiltered 12 | wilcoxonclr,355467,wilcoxonclr,Wilcoxon (CLR),Unfiltered 13 | wilcoxonrare,41222,wilcoxonrare,Wilcoxon (rare),Unfiltered 14 | limma_voom_TMM,578561,limma_voom_TMM,limma voom (TMM),Unfiltered 15 | limma_voom_TMMwsp,625338,limma_voom_TMMwsp,limma voom (TMMwsp),Unfiltered 16 | -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig1C_unfilt_total_hits.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig1C_unfilt_total_hits.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig1D_filt_total_hits.csv: -------------------------------------------------------------------------------- 1 | ,value,Tool,Tool_rename,Filt 2 | aldex2,10323,aldex2,ALDEx2,Filtered 3 | ancom,3758,ancom,ANCOM-II,Filtered 4 | corncob,17362,corncob,corncob,Filtered 5 | deseq2,17462,deseq2,DESeq2,Filtered 6 | edger,29139,edger,edgeR,Filtered 7 | lefse,23598,lefse,LEfSe,Filtered 8 | maaslin2,20172,maaslin2,MaAsLin2,Filtered 9 | maaslin2rare,17193,maaslin2rare,MaAsLin2 (rare),Filtered 10 | metagenomeSeq,17725,metagenomeSeq,metagenomeSeq,Filtered 11 | ttestrare,15480,ttestrare,t-test (rare),Filtered 12 | wilcoxonclr,24134,wilcoxonclr,Wilcoxon (CLR),Filtered 13 | wilcoxonrare,17471,wilcoxonrare,Wilcoxon (rare),Filtered 14 | limma_voom_TMM,23412,limma_voom_TMM,limma voom (TMM),Filtered 15 | limma_voom_TMMwsp,24917,limma_voom_TMMwsp,limma voom (TMMwsp),Filtered 16 | -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig1D_filt_total_hits.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig1D_filt_total_hits.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig2A_chimera_percents.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig2A_chimera_percents.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig2B_chimera_spearman.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig2B_chimera_spearman.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig3A.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig3A.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig3B.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig3B.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig4_CLR_07.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig4_CLR_07.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig4_CLR_09.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig4_CLR_09.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig4_RA_07.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig4_RA_07.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig4_RA_09.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig4_RA_09.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig5A_filt.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig5A_filt.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig5B_unfilt.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig5B_unfilt.csv.gz -------------------------------------------------------------------------------- /Plotting_data/Supp_figures/Supp_Fig8_data.csv.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/Supp_figures/Supp_Fig8_data.csv.gz -------------------------------------------------------------------------------- /Plotting_data/source_data_all.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/nearinj/Comparison_of_DA_microbiome_methods/f67e54a308ab002d310490f8aa6d89410aa7181e/Plotting_data/source_data_all.xlsx --------------------------------------------------------------------------------