├── codecov.yml ├── .gitignore ├── screenshots ├── screenshot_qc.png ├── screenshot_global.png ├── screenshot_differential_expression.png └── screenshot_differential_adenylation.png ├── R ├── utils-pipe.R ├── nanotail-package.R ├── polya_annotate.R ├── read_polyA_data.R ├── polya_helper_functions.R └── polya_stats.R ├── .travis.yml ├── man ├── pipe.Rd ├── plot_polyA_PCA.Rd ├── gm_mean.Rd ├── nanotail_ggplot2_theme.Rd ├── spread_multiple.Rd ├── annotate_with_annotables.Rd ├── calculate_scaling_vector_for_virutal_gel.Rd ├── remove_failed_reads.Rd ├── nanoTailApp.Rd ├── annotate_with_org_packages.Rd ├── subsample_table.Rd ├── plot_nanopolish_qc.Rd ├── get_nanopolish_processing_info.Rd ├── stat_median_line.Rd ├── plot_quantiles.Rd ├── calculate_pca.Rd ├── annotate_with_biomart.Rd ├── plot_MA.Rd ├── read_polya_single.Rd ├── getmode.Rd ├── plot_volcano.Rd ├── summarize_polya_per_transcript.Rd ├── summarize_polya.Rd ├── dot-kruskal_polya.Rd ├── normalize_counts_to_depth.Rd ├── read_polya_multiple.Rd ├── calculate_diff_exp_binom.Rd ├── dot-basic_aesthetics.Rd ├── plot_virtual_gel.Rd ├── dot-polya_stats.Rd ├── plot_annotations_comparison_boxplot.Rd ├── plot_counts_scatter.Rd ├── plot_polya_boxplot.Rd ├── kruskal_polya.Rd ├── plot_polya_violin.Rd ├── plot_polya_distribution.Rd └── calculate_polya_stats.Rd ├── tests ├── testthat │ ├── test-shiny_app.R │ ├── test-helper_functions.R │ ├── test-polya_annotate.R │ ├── test-read_polyA_data.R │ ├── test-polya_stats.R │ └── test-polya_plots.R └── testthat.R ├── inst └── extdata │ └── about.md ├── appveyor.yml ├── NAMESPACE ├── DESCRIPTION ├── README.md ├── LICENSE └── LICENSE.md /codecov.yml: -------------------------------------------------------------------------------- 1 | comment: false 2 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .Rproj.user 2 | .Rhistory 3 | .RData 4 | .Ruserdata 5 | nanotail.Rproj 6 | temp 7 | inst/libs 8 | -------------------------------------------------------------------------------- /screenshots/screenshot_qc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smaegol/nanotail/HEAD/screenshots/screenshot_qc.png -------------------------------------------------------------------------------- /screenshots/screenshot_global.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smaegol/nanotail/HEAD/screenshots/screenshot_global.png -------------------------------------------------------------------------------- /screenshots/screenshot_differential_expression.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smaegol/nanotail/HEAD/screenshots/screenshot_differential_expression.png -------------------------------------------------------------------------------- /screenshots/screenshot_differential_adenylation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smaegol/nanotail/HEAD/screenshots/screenshot_differential_adenylation.png -------------------------------------------------------------------------------- /R/utils-pipe.R: -------------------------------------------------------------------------------- 1 | #' Pipe operator 2 | #' 3 | #' See \code{magrittr::\link[magrittr]{\%>\%}} for details. 4 | #' 5 | #' @name %>% 6 | #' @rdname pipe 7 | #' @keywords internal 8 | #' @export 9 | #' @importFrom magrittr %>% 10 | #' @usage lhs \%>\% rhs 11 | NULL 12 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | # R for travis: see documentation at https://docs.travis-ci.com/user/languages/r 2 | 3 | language: R 4 | sudo: false 5 | cache: packages 6 | 7 | warnings_are_errors: false 8 | 9 | r_packages: 10 | - covr 11 | 12 | after_success: 13 | - Rscript -e 'library(covr); codecov()' 14 | -------------------------------------------------------------------------------- /man/pipe.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/utils-pipe.R 3 | \name{\%>\%} 4 | \alias{\%>\%} 5 | \title{Pipe operator} 6 | \usage{ 7 | lhs \%>\% rhs 8 | } 9 | \description{ 10 | See \code{magrittr::\link[magrittr]{\%>\%}} for details. 11 | } 12 | \keyword{internal} 13 | -------------------------------------------------------------------------------- /R/nanotail-package.R: -------------------------------------------------------------------------------- 1 | ## usethis namespace: start 2 | #' @importFrom tibble tibble 3 | #' @importFrom stats as.formula 4 | #' @importFrom stats glm 5 | #' @importFrom stats median 6 | #' @importFrom stats p.adjust 7 | #' @importFrom stats prcomp 8 | #' @importFrom stats sd 9 | #' @importFrom stats wilcox.test 10 | #' @importFrom utils packageVersion 11 | ## usethis namespace: end 12 | NULL 13 | -------------------------------------------------------------------------------- /man/plot_polyA_PCA.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_polyA_PCA} 4 | \alias{plot_polyA_PCA} 5 | \title{PCA biplot} 6 | \usage{ 7 | plot_polyA_PCA(pca_object, samples_names) 8 | } 9 | \arguments{ 10 | \item{pca_object}{pca object} 11 | 12 | \item{samples_names}{names of samples to be shown on the plot} 13 | } 14 | \value{ 15 | \link[ggplot2]{ggplot} object 16 | } 17 | \description{ 18 | Plots PCA biplot using \link[ggbiplot]{ggbiplot} 19 | } 20 | -------------------------------------------------------------------------------- /man/gm_mean.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \name{gm_mean} 4 | \alias{gm_mean} 5 | \title{Calculates geometric mean} 6 | \usage{ 7 | gm_mean(x, na.rm = TRUE) 8 | } 9 | \arguments{ 10 | \item{x}{input vector} 11 | 12 | \item{na.rm}{should NA values be removed?} 13 | } 14 | \value{ 15 | geometric mean of values provided as an input 16 | } 17 | \description{ 18 | Calculates geometric mean 19 | } 20 | \examples{ 21 | a <- rnorm(100,33,5) 22 | gm_mean(a) 23 | } 24 | -------------------------------------------------------------------------------- /man/nanotail_ggplot2_theme.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \docType{data} 4 | \name{nanotail_ggplot2_theme} 5 | \alias{nanotail_ggplot2_theme} 6 | \title{Default theme for ggplot2-based plots in the NanoTail package} 7 | \format{ 8 | An object of class \code{theme} (inherits from \code{gg}) of length 4. 9 | } 10 | \usage{ 11 | nanotail_ggplot2_theme 12 | } 13 | \description{ 14 | Default theme for ggplot2-based plots in the NanoTail package 15 | } 16 | \keyword{datasets} 17 | -------------------------------------------------------------------------------- /man/spread_multiple.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \name{spread_multiple} 4 | \alias{spread_multiple} 5 | \title{Spread multiple columns} 6 | \usage{ 7 | spread_multiple(df, key, value) 8 | } 9 | \arguments{ 10 | \item{df}{data frame to apply spread on} 11 | 12 | \item{key}{as in \link{spread}} 13 | 14 | \item{value}{vector of columns to be taken as value for \link{spread}} 15 | } 16 | \value{ 17 | \link{tibble} 18 | } 19 | \description{ 20 | Spread multiple columns 21 | } 22 | -------------------------------------------------------------------------------- /man/annotate_with_annotables.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_annotate.R 3 | \name{annotate_with_annotables} 4 | \alias{annotate_with_annotables} 5 | \title{Annotate polyA predictions using annotables} 6 | \usage{ 7 | annotate_with_annotables(polya_data, genome) 8 | } 9 | \arguments{ 10 | \item{polya_data}{polya data table to annotate} 11 | 12 | \item{genome}{valid genome from annotables to use for annotation} 13 | } 14 | \value{ 15 | a \link[tibble]{tibble} 16 | } 17 | \description{ 18 | Annotate polyA predictions using annotables 19 | } 20 | -------------------------------------------------------------------------------- /tests/testthat/test-shiny_app.R: -------------------------------------------------------------------------------- 1 | context("Test shiny app") 2 | 3 | library(assertthat) 4 | library(testthat) 5 | library(assertive) 6 | 7 | 8 | test_that("valid parameters are provided for nanoTailApp()",{ 9 | 10 | 11 | expect_error(nanoTailApp()) 12 | expect_error(nanoTailApp(empty_polya_data_table)) 13 | #expect_silent(nanoTailApp(example_valid_polya_table)) 14 | expect_error(nanoTailApp(example_valid_polya_table %>% dplyr::select(-polya_length))) 15 | expect_error(nanoTailApp(example_valid_polya_table %>% dplyr::select(-transcript))) 16 | expect_error(nanoTailApp(example_valid_polya_table %>% dplyr::select(-sample_name))) 17 | }) 18 | 19 | 20 | -------------------------------------------------------------------------------- /tests/testthat/test-helper_functions.R: -------------------------------------------------------------------------------- 1 | context("Helper functions") 2 | 3 | test_that("geometric mean calculation works",{ 4 | 5 | empty_vector <- vector() 6 | test_vector <- (seq(10,100)) 7 | test_vector_with_NAs <- (rep(c(seq(20,40),NA),10)) 8 | non_numeric_vector <- c(1,2,3,"A") 9 | expect_error(gm_mean(empty_vector)) 10 | expect_error(gm_mean(non_numeric_vector)) 11 | expect_error(gm_mean(test_vector.na.rm="TRUE")) 12 | expect_equal(gm_mean(5),5) 13 | expect_equal(round(gm_mean(test_vector)),round(47.29746)) 14 | expect_true(is.na(gm_mean(test_vector_with_NAs,na.rm = FALSE))) 15 | expect_false(is.na(gm_mean(test_vector_with_NAs,na.rm = TRUE))) 16 | }) 17 | -------------------------------------------------------------------------------- /man/calculate_scaling_vector_for_virutal_gel.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \name{calculate_scaling_vector_for_virutal_gel} 4 | \alias{calculate_scaling_vector_for_virutal_gel} 5 | \title{Calculates scaling vector for virtual gel plotting} 6 | \usage{ 7 | calculate_scaling_vector_for_virutal_gel(input_data, groupingFactor) 8 | } 9 | \arguments{ 10 | \item{input_data}{input polyA table for calculation of scaling factor (count of reads)} 11 | 12 | \item{groupingFactor}{for which factor calculate counts} 13 | } 14 | \value{ 15 | named vector 16 | } 17 | \description{ 18 | Calculates scaling vector for virtual gel plotting 19 | } 20 | -------------------------------------------------------------------------------- /man/remove_failed_reads.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/read_polyA_data.R 3 | \name{remove_failed_reads} 4 | \alias{remove_failed_reads} 5 | \title{Removes reads which failed during Nanopolish polya processing} 6 | \usage{ 7 | remove_failed_reads(polya_data) 8 | } 9 | \arguments{ 10 | \item{polya_data}{output table from \link{read_polya_single} or \link{read_polya_multiple}} 11 | } 12 | \value{ 13 | a \link[tibble:tibble-package]{tibble} with only reads having qc_tag=='PASS' 14 | } 15 | \description{ 16 | Convenient function to quickly remove all reads failing during nanopolish polya processing 17 | } 18 | \seealso{ 19 | \link{read_polya_single}, \link{read_polya_multiple} 20 | } 21 | -------------------------------------------------------------------------------- /man/nanoTailApp.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_shiny_app.R 3 | \name{nanoTailApp} 4 | \alias{nanoTailApp} 5 | \title{wrapper for NanoTail Shiny interface} 6 | \usage{ 7 | nanoTailApp( 8 | polya_table, 9 | precomputed_polya_statistics = NA, 10 | precomputed_annotations = NA 11 | ) 12 | } 13 | \arguments{ 14 | \item{polya_table}{polyA predictions table. Can be obtained with \link{read_polya_multiple}} 15 | 16 | \item{precomputed_polya_statistics}{precomputed differential adenylation table (obtained with \link{calculate_polya_stats})} 17 | 18 | \item{precomputed_annotations}{precomputed annotations} 19 | } 20 | \description{ 21 | wrapper for NanoTail Shiny interface 22 | } 23 | -------------------------------------------------------------------------------- /man/annotate_with_org_packages.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_annotate.R 3 | \name{annotate_with_org_packages} 4 | \alias{annotate_with_org_packages} 5 | \title{Title} 6 | \usage{ 7 | annotate_with_org_packages( 8 | polya_data, 9 | columns_of_annotation = c("GENENAME", "SYMBOL"), 10 | keytype = "ENSEMBLTRANS", 11 | organism = "mus_musculus" 12 | ) 13 | } 14 | \arguments{ 15 | \item{polya_data}{polya data table to annotate} 16 | 17 | \item{columns_of_annotation}{which columns to use} 18 | 19 | \item{keytype}{whic keytype to use} 20 | 21 | \item{organism}{whic organism database to use} 22 | } 23 | \value{ 24 | a \link[tibble]{tibble} 25 | } 26 | \description{ 27 | Title 28 | } 29 | -------------------------------------------------------------------------------- /man/subsample_table.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \name{subsample_table} 4 | \alias{subsample_table} 5 | \title{Subsample a date frame} 6 | \usage{ 7 | subsample_table(input_table, groupingFactor = NA, subsample = NA) 8 | } 9 | \arguments{ 10 | \item{input_table}{input table for subsampling} 11 | 12 | \item{groupingFactor}{grouping factor(s)} 13 | 14 | \item{subsample}{specify absolute number of rows or fraction to subsample from the data frame (group-wise)} 15 | } 16 | \value{ 17 | \link{tibble} 18 | } 19 | \description{ 20 | Uses base subsetting and \link{sample} or dplyr \link[dplyr]{sample_n} or \link[dplyr]{sample_frac} to get the subset of the bigger data.frame or tibble 21 | } 22 | -------------------------------------------------------------------------------- /man/plot_nanopolish_qc.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_nanopolish_qc} 4 | \alias{plot_nanopolish_qc} 5 | \title{Plot Nanopolish polya QC} 6 | \usage{ 7 | plot_nanopolish_qc(nanopolish_processing_info, frequency = TRUE, ...) 8 | } 9 | \arguments{ 10 | \item{nanopolish_processing_info}{output of \link{get_nanopolish_processing_info}} 11 | 12 | \item{frequency}{show frequency plot instead of counts plot} 13 | 14 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 15 | } 16 | \value{ 17 | \link[ggplot2]{ggplot} object 18 | } 19 | \description{ 20 | Plot Nanopolish polya QC 21 | } 22 | -------------------------------------------------------------------------------- /man/get_nanopolish_processing_info.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{get_nanopolish_processing_info} 4 | \alias{get_nanopolish_processing_info} 5 | \title{Get information about nanopolish processing} 6 | \usage{ 7 | get_nanopolish_processing_info(polya_data, grouping_factor = NA) 8 | } 9 | \arguments{ 10 | \item{polya_data}{A data.frame or tibble containig unfiltered polya output from Nanopolish,} 11 | 12 | \item{grouping_factor}{How to group results (e.g. by sample_name) 13 | best read with \link[nanotail]{read_polya_single} or \link[nanotail]{read_polya_multiple}} 14 | } 15 | \value{ 16 | A \link[tibble]{tibble} with counts for each processing state 17 | } 18 | \description{ 19 | Process the information returned by \code{nanopolish polya} in the \code{qc_tag} column 20 | } 21 | -------------------------------------------------------------------------------- /man/stat_median_line.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \name{stat_median_line} 4 | \alias{stat_median_line} 5 | \title{Helper function for calculating median stat for violin/boxpolot ggplot plots} 6 | \usage{ 7 | stat_median_line( 8 | mapping = NULL, 9 | data = NULL, 10 | geom = "hline", 11 | position = "identity", 12 | na.rm = FALSE, 13 | show.legend = NA, 14 | inherit.aes = TRUE, 15 | ... 16 | ) 17 | } 18 | \arguments{ 19 | \item{mapping}{} 20 | 21 | \item{data}{} 22 | 23 | \item{geom}{} 24 | 25 | \item{position}{} 26 | 27 | \item{na.rm}{} 28 | 29 | \item{show.legend}{} 30 | 31 | \item{inherit.aes}{} 32 | 33 | \item{...}{} 34 | } 35 | \value{ 36 | 37 | } 38 | \description{ 39 | Helper function for calculating median stat for violin/boxpolot ggplot plots 40 | } 41 | -------------------------------------------------------------------------------- /man/plot_quantiles.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_quantiles} 4 | \alias{plot_quantiles} 5 | \title{Plot quantiles} 6 | \usage{ 7 | plot_quantiles( 8 | summarized_data, 9 | transcript_id, 10 | transcript_id_column = "transcript", 11 | groupBy 12 | ) 13 | } 14 | \arguments{ 15 | \item{summarized_data}{\itemize{ 16 | \item summarized data table (output of summarize_polya_per_transcript, with quantiles calculated) 17 | }} 18 | 19 | \item{transcript_id}{\itemize{ 20 | \item id of transcript to show 21 | }} 22 | 23 | \item{transcript_id_column}{\itemize{ 24 | \item column with transcript ids 25 | }} 26 | 27 | \item{groupBy}{\itemize{ 28 | \item which column use for grouping (e.g. with timepoints) 29 | }} 30 | } 31 | \value{ 32 | ggplot object 33 | } 34 | \description{ 35 | Plot quantiles 36 | } 37 | -------------------------------------------------------------------------------- /man/calculate_pca.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{calculate_pca} 4 | \alias{calculate_pca} 5 | \title{Calculates PCA using polya predictions or counts} 6 | \usage{ 7 | calculate_pca( 8 | polya_data_summarized, 9 | parameter = "polya_median", 10 | transcript_id_column = "transcript" 11 | ) 12 | } 13 | \arguments{ 14 | \item{polya_data_summarized}{summarized polyA predictions. Generate use \link{summarize_polya}} 15 | 16 | \item{parameter}{\itemize{ 17 | \item parameter used for PCA calculation. One of: polya_median,polya_mean,polya_gm_mean,counts 18 | }} 19 | 20 | \item{transcript_id_column}{column which respresnrt transcript id} 21 | } 22 | \value{ 23 | pca object 24 | } 25 | \description{ 26 | Needs polyA predictions table summarized by \link{summarize_polya} function, using "sample_name" as summary_factors 27 | } 28 | -------------------------------------------------------------------------------- /man/annotate_with_biomart.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_annotate.R 3 | \name{annotate_with_biomart} 4 | \alias{annotate_with_biomart} 5 | \title{Title} 6 | \usage{ 7 | annotate_with_biomart( 8 | polya_data, 9 | attributes_to_get = c("ensembl_transcript_id", "external_gene_name", "description", 10 | "transcript_biotype"), 11 | filters = "ensembl_transcript_id", 12 | mart_to_use = NA 13 | ) 14 | } 15 | \arguments{ 16 | \item{polya_data}{polya data table to annotate} 17 | 18 | \item{attributes_to_get}{what annotations should be retrieved. Default = c('external_gene_name','description','transcript_biotype')} 19 | 20 | \item{filters}{which column should be matched in the target mart} 21 | 22 | \item{mart_to_use}{mart object created with \link[biomaRt]{useMart} or \link[biomaRt]{useEnsembl}} 23 | } 24 | \value{ 25 | a \link[tibble]{tibble} 26 | } 27 | \description{ 28 | Title 29 | } 30 | -------------------------------------------------------------------------------- /tests/testthat/test-polya_annotate.R: -------------------------------------------------------------------------------- 1 | context("annotation of polya predictions table") 2 | 3 | test_that("annotation with annotables works",{ 4 | 5 | expect_error(annotate_with_annotables()) 6 | expect_error(annotate_with_annotables(empty_polya_data_table)) 7 | 8 | expect_error(annotate_with_annotables(example_valid_polya_table)) 9 | expect_error(annotate_with_annotables(empty_polya_data_table,"grcm38")) 10 | 11 | }) 12 | 13 | 14 | test_that("annotation with biomart works",{ 15 | 16 | 17 | 18 | number_of_reads_per_sample=20000 19 | number_of_transcripts_per_sample=50 20 | #mouse_genes_ensembl_mart <- biomaRt::useMart("ensembl",dataset="mmusculus_gene_ensembl") 21 | 22 | 23 | 24 | expect_error(annotate_with_biomart()) 25 | expect_error(annotate_with_biomart(empty_polya_data_table)) 26 | 27 | expect_error(annotate_with_biomart(example_valid_polya_table)) 28 | expect_error(annotate_with_biomart(empty_polya_data_table)) 29 | 30 | 31 | }) 32 | -------------------------------------------------------------------------------- /man/plot_MA.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_MA} 4 | \alias{plot_MA} 5 | \title{Plots MA plot of differential expression analysis} 6 | \usage{ 7 | plot_MA(input_data, transcript_id_column, labels = FALSE, nlabels = 10, ...) 8 | } 9 | \arguments{ 10 | \item{input_data}{a table with output from \link{calculate_diff_exp_binom}} 11 | 12 | \item{transcript_id_column}{column used for transcript id} 13 | 14 | \item{labels}{show point labels using ggrepel} 15 | 16 | \item{nlabels}{number of labels to show} 17 | 18 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 19 | } 20 | \value{ 21 | \link[ggplot2]{ggplot} object 22 | } 23 | \description{ 24 | Crates simple MA plot, with log10(mean expression) on the X-axis and log2(fold_change) on the Y-axis 25 | } 26 | -------------------------------------------------------------------------------- /man/read_polya_single.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/read_polyA_data.R 3 | \name{read_polya_single} 4 | \alias{read_polya_single} 5 | \title{Read Single Nanopolish polyA preditions from file} 6 | \usage{ 7 | read_polya_single(polya_path, gencode = TRUE, sample_name = NA) 8 | } 9 | \arguments{ 10 | \item{polya_path}{path to nanopolish output file} 11 | 12 | \item{gencode}{are contig names GENCODE-compliant. 13 | Can get transcript names and ensembl_transcript IDs if reads were mapped for example to Gencode reference transcriptome} 14 | 15 | \item{sample_name}{sample name (optional), provided as a string. 16 | If specified will be included as an additional column sample_name.} 17 | } 18 | \value{ 19 | a \link[tibble:tibble-package]{tibble} with polya predictions 20 | } 21 | \description{ 22 | This is the basic function used to import output from \code{nanopolish polya} to R 23 | } 24 | \seealso{ 25 | \link{read_polya_multiple} 26 | } 27 | -------------------------------------------------------------------------------- /man/getmode.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_helper_functions.R 3 | \name{getmode} 4 | \alias{getmode} 5 | \title{Function calculating statistical mode of given vector.} 6 | \usage{ 7 | getmode(x, method = "density", na.rm = FALSE) 8 | } 9 | \arguments{ 10 | \item{x}{\link{character} data for which the most frequent value is to be calculated 11 | (polya_data column with the lengths of the poly(A) tails)} 12 | 13 | \item{method}{\link{character} "density"/"value"; density mode is computed 14 | by default.} 15 | 16 | \item{na.rm}{\link{boolean} parameter defining whether to remove missing values or 17 | not. By a default set to false} 18 | } 19 | \value{ 20 | statistical mode of given vector. 21 | } 22 | \description{ 23 | Function calculating statistical mode of given vector. 24 | } 25 | \examples{ 26 | \dontrun{ 27 | 28 | getmode(x = polya_data$tail_length, 29 | method = "density", 30 | na.rm = FALSE) 31 | 32 | } 33 | 34 | } 35 | -------------------------------------------------------------------------------- /inst/extdata/about.md: -------------------------------------------------------------------------------- 1 | ## NanoTail 2 | 3 | The goal of **NanoTail** is to provide a set of functions to manipulate and analyze data coming from polyA lengths estimations done using Oxford Nanopore Direct RNA sequencing and Nanopolish software. The software is still in thee development phase so all suggestions are welcome. Please also expect the code to be changed frequently, so use it with caution. 4 | 5 | ## Usage 6 | 7 | Please use navigation options in the sidebar (located on the left) to access analysis functions and plots. NanoTail currently supports differential adenylation analysis using Wilcoxon and Kolmogorov-Smirnov tests and differential expression analysis using binomTest from EdgeR. More analysis options are in the development and are expected to be available soon. 8 | 9 | ## Citation 10 | 11 | Please cite NanoTail as: 12 | Krawczyk PS et al., NanoTail - R package for exploratory analysis of Nanopore Direct RNA based polyA lengths estimations 13 | 14 | 15 | --- 16 | 17 | (C) Pawel Krawczyk 2019 18 | -------------------------------------------------------------------------------- /man/plot_volcano.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_volcano} 4 | \alias{plot_volcano} 5 | \title{Plots volcano plot of differential expression analysis} 6 | \usage{ 7 | plot_volcano( 8 | input_data, 9 | transcript_id_column, 10 | labels = FALSE, 11 | nlabels = 10, 12 | ... 13 | ) 14 | } 15 | \arguments{ 16 | \item{input_data}{a table with output from \link{calculate_diff_exp_binom} or \link{calculate_polya_stats}} 17 | 18 | \item{transcript_id_column}{column used for transcript id} 19 | 20 | \item{labels}{show point labels using ggrepel} 21 | 22 | \item{nlabels}{number of labels to show 23 | #'} 24 | 25 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 26 | } 27 | \value{ 28 | \link[ggplot2]{ggplot} object 29 | } 30 | \description{ 31 | Plots volcano plot of differential expression analysis 32 | } 33 | -------------------------------------------------------------------------------- /man/summarize_polya_per_transcript.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{summarize_polya_per_transcript} 4 | \alias{summarize_polya_per_transcript} 5 | \title{Summarize poly(A) data per transcript} 6 | \usage{ 7 | summarize_polya_per_transcript( 8 | polya_data, 9 | groupBy = NULL, 10 | transcript_id_column = transcript, 11 | summary_functions = list("median", "mean"), 12 | quantiles = NA 13 | ) 14 | } 15 | \arguments{ 16 | \item{polya_data}{input table with poly(A) data.} 17 | 18 | \item{transcript_id_column}{column with transcript identifier. Default to "transcript"} 19 | 20 | \item{summary_functions}{list of summary functions. Set to NA to get only counts per transcript} 21 | 22 | \item{quantiles}{vector with quantile values (optional)} 23 | 24 | \item{summary_factors}{vector of grouping columns. Set to NULL to omit grouping} 25 | } 26 | \value{ 27 | a tibble with summarized poly(A) length data 28 | } 29 | \description{ 30 | Summarize poly(A) data per transcript 31 | } 32 | -------------------------------------------------------------------------------- /man/summarize_polya.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{summarize_polya} 4 | \alias{summarize_polya} 5 | \title{Summarizes input polya table} 6 | \usage{ 7 | summarize_polya( 8 | polya_data, 9 | summary_factors = c("group"), 10 | transcript_id_column = c("transcript") 11 | ) 12 | } 13 | \arguments{ 14 | \item{polya_data}{input table with polyA predictions} 15 | 16 | \item{summary_factors}{specifies column used for grouping (default: group)} 17 | 18 | \item{transcript_id_column}{specifies which column use as transcript identifier (default: transcript). Set to \code{NULL} to omit per-transcript stats} 19 | } 20 | \value{ 21 | long-format \link[tibble]{tibble} with per-transcript statistics for each sample 22 | } 23 | \description{ 24 | Summarizes input table with polyA predictions, calculating medians, mean, geometric means and standard deviation values for each transcript (default). 25 | To get overall summary for each sample or group, specify \code{transcript_id_column=NULL} 26 | } 27 | -------------------------------------------------------------------------------- /man/dot-kruskal_polya.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{.kruskal_polya} 4 | \alias{.kruskal_polya} 5 | \title{Compute Kruskal-Wallis test on single poly(A) data} 6 | \usage{ 7 | .kruskal_polya( 8 | input_data, 9 | grouping_factor = "sample_name", 10 | verbose = F, 11 | verbosity_level = 1 12 | ) 13 | 14 | .kruskal_polya( 15 | input_data, 16 | grouping_factor = "sample_name", 17 | verbose = F, 18 | verbosity_level = 1 19 | ) 20 | } 21 | \arguments{ 22 | \item{input_data}{input data.frame (for single transcript)} 23 | 24 | \item{grouping_factor}{which column contains group information} 25 | 26 | \item{verbose}{verbose output} 27 | 28 | \item{verbosity_level}{how verbose the output should be (levels 1 - little verbosity, or 2 - very verbose)} 29 | } 30 | \value{ 31 | data.frame with test statistics 32 | 33 | data.frame with test statistics 34 | } 35 | \description{ 36 | Compute Kruskal-Wallis test on single poly(A) data 37 | 38 | Compute Kruskal-Wallis test on single poly(A) data 39 | } 40 | -------------------------------------------------------------------------------- /man/normalize_counts_to_depth.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{normalize_counts_to_depth} 4 | \alias{normalize_counts_to_depth} 5 | \title{Normalize counts to sequencingdepth} 6 | \usage{ 7 | normalize_counts_to_depth( 8 | summarized_data, 9 | raw_data, 10 | spike_in_data = NULL, 11 | groupBy, 12 | force = F 13 | ) 14 | } 15 | \arguments{ 16 | \item{summarized_data}{\itemize{ 17 | \item output of summarize_polya_per_transcript() 18 | }} 19 | 20 | \item{raw_data}{\itemize{ 21 | \item raw polyA data (loaded with read_polya_single() or read_polya_multiple()) 22 | }} 23 | 24 | \item{spike_in_data}{\itemize{ 25 | \item spike-in data for normalization (optional) (raw polya data loaded with read_polya_single() or read_polya_multiple(), with the same metadata as raw data) 26 | }} 27 | 28 | \item{groupBy}{\itemize{ 29 | \item grouping variable 30 | }} 31 | 32 | \item{force}{\itemize{ 33 | \item force recalculation 34 | }} 35 | } 36 | \value{ 37 | data.frame (tibble) with normalized data 38 | } 39 | \description{ 40 | Normalize counts to sequencingdepth 41 | } 42 | -------------------------------------------------------------------------------- /man/read_polya_multiple.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/read_polyA_data.R 3 | \name{read_polya_multiple} 4 | \alias{read_polya_multiple} 5 | \title{Reads multiple nanopolish polyA predictions at once} 6 | \usage{ 7 | read_polya_multiple(samples_table, ...) 8 | } 9 | \arguments{ 10 | \item{samples_table}{data.frame or tibble containing samples metadata and paths to files. 11 | Should have at least two columns: \itemize{ 12 | \item polya_path - containing path to the polya predictions file 13 | \item sample_name - unique name of the sample 14 | } 15 | Additional columns can provide metadata which will be included in the final table} 16 | 17 | \item{...}{\itemize{ 18 | \item additional parameters to pass to read_polya_single(), like gencode=(TRUE/FALSE) 19 | }} 20 | } 21 | \value{ 22 | a \link[tibble:tibble-package]{tibble} containing polyA predictions for all specified samples, with metadata provided in samples_table 23 | stored as separate columns 24 | } 25 | \description{ 26 | This function can be used to load any number of files with polyA predictions with single invocation, 27 | allowing for metadata specification. 28 | } 29 | \seealso{ 30 | \link{read_polya_single} 31 | } 32 | -------------------------------------------------------------------------------- /man/calculate_diff_exp_binom.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{calculate_diff_exp_binom} 4 | \alias{calculate_diff_exp_binom} 5 | \title{Performs differential expression analysis} 6 | \usage{ 7 | calculate_diff_exp_binom( 8 | polya_data, 9 | grouping_factor = NA, 10 | condition1 = NA, 11 | condition2 = NA, 12 | alpha = 0.05, 13 | summarized_input = FALSE 14 | ) 15 | } 16 | \arguments{ 17 | \item{polya_data}{polya_data tibble} 18 | 19 | \item{grouping_factor}{name of column containing factor with groups for comparison} 20 | 21 | \item{condition1}{first condition to compare} 22 | 23 | \item{condition2}{second condition to compare} 24 | 25 | \item{alpha}{threshold for a pvalue, to treat the result as significant (default = 0.05)} 26 | 27 | \item{summarized_input}{is input table already summarized?} 28 | } 29 | \value{ 30 | a tibble with differential expression results 31 | } 32 | \description{ 33 | Uses counts for each identified transcript to calculate differential expression between specified groups. 34 | This function is a wrapper for \code{\link[edgeR]{binomTest}} from \code{edgeR} package 35 | } 36 | \seealso{ 37 | \link[edgeR]{binomTest} 38 | } 39 | -------------------------------------------------------------------------------- /man/dot-basic_aesthetics.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{.basic_aesthetics} 4 | \alias{.basic_aesthetics} 5 | \title{Title} 6 | \usage{ 7 | .basic_aesthetics( 8 | ggplot_object, 9 | scale_x_limit_low = NA, 10 | scale_x_limit_high = NA, 11 | scale_y_limit_low = NA, 12 | scale_y_limit_high = NA, 13 | color_palette = "Set1", 14 | plot_title = NA, 15 | color_mode = "color", 16 | axis_titles_size = 16 17 | ) 18 | } 19 | \arguments{ 20 | \item{ggplot_object}{ggplot2 object to manipulate asesthetics} 21 | 22 | \item{scale_x_limit_low}{lower limit of x continuous scale} 23 | 24 | \item{scale_x_limit_high}{upper limit of x continuous scale} 25 | 26 | \item{scale_y_limit_low}{lower limit of y continuous scale} 27 | 28 | \item{scale_y_limit_high}{upper limit of y continuous scale} 29 | 30 | \item{color_palette}{color palette (one from RColorBrewer of ggsci packages)} 31 | 32 | \item{plot_title}{Title of the plot} 33 | 34 | \item{color_mode}{if using color, fill or both, when specifying color_palette} 35 | 36 | \item{axis_titles_size}{size of axis titles} 37 | } 38 | \value{ 39 | \link[ggplot2]{ggplot} object 40 | } 41 | \description{ 42 | Title 43 | } 44 | -------------------------------------------------------------------------------- /man/plot_virtual_gel.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_virtual_gel} 4 | \alias{plot_virtual_gel} 5 | \title{Title} 6 | \usage{ 7 | plot_virtual_gel( 8 | input_data, 9 | groupingFactor, 10 | valuesColumn, 11 | density_bw = 0.6, 12 | kernel = "gaussian", 13 | shift_bands = 0, 14 | kernel_from = 0, 15 | kernel_to = NA, 16 | scale_by_size = T, 17 | scaling_vector = NA 18 | ) 19 | } 20 | \arguments{ 21 | \item{input_data}{data frame (or tibble) with input values} 22 | 23 | \item{groupingFactor}{factor to group input table by} 24 | 25 | \item{valuesColumn}{column with numeric values to calculate density on} 26 | 27 | \item{density_bw}{bandwidth of density (bw argument to \link{density} function, default=1 )} 28 | 29 | \item{kernel}{kenrel to use} 30 | 31 | \item{shift_bands}{shift bands by specified value} 32 | 33 | \item{kernel_from}{from which value start density estimation} 34 | 35 | \item{kernel_to}{to which value perform density estimation} 36 | 37 | \item{scale_by_size}{should densities be scaled by sample size} 38 | 39 | \item{scaling_vector}{vector containing scaling factors} 40 | } 41 | \value{ 42 | list containing plot and density estimates (data.frame) 43 | } 44 | \description{ 45 | Title 46 | } 47 | -------------------------------------------------------------------------------- /appveyor.yml: -------------------------------------------------------------------------------- 1 | # DO NOT CHANGE the "init" and "install" sections below 2 | 3 | # Download script file from GitHub 4 | init: 5 | ps: | 6 | $ErrorActionPreference = "Stop" 7 | Invoke-WebRequest http://raw.github.com/krlmlr/r-appveyor/master/scripts/appveyor-tool.ps1 -OutFile "..\appveyor-tool.ps1" 8 | Import-Module '..\appveyor-tool.ps1' 9 | 10 | install: 11 | ps: Bootstrap 12 | 13 | cache: 14 | - C:\RLibrary 15 | 16 | environment: 17 | NOT_CRAN: true 18 | # env vars that may need to be set, at least temporarily, from time to time 19 | # see https://github.com/krlmlr/r-appveyor#readme for details 20 | # USE_RTOOLS: true 21 | # R_REMOTES_STANDALONE: true 22 | 23 | # Adapt as necessary starting from here 24 | 25 | build_script: 26 | - travis-tool.sh install_deps 27 | 28 | test_script: 29 | - travis-tool.sh run_tests 30 | 31 | on_failure: 32 | - 7z a failure.zip *.Rcheck\* 33 | - appveyor PushArtifact failure.zip 34 | 35 | artifacts: 36 | - path: '*.Rcheck\**\*.log' 37 | name: Logs 38 | 39 | - path: '*.Rcheck\**\*.out' 40 | name: Logs 41 | 42 | - path: '*.Rcheck\**\*.fail' 43 | name: Logs 44 | 45 | - path: '*.Rcheck\**\*.Rout' 46 | name: Logs 47 | 48 | - path: '\*_*.tar.gz' 49 | name: Bits 50 | 51 | - path: '\*_*.zip' 52 | name: Bits 53 | -------------------------------------------------------------------------------- /man/dot-polya_stats.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{.polya_stats} 4 | \alias{.polya_stats} 5 | \title{Calculates polyA statistics for single group of reads (for single transcript)} 6 | \usage{ 7 | .polya_stats( 8 | polya_data, 9 | stat_test, 10 | grouping_factor, 11 | min_reads = 0, 12 | use_dwell_time = FALSE, 13 | custom_glm_formula = NA 14 | ) 15 | } 16 | \arguments{ 17 | \item{polya_data}{\itemize{ 18 | \item input data frame with polyA predictions 19 | }} 20 | 21 | \item{stat_test}{\itemize{ 22 | \item statistical test to use. One of : Wilcoxon, KS (Kolmogorov-Smirnov) or glm (Generalized Linear Model). All tests use log2(polya_length) as a response variable 23 | }} 24 | 25 | \item{grouping_factor}{\itemize{ 26 | \item factor defining groups (Need to have 2 levels) 27 | }} 28 | 29 | \item{min_reads}{\itemize{ 30 | \item minimum reads per group to include in the statistics calculation 31 | }} 32 | 33 | \item{use_dwell_time}{\itemize{ 34 | \item use dwell time instead of calculated polya length for statistics 35 | }} 36 | 37 | \item{custom_glm_formula}{\itemize{ 38 | \item custom glm formula (when using glm for statistics) 39 | }} 40 | } 41 | \value{ 42 | data frame 43 | } 44 | \description{ 45 | Calculates polyA statistics for single group of reads (for single transcript) 46 | } 47 | -------------------------------------------------------------------------------- /NAMESPACE: -------------------------------------------------------------------------------- 1 | # Generated by roxygen2: do not edit by hand 2 | 3 | export("%>%") 4 | export(annotate_with_annotables) 5 | export(annotate_with_biomart) 6 | export(annotate_with_org_packages) 7 | export(calculate_diff_exp_binom) 8 | export(calculate_pca) 9 | export(calculate_polya_stats) 10 | export(calculate_scaling_vector_for_virutal_gel) 11 | export(get_nanopolish_processing_info) 12 | export(getmode) 13 | export(gm_mean) 14 | export(kruskal_polya) 15 | export(nanoTailApp) 16 | export(nanotail_ggplot2_theme) 17 | export(normalize_counts_to_depth) 18 | export(plot_MA) 19 | export(plot_annotations_comparison_boxplot) 20 | export(plot_counts_scatter) 21 | export(plot_nanopolish_qc) 22 | export(plot_polyA_PCA) 23 | export(plot_polya_boxplot) 24 | export(plot_polya_distribution) 25 | export(plot_polya_violin) 26 | export(plot_quantiles) 27 | export(plot_virtual_gel) 28 | export(plot_volcano) 29 | export(read_polya_multiple) 30 | export(read_polya_single) 31 | export(remove_failed_reads) 32 | export(spread_multiple) 33 | export(stat_median_line) 34 | export(subsample_table) 35 | export(summarize_polya) 36 | export(summarize_polya_per_transcript) 37 | importFrom(magrittr,"%>%") 38 | importFrom(stats,as.formula) 39 | importFrom(stats,glm) 40 | importFrom(stats,median) 41 | importFrom(stats,p.adjust) 42 | importFrom(stats,prcomp) 43 | importFrom(stats,sd) 44 | importFrom(stats,wilcox.test) 45 | importFrom(tibble,tibble) 46 | importFrom(utils,packageVersion) 47 | -------------------------------------------------------------------------------- /man/plot_annotations_comparison_boxplot.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_annotations_comparison_boxplot} 4 | \alias{plot_annotations_comparison_boxplot} 5 | \title{Title} 6 | \usage{ 7 | plot_annotations_comparison_boxplot( 8 | annotated_polya_data, 9 | annotation_factor = NA, 10 | grouping_factor = NA, 11 | condition1 = NA, 12 | condition2 = NA, 13 | annotation_levels = c(), 14 | violin = FALSE, 15 | ... 16 | ) 17 | } 18 | \arguments{ 19 | \item{annotated_polya_data}{data frame(or tibble) with polyA predictions and associated annotations} 20 | 21 | \item{annotation_factor}{column specifying factor grouping transcripts by annotation} 22 | 23 | \item{grouping_factor}{column in polya_data_table specifing factor grouping samples} 24 | 25 | \item{condition1}{if only 2 conditions to show, choose which one is first} 26 | 27 | \item{condition2}{if only 2 conditions to show, choose which one is second} 28 | 29 | \item{annotation_levels}{vector specifying selected annotation levels from annotation_factor} 30 | 31 | \item{violin}{plot violin instead of boxplot?} 32 | 33 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 34 | } 35 | \value{ 36 | \link[ggplot2]{ggplot} object 37 | } 38 | \description{ 39 | Title 40 | } 41 | -------------------------------------------------------------------------------- /man/plot_counts_scatter.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_counts_scatter} 4 | \alias{plot_counts_scatter} 5 | \title{Title} 6 | \usage{ 7 | plot_counts_scatter( 8 | polya_data_summarized, 9 | groupingFactor = NA, 10 | condition1 = NA, 11 | condition2 = NA, 12 | min_counts = 0, 13 | max_counts = 0, 14 | points_coloring_factor = NA, 15 | repel_elements = NA, 16 | repel_group = NA, 17 | transcript_id_column = "transcript", 18 | ... 19 | ) 20 | } 21 | \arguments{ 22 | \item{polya_data_summarized}{polyA predictions table, summarized using \link{summarize_polya}} 23 | 24 | \item{groupingFactor}{name of column used for grouping} 25 | 26 | \item{condition1}{first condition to use for plotting} 27 | 28 | \item{condition2}{second condition to use for plotting} 29 | 30 | \item{min_counts}{minimum number of counts to be shown} 31 | 32 | \item{max_counts}{maximum number of counts to be shown} 33 | 34 | \item{points_coloring_factor}{factor specifying how to color points} 35 | 36 | \item{repel_elements}{TBD} 37 | 38 | \item{repel_group}{TBD} 39 | 40 | \item{transcript_id_column}{TBD 41 | #'} 42 | 43 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 44 | } 45 | \value{ 46 | \link[ggplot2]{ggplot} object 47 | } 48 | \description{ 49 | Title 50 | } 51 | -------------------------------------------------------------------------------- /man/plot_polya_boxplot.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_polya_boxplot} 4 | \alias{plot_polya_boxplot} 5 | \title{Plots boxplot of estimated polya lengths} 6 | \usage{ 7 | plot_polya_boxplot( 8 | polya_data, 9 | groupingFactor, 10 | additional_grouping_factor = NA, 11 | condition1 = NA, 12 | condition2 = NA, 13 | violin = FALSE, 14 | add_points = FALSE, 15 | max_points = 500, 16 | auto_scale = T, 17 | ... 18 | ) 19 | } 20 | \arguments{ 21 | \item{polya_data}{input table with polyA predictions} 22 | 23 | \item{groupingFactor}{which factor to use for grouping} 24 | 25 | \item{additional_grouping_factor}{additional coloring grouping factor} 26 | 27 | \item{condition1}{First condition to include on the plot} 28 | 29 | \item{condition2}{Second condition to include on the plot} 30 | 31 | \item{violin}{Should violin plot be plotted instead of boxplot?} 32 | 33 | \item{add_points}{should individual points be plotted (only if less than max_points). Represented as \link[ggforce]{geom_sina}} 34 | 35 | \item{max_points}{maximum number of points to be plotted if add_points is specified} 36 | 37 | \item{auto_scale}{automatically adjust axis scales (default=TRUE)} 38 | 39 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 40 | } 41 | \value{ 42 | \link[ggplot2]{ggplot} object 43 | } 44 | \description{ 45 | Plots boxplot of estimated polya lengths 46 | } 47 | -------------------------------------------------------------------------------- /man/kruskal_polya.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{kruskal_polya} 4 | \alias{kruskal_polya} 5 | \title{Compute Kruskal-Wallis test on poly(A) data} 6 | \usage{ 7 | kruskal_polya( 8 | input_data, 9 | grouping_factor = "sample_name", 10 | transcript_id = "transcript", 11 | verbose = F, 12 | verbosity_level = 1 13 | ) 14 | 15 | kruskal_polya( 16 | input_data, 17 | grouping_factor = "sample_name", 18 | transcript_id = "transcript", 19 | verbose = F, 20 | verbosity_level = 1 21 | ) 22 | } 23 | \arguments{ 24 | \item{input_data}{\itemize{ 25 | \item input tibble/data.frame with nanopolish output. 26 | }} 27 | 28 | \item{grouping_factor}{\itemize{ 29 | \item which column contains group information 30 | }} 31 | 32 | \item{transcript_id}{column which transcript ids} 33 | 34 | \item{verbose}{verbose output} 35 | 36 | \item{verbosity_level}{how verbose the output should be (levels 1 - little verbosity, or 2 - very verbose)} 37 | } 38 | \value{ 39 | data.frame with statistis 40 | 41 | data.frame with statistis 42 | } 43 | \description{ 44 | Compute Kruskal-Wallis test on poly(A) data 45 | 46 | Compute Kruskal-Wallis test on poly(A) data 47 | } 48 | \examples{ 49 | \dontrun{ 50 | polya_table <- nanotail::read_polya_single("nanopolish.tsv") 51 | kruskal_polya(polya_table,grouping_factor="group",transcript_id="transcript",verbose=T) 52 | } 53 | \dontrun{ 54 | polya_table <- nanotail::read_polya_single("nanopolish.tsv") 55 | kruskal_polya(polya_table,grouping_factor="group",transcript_id="transcript",verbose=T) 56 | } 57 | } 58 | -------------------------------------------------------------------------------- /man/plot_polya_violin.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_polya_violin} 4 | \alias{plot_polya_violin} 5 | \title{Plots violin plot of estimated polya lengths, other version} 6 | \usage{ 7 | plot_polya_violin( 8 | polya_data, 9 | groupingFactor, 10 | additional_grouping_factor = NA, 11 | condition1 = NA, 12 | condition2 = NA, 13 | violin = FALSE, 14 | add_points = FALSE, 15 | max_points = 500, 16 | add_boxplot = TRUE, 17 | fill_by = NA, 18 | auto_scale = T, 19 | transcript_id, 20 | transcript_id_column = "transcript", 21 | ... 22 | ) 23 | } 24 | \arguments{ 25 | \item{polya_data}{input table with polyA predictions} 26 | 27 | \item{groupingFactor}{which factor to use for grouping} 28 | 29 | \item{additional_grouping_factor}{additional coloring grouping factor} 30 | 31 | \item{condition1}{First condition to include on the plot} 32 | 33 | \item{condition2}{Second condition to include on the plot} 34 | 35 | \item{violin}{Should violin plot be plotted instead of boxplot?} 36 | 37 | \item{add_points}{should individual points be plotted (only if less than max_points). Represented as \link[ggforce]{geom_sina}} 38 | 39 | \item{max_points}{maximum number of points to be plotted if add_points is specified} 40 | 41 | \item{add_boxplot}{Add boxplot inside violin?} 42 | 43 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 44 | } 45 | \value{ 46 | \link[ggplot2]{ggplot} object 47 | } 48 | \description{ 49 | Plots violin plot of estimated polya lengths, other version 50 | } 51 | -------------------------------------------------------------------------------- /DESCRIPTION: -------------------------------------------------------------------------------- 1 | Package: nanotail 2 | Title: Analysis and visualisation of Nanopolish-based polyA lengths estimations 3 | Version: 0.1.0 4 | Authors@R: 5 | person(given = "Pawel", 6 | family = "Krawczyk", 7 | role = c("aut", "cre"), 8 | email = "p.krawczyk@ibb.waw.pl", 9 | comment = c(ORCID = "0000-0001-9531-1298")) 10 | Maintainer: 11 | Description: Provides functions for visualization and exploratory analysis of Oxford Nanopore direct RNA seq and Nanopolish based polyA lengths predictions. 12 | License: GPL-3 + file LICENSE 13 | Encoding: UTF-8 14 | LazyData: true 15 | Roxygen: list(markdown = TRUE) 16 | RoxygenNote: 7.2.1 17 | biocViews: 18 | Depends: 19 | R (>= 3.5) 20 | Suggests: 21 | annotables (>= 0.1.91), 22 | ggbiplot (>= 0.55), 23 | biomaRt (>= 2.38.0) 24 | Imports: 25 | magrittr (>= 1.5), 26 | tidyr (>= 0.8.2), 27 | dplyr (>= 0.7.8), 28 | data.table (>= 1.11.8), 29 | shiny (>= 1.3.1), 30 | assertthat (>= 0.2.1), 31 | assertive (>= 0.3.5), 32 | purrr (>= 0.2.5), 33 | FSA (>= 0.8.21), 34 | tibble (>= 1.4.2), 35 | shinydashboard (>= 0.7.1), 36 | shinyWidgets (>= 0.4.8), 37 | RColorBrewer (>= 1.1.2), 38 | edgeR (>= 3.24.3), 39 | forcats (>= 0.4.0), 40 | multcomp (>= 1.4.10), 41 | ggplot2 (>= 3.1.1), 42 | plotly (>= 4.8.0), 43 | testthat (>= 2.0.1), 44 | shinycssloaders (>= 0.2.0), 45 | DT (>= 0.5), 46 | stringr (>= 1.4.0), 47 | rlang (>= 0.3.0.1), 48 | ggsci (>= 2.9), 49 | AnnotationDbi, 50 | ggforce, 51 | ggrepel, 52 | modeest (>= 2.3.3), 53 | effsize 54 | Remotes: 55 | stephenturner/annotables, 56 | vqv/ggbiplot 57 | -------------------------------------------------------------------------------- /man/plot_polya_distribution.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_plots.R 3 | \name{plot_polya_distribution} 4 | \alias{plot_polya_distribution} 5 | \title{Plots polya distribution as ndensity plot} 6 | \usage{ 7 | plot_polya_distribution( 8 | polya_data, 9 | groupingFactor = NA, 10 | parameter_to_plot = "polya_length", 11 | condition1 = NA, 12 | condition2 = NA, 13 | show_center_values = "none", 14 | subsample = NA, 15 | ndensity = TRUE, 16 | mode_method = "density", 17 | auto_scale = T, 18 | transcript_id = NULL, 19 | transcript_id_column = "transcript", 20 | ... 21 | ) 22 | } 23 | \arguments{ 24 | \item{polya_data}{input data with polyA predictions} 25 | 26 | \item{groupingFactor}{how to group} 27 | 28 | \item{parameter_to_plot}{what to plot on x scale (defaults to polya_length)} 29 | 30 | \item{condition1}{First condition to include on the plot} 31 | 32 | \item{condition2}{Second condition to include on the plot} 33 | 34 | \item{show_center_values}{Show center values as vertical line. Possible values: "none","median","mean"} 35 | 36 | \item{subsample}{Subsample input table, provide either absolute number or fraction} 37 | 38 | \item{ndensity}{Should ndensity (scaled density) be plotted instead of normal denisty (default = TRUE)} 39 | 40 | \item{mode_method}{method used for the mode calculation (argument to modeest::mlv method parameter)} 41 | 42 | \item{auto_scale}{automatically adjust axis scales (default=TRUE)} 43 | 44 | \item{...}{parameters passed to .basic_aesthetics function (scale_x_limit_low = NA, scale_x_limit_high = NA, scale_y_limit_low = NA, scale_y_limit_high = NA, color_palette = "Set1",plot_title=NA)} 45 | } 46 | \value{ 47 | \link[ggplot2]{ggplot} object 48 | } 49 | \description{ 50 | Plots polya distribution as ndensity plot 51 | } 52 | -------------------------------------------------------------------------------- /man/calculate_polya_stats.Rd: -------------------------------------------------------------------------------- 1 | % Generated by roxygen2: do not edit by hand 2 | % Please edit documentation in R/polya_stats.R 3 | \name{calculate_polya_stats} 4 | \alias{calculate_polya_stats} 5 | \title{Calculates basic statistics for polya lengths} 6 | \usage{ 7 | calculate_polya_stats( 8 | polya_data, 9 | transcript_id_column = "transcript", 10 | min_reads = 0, 11 | grouping_factor = "sample_name", 12 | condition1 = NA, 13 | condition2 = NA, 14 | stat_test = "Wilcoxon", 15 | alpha = 0.05, 16 | add_summary = TRUE, 17 | length_summary_to_show = "gm_mean", 18 | ... 19 | ) 20 | } 21 | \arguments{ 22 | \item{polya_data}{input table with polyA predictions} 23 | 24 | \item{transcript_id_column}{\itemize{ 25 | \item name of the column with transcript ids (default = "transcript") 26 | }} 27 | 28 | \item{min_reads}{minimum number of reads to include transcript in the analysis} 29 | 30 | \item{grouping_factor}{which column defines groups (default: sample_name)} 31 | 32 | \item{condition1}{if \code{grouping_factor} has more than 2 levels, which level use for comparison} 33 | 34 | \item{condition2}{if \code{grouping_factor} has more than 2 levels, which level use for comparison} 35 | 36 | \item{stat_test}{what statistical test to use for testing, currently supports "Wilcoxon" (for \link{wilcox.test}), "KS" (for \link[FSA]{ksTest} from FSA package) or "glm" (for \link{glm})} 37 | 38 | \item{alpha}{\itemize{ 39 | \item alpha value to consider a hit significant (default - 0.05) 40 | }} 41 | 42 | \item{add_summary}{\itemize{ 43 | \item add summary (mean polya lengths, counts) to statistics results? 44 | }} 45 | 46 | \item{length_summary_to_show}{\itemize{ 47 | \item which length summary to show ("median"/"mean"/"gm_mean") 48 | }} 49 | 50 | \item{...}{\itemize{ 51 | \item additional parameters to pass to .polya_stats (custom_glm_formula,use_dwell_time) 52 | }} 53 | } 54 | \value{ 55 | summary table with pvalues and median/mean values associated to each transcript 56 | } 57 | \description{ 58 | Takes polyA predictions table as input and checks if there is significant difference in polyA lengths between chosen conditions for each transcript. 59 | By default, Wilcoxon Rank Sum (\link{wilcox.test}) test is used. 60 | } 61 | -------------------------------------------------------------------------------- /tests/testthat/test-read_polyA_data.R: -------------------------------------------------------------------------------- 1 | context("test functions for data import and filtering") 2 | 3 | library(assertthat) 4 | library(testthat) 5 | library(assertive) 6 | 7 | empty_sample_table = data.frame() 8 | 9 | sample_table_with_correct_columns_wrong_data = data.frame(sample_name = c("iorem","ipsum"),polya_path=c("iorem","ipsum")) 10 | sample_table_with_wrong_columns = data.frame(sample_name_wrong = c("iorem","ipsum"),polya_path_wrong=c("iorem","ipsum")) 11 | 12 | 13 | test_that("read_polya_single correctly parses provided parameters",{ 14 | expect_error(read_polya_single("")) 15 | expect_error(read_polya_single("/foo/bar")) 16 | expect_error(read_polya_single(" ",gencode="TRUE")) 17 | expect_error(read_polya_single(" ",gencode="FALSE")) 18 | expect_error(read_polya_single(" ",gencode=FALSE,sample_name="sample1")) 19 | expect_error(read_polya_single(sample_tempfile1,gencode="FALSE",sample_name="sample1")) 20 | }) 21 | 22 | test_that("polya data are correctly read from files",{ 23 | empty_tempfile = tempfile() 24 | expect_error(read_polya_single(empty_tempfile)) 25 | expect_message(read_polya_single(sample_tempfile1),"Loading data from",fixed=TRUE) 26 | expect_message(read_polya_single(sample_tempfile1,gencode=TRUE),"Loading data from",fixed=TRUE) 27 | expect_warning(read_polya_single(sample_tempfile1,gencode=TRUE,sample_name="sample1"),"sample_name was provided in the input file",fixed=TRUE,all=FALSE) 28 | expect_message(read_polya_multiple(example_sample_table),"Loading data from",fixed=TRUE) 29 | expect_length(rownames(read_polya_multiple(example_sample_table)),number_of_reads_per_sample*2) 30 | }) 31 | 32 | 33 | 34 | test_that("Sample table is correctly provided",{ 35 | expect_error(read_polya_multiple()) 36 | expect_error(read_polya_multiple(samples_table = empty_sample_table)) 37 | expect_error(read_polya_multiple(samples_table = sample_table_with_wrong_columns)) 38 | expect_error(read_polya_multiple(samples_table = sample_table_with_correct_columns_wrong_data)) 39 | }) 40 | 41 | test_that("Filtering works",{ 42 | example_polya_table_read_from_disk <- read_polya_multiple(samples_table = example_sample_table) 43 | expect_error(remove_failed_reads()) 44 | expect_error(remove_failed_reads(empty_sample_table)) 45 | expect_silent(remove_failed_reads(example_valid_polya_table)) 46 | }) 47 | -------------------------------------------------------------------------------- /tests/testthat/test-polya_stats.R: -------------------------------------------------------------------------------- 1 | context("test functions for statistics calculation") 2 | 3 | 4 | library(assertthat) 5 | library(testthat) 6 | library(assertive) 7 | 8 | 9 | 10 | test_that("Valid input parameters provided for calculate_polya_stats()",{ 11 | expect_error(calculate_polya_stats()) 12 | expect_error(calculate_polya_stats(empty_polya_data_table)) 13 | 14 | #expect_silent(calculate_polya_stats(example_valid_polya_table,grouping_factor="group")) 15 | #expect_silent(calculate_polya_stats(example_valid_polya_table,grouping_factor="group")) 16 | #expect_silent(calculate_polya_stats(example_valid_polya_table,grouping_factor="group")) 17 | #expect_silent(calculate_polya_stats(example_valid_polya_table,grouping_factor="group")) 18 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",stat_test = "ttest"),"Please provide one of available statistical tests") 19 | 20 | #expect_silent(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",stat_test="glm",custom_glm_formula = "polya_length ~ group")) 21 | #expect_silent(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",stat_test="glm",custom_glm_formula = polya_length ~ group)) 22 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",stat_test="glm",custom_glm_formula = polya_length ~ group + group2)) 23 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",stat_test="glm",custom_glm_formula = polya_length ~ NULL)) 24 | 25 | #expect_silent(calculate_polya_stats(example_valid_polya_table_3levels,grouping_factor="group",condition1 = "group1",condition2 = "group2")) 26 | expect_error(calculate_polya_stats(example_valid_polya_table_3levels,grouping_factor="group",condition1 = "group1",condition2 = "nonexistent_group")) 27 | expect_error(calculate_polya_stats(example_valid_polya_table_3levels,grouping_factor="group",condition2 = "group2",condition1 = "nonexistent_group")) 28 | expect_error(calculate_polya_stats(example_valid_polya_table_3levels,grouping_factor="group")) 29 | expect_error(calculate_polya_stats(example_polya_table_sample1,grouping_factor="group")) 30 | 31 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="non-existent-group")) 32 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",use_dwell_time = "TRUE")) 33 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",min_reads = "2")) 34 | expect_error(calculate_polya_stats(example_valid_polya_table,grouping_factor="group",min_reads = NULL)) 35 | }) 36 | 37 | 38 | test_that("Valid input parameters provided for calculate_pca()",{ 39 | 40 | summarized_example_valid_polya_table <- summarize_polya(example_valid_polya_table,summary_factors = "sample_name") 41 | 42 | expect_error(calculate_pca()) 43 | expect_error(calculate_pca(empty_polya_data_table)) 44 | expect_error(calculate_pca(example_valid_polya_table)) 45 | expect_error(calculate_pca(example_valid_polya_table,parameter = "polya_imagined_summary")) 46 | expect_named(calculate_pca(summarized_example_valid_polya_table),c("pca","sample_names"),ignore.order = TRUE) 47 | expect_error(calculate_pca(summarized_example_valid_polya_table %>% dplyr::select(-sample_name))) 48 | expect_error(calculate_pca(summarized_example_valid_polya_table %>% dplyr::ungroup() %>% dplyr::select(-transcript))) 49 | }) 50 | 51 | 52 | test_that("summarize polyA is working",{ 53 | expect_error(summarize_polya()) 54 | expect_error(summarize_polya(empty_polya_data_table)) 55 | expect_error(summarize_polya(example_valid_polya_table,summary_factors = 1)) 56 | expect_error(summarize_polya(example_valid_polya_table_3levels,summary_factors = "non-existent-factor")) 57 | #expect_silent(summarize_polya(example_valid_polya_table_3levels)) 58 | }) 59 | 60 | 61 | test_that("Valid input parameters provided for calculate_diff_exp_binom()",{ 62 | expect_error(calculate_diff_exp_binom()) 63 | expect_error(calculate_diff_exp_binom(empty_polya_data_table)) 64 | 65 | expect_error(calculate_diff_exp_binom(example_valid_polya_table)) 66 | expect_error(calculate_diff_exp_binom(example_valid_polya_table,grouping_factor = "group")) 67 | 68 | expect_error(calculate_diff_exp_binom(example_valid_polya_table,grouping_factor = "group",condition1 = "group1", condition2 = "non-existent-factor-level")) 69 | expect_error(calculate_diff_exp_binom(example_valid_polya_table,grouping_factor = "group",condition2 = "group1", condition1 = "non-existent-factor-level")) 70 | 71 | #expect_length(rownames(calculate_diff_exp_binom(example_valid_polya_table,grouping_factor = "group",condition1 = "group1",condition2="group2")),50) 72 | }) 73 | 74 | -------------------------------------------------------------------------------- /R/polya_annotate.R: -------------------------------------------------------------------------------- 1 | #' Annotate polyA predictions using annotables 2 | #' 3 | #' @param polya_data polya data table to annotate 4 | #' @param genome valid genome from annotables to use for annotation 5 | #' 6 | #' @return a \link[tibble]{tibble} 7 | #' @export 8 | #' 9 | annotate_with_annotables <- function(polya_data,genome) { 10 | 11 | if ( !requireNamespace('annotables',quietly = TRUE) ) { 12 | stop("NanoTail requires 'annotables'. Please install it using 13 | install.packages('devtools') 14 | devtools::install_github('stephenturner/annotables')") 15 | } 16 | require(annotables) 17 | 18 | 19 | if (missing(polya_data)) { 20 | stop("Please provide data.frame with polyA predictions as an input.", 21 | call. = FALSE) 22 | } 23 | 24 | if (missing(genome)) { 25 | stop("Please provide valid genome from annotables package to use for annotation.", 26 | call. = FALSE) 27 | } 28 | 29 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data frame provided as an input (polya_data). Please provide valid input") 30 | 31 | tx_to_gene_table = paste0(genome,"_tx2gene") 32 | # Annotatio join, with last step to deduplicate annotations - remove duplicates which occurs due to e.g multiple entrez ids for each transcript 33 | polya_data_annotated <- polya_data %>% dplyr::left_join( eval(as.symbol(tx_to_gene_table)),by=c("ensembl_transcript_id_short" = "enstxp")) %>% dplyr::left_join(eval(as.name(genome)) %>% dplyr::group_by(ensgene) %>% dplyr::slice(1) %>% dplyr::ungroup()) 34 | 35 | #Explictly convert selected columns to factors (required for proper visualization) 36 | polya_data_annotated$biotype <- as.factor(polya_data_annotated$biotype) 37 | polya_data_annotated$strand <- as.factor(polya_data_annotated$strand) 38 | polya_data_annotated$chr <- as.factor(polya_data_annotated$chr) 39 | 40 | 41 | 42 | 43 | return(polya_data_annotated) 44 | } 45 | 46 | 47 | #' Title 48 | #' 49 | #' @param polya_data polya data table to annotate 50 | #' @param attributes_to_get what annotations should be retrieved. Default = c('external_gene_name','description','transcript_biotype') 51 | #' @param filters which column should be matched in the target mart 52 | #' @param mart_to_use mart object created with \link[biomaRt]{useMart} or \link[biomaRt]{useEnsembl} 53 | #' 54 | #' @return a \link[tibble]{tibble} 55 | #' @export 56 | annotate_with_biomart <- function(polya_data,attributes_to_get=c('ensembl_transcript_id','external_gene_name','description','transcript_biotype'),filters='ensembl_transcript_id',mart_to_use=NA) { 57 | 58 | if (missing(polya_data)) { 59 | stop("Please provide data.frame with polyA predictions as an input.", 60 | call. = FALSE) 61 | } 62 | 63 | if (missing(mart_to_use)) { 64 | stop("Please provide valid mart object", 65 | call. = FALSE) 66 | } 67 | 68 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data frame provided as an input (polya_data). Please provide valid input") 69 | assertthat::assert_that(class(mart_to_use)=="Mart",msg="Please provide valid mart object") 70 | assertthat::assert_that(length(attributes)>0,msg="please provide attributes") 71 | 72 | ensembl_ids = unique(polya_data$ensembl_transcript_id_short) 73 | ensembl_ids <- ensembl_ids[!is.na(ensembl_ids)] 74 | 75 | polya_data <- polya_data %>% dplyr::rename(ensembl_transcript_id = ensembl_transcript_id_short) 76 | 77 | # if using biomaRt version older than from Bioconductor 3.9, it cannot process more than 500 values at once 78 | if (packageVersion("biomaRt")<"2.40.0") { 79 | number_of_items <- length(ensembl_ids) 80 | annotation_data=data.frame() 81 | for (z in seq(1,number_of_items,by = 500)) { 82 | 83 | annotation_data_temp<-getBM(attributes=attributes_to_get, filters =filters, values = ensembl_ids[z:(z+499)], mart = mart_to_use) 84 | #print(annotation_data_temp) 85 | annotation_data<-rbind(annotation_data,annotation_data_temp) 86 | } 87 | } 88 | # since biomaRt 2.40 batch submission is possible 89 | else { 90 | annotation_data<-biomaRt::getBM(attributes=attributes_to_get, filters = filters, values = ensembl_ids, mart = mart_to_use) 91 | } 92 | polya_data_annotated <- polya_data %>% dplyr::left_join(annotation_data) 93 | 94 | return(polya_data_annotated) 95 | } 96 | 97 | 98 | #' Title 99 | #' 100 | #' @param columns_of_annotation which columns to use 101 | #' @param keytype whic keytype to use 102 | #' @param organism whic organism database to use 103 | #' @param polya_data polya data table to annotate 104 | #' 105 | #' @return a \link[tibble]{tibble} 106 | #' @export 107 | annotate_with_org_packages <- function(polya_data,columns_of_annotation=c("GENENAME","SYMBOL"),keytype='ENSEMBLTRANS',organism="mus_musculus") { 108 | 109 | if (missing(polya_data)) { 110 | stop("Please provide data.frame with polyA predictions as an input.", 111 | call. = FALSE) 112 | } 113 | 114 | 115 | # currently thos supported 116 | valid_org_packages = list("homo_sapiens" = "org.Hs.eg.db", "mus_musculus" = "org.Mm.eg.db","rattus_norvegicus" = "org.rn.eg.db","saccharomyces_cerevisiae" = "org.Sc.sgd.db","caenorhabditis_elegans" = "org.Ce.eg.db") 117 | 118 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data frame provided as an input (polya_data). Please provide valid input") 119 | assertthat::assert_that(length(columns_of_annotation)>0,msg="please provide columns of annotation") 120 | 121 | ensembl_ids = unique(polya_data$ensembl_transcript_id_short) 122 | ensembl_ids <- ensembl_ids[!is.na(ensembl_ids)] 123 | 124 | 125 | 126 | polya_data <- polya_data %>% dplyr::rename(!! rlang::sym(keytype) := ensembl_transcript_id_short) 127 | 128 | 129 | 130 | 131 | annotation_data<-AnnotationDbi::select(eval(parse(text = valid_org_packages[[organism]])),columns = columns_of_annotation,keytype = keytype,keys = ensembl_ids) 132 | 133 | polya_data_annotated <- polya_data %>% dplyr::left_join(annotation_data) 134 | 135 | return(polya_data_annotated) 136 | } 137 | 138 | -------------------------------------------------------------------------------- /R/read_polyA_data.R: -------------------------------------------------------------------------------- 1 | #' Read Single Nanopolish polyA preditions from file 2 | #' 3 | #' This is the basic function used to import output from \code{nanopolish polya} to R 4 | #' 5 | #' @param polya_path path to nanopolish output file 6 | #' @param sample_name sample name (optional), provided as a string. 7 | #' If specified will be included as an additional column sample_name. 8 | #' @param gencode are contig names GENCODE-compliant. 9 | #' Can get transcript names and ensembl_transcript IDs if reads were mapped for example to Gencode reference transcriptome 10 | #' 11 | #' @seealso \link{read_polya_multiple} 12 | #' 13 | #' @export 14 | #' 15 | #' @return a [tibble][tibble::tibble-package] with polya predictions 16 | #' 17 | read_polya_single <- function(polya_path, gencode = TRUE, sample_name = NA, dorado = FALSE) { 18 | # required asserts 19 | 20 | #check if parameters are provided 21 | if (missing(polya_path)) { 22 | stop("The path to polyA predictions (argument polya_path) is missing", 23 | call. = FALSE) 24 | } 25 | assertthat::assert_that(assertive::is_a_non_missing_nor_empty_string(polya_path),msg = "Empty string provided as an input. Please provide a polya_path as a string") 26 | assertthat::assert_that(assertive::is_existing_file(polya_path),msg=paste("File ",polya_path," not exists",sep="")) 27 | assertthat::assert_that(assertive::is_non_empty_file(polya_path),msg=paste("File ",polya_path," is empty",sep="")) 28 | assertthat::assert_that(assertive::is_a_bool(gencode),msg="Please provide TRUE/FALSE values for gencode parameter") 29 | 30 | message(paste0("Loading data from ",polya_path)) 31 | 32 | #integer64 set to "numeric" to avoid inconsistences when called from read_polya_multiple 33 | 34 | file_header <- read.table(polya_path,nrows=1) 35 | if (sum(grepl("pt",file_header))>0) { 36 | message("Seems like output from dorado. ") 37 | dorado = TRUE 38 | } 39 | 40 | polya_data <- data.table::fread(polya_path, integer64 = "numeric", data.table = F,header=TRUE,stringsAsFactors = FALSE,check.names = TRUE,showProgress = FALSE) %>% dplyr::as_tibble() 41 | if (!dorado) { 42 | polya_data <- polya_data %>% dplyr::mutate(polya_length = round(polya_length),dwell_time=transcript_start-polya_start) 43 | } 44 | else { 45 | polya_data <- polya_data %>% dplyr::mutate(polya_length = round(pt),dwell_time=NA) %>% dplyr::rename(contig=reference) 46 | } 47 | # change first column name 48 | colnames(polya_data)[1] <- "read_id" 49 | # transcript names, if mapping to gencode transcriptome 50 | if (gencode == TRUE) { 51 | transcript_names <- gsub(".*?\\|.*?\\|.*?\\|.*?\\|.*?\\|(.*?)\\|.*", "\\1", polya_data$contig) 52 | polya_data$transcript <- transcript_names 53 | ensembl_transcript_ids <- gsub("^(.*?)\\|.*\\|.*", "\\1", polya_data$contig) 54 | ensembl_transcript_ids_short <- gsub("(.*)\\..*", "\\1", ensembl_transcript_ids) # without version number 55 | polya_data$ensembl_transcript_id_full <- ensembl_transcript_ids 56 | polya_data$ensembl_transcript_id_short <- ensembl_transcript_ids_short 57 | } 58 | else { 59 | polya_data <- polya_data %>% dplyr::rename(transcript = contig) 60 | } 61 | 62 | if(!is.na(sample_name)) { 63 | # set sample_name (if was set) 64 | if (! "sample_name" %in% colnames(polya_data)) { 65 | warning("sample_name was provided in the input file. Overwriting with the provided one") 66 | } 67 | polya_data$sample_name = sample_name 68 | polya_data$sample_name <- as.factor(polya_data$sample_name) 69 | } 70 | 71 | return(polya_data) 72 | } 73 | 74 | 75 | # TODO Benchmark na lapply/for loop 76 | 77 | #' Reads multiple nanopolish polyA predictions at once 78 | #' 79 | #' This function can be used to load any number of files with polyA predictions with single invocation, 80 | #' allowing for metadata specification. 81 | #' 82 | #' 83 | #' @param samples_table data.frame or tibble containing samples metadata and paths to files. 84 | #' Should have at least two columns: \itemize{ 85 | #' \item polya_path - containing path to the polya predictions file 86 | #' \item sample_name - unique name of the sample 87 | #' } 88 | #' Additional columns can provide metadata which will be included in the final table 89 | #' @param ... - additional parameters to pass to read_polya_single(), like gencode=(TRUE/FALSE) 90 | #' 91 | #' @return a [tibble][tibble::tibble-package] containing polyA predictions for all specified samples, with metadata provided in samples_table 92 | #' stored as separate columns 93 | #' 94 | #' @seealso \link{read_polya_single} 95 | #' 96 | #' @export 97 | #' 98 | read_polya_multiple <- function(samples_table,...) { 99 | 100 | if (missing(samples_table)) { 101 | stop("Samples table argument is missing", 102 | call. = FALSE) 103 | } 104 | 105 | assertthat::assert_that(assertive::has_rows(samples_table),msg = "Empty data frame provided as an input (samples_table). Please provide samples_table describing data to load") 106 | assertthat::assert_that("polya_path" %in% colnames(samples_table),msg = "Samples table should contain at least polya_path and sample_name columns") 107 | assertthat::assert_that("sample_name" %in% colnames(samples_table),msg = "Samples table should contain at least polya_path and sample_name columns") 108 | 109 | samples_data <- samples_table %>% dplyr::as.tbl() %>% dplyr::mutate_if(is.character,as.factor) %>% dplyr::mutate(polya_path = as.character(polya_path)) %>% dplyr::group_by(sample_name) %>% dplyr::mutate(polya_contents=purrr::map(polya_path, function(x) read_polya_single(x))) %>% dplyr::ungroup() %>% dplyr::select(-polya_path) 110 | polya_data <- tidyr::unnest(samples_data) 111 | 112 | return(polya_data) 113 | } 114 | 115 | 116 | #' Removes reads which failed during Nanopolish polya processing 117 | #' 118 | #' Convenient function to quickly remove all reads failing during nanopolish polya processing 119 | #' 120 | #' @param polya_data output table from \link{read_polya_single} or \link{read_polya_multiple} 121 | #' 122 | #' @return a [tibble][tibble::tibble-package] with only reads having qc_tag=='PASS' 123 | #' 124 | #' @export 125 | #' 126 | #' @seealso \link{read_polya_single}, \link{read_polya_multiple} 127 | #' 128 | remove_failed_reads <- function(polya_data) { 129 | 130 | if (missing(polya_data)) { 131 | stop("Please provide data.frame with polyA predictions as an input.", 132 | call. = FALSE) 133 | } 134 | 135 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data frame provided as an input (polya_data). Please provide valid input") 136 | 137 | filtered_polya_data <- polya_data %>% dplyr::filter(qc_tag=='PASS') 138 | return(filtered_polya_data) 139 | } 140 | 141 | 142 | -------------------------------------------------------------------------------- /tests/testthat.R: -------------------------------------------------------------------------------- 1 | library(testthat) 2 | library(nanotail) 3 | 4 | 5 | #define testing environment for all tests: 6 | empty_polya_data_table = data.frame() 7 | qc_values <- c(rep("PASS",10),"ADAPTER","READ_FAILED_LOAD","SUFFCLIP","NOREGION") 8 | one_line_polya_data_table = data.frame(sample_name="wt1",group="wt",read_id="1234567890",polya_length=100,position=1,contig="contig",leader_start=1,adapter_start=1,polya_start=1,qc_tag="PASS",transcript="transcript") 9 | two_line_polya_data_table = data.frame(sample_name=c("wt1","mut1"),group=c("wt","mut"),read_id=c("1234567890","1234567891"),polya_length=c(100,20),position=rep(1,2),contig=rep("contig1",2),leader_start=rep(1,2),adapter_start=rep(100,2),polya_start=rep(1,2),qc_tag=rep("PASS",2),transcript=rep("transcript",2)) 10 | 11 | # generation of valid multi-sample polyA table (resembling output of read_polya_multiple()) 12 | number_of_reads_per_sample=20000 13 | number_of_transcripts_per_sample=50 14 | example_polya_table_sample1 = data.frame(sample_name="sample1",group="group1",read_id=paste0("sample1_",seq(1,number_of_reads_per_sample)),transcript=rep(paste0("transcript",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),polya_length=c(rlnorm(number_of_reads_per_sample,meanlog=4,sdlog=1)),qc_tag=qc_values[sample(14,20000,replace = TRUE)],position=sample(1000,number_of_reads_per_sample,replace=TRUE),leader_start=sample(seq(1,100),number_of_reads_per_sample,replace=TRUE),adapter_start=sample(seq(100,200),number_of_reads_per_sample,replace=TRUE),polya_start=sample(seq(200,500),number_of_reads_per_sample,replace=TRUE),transcript_start=sample(seq(1000,10000),number_of_reads_per_sample,replace=TRUE),read_rate=rnorm(n = number_of_reads_per_sample,mean = 70,sd=20)) 15 | example_polya_table_sample2 = data.frame(sample_name="sample2",group="group2",read_id=paste0("sample2_",seq(1,number_of_reads_per_sample)),transcript=rep(paste0("transcript",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),polya_length=c(rlnorm(number_of_reads_per_sample,meanlog=3,sdlog=1)),qc_tag=qc_values[sample(14,20000,replace = TRUE)],position=sample(1000,number_of_reads_per_sample,replace=TRUE),leader_start=sample(seq(1,100),number_of_reads_per_sample,replace=TRUE),adapter_start=sample(seq(100,200),number_of_reads_per_sample,replace=TRUE),polya_start=sample(seq(200,500),number_of_reads_per_sample,replace=TRUE),transcript_start=sample(seq(1000,10000),number_of_reads_per_sample,replace=TRUE),read_rate=rnorm(n = number_of_reads_per_sample,mean = 70,sd=20)) 16 | example_polya_table_sample3 = data.frame(sample_name="sample3",group="group3",read_id=paste0("sample2_",seq(1,number_of_reads_per_sample)),transcript=rep(paste0("transcript",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),polya_length=c(rlnorm(number_of_reads_per_sample,meanlog=3,sdlog=1)),qc_tag=qc_values[sample(14,20000,replace = TRUE)],position=sample(1000,number_of_reads_per_sample,replace=TRUE),leader_start=sample(seq(1,100),number_of_reads_per_sample,replace=TRUE),adapter_start=sample(seq(100,200),number_of_reads_per_sample,replace=TRUE),polya_start=sample(seq(200,500),number_of_reads_per_sample,replace=TRUE),transcript_start=sample(seq(1000,10000),number_of_reads_per_sample,replace=TRUE),read_rate=rnorm(n = number_of_reads_per_sample,mean = 70,sd=20)) 17 | example_valid_polya_table = rbind(example_polya_table_sample1,example_polya_table_sample2) 18 | example_valid_polya_table$group <- factor(example_valid_polya_table$group) 19 | example_valid_polya_table$sample_name <- factor(example_valid_polya_table$sample_name) 20 | example_valid_polya_table$qc_tag <- factor(example_valid_polya_table$qc_tag) 21 | example_valid_polya_table_3levels = rbind(example_polya_table_sample1,example_polya_table_sample2,example_polya_table_sample3) 22 | example_valid_polya_table_3levels$group <- factor(example_valid_polya_table_3levels$group) 23 | example_valid_polya_table_3levels$sample_name <- factor(example_valid_polya_table_3levels$sample_name) 24 | example_valid_polya_table_3levels$qc_tag <- factor(example_valid_polya_table_3levels$qc_tag) 25 | 26 | 27 | example_polya_table_mouse = data.frame(sample_name="sample1",group="group1",read_id=paste0("sample1_",seq(1,number_of_reads_per_sample)),transcript=rep(paste0("ENSMUST000001049",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),ensembl_transcript_id_short=rep(paste0("ENSMUST000001049",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),polya_length=c(rlnorm(number_of_reads_per_sample,meanlog=4,sdlog=1)),qc_tag=qc_values[sample(14,20000,replace = TRUE)],position=sample(1000,number_of_reads_per_sample,replace=TRUE),leader_start=sample(seq(1,100),number_of_reads_per_sample,replace=TRUE),adapter_start=sample(seq(100,200),number_of_reads_per_sample,replace=TRUE),polya_start=sample(seq(200,500),number_of_reads_per_sample,replace=TRUE),transcript_start=sample(seq(1000,10000),number_of_reads_per_sample,replace=TRUE),read_rate=rnorm(n = number_of_reads_per_sample,mean = 70,sd=20)) 28 | 29 | # generation of valid polyA tables to be saved to temp files (for testing or data import functions) 30 | example_polya_table_sample1 = data.frame(read_id=paste0("sample1_",seq(1,number_of_reads_per_sample)),contig=rep(paste0("transcript",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),polya_length=c(rlnorm(number_of_reads_per_sample,meanlog=4,sdlog=1)),qc_tag=qc_values[sample(14,20000,replace = TRUE)],position=sample(1000,number_of_reads_per_sample,replace=TRUE),leader_start=sample(seq(1,100),number_of_reads_per_sample,replace=TRUE),adapter_start=sample(seq(100,200),number_of_reads_per_sample,replace=TRUE),polya_start=sample(seq(200,500),number_of_reads_per_sample,replace=TRUE),transcript_start=sample(seq(1000,10000),number_of_reads_per_sample,replace=TRUE),read_rate=rnorm(n = number_of_reads_per_sample,mean = 70,sd=20)) 31 | example_polya_table_sample2 = data.frame(read_id=paste0("sample2_",seq(1,number_of_reads_per_sample)),contig=rep(paste0("transcript",seq(1,number_of_transcripts_per_sample)),number_of_reads_per_sample/number_of_transcripts_per_sample),polya_length=c(rlnorm(number_of_reads_per_sample,meanlog=3,sdlog=1)),qc_tag=qc_values[sample(14,20000,replace = TRUE)],position=sample(1000,number_of_reads_per_sample,replace=TRUE),leader_start=sample(seq(1,100),number_of_reads_per_sample,replace=TRUE),adapter_start=sample(seq(100,200),number_of_reads_per_sample,replace=TRUE),polya_start=sample(seq(200,500),number_of_reads_per_sample,replace=TRUE),transcript_start=sample(seq(1000,10000),number_of_reads_per_sample,replace=TRUE),read_rate=rnorm(n = number_of_reads_per_sample,mean = 70,sd=20)) 32 | 33 | sample_tempfile1 <- tempfile() 34 | sample_tempfile2 <- tempfile() 35 | 36 | write.table(example_polya_table_sample1,sample_tempfile1,quote = FALSE,sep = "\t",col.names = TRUE,row.names = FALSE) 37 | write.table(example_polya_table_sample2,sample_tempfile2,quote = FALSE,sep = "\t",col.names = TRUE,row.names = FALSE) 38 | 39 | example_sample_table <- data.frame(polya_path=c(sample_tempfile1,sample_tempfile2),sample_name=c("sample1","sample2"),group=c("group1","group2")) 40 | 41 | 42 | test_check("nanotail") 43 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # nanotail 2 | 3 | 4 | [![Build Status](https://travis-ci.org/smaegol/nanotail.svg?branch=master)](https://travis-ci.org/smaegol/nanotail) 5 | [![codecov](https://codecov.io/gh/smaegol/nanotail/branch/master/graph/badge.svg)](https://codecov.io/gh/smaegol/nanotail) 6 | [![DOI](https://zenodo.org/badge/176952175.svg)](https://zenodo.org/badge/latestdoi/176952175) 7 | [![Licence](https://img.shields.io/badge/licence-GPL--3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0.en.html) 8 | [![GitHub release](https://img.shields.io/github/release/smaegol/nanotail.svg) 9 | 10 | 11 | 12 | The goal of **NanoTail** is to provide a set of functions to manipulate and analyze data coming from polyA lengths estimations done using Oxford Nanopore Direct RNA sequencing and Nanopolish software. Existing solutions, like [Pipeline for testing shifts in poly(A) tail lengths estimated by nanopolish](https://github.com/nanoporetech/pipeline-polya-diff/) are, in our opinion, not sufficient for in-depth analysis of such data. 13 | The software is still in the development phase so all suggestions are welcome. Please also expect the code to be changed frequently, so use it with caution. 14 | 15 | ## Installation 16 | 17 | ### Prerequisities 18 | 19 | As `asserrtive` package was [removed from CRAN](https://cran.r-project.org/web/packages/assertive/index.html) it is currently impossible to install nanotail without prior manual installation of assertive package. We are working on exchanging the `assertive` package with its equivalent. However, for now, it is required to install all assertive packages manually: 20 | 21 | ```r 22 | install.packages("devtools") 23 | devtools::install_bitbucket("richierocks/assertive.properties") # install this one first as other packages depend on it 24 | devtools::install_bitbucket(c("richierocks/assertive.files", "richierocks/assertive.strings", "richierocks/assertive.numbers", "richierocks/assertive.matrices", "richierocks/assertive.sets", "richierocks/assertive.strings", "richierocks/assertive.models", "richierocks/assertive.reflection", "richierocks/assertive.types", "richierocks/assertive.datetimes", "richierocks/assertive.data", "richierocks/assertive.data.uk", "richierocks/assertive.data.us", "richierocks/assertive.code")) 25 | devtools::install_bitbucket("richierocks/assertive.properties") # install this one first as other packages depend on it 26 | devtools::install_bitbucket("richierocks/assertive") 27 | ``` 28 | 29 | 30 | 31 | Now you can install the developmental version of Nanotail with 32 | 33 | ``` r 34 | devtools::install_github('smaegol/nanotail') 35 | library(nanotail) 36 | ``` 37 | 38 | ## Input data 39 | 40 | NanoTail needs output from [nanopolish](https://github.com/jts/nanopolish) polya to work. It can read a single output file with `read_polya_single`: 41 | 42 | ``` r 43 | path <- "/location/of/nanopolish/output" 44 | polya_data <- read_polya_single(path) 45 | ``` 46 | 47 | It can also read multiple samples at once and associate any metadata with them. 48 | Let's assume we have performed an experiment, targeting one of the polyA polymerases. 2 replicates were sequenced for control samples, and 2 replicates sequenced for samples with mutant PAP, therefore after all analysis we have 4 files with [nanopolish](https://github.com/jts/nanopolish) polya output. To read all of them at once, we can use command `read_polya_multiple` and associate metadata using samples_table data.frame: 49 | 50 | ``` r 51 | samples_table <- data.frame(polya_path = c(path1,path2,path3,path4), 52 | sample_name =c("wt1","mu1","wt2","mut2"), 53 | group = c("wt","mut","wt","mut")) 54 | polya_data_multiple <- read_polya_multiple(samples_table) 55 | ``` 56 | 57 | To obtain nanopolish predictions one can use [Pipeline for calling poly(A) tail lengths from nanopore direct RNA data using nanopolish](https://github.com/nanoporetech/pipeline-polya-ng) 58 | 59 | ## Shiny App 60 | 61 | Once data are imported they can be processed in the R environment using NanoTail functions described below or, more convenient, the interactive Shiny app can be launched, allowing for easy exploration of obtained data. To launch the app for the data imported above: 62 | 63 | ``` r 64 | nanoTailApp(polya_table = polya_data_multiple) 65 | 66 | ``` 67 | 68 | ## Nanopolish output QC 69 | 70 | To get overall information about the output of NanoPolish polya analysis, please use `get_nanopolish_processing_info()` function. Obtained summary can be plotted using `plot_nanopolish_qc()`. Summary of the analysis is also shown in the *QC info* tab of the Shiny App. 71 | 72 | ![Nanopolish polya QC info shown in the Shiny App](https://github.com/smaegol/nanotail/blob/master/screenshots/screenshot_qc.png) 73 | 74 | 75 | ## Global distribution of polyA lengths 76 | 77 | Global distribution of polyA tails lengths can be plotted with `plot_polya_distribution()` function, which produces the density plot, allowing for comparison of the distribution of polyA lengths between samples. The same plot can be seen in the *Global polya distribution* tab of the Shiny App. 78 | 79 | ![Example global distribution density plot](https://github.com/smaegol/nanotail/blob/master/screenshots/screenshot_global.png) 80 | 81 | 82 | 83 | ## Statistical analysis of polyA predictions 84 | 85 | NanoTail is intended to analyze differential adenylation. For this purpose 3 statistical tests can be employed, allowing or comparison of polyA lengths of individual transcripts between selected conditions: 86 | * Wilcoxon rank-sum test ([Mann-Whitney U-test](https://en.wikipedia.org/wiki/Mann%E2%80%93Whitney_U_test)) 87 | * [Kolmogorov-Smirnov test](https://en.wikipedia.org/wiki/Kolmogorov%E2%80%93Smirnov_test) of the equality of distributions 88 | * [generalized linear model](https://en.wikipedia.org/wiki/Generalized_linear_model) with log(polya_length) as the response, and post-hoc Tukey test 89 | 90 | Differential adenylation analysis can be performed with the `calculate_polya_stats` function, or within the *Differential adenylation* tab in the Shiny App. 91 | 92 | ![Differential adenylation tab](https://github.com/smaegol/nanotail/blob/master/screenshots/screenshot_differential_adenylation.png) 93 | 94 | 95 | ## Differential expression analysis 96 | 97 | NanoTail provides also the possibility of very basic differential expression testing, using binomTest from the [edgeR](https://bioconductor.org/packages/release/bioc/html/edgeR.html) package. This functionality is still in the development and may not work as expected. To calculate differential expression please use `calculate_diff_exp_binom()` function or use Shiny App. 98 | 99 | ![Differential adenylation tab](https://github.com/smaegol/nanotail/blob/master/screenshots/screenshot_differential_expression.png) 100 | 101 | 102 | ## Citation 103 | 104 | Please cite NanoTail as: 105 | Krawczyk PS et al., NanoTail - R package for exploratory analysis of Nanopore Direct RNA based polyA lengths estimations 106 | 107 | Preprint in the preparation. 108 | 109 | 110 | ## TBD & plans 111 | 112 | * Import of polya predictions from software other then NanoPolish (poreplex,tailfindr,?) 113 | * Analysis of predictions based on genome-mapping (now only transcriptome-mapping is supported) 114 | * Annotation of results and enrichment analysis 115 | * Squiggle visualization of polyA tails 116 | 117 | ## Support 118 | 119 | Any issues connected with the NanoTail should be addressed to Pawel Krawczyk (p.krawczyk (at) ibb.waw.pl). 120 | -------------------------------------------------------------------------------- /R/polya_helper_functions.R: -------------------------------------------------------------------------------- 1 | #' Calculates geometric mean 2 | #' 3 | #' @param x input vector 4 | #' @param na.rm should NA values be removed? 5 | #' 6 | #' @return geometric mean of values provided as an input 7 | #' @export 8 | #' 9 | #' @examples 10 | #' a <- rnorm(100,33,5) 11 | #' gm_mean(a) 12 | gm_mean = function(x, na.rm=TRUE){ 13 | 14 | assertthat::assert_that(is.vector(x),msg = "Please provide numeric vector as an input for gm_mean") 15 | assertthat::assert_that(length(x)>0,msg = "Empty vector provided as input") 16 | assertthat::assert_that(assertive::is_a_bool(na.rm),msg = "Please provide boolean value for na.rm option") 17 | assertthat::assert_that(assertive::is_numeric(x),msg = "Please provide numeric vector as input") 18 | if (length(x)==1) { 19 | gm_mean=x[1] 20 | } 21 | else { 22 | gm_mean = exp(sum(log(x[x > 0]), na.rm=na.rm) / length(x)) 23 | } 24 | return(gm_mean) 25 | } 26 | 27 | 28 | 29 | #' Subsample a date frame 30 | #' 31 | #' Uses base subsetting and \link{sample} or dplyr \link[dplyr]{sample_n} or \link[dplyr]{sample_frac} to get the subset of the bigger data.frame or tibble 32 | #' 33 | #' @param input_table input table for subsampling 34 | #' @param groupingFactor grouping factor(s) 35 | #' @param subsample specify absolute number of rows or fraction to subsample from the data frame (group-wise) 36 | #' 37 | #' @return \link{tibble} 38 | #' @export 39 | #' 40 | subsample_table <- function(input_table,groupingFactor=NA,subsample=NA) 41 | { 42 | if (missing(input_table)) { 43 | stop("PolyA predictions are missing. Please provide a valid polya_data argument", 44 | call. = FALSE) 45 | } 46 | 47 | #assertthat::assert_that(is.numeric(reads_to_subsample),"Non-numeric argument for reads_to_subsample") 48 | 49 | assertthat::assert_that(!is.na(subsample),msg = "Please provide subsample option as an integer or fraction") 50 | 51 | if (isTRUE(round(subsample)==subsample)) { 52 | subsample_number = TRUE 53 | } 54 | else { 55 | subsample_number = FALSE 56 | } 57 | 58 | #if set to 0 - do not subsample - return input table)) 59 | if (subsample==0) { 60 | return(input_table) 61 | } 62 | else { 63 | if(!is.na(groupingFactor)) { 64 | # group, if required 65 | assertthat::assert_that(groupingFactor %in% colnames(input_table),msg=paste0(groupingFactor," is not a column of input dataset")) 66 | input_table <- input_table %>% group_by(.dots = groupingFactor) 67 | if (subsample_number) { 68 | input_table <- dplyr::sample_n(input_table,subsample) 69 | } 70 | else { 71 | input_table <- dplyr::sample_frac(input_table,subsample) 72 | } 73 | } 74 | else { 75 | if (any(class(polya_test_lymph2)=="grouped_df")) { 76 | grouping_var = dplyr::group_vars(input_table) 77 | #input_table %>% ungroup(input_table) 78 | } 79 | if (subsample_number) { 80 | input_table <- input_table[sample(nrow(input_table),subsample),] 81 | } 82 | else { 83 | input_table <- dplyr::sample_frac(input_table,subsample) 84 | } 85 | } 86 | 87 | return(input_table) 88 | } 89 | } 90 | 91 | 92 | 93 | 94 | 95 | axis_elements_size=15 96 | axis_titles_size=18 97 | #' Default theme for ggplot2-based plots in the NanoTail package 98 | #' @export 99 | nanotail_ggplot2_theme <- ggplot2::theme(axis.title = ggplot2::element_text(size=axis_titles_size),axis.text = ggplot2::element_text(size=axis_elements_size),legend.text = ggplot2::element_text(size=axis_elements_size),legend.title = ggplot2::element_text(size=axis_titles_size)) 100 | 101 | 102 | 103 | 104 | # based on https://community.rstudio.com/t/spread-with-multiple-value-columns/5378/2 105 | #' Spread multiple columns 106 | #' 107 | #' @param df data frame to apply spread on 108 | #' @param key as in \link{spread} 109 | #' @param value vector of columns to be taken as value for \link{spread} 110 | #' 111 | #' @return \link{tibble} 112 | #' @export 113 | #' 114 | spread_multiple <- function(df, key, value) { 115 | # quote key 116 | keyq <- rlang::enquo(key) 117 | # break value vector into quotes 118 | valueq <- rlang::enquo(value) 119 | s <- rlang::quos(!!valueq) 120 | df %>% tidyr::gather(variable, value, !!!s) %>% 121 | tidyr::unite(temp, !!keyq, variable) %>% 122 | tidyr::spread(temp, value) 123 | } 124 | 125 | 126 | #' Calculates scaling vector for virtual gel plotting 127 | #' 128 | #' @param input_data input polyA table for calculation of scaling factor (count of reads) 129 | #' @param groupingFactor for which factor calculate counts 130 | #' 131 | #' @return named vector 132 | #' @export 133 | #' 134 | calculate_scaling_vector_for_virutal_gel <- function(input_data,groupingFactor) { 135 | scaling_vector <- summarize_polya(input_data,transcript_id_column = groupingFactor) %>% dplyr::select(!!rlang::sym(groupingFactor),counts) %>% tibble::deframe() 136 | return(scaling_vector) 137 | } 138 | 139 | 140 | 141 | StatMedianLine <- ggplot2::ggproto("StatMedianLine", ggplot2::Stat, 142 | compute_group = function(data, scales) { 143 | transform(data, yintercept=median(y)) 144 | }, 145 | required_aes = c("x", "y") 146 | ) 147 | 148 | #' Helper function for calculating median stat for violin/boxpolot ggplot plots 149 | #' 150 | #' @param mapping 151 | #' @param data 152 | #' @param geom 153 | #' @param position 154 | #' @param na.rm 155 | #' @param show.legend 156 | #' @param inherit.aes 157 | #' @param ... 158 | #' 159 | #' @return 160 | #' @export 161 | #' 162 | stat_median_line <- function(mapping = NULL, data = NULL, geom = "hline", 163 | position = "identity", na.rm = FALSE, show.legend = NA, 164 | inherit.aes = TRUE, ...) { 165 | ggplot2::layer( 166 | stat = StatMedianLine, data = data, mapping = mapping, geom = geom, 167 | position = position, show.legend = show.legend, inherit.aes = inherit.aes, 168 | params = list(na.rm = na.rm, ...) 169 | ) 170 | } 171 | 172 | 173 | #' Function calculating statistical mode of given vector. 174 | #' 175 | #' @param x [character] data for which the most frequent value is to be calculated 176 | #' (polya_data column with the lengths of the poly(A) tails) 177 | #' 178 | #' @param method [character] "density"/"value"; density mode is computed 179 | #' by default. 180 | #' 181 | #' @param na.rm [boolean] parameter defining whether to remove missing values or 182 | #' not. By a default set to false 183 | #' 184 | #' @return statistical mode of given vector. 185 | #' @export 186 | #' 187 | #' @examples 188 | #' \dontrun{ 189 | #' 190 | #' getmode(x = polya_data$tail_length, 191 | #' method = "density", 192 | #' na.rm = FALSE) 193 | #' 194 | #' } 195 | #' 196 | getmode <- function(x, method ="density", na.rm = FALSE) { 197 | x <- unlist(x) 198 | if (na.rm) { 199 | x <- x[!is.na(x)] 200 | } 201 | 202 | if (method %in% c("value", "density", "") | is.na(method)) { 203 | # Return actual mode (from the real values in dataset) 204 | if (method %in% c("density", "")) { 205 | 206 | # Return density mode for normalized data - only for numeric!) 207 | d <- density(x) 208 | return(d$x[d$y==max(d$y)]) 209 | #return(modeest::mlv(x,na.rm=TRUE,method="parzen", abc=T)) #in some cases this method produces weird output 210 | 211 | } else if (method %in% c("value")) { 212 | 213 | uniqx <- unique(x) 214 | n <- length(uniqx) 215 | freqx <- tabulate(match(x, uniqx)) 216 | modex <- freqx == max(freqx) 217 | return(uniqx[which(modex)]) 218 | } 219 | } 220 | } -------------------------------------------------------------------------------- /tests/testthat/test-polya_plots.R: -------------------------------------------------------------------------------- 1 | context("Test plotting functions") 2 | 3 | library(assertthat) 4 | library(testthat) 5 | library(assertive) 6 | 7 | 8 | test_that("valid parameters are provided for plot_polya_distribution()",{ 9 | 10 | expect_error(plot_polya_distribution()) 11 | #expect_silent(plot_polya_distribution(example_valid_polya_table)) 12 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "non-existent_group")) 13 | #expect_silent(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group")) 14 | #expect_silent(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group2")) 15 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="non-existent_group")) 16 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",condition2="group1",condition1="non-existent_group")) 17 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group1")) 18 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",scale_x_limit_low = 0)) 19 | #expect_silent(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",scale_x_limit_low = 0,scale_x_limit_high = 200)) 20 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",scale_x_limit_low = "0",scale_x_limit_high = 200)) 21 | expect_error(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",scale_x_limit_low = 0,scale_x_limit_high = "200")) 22 | expect_warning(plot_polya_distribution(example_valid_polya_table,groupingFactor = "group",scale_x_limit_low = 0,scale_x_limit_high = 200,color_palette = "non_existent_palette"),"Please provide valid color palette",all = FALSE,fixed=TRUE) 23 | }) 24 | 25 | test_that("valid parameters are provided for plot_polya_boxplot()",{ 26 | 27 | expect_error(plot_polya_boxplot()) 28 | expect_error(plot_polya_boxplot(example_valid_polya_table)) 29 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "non-existent_group")) 30 | expect_silent(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group")) 31 | expect_silent(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group2")) 32 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="non-existent_group")) 33 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",condition2="group1",condition1="non-existent_group")) 34 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group1")) 35 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",scale_y_limit_low = 0)) 36 | expect_silent(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",scale_y_limit_low = 0,scale_y_limit_high = 200)) 37 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",scale_y_limit_low = "0",scale_y_limit_high = 200)) 38 | expect_error(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",scale_y_limit_low = 0,scale_y_limit_high = "200")) 39 | expect_warning(plot_polya_boxplot(example_valid_polya_table,groupingFactor = "group",scale_y_limit_low = 0,scale_y_limit_high = 200,color_palette = "non_existent_palette"),"Please provide valid color palette",all = FALSE,fixed=TRUE) 40 | }) 41 | 42 | 43 | test_that("valid parameters are provided for plot_counts_scatter()",{ 44 | 45 | summarized_example_valid_polya_table <- summarize_polya(example_valid_polya_table,summary_factors = "group") 46 | 47 | expect_error(plot_counts_scatter()) 48 | expect_error(plot_counts_scatter(example_valid_polya_table)) 49 | expect_error(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group")) 50 | expect_warning(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group2"),"Ignoring unknown aesthetics: text",fixed=TRUE) 51 | expect_error(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="non-existent_group")) 52 | expect_error(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition2="group1",condition1="non-existent_group")) 53 | expect_error(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group1")) 54 | expect_error(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",max_counts = 0)) 55 | expect_warning(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group2",max_counts=200),"Ignoring unknown aesthetics: text",fixed=TRUE) 56 | expect_error(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group2",max_counts="200")) 57 | expect_warning(plot_counts_scatter(summarized_example_valid_polya_table,groupingFactor = "group",condition1="group1",condition2="group2",max_counts=200,color_palette = "non_existent_palette"),"Please provide valid color palette",all = FALSE,fixed=TRUE) 58 | 59 | }) 60 | 61 | 62 | test_that("valid parameters are provided for plot_nanopolish_qc()",{ 63 | 64 | nanopolish_qc_of_example_valid_polya_table <- get_nanopolish_processing_info(example_valid_polya_table) 65 | grouped_nanopolish_qc_of_example_valid_polya_table <- get_nanopolish_processing_info(example_valid_polya_table,grouping_factor = "sample_name") 66 | 67 | expect_error(plot_nanopolish_qc()) 68 | expect_error(plot_nanopolish_qc(example_valid_polya_table)) 69 | expect_error(plot_nanopolish_qc(empty_polya_data_table)) 70 | expect_silent(plot_nanopolish_qc(nanopolish_qc_of_example_valid_polya_table)) 71 | expect_silent(plot_nanopolish_qc(nanopolish_qc_of_example_valid_polya_table,frequency = FALSE)) 72 | expect_error(plot_nanopolish_qc(nanopolish_qc_of_example_valid_polya_table,frequency = "FALSE")) 73 | expect_warning(plot_nanopolish_qc(grouped_nanopolish_qc_of_example_valid_polya_table,color_palette = "non_existent_palette"),"Please provide valid color palette",all = FALSE,fixed=TRUE) 74 | }) 75 | 76 | 77 | 78 | test_that("valid parameters are provided for plot_volcano()",{ 79 | 80 | binom_test_output_of_example_valid_polya_table <- calculate_diff_exp_binom(example_valid_polya_table,grouping_factor = "group",condition1 = "group1",condition2 = "group2") 81 | expect_error 82 | expect_error(plot_volcano()) 83 | expect_error(plot_volcano(empty_polya_data_table)) 84 | expect_silent(plot_volcano(binom_test_output_of_example_valid_polya_table)) 85 | expect_error(plot_volcano(binom_test_output_of_example_valid_polya_table %>% dplyr::select(-fold_change))) 86 | expect_error(plot_volcano(binom_test_output_of_example_valid_polya_table %>% dplyr::select(-padj))) 87 | expect_error(plot_volcano(binom_test_output_of_example_valid_polya_table %>% dplyr::select(-significance))) 88 | expect_warning(plot_volcano(binom_test_output_of_example_valid_polya_table,color_palette = "non_existent_palette"),"Please provide valid color palette",all = FALSE,fixed=TRUE) 89 | }) 90 | 91 | test_that("valid parameters are provided for plot_MA()",{ 92 | 93 | binom_test_output_of_example_valid_polya_table <- calculate_diff_exp_binom(example_valid_polya_table,grouping_factor = "group",condition1 = "group1",condition2 = "group2") 94 | expect_error(plot_MA()) 95 | expect_error(plot_MA(example_valid_polya_table)) 96 | expect_error(plot_MA(empty_polya_data_table)) 97 | expect_silent(plot_MA(binom_test_output_of_example_valid_polya_table)) 98 | expect_error(plot_MA(binom_test_output_of_example_valid_polya_table %>% dplyr::select(-fold_change))) 99 | expect_error(plot_MA(binom_test_output_of_example_valid_polya_table %>% dplyr::select(-mean_expr))) 100 | expect_error(plot_MA(binom_test_output_of_example_valid_polya_table %>% dplyr::select(-significance))) 101 | expect_warning(plot_MA(binom_test_output_of_example_valid_polya_table,color_palette = "non_existent_palette"),"Please provide valid color palette",all = FALSE,fixed=TRUE) 102 | }) 103 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | -------------------------------------------------------------------------------- /LICENSE.md: -------------------------------------------------------------------------------- 1 | GNU General Public License 2 | ========================== 3 | 4 | _Version 3, 29 June 2007_ 5 | _Copyright © 2007 Free Software Foundation, Inc. <>_ 6 | 7 | Everyone is permitted to copy and distribute verbatim copies of this license 8 | document, but changing it is not allowed. 9 | 10 | ## Preamble 11 | 12 | The GNU General Public License is a free, copyleft license for software and other 13 | kinds of works. 14 | 15 | The licenses for most software and other practical works are designed to take away 16 | your freedom to share and change the works. By contrast, the GNU General Public 17 | License is intended to guarantee your freedom to share and change all versions of a 18 | program--to make sure it remains free software for all its users. We, the Free 19 | Software Foundation, use the GNU General Public License for most of our software; it 20 | applies also to any other work released this way by its authors. You can apply it to 21 | your programs, too. 22 | 23 | When we speak of free software, we are referring to freedom, not price. Our General 24 | Public Licenses are designed to make sure that you have the freedom to distribute 25 | copies of free software (and charge for them if you wish), that you receive source 26 | code or can get it if you want it, that you can change the software or use pieces of 27 | it in new free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you these rights or 30 | asking you to surrender the rights. Therefore, you have certain responsibilities if 31 | you distribute copies of the software, or if you modify it: responsibilities to 32 | respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether gratis or for a fee, 35 | you must pass on to the recipients the same freedoms that you received. You must make 36 | sure that they, too, receive or can get the source code. And you must show them these 37 | terms so they know their rights. 38 | 39 | Developers that use the GNU GPL protect your rights with two steps: **(1)** assert 40 | copyright on the software, and **(2)** offer you this License giving you legal permission 41 | to copy, distribute and/or modify it. 42 | 43 | For the developers' and authors' protection, the GPL clearly explains that there is 44 | no warranty for this free software. For both users' and authors' sake, the GPL 45 | requires that modified versions be marked as changed, so that their problems will not 46 | be attributed erroneously to authors of previous versions. 47 | 48 | Some devices are designed to deny users access to install or run modified versions of 49 | the software inside them, although the manufacturer can do so. This is fundamentally 50 | incompatible with the aim of protecting users' freedom to change the software. The 51 | systematic pattern of such abuse occurs in the area of products for individuals to 52 | use, which is precisely where it is most unacceptable. Therefore, we have designed 53 | this version of the GPL to prohibit the practice for those products. If such problems 54 | arise substantially in other domains, we stand ready to extend this provision to 55 | those domains in future versions of the GPL, as needed to protect the freedom of 56 | users. 57 | 58 | Finally, every program is threatened constantly by software patents. States should 59 | not allow patents to restrict development and use of software on general-purpose 60 | computers, but in those that do, we wish to avoid the special danger that patents 61 | applied to a free program could make it effectively proprietary. To prevent this, the 62 | GPL assures that patents cannot be used to render the program non-free. 63 | 64 | The precise terms and conditions for copying, distribution and modification follow. 65 | 66 | ## TERMS AND CONDITIONS 67 | 68 | ### 0. Definitions 69 | 70 | “This License” refers to version 3 of the GNU General Public License. 71 | 72 | “Copyright” also means copyright-like laws that apply to other kinds of 73 | works, such as semiconductor masks. 74 | 75 | “The Program” refers to any copyrightable work licensed under this 76 | License. Each licensee is addressed as “you”. “Licensees” and 77 | “recipients” may be individuals or organizations. 78 | 79 | To “modify” a work means to copy from or adapt all or part of the work in 80 | a fashion requiring copyright permission, other than the making of an exact copy. The 81 | resulting work is called a “modified version” of the earlier work or a 82 | work “based on” the earlier work. 83 | 84 | A “covered work” means either the unmodified Program or a work based on 85 | the Program. 86 | 87 | To “propagate” a work means to do anything with it that, without 88 | permission, would make you directly or secondarily liable for infringement under 89 | applicable copyright law, except executing it on a computer or modifying a private 90 | copy. Propagation includes copying, distribution (with or without modification), 91 | making available to the public, and in some countries other activities as well. 92 | 93 | To “convey” a work means any kind of propagation that enables other 94 | parties to make or receive copies. Mere interaction with a user through a computer 95 | network, with no transfer of a copy, is not conveying. 96 | 97 | An interactive user interface displays “Appropriate Legal Notices” to the 98 | extent that it includes a convenient and prominently visible feature that **(1)** 99 | displays an appropriate copyright notice, and **(2)** tells the user that there is no 100 | warranty for the work (except to the extent that warranties are provided), that 101 | licensees may convey the work under this License, and how to view a copy of this 102 | License. If the interface presents a list of user commands or options, such as a 103 | menu, a prominent item in the list meets this criterion. 104 | 105 | ### 1. Source Code 106 | 107 | The “source code” for a work means the preferred form of the work for 108 | making modifications to it. “Object code” means any non-source form of a 109 | work. 110 | 111 | A “Standard Interface” means an interface that either is an official 112 | standard defined by a recognized standards body, or, in the case of interfaces 113 | specified for a particular programming language, one that is widely used among 114 | developers working in that language. 115 | 116 | The “System Libraries” of an executable work include anything, other than 117 | the work as a whole, that **(a)** is included in the normal form of packaging a Major 118 | Component, but which is not part of that Major Component, and **(b)** serves only to 119 | enable use of the work with that Major Component, or to implement a Standard 120 | Interface for which an implementation is available to the public in source code form. 121 | A “Major Component”, in this context, means a major essential component 122 | (kernel, window system, and so on) of the specific operating system (if any) on which 123 | the executable work runs, or a compiler used to produce the work, or an object code 124 | interpreter used to run it. 125 | 126 | The “Corresponding Source” for a work in object code form means all the 127 | source code needed to generate, install, and (for an executable work) run the object 128 | code and to modify the work, including scripts to control those activities. However, 129 | it does not include the work's System Libraries, or general-purpose tools or 130 | generally available free programs which are used unmodified in performing those 131 | activities but which are not part of the work. For example, Corresponding Source 132 | includes interface definition files associated with source files for the work, and 133 | the source code for shared libraries and dynamically linked subprograms that the work 134 | is specifically designed to require, such as by intimate data communication or 135 | control flow between those subprograms and other parts of the work. 136 | 137 | The Corresponding Source need not include anything that users can regenerate 138 | automatically from other parts of the Corresponding Source. 139 | 140 | The Corresponding Source for a work in source code form is that same work. 141 | 142 | ### 2. Basic Permissions 143 | 144 | All rights granted under this License are granted for the term of copyright on the 145 | Program, and are irrevocable provided the stated conditions are met. This License 146 | explicitly affirms your unlimited permission to run the unmodified Program. The 147 | output from running a covered work is covered by this License only if the output, 148 | given its content, constitutes a covered work. This License acknowledges your rights 149 | of fair use or other equivalent, as provided by copyright law. 150 | 151 | You may make, run and propagate covered works that you do not convey, without 152 | conditions so long as your license otherwise remains in force. You may convey covered 153 | works to others for the sole purpose of having them make modifications exclusively 154 | for you, or provide you with facilities for running those works, provided that you 155 | comply with the terms of this License in conveying all material for which you do not 156 | control copyright. Those thus making or running the covered works for you must do so 157 | exclusively on your behalf, under your direction and control, on terms that prohibit 158 | them from making any copies of your copyrighted material outside their relationship 159 | with you. 160 | 161 | Conveying under any other circumstances is permitted solely under the conditions 162 | stated below. Sublicensing is not allowed; section 10 makes it unnecessary. 163 | 164 | ### 3. Protecting Users' Legal Rights From Anti-Circumvention Law 165 | 166 | No covered work shall be deemed part of an effective technological measure under any 167 | applicable law fulfilling obligations under article 11 of the WIPO copyright treaty 168 | adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention 169 | of such measures. 170 | 171 | When you convey a covered work, you waive any legal power to forbid circumvention of 172 | technological measures to the extent such circumvention is effected by exercising 173 | rights under this License with respect to the covered work, and you disclaim any 174 | intention to limit operation or modification of the work as a means of enforcing, 175 | against the work's users, your or third parties' legal rights to forbid circumvention 176 | of technological measures. 177 | 178 | ### 4. Conveying Verbatim Copies 179 | 180 | You may convey verbatim copies of the Program's source code as you receive it, in any 181 | medium, provided that you conspicuously and appropriately publish on each copy an 182 | appropriate copyright notice; keep intact all notices stating that this License and 183 | any non-permissive terms added in accord with section 7 apply to the code; keep 184 | intact all notices of the absence of any warranty; and give all recipients a copy of 185 | this License along with the Program. 186 | 187 | You may charge any price or no price for each copy that you convey, and you may offer 188 | support or warranty protection for a fee. 189 | 190 | ### 5. Conveying Modified Source Versions 191 | 192 | You may convey a work based on the Program, or the modifications to produce it from 193 | the Program, in the form of source code under the terms of section 4, provided that 194 | you also meet all of these conditions: 195 | 196 | * **a)** The work must carry prominent notices stating that you modified it, and giving a 197 | relevant date. 198 | * **b)** The work must carry prominent notices stating that it is released under this 199 | License and any conditions added under section 7. This requirement modifies the 200 | requirement in section 4 to “keep intact all notices”. 201 | * **c)** You must license the entire work, as a whole, under this License to anyone who 202 | comes into possession of a copy. This License will therefore apply, along with any 203 | applicable section 7 additional terms, to the whole of the work, and all its parts, 204 | regardless of how they are packaged. This License gives no permission to license the 205 | work in any other way, but it does not invalidate such permission if you have 206 | separately received it. 207 | * **d)** If the work has interactive user interfaces, each must display Appropriate Legal 208 | Notices; however, if the Program has interactive interfaces that do not display 209 | Appropriate Legal Notices, your work need not make them do so. 210 | 211 | A compilation of a covered work with other separate and independent works, which are 212 | not by their nature extensions of the covered work, and which are not combined with 213 | it such as to form a larger program, in or on a volume of a storage or distribution 214 | medium, is called an “aggregate” if the compilation and its resulting 215 | copyright are not used to limit the access or legal rights of the compilation's users 216 | beyond what the individual works permit. Inclusion of a covered work in an aggregate 217 | does not cause this License to apply to the other parts of the aggregate. 218 | 219 | ### 6. Conveying Non-Source Forms 220 | 221 | You may convey a covered work in object code form under the terms of sections 4 and 222 | 5, provided that you also convey the machine-readable Corresponding Source under the 223 | terms of this License, in one of these ways: 224 | 225 | * **a)** Convey the object code in, or embodied in, a physical product (including a 226 | physical distribution medium), accompanied by the Corresponding Source fixed on a 227 | durable physical medium customarily used for software interchange. 228 | * **b)** Convey the object code in, or embodied in, a physical product (including a 229 | physical distribution medium), accompanied by a written offer, valid for at least 230 | three years and valid for as long as you offer spare parts or customer support for 231 | that product model, to give anyone who possesses the object code either **(1)** a copy of 232 | the Corresponding Source for all the software in the product that is covered by this 233 | License, on a durable physical medium customarily used for software interchange, for 234 | a price no more than your reasonable cost of physically performing this conveying of 235 | source, or **(2)** access to copy the Corresponding Source from a network server at no 236 | charge. 237 | * **c)** Convey individual copies of the object code with a copy of the written offer to 238 | provide the Corresponding Source. This alternative is allowed only occasionally and 239 | noncommercially, and only if you received the object code with such an offer, in 240 | accord with subsection 6b. 241 | * **d)** Convey the object code by offering access from a designated place (gratis or for 242 | a charge), and offer equivalent access to the Corresponding Source in the same way 243 | through the same place at no further charge. You need not require recipients to copy 244 | the Corresponding Source along with the object code. If the place to copy the object 245 | code is a network server, the Corresponding Source may be on a different server 246 | (operated by you or a third party) that supports equivalent copying facilities, 247 | provided you maintain clear directions next to the object code saying where to find 248 | the Corresponding Source. Regardless of what server hosts the Corresponding Source, 249 | you remain obligated to ensure that it is available for as long as needed to satisfy 250 | these requirements. 251 | * **e)** Convey the object code using peer-to-peer transmission, provided you inform 252 | other peers where the object code and Corresponding Source of the work are being 253 | offered to the general public at no charge under subsection 6d. 254 | 255 | A separable portion of the object code, whose source code is excluded from the 256 | Corresponding Source as a System Library, need not be included in conveying the 257 | object code work. 258 | 259 | A “User Product” is either **(1)** a “consumer product”, which 260 | means any tangible personal property which is normally used for personal, family, or 261 | household purposes, or **(2)** anything designed or sold for incorporation into a 262 | dwelling. In determining whether a product is a consumer product, doubtful cases 263 | shall be resolved in favor of coverage. For a particular product received by a 264 | particular user, “normally used” refers to a typical or common use of 265 | that class of product, regardless of the status of the particular user or of the way 266 | in which the particular user actually uses, or expects or is expected to use, the 267 | product. A product is a consumer product regardless of whether the product has 268 | substantial commercial, industrial or non-consumer uses, unless such uses represent 269 | the only significant mode of use of the product. 270 | 271 | “Installation Information” for a User Product means any methods, 272 | procedures, authorization keys, or other information required to install and execute 273 | modified versions of a covered work in that User Product from a modified version of 274 | its Corresponding Source. The information must suffice to ensure that the continued 275 | functioning of the modified object code is in no case prevented or interfered with 276 | solely because modification has been made. 277 | 278 | If you convey an object code work under this section in, or with, or specifically for 279 | use in, a User Product, and the conveying occurs as part of a transaction in which 280 | the right of possession and use of the User Product is transferred to the recipient 281 | in perpetuity or for a fixed term (regardless of how the transaction is 282 | characterized), the Corresponding Source conveyed under this section must be 283 | accompanied by the Installation Information. But this requirement does not apply if 284 | neither you nor any third party retains the ability to install modified object code 285 | on the User Product (for example, the work has been installed in ROM). 286 | 287 | The requirement to provide Installation Information does not include a requirement to 288 | continue to provide support service, warranty, or updates for a work that has been 289 | modified or installed by the recipient, or for the User Product in which it has been 290 | modified or installed. Access to a network may be denied when the modification itself 291 | materially and adversely affects the operation of the network or violates the rules 292 | and protocols for communication across the network. 293 | 294 | Corresponding Source conveyed, and Installation Information provided, in accord with 295 | this section must be in a format that is publicly documented (and with an 296 | implementation available to the public in source code form), and must require no 297 | special password or key for unpacking, reading or copying. 298 | 299 | ### 7. Additional Terms 300 | 301 | “Additional permissions” are terms that supplement the terms of this 302 | License by making exceptions from one or more of its conditions. Additional 303 | permissions that are applicable to the entire Program shall be treated as though they 304 | were included in this License, to the extent that they are valid under applicable 305 | law. If additional permissions apply only to part of the Program, that part may be 306 | used separately under those permissions, but the entire Program remains governed by 307 | this License without regard to the additional permissions. 308 | 309 | When you convey a copy of a covered work, you may at your option remove any 310 | additional permissions from that copy, or from any part of it. (Additional 311 | permissions may be written to require their own removal in certain cases when you 312 | modify the work.) You may place additional permissions on material, added by you to a 313 | covered work, for which you have or can give appropriate copyright permission. 314 | 315 | Notwithstanding any other provision of this License, for material you add to a 316 | covered work, you may (if authorized by the copyright holders of that material) 317 | supplement the terms of this License with terms: 318 | 319 | * **a)** Disclaiming warranty or limiting liability differently from the terms of 320 | sections 15 and 16 of this License; or 321 | * **b)** Requiring preservation of specified reasonable legal notices or author 322 | attributions in that material or in the Appropriate Legal Notices displayed by works 323 | containing it; or 324 | * **c)** Prohibiting misrepresentation of the origin of that material, or requiring that 325 | modified versions of such material be marked in reasonable ways as different from the 326 | original version; or 327 | * **d)** Limiting the use for publicity purposes of names of licensors or authors of the 328 | material; or 329 | * **e)** Declining to grant rights under trademark law for use of some trade names, 330 | trademarks, or service marks; or 331 | * **f)** Requiring indemnification of licensors and authors of that material by anyone 332 | who conveys the material (or modified versions of it) with contractual assumptions of 333 | liability to the recipient, for any liability that these contractual assumptions 334 | directly impose on those licensors and authors. 335 | 336 | All other non-permissive additional terms are considered “further 337 | restrictions” within the meaning of section 10. If the Program as you received 338 | it, or any part of it, contains a notice stating that it is governed by this License 339 | along with a term that is a further restriction, you may remove that term. If a 340 | license document contains a further restriction but permits relicensing or conveying 341 | under this License, you may add to a covered work material governed by the terms of 342 | that license document, provided that the further restriction does not survive such 343 | relicensing or conveying. 344 | 345 | If you add terms to a covered work in accord with this section, you must place, in 346 | the relevant source files, a statement of the additional terms that apply to those 347 | files, or a notice indicating where to find the applicable terms. 348 | 349 | Additional terms, permissive or non-permissive, may be stated in the form of a 350 | separately written license, or stated as exceptions; the above requirements apply 351 | either way. 352 | 353 | ### 8. Termination 354 | 355 | You may not propagate or modify a covered work except as expressly provided under 356 | this License. Any attempt otherwise to propagate or modify it is void, and will 357 | automatically terminate your rights under this License (including any patent licenses 358 | granted under the third paragraph of section 11). 359 | 360 | However, if you cease all violation of this License, then your license from a 361 | particular copyright holder is reinstated **(a)** provisionally, unless and until the 362 | copyright holder explicitly and finally terminates your license, and **(b)** permanently, 363 | if the copyright holder fails to notify you of the violation by some reasonable means 364 | prior to 60 days after the cessation. 365 | 366 | Moreover, your license from a particular copyright holder is reinstated permanently 367 | if the copyright holder notifies you of the violation by some reasonable means, this 368 | is the first time you have received notice of violation of this License (for any 369 | work) from that copyright holder, and you cure the violation prior to 30 days after 370 | your receipt of the notice. 371 | 372 | Termination of your rights under this section does not terminate the licenses of 373 | parties who have received copies or rights from you under this License. If your 374 | rights have been terminated and not permanently reinstated, you do not qualify to 375 | receive new licenses for the same material under section 10. 376 | 377 | ### 9. Acceptance Not Required for Having Copies 378 | 379 | You are not required to accept this License in order to receive or run a copy of the 380 | Program. Ancillary propagation of a covered work occurring solely as a consequence of 381 | using peer-to-peer transmission to receive a copy likewise does not require 382 | acceptance. However, nothing other than this License grants you permission to 383 | propagate or modify any covered work. These actions infringe copyright if you do not 384 | accept this License. Therefore, by modifying or propagating a covered work, you 385 | indicate your acceptance of this License to do so. 386 | 387 | ### 10. Automatic Licensing of Downstream Recipients 388 | 389 | Each time you convey a covered work, the recipient automatically receives a license 390 | from the original licensors, to run, modify and propagate that work, subject to this 391 | License. You are not responsible for enforcing compliance by third parties with this 392 | License. 393 | 394 | An “entity transaction” is a transaction transferring control of an 395 | organization, or substantially all assets of one, or subdividing an organization, or 396 | merging organizations. If propagation of a covered work results from an entity 397 | transaction, each party to that transaction who receives a copy of the work also 398 | receives whatever licenses to the work the party's predecessor in interest had or 399 | could give under the previous paragraph, plus a right to possession of the 400 | Corresponding Source of the work from the predecessor in interest, if the predecessor 401 | has it or can get it with reasonable efforts. 402 | 403 | You may not impose any further restrictions on the exercise of the rights granted or 404 | affirmed under this License. For example, you may not impose a license fee, royalty, 405 | or other charge for exercise of rights granted under this License, and you may not 406 | initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging 407 | that any patent claim is infringed by making, using, selling, offering for sale, or 408 | importing the Program or any portion of it. 409 | 410 | ### 11. Patents 411 | 412 | A “contributor” is a copyright holder who authorizes use under this 413 | License of the Program or a work on which the Program is based. The work thus 414 | licensed is called the contributor's “contributor version”. 415 | 416 | A contributor's “essential patent claims” are all patent claims owned or 417 | controlled by the contributor, whether already acquired or hereafter acquired, that 418 | would be infringed by some manner, permitted by this License, of making, using, or 419 | selling its contributor version, but do not include claims that would be infringed 420 | only as a consequence of further modification of the contributor version. For 421 | purposes of this definition, “control” includes the right to grant patent 422 | sublicenses in a manner consistent with the requirements of this License. 423 | 424 | Each contributor grants you a non-exclusive, worldwide, royalty-free patent license 425 | under the contributor's essential patent claims, to make, use, sell, offer for sale, 426 | import and otherwise run, modify and propagate the contents of its contributor 427 | version. 428 | 429 | In the following three paragraphs, a “patent license” is any express 430 | agreement or commitment, however denominated, not to enforce a patent (such as an 431 | express permission to practice a patent or covenant not to sue for patent 432 | infringement). To “grant” such a patent license to a party means to make 433 | such an agreement or commitment not to enforce a patent against the party. 434 | 435 | If you convey a covered work, knowingly relying on a patent license, and the 436 | Corresponding Source of the work is not available for anyone to copy, free of charge 437 | and under the terms of this License, through a publicly available network server or 438 | other readily accessible means, then you must either **(1)** cause the Corresponding 439 | Source to be so available, or **(2)** arrange to deprive yourself of the benefit of the 440 | patent license for this particular work, or **(3)** arrange, in a manner consistent with 441 | the requirements of this License, to extend the patent license to downstream 442 | recipients. “Knowingly relying” means you have actual knowledge that, but 443 | for the patent license, your conveying the covered work in a country, or your 444 | recipient's use of the covered work in a country, would infringe one or more 445 | identifiable patents in that country that you have reason to believe are valid. 446 | 447 | If, pursuant to or in connection with a single transaction or arrangement, you 448 | convey, or propagate by procuring conveyance of, a covered work, and grant a patent 449 | license to some of the parties receiving the covered work authorizing them to use, 450 | propagate, modify or convey a specific copy of the covered work, then the patent 451 | license you grant is automatically extended to all recipients of the covered work and 452 | works based on it. 453 | 454 | A patent license is “discriminatory” if it does not include within the 455 | scope of its coverage, prohibits the exercise of, or is conditioned on the 456 | non-exercise of one or more of the rights that are specifically granted under this 457 | License. You may not convey a covered work if you are a party to an arrangement with 458 | a third party that is in the business of distributing software, under which you make 459 | payment to the third party based on the extent of your activity of conveying the 460 | work, and under which the third party grants, to any of the parties who would receive 461 | the covered work from you, a discriminatory patent license **(a)** in connection with 462 | copies of the covered work conveyed by you (or copies made from those copies), or **(b)** 463 | primarily for and in connection with specific products or compilations that contain 464 | the covered work, unless you entered into that arrangement, or that patent license 465 | was granted, prior to 28 March 2007. 466 | 467 | Nothing in this License shall be construed as excluding or limiting any implied 468 | license or other defenses to infringement that may otherwise be available to you 469 | under applicable patent law. 470 | 471 | ### 12. No Surrender of Others' Freedom 472 | 473 | If conditions are imposed on you (whether by court order, agreement or otherwise) 474 | that contradict the conditions of this License, they do not excuse you from the 475 | conditions of this License. If you cannot convey a covered work so as to satisfy 476 | simultaneously your obligations under this License and any other pertinent 477 | obligations, then as a consequence you may not convey it at all. For example, if you 478 | agree to terms that obligate you to collect a royalty for further conveying from 479 | those to whom you convey the Program, the only way you could satisfy both those terms 480 | and this License would be to refrain entirely from conveying the Program. 481 | 482 | ### 13. Use with the GNU Affero General Public License 483 | 484 | Notwithstanding any other provision of this License, you have permission to link or 485 | combine any covered work with a work licensed under version 3 of the GNU Affero 486 | General Public License into a single combined work, and to convey the resulting work. 487 | The terms of this License will continue to apply to the part which is the covered 488 | work, but the special requirements of the GNU Affero General Public License, section 489 | 13, concerning interaction through a network will apply to the combination as such. 490 | 491 | ### 14. Revised Versions of this License 492 | 493 | The Free Software Foundation may publish revised and/or new versions of the GNU 494 | General Public License from time to time. Such new versions will be similar in spirit 495 | to the present version, but may differ in detail to address new problems or concerns. 496 | 497 | Each version is given a distinguishing version number. If the Program specifies that 498 | a certain numbered version of the GNU General Public License “or any later 499 | version” applies to it, you have the option of following the terms and 500 | conditions either of that numbered version or of any later version published by the 501 | Free Software Foundation. If the Program does not specify a version number of the GNU 502 | General Public License, you may choose any version ever published by the Free 503 | Software Foundation. 504 | 505 | If the Program specifies that a proxy can decide which future versions of the GNU 506 | General Public License can be used, that proxy's public statement of acceptance of a 507 | version permanently authorizes you to choose that version for the Program. 508 | 509 | Later license versions may give you additional or different permissions. However, no 510 | additional obligations are imposed on any author or copyright holder as a result of 511 | your choosing to follow a later version. 512 | 513 | ### 15. Disclaimer of Warranty 514 | 515 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. 516 | EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES 517 | PROVIDE THE PROGRAM “AS IS” WITHOUT WARRANTY OF ANY KIND, EITHER 518 | EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF 519 | MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE 520 | QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE 521 | DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 522 | 523 | ### 16. Limitation of Liability 524 | 525 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY 526 | COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS 527 | PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, 528 | INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE 529 | PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE 530 | OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE 531 | WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE 532 | POSSIBILITY OF SUCH DAMAGES. 533 | 534 | ### 17. Interpretation of Sections 15 and 16 535 | 536 | If the disclaimer of warranty and limitation of liability provided above cannot be 537 | given local legal effect according to their terms, reviewing courts shall apply local 538 | law that most closely approximates an absolute waiver of all civil liability in 539 | connection with the Program, unless a warranty or assumption of liability accompanies 540 | a copy of the Program in return for a fee. 541 | 542 | _END OF TERMS AND CONDITIONS_ 543 | 544 | ## How to Apply These Terms to Your New Programs 545 | 546 | If you develop a new program, and you want it to be of the greatest possible use to 547 | the public, the best way to achieve this is to make it free software which everyone 548 | can redistribute and change under these terms. 549 | 550 | To do so, attach the following notices to the program. It is safest to attach them 551 | to the start of each source file to most effectively state the exclusion of warranty; 552 | and each file should have at least the “copyright” line and a pointer to 553 | where the full notice is found. 554 | 555 | 556 | Copyright (C) 2019 Pawel Krawczyk 557 | 558 | This program is free software: you can redistribute it and/or modify 559 | it under the terms of the GNU General Public License as published by 560 | the Free Software Foundation, either version 3 of the License, or 561 | (at your option) any later version. 562 | 563 | This program is distributed in the hope that it will be useful, 564 | but WITHOUT ANY WARRANTY; without even the implied warranty of 565 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 566 | GNU General Public License for more details. 567 | 568 | You should have received a copy of the GNU General Public License 569 | along with this program. If not, see . 570 | 571 | Also add information on how to contact you by electronic and paper mail. 572 | 573 | If the program does terminal interaction, make it output a short notice like this 574 | when it starts in an interactive mode: 575 | 576 | nanotail Copyright (C) 2019 Pawel Krawczyk 577 | This program comes with ABSOLUTELY NO WARRANTY; for details type 'show w'. 578 | This is free software, and you are welcome to redistribute it 579 | under certain conditions; type 'show c' for details. 580 | 581 | The hypothetical commands `show w` and `show c` should show the appropriate parts of 582 | the General Public License. Of course, your program's commands might be different; 583 | for a GUI interface, you would use an “about box”. 584 | 585 | You should also get your employer (if you work as a programmer) or school, if any, to 586 | sign a “copyright disclaimer” for the program, if necessary. For more 587 | information on this, and how to apply and follow the GNU GPL, see 588 | <>. 589 | 590 | The GNU General Public License does not permit incorporating your program into 591 | proprietary programs. If your program is a subroutine library, you may consider it 592 | more useful to permit linking proprietary applications with the library. If this is 593 | what you want to do, use the GNU Lesser General Public License instead of this 594 | License. But first, please read 595 | <>. 596 | -------------------------------------------------------------------------------- /R/polya_stats.R: -------------------------------------------------------------------------------- 1 | #' Calculates basic statistics for polya lengths 2 | #' 3 | #' Takes polyA predictions table as input and checks if there is significant difference in polyA lengths between chosen conditions for each transcript. 4 | #' By default, Wilcoxon Rank Sum (\link{wilcox.test}) test is used. 5 | #' 6 | #' @param polya_data input table with polyA predictions 7 | #' @param min_reads minimum number of reads to include transcript in the analysis 8 | #' @param grouping_factor which column defines groups (default: sample_name) 9 | #' @param condition1 if `grouping_factor` has more than 2 levels, which level use for comparison 10 | #' @param condition2 if `grouping_factor` has more than 2 levels, which level use for comparison 11 | #' @param transcript_id_column - name of the column with transcript ids (default = "transcript") 12 | #' @param alpha - alpha value to consider a hit significant (default - 0.05) 13 | #' @param add_summary - add summary (mean polya lengths, counts) to statistics results? 14 | #' @param length_summary_to_show - which length summary to show ("median"/"mean"/"gm_mean") 15 | #' @param ... - additional parameters to pass to .polya_stats (custom_glm_formula,use_dwell_time) 16 | #' @param stat_test what statistical test to use for testing, currently supports "Wilcoxon" (for \link{wilcox.test}), "KS" (for \link[FSA]{ksTest} from FSA package) or "glm" (for \link{glm}) 17 | #' 18 | #' @return summary table with pvalues and median/mean values associated to each transcript 19 | #' 20 | #' @export 21 | #' 22 | calculate_polya_stats <- function(polya_data, transcript_id_column = "transcript", min_reads = 0, grouping_factor = "sample_name",condition1=NA,condition2=NA,stat_test="Wilcoxon",alpha=0.05,add_summary=TRUE,length_summary_to_show = "gm_mean",...) 23 | { 24 | 25 | 26 | if (missing(polya_data)) { 27 | stop("PolyA predictions are missing. Please provide a valid polya_data argument", 28 | call. = FALSE) 29 | } 30 | 31 | 32 | 33 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data.frame provided as an input") 34 | 35 | 36 | 37 | 38 | 39 | # if grouping factor has more than two levels 40 | if (length(levels(polya_data[[grouping_factor]]))>2) { 41 | if(is.na(condition1) && is.na(condition2)) { 42 | #throw error when no conditions for comparison are specified 43 | stop(paste0("grouping_factor ",grouping_factor," has more than 2 levels. Please specify condtion1 and condition2 to select comparison pairs")) 44 | } 45 | else { 46 | # filter input data leaving only specified conditions, dropping other factor levels 47 | assertthat::assert_that(condition1 %in% levels(polya_data[[grouping_factor]]),msg=paste0(condition1," is not a level of ",grouping_factor," (grouping_factor)")) 48 | assertthat::assert_that(condition2 %in% levels(polya_data[[grouping_factor]]),msg=paste0(condition2," is not a level of ",grouping_factor," (grouping_factor)")) 49 | assertthat::assert_that(condition2 != condition1,msg="condition2 should be different than condition1") 50 | polya_data <- polya_data %>% dplyr::filter(!!rlang::sym(grouping_factor) %in% c(condition1,condition2)) %>% dplyr::mutate() %>% droplevels() 51 | } 52 | } 53 | else if (length(levels(polya_data[[grouping_factor]]))==1) { 54 | stop("Only 1 level present for grouping factor. Choose another groping factor for comparison") 55 | } 56 | else { 57 | condition1 = levels(polya_data[[grouping_factor]])[1] 58 | condition2 = levels(polya_data[[grouping_factor]])[2] 59 | } 60 | 61 | polya_data_stat <- 62 | polya_data %>% dplyr::mutate(transcript2=transcript) %>% dplyr::group_by(.dots = c(transcript_id_column)) %>% tidyr::nest() 63 | 64 | #future::plan(future::multiprocess()) 65 | polya_data_stat <- polya_data_stat %>% dplyr::mutate(stats=purrr::map(data,.polya_stats,grouping_factor=grouping_factor,stat_test=stat_test,min_reads=min_reads,...)) %>% dplyr::select(-data) %>% tidyr::unnest() 66 | message("calculating statistics") 67 | #polya_data_stat <- polya_data_stat %>% dplyr::mutate(stats=furrr::future_map(data,.polya_stats,grouping_factor=grouping_factor,stat_test=stat_test,min_reads=min_reads,...)) %>% dplyr::select(-data) %>% tidyr::unnest() 68 | message("Finished") 69 | if (add_summary) { 70 | polyA_data_stat_summary <- summarize_polya(polya_data,summary_factors = grouping_factor,transcript_id_column = transcript_id_column) %>% dplyr::select(!!rlang::sym(transcript_id_column),counts,!!rlang::sym(grouping_factor),!!rlang::sym(paste0("polya_",length_summary_to_show))) %>% spread_multiple(!!rlang::sym(grouping_factor),c(counts,!!rlang::sym(paste0("polya_",length_summary_to_show)))) 71 | polya_data_stat <- polya_data_stat %>% dplyr::full_join(polyA_data_stat_summary,by=transcript_id_column) 72 | polya_data_stat$length_diff <- polya_data_stat[[paste0(condition2,"_polya_",length_summary_to_show)]] - polya_data_stat[[paste0(condition1,"_polya_",length_summary_to_show)]] 73 | polya_data_stat$fold_change <- polya_data_stat[[paste0(condition2,"_polya_",length_summary_to_show)]] / polya_data_stat[[paste0(condition1,"_polya_",length_summary_to_show)]] 74 | } 75 | message("Adjusting p.value") 76 | 77 | polya_data_stat$padj <- p.adjust(polya_data_stat$p.value, method = "BH",n = nrow(polya_data_stat[!is.na(polya_data_stat$p.value),])) 78 | 79 | polya_data_stat<- polya_data_stat %>% dplyr::mutate(effect_size=dplyr::case_when((abs(cohen_d))<0.2 ~ "negligible",(abs(cohen_d)<0.5) ~ "small", (abs(cohen_d)<0.8) ~ "medium",(abs(cohen_d)>=0.8) ~ "large",TRUE ~ "NA")) 80 | 81 | # create significance factor 82 | polya_data_stat <- 83 | polya_data_stat %>% dplyr::mutate(significance = dplyr::case_when(is.na(padj) ~ "NotSig", 84 | (padj < alpha) ~ paste0("FDR<", alpha), 85 | TRUE ~ "NotSig")) 86 | 87 | polya_data_stat$stats_code <- sapply(polya_data_stat$stats_code,FUN = function(x) {stat_codes_list[[x]]},simplify = "vector",USE.NAMES = FALSE) %>% unlist() 88 | 89 | 90 | 91 | polya_data_stat <- polya_data_stat %>% dplyr::arrange(padj) 92 | #polya_data_stat_short <- polya_data_stat %>% dplyr::select(!!rlang::sym(transcript_id_column),dplyr::ends_with("counts"),dplyr::ends_with("gm_mean"),p.value,padj,stats_code) 93 | 94 | 95 | #return( 96 | # list(summary = polya_data_stat,summary_short = polya_data_stat_short)) 97 | return(polya_data_stat) 98 | } 99 | 100 | 101 | 102 | stat_codes_list = list(OK = "OK", 103 | G1_NA = "GROUP1_NA", 104 | G2_NA = "GROUP2_NA", 105 | G1_LC = "G1_LOW_COUNT", 106 | G2_LC = "G2_LOW_COUNT", 107 | B_NA = "DATA FOR BOTH GROUPS NOT AVAILABLE", 108 | B_LC = "LOW COUNTS FOR BOTH GROUPS", 109 | G_LC = "LOW COUNT FOR ONE GROUP", 110 | G_NA = "DATA FOR ONE GROUP NOT AVAILABLE", 111 | ERR = "OTHER ERROR", 112 | GLM_GROUP = "MISSING FACTOR LEVEL IN GLM CALL") 113 | 114 | #' Calculates polyA statistics for single group of reads (for single transcript) 115 | #' 116 | #' @param polya_data - input data frame with polyA predictions 117 | #' @param stat_test - statistical test to use. One of : Wilcoxon, KS (Kolmogorov-Smirnov) or glm (Generalized Linear Model). All tests use log2(polya_length) as a response variable 118 | #' @param grouping_factor - factor defining groups (Need to have 2 levels) 119 | #' @param min_reads - minimum reads per group to include in the statistics calculation 120 | #' @param use_dwell_time - use dwell time instead of calculated polya length for statistics 121 | #' @param custom_glm_formula - custom glm formula (when using glm for statistics) 122 | #' 123 | #' @return data frame 124 | #' 125 | .polya_stats <- function(polya_data,stat_test,grouping_factor,min_reads=0,use_dwell_time = FALSE,custom_glm_formula = NA) { 126 | 127 | 128 | if (missing(polya_data)) { 129 | stop("PolyA predictions are missing. Please provide a valid polya_data argument", 130 | call. = FALSE) 131 | } 132 | 133 | 134 | available_statistical_tests = c("Wilcoxon","KS","glm") 135 | 136 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data.frame provided as an input") 137 | 138 | assertthat::assert_that(stat_test %in% available_statistical_tests,msg = "Please provide one of available statistical tests (Wilcoxon, KS or glm)") 139 | assertthat::assert_that(assertthat::is.number(min_reads),msg = "Non-numeric parameter provided (min_reads)") 140 | assertthat::assert_that(assertive::is_a_bool(use_dwell_time),msg="Non-boolean value provided for option use_dwell_time.") 141 | assertthat::assert_that(grouping_factor %in% colnames(polya_data),msg=paste0(grouping_factor," is not a column of input dataset")) 142 | 143 | 144 | 145 | # if grouping factor has more than two levels 146 | if (length(levels(polya_data[[grouping_factor]]))>2) { 147 | if(is.na(condition1) && is.na(condition2)) { 148 | #throw error when no conditions for comparison are specified 149 | stop(paste0("grouping_factor ",grouping_factor," has more than 2 levels. Please specify condtion1 and condition2 to select comparison pairs")) 150 | } 151 | else { 152 | # filter input data leaving only specified conditions, dropping other factor levels 153 | assertthat::assert_that(condition1 %in% levels(polya_data[[grouping_factor]]),msg=paste0(condition1," is not a level of ",grouping_factor," (grouping_factor)")) 154 | assertthat::assert_that(condition2 %in% levels(polya_data[[grouping_factor]]),msg=paste0(condition2," is not a level of ",grouping_factor," (grouping_factor)")) 155 | assertthat::assert_that(condition2 != condition1,msg="condition2 should be different than condition1") 156 | polya_data <- polya_data %>% dplyr::filter(!!rlang::sym(grouping_factor) %in% c(condition1,condition2)) %>% droplevels() 157 | } 158 | } 159 | else if (length(levels(polya_data[[grouping_factor]]))==1) { 160 | stop("Only 1 level present for grouping factor. Choose another groping factor for comparison") 161 | } 162 | else { 163 | condition1 = levels(polya_data[[grouping_factor]])[1] 164 | condition2 = levels(polya_data[[grouping_factor]])[2] 165 | } 166 | 167 | 168 | # initial status code 169 | stats_code = codes_stats = "OK" 170 | # calculate group counts 171 | group_counts = polya_data %>% dplyr::group_by(.dots = c(grouping_factor)) %>% dplyr::count() 172 | 173 | stats <- NA 174 | cohend <- NA 175 | if (use_dwell_time) { 176 | statistics_formula <- paste0("dwell_time ~",grouping_factor) 177 | } 178 | else { 179 | statistics_formula <- paste0("log2(polya_length) ~",grouping_factor) 180 | } 181 | 182 | if ((!missing(custom_glm_formula)) & (stat_test!='glm')) { 183 | warning("custom_glm_formula specified but glm is not used for statistics calculation. Formula will be ignored") 184 | } 185 | 186 | 187 | if (nrow(group_counts)==2) { 188 | if (group_counts[1,]$n < min_reads) { 189 | if (group_counts[2,]$n < min_reads) { 190 | #message("Not enough counts for both groups") 191 | stats_code = "B_LC" 192 | } 193 | else { 194 | #message(paste0("Not enough counts for group ",group_counts[1,]$group)) 195 | stats_code = "G_LC" 196 | } 197 | } 198 | else if (group_counts[2,]$n < min_reads) { 199 | #message(paste0("Not enough counts for group ",group_counts[2,]$group)) 200 | stats_code = "G_LC" 201 | } 202 | else { 203 | #calculate cohen's d parameter 204 | cohend<-effsize::cohen.d(data=polya_data,as.formula(paste0("polya_length ~",grouping_factor)))$estimate 205 | if (stat_test=="Wilcoxon") { 206 | #print(polya_data$transcript2) 207 | stats <- suppressWarnings(wilcox.test(as.formula(statistics_formula),polya_data))$p.value 208 | } 209 | else if (stat_test=="KS") { 210 | stats <- FSA::ksTest(as.formula(statistics_formula),data=polya_data)$p.value 211 | } 212 | else if (stat_test=="glm") { 213 | valid_glm_groups = TRUE 214 | if(!missing(custom_glm_formula)) { 215 | custom_glm_formula <- substitute(custom_glm_formula) 216 | glm_groups<-all.vars(as.formula(custom_glm_formula))[-1] 217 | assertthat::assert_that(length(glm_groups)>0,msg="Please provide valid custom_glm_formula (with the correct categorical explanatory variable)") 218 | assertthat::assert_that(all(glm_groups %in% colnames(polya_data)),msg = "wrong custom glm formula. Please provide valid column names as explanatory variable") 219 | # check that at least 2 levels present for each explanatory variable 220 | for (glm_group in glm_groups) { 221 | if (length(unique(polya_data[[glm_group]]))<2) { 222 | valid_glm_groups = FALSE 223 | } 224 | } 225 | # check that each explanatory variable has the same number of levels for each other(for example batches for batch effect formula) 226 | # will fail if there is any intersect of explanatory variables with 0 count 227 | if(!all(table(polya_data %>% dplyr::select(glm_groups))>0)) { 228 | valid_glm_groups = FALSE 229 | } 230 | statistics_formula = custom_glm_formula 231 | } 232 | 233 | if (valid_glm_groups) { 234 | # required, as log2(0) produces inf, throwing error in glm 235 | polya_data <- polya_data %>% dplyr::mutate(polya_length = ifelse(polya_length==0,1,polya_length)) 236 | mcp_call <- paste0("multcomp::mcp(",grouping_factor,' = "Tukey")') 237 | stats <- summary(multcomp::glht(glm(formula = as.formula(statistics_formula),data=polya_data),eval(parse(text = mcp_call))))$test$pvalues[1] 238 | 239 | #polya_data_stat <- polya_data_stat %>% dplyr::mutate(stats = suppressWarnings(coef(summary(glm(formula = as.formula(statistics_formula))))[2,4])) 240 | } 241 | else{ 242 | stats <- NA 243 | stats_code <- "GLM_GROUP" 244 | } 245 | } 246 | else { 247 | stop("wrong stat_test parameter provided") 248 | } 249 | } 250 | } 251 | else if (nrow(group_counts)==1) { 252 | stats_code = "G_NA" 253 | } 254 | else if (nrow(group_counts)==0) { 255 | stats_code = "B_NA" 256 | } 257 | else { 258 | stats_code = "ERR" 259 | } 260 | 261 | 262 | stats<-tibble::tibble(p.value=stats,stats_code=as.character(stats_code),cohen_d=cohend) 263 | 264 | return(stats) 265 | 266 | } 267 | 268 | 269 | #' Summarizes input polya table 270 | #' 271 | #' Summarizes input table with polyA predictions, calculating medians, mean, geometric means and standard deviation values for each transcript (default). 272 | #' To get overall summary for each sample or group, specify `transcript_id_column=NULL` 273 | #' 274 | #' @param polya_data input table with polyA predictions 275 | #' @param summary_factors specifies column used for grouping (default: group) 276 | #' @param transcript_id_column specifies which column use as transcript identifier (default: transcript). Set to `NULL` to omit per-transcript stats 277 | #' 278 | #' @return long-format \link[tibble]{tibble} with per-transcript statistics for each sample 279 | #' @export 280 | #' 281 | summarize_polya <- function(polya_data,summary_factors = c("group"),transcript_id_column = c("transcript")) { 282 | 283 | if (missing(polya_data)) { 284 | stop("PolyA predictions are missing. Please provide a valid polya_data argument", 285 | call. = FALSE) 286 | } 287 | 288 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data.frame provided as an input") 289 | assertthat::assert_that(assertive::is_character(summary_factors),msg = "Non-character argument is not alowed for `summary factors`. Please provide either string or vector of strings") 290 | assertthat::assert_that(all(summary_factors %in% colnames(polya_data)),msg="Non-existent column name provided as the argument (summary_factors)") 291 | 292 | polya_data_summarized <- 293 | polya_data %>% dplyr::ungroup() %>% dplyr::group_by(.dots = c(transcript_id_column,summary_factors)) %>% dplyr::summarise( 294 | counts = dplyr::n(), 295 | polya_mean = mean(polya_length), 296 | polya_sd = sd(polya_length), 297 | polya_median = median(polya_length), 298 | polya_gm_mean = gm_mean(polya_length), 299 | polya_sem = polya_sd/sqrt(counts) 300 | ) 301 | return(polya_data_summarized) 302 | } 303 | 304 | calculate_quantiles <- function(x,probs=c(0.1,0.9)) { 305 | 306 | data.frame(quantile_val=quantile(x,probs),quantile=probs) 307 | } 308 | 309 | 310 | #' Summarize poly(A) data per transcript 311 | #' 312 | #' @param polya_data input table with poly(A) data. 313 | #' @param summary_factors vector of grouping columns. Set to NULL to omit grouping 314 | #' @param transcript_id_column column with transcript identifier. Default to "transcript" 315 | #' @param summary_functions list of summary functions. Set to NA to get only counts per transcript 316 | #' @param quantiles vector with quantile values (optional) 317 | #' 318 | #' @return a tibble with summarized poly(A) length data 319 | #' @export 320 | #' 321 | #' @examples 322 | summarize_polya_per_transcript <- function(polya_data,groupBy=NULL,transcript_id_column=transcript,summary_functions=list("median","mean"),quantiles=NA) { 323 | 324 | if (missing(polya_data)) { 325 | stop("PolyA predictions are missing. Please provide a valid polya_data argument", 326 | call. = FALSE) 327 | } 328 | 329 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data.frame provided as an input") 330 | # assertthat::assert_that(assertive::is_character(summary_factors),msg = "Non-character argument is not allowed for `summary factors`. Please provide either string or vector of strings") 331 | #assertthat::assert_that(all(as.character(summary_factors) %in% colnames(polya_data)),msg="Non-existent column name provided as the argument (summary_factors)") 332 | 333 | #summary_label = paste0("polya_",summary_function) 334 | 335 | 336 | if(!is.na(summary_functions)) { 337 | 338 | names(summary_functions)= summary_functions 339 | summary_functions <- sapply(summary_functions,get) 340 | 341 | polya_data_summarized <- 342 | polya_data %>% dplyr::ungroup() %>% dplyr::group_by(across(c({{ transcript_id_column }},{{ groupBy }}))) %>% dplyr::summarise(counts = dplyr::n(),across(polya_length,.fns=summary_functions)) 343 | 344 | } 345 | else { 346 | polya_data_summarized <- 347 | polya_data %>% dplyr::ungroup() %>% dplyr::group_by(across(c({{ transcript_id_column }},{{ groupBy }}))) %>% dplyr::summarise(counts = dplyr::n()) 348 | 349 | } 350 | if (!is.na(quantiles)) { 351 | polya_data_summarized_quantiles <- 352 | polya_data %>% dplyr::ungroup() %>% dplyr::group_by(across(c({{ transcript_id_column }},{{ groupBy }}))) %>% dplyr::summarise(calculate_quantiles(polya_length,probs=quantiles)) %>% tidyr::pivot_wider(names_from="quantile",values_from="quantile_val",names_prefix = "q_") 353 | polya_data_summarized <- polya_data_summarized %>% dplyr::left_join(polya_data_summarized_quantiles) 354 | 355 | } 356 | 357 | 358 | return(polya_data_summarized) 359 | } 360 | 361 | 362 | #' Calculates PCA using polya predictions or counts 363 | #' 364 | #' Needs polyA predictions table summarized by \link{summarize_polya} function, using "sample_name" as summary_factors 365 | #' 366 | #' @param polya_data_summarized summarized polyA predictions. Generate use \link{summarize_polya} 367 | #' @param parameter - parameter used for PCA calculation. One of: polya_median,polya_mean,polya_gm_mean,counts 368 | #' @param transcript_id_column column which respresnrt transcript id 369 | #' 370 | #' @return pca object 371 | #' @export 372 | #' 373 | calculate_pca <- function(polya_data_summarized,parameter="polya_median",transcript_id_column = "transcript") { 374 | 375 | 376 | if (missing(polya_data_summarized)) { 377 | stop("Summarized PolyA predictions are missing. Please provide a valid polya_data_summarized argument", 378 | call. = FALSE) 379 | } 380 | 381 | assertthat::assert_that(assertive::has_rows(polya_data_summarized),msg = "Empty data.frame provided as an input") 382 | assertthat::assert_that(assertive::is_character(parameter),msg = "Non-character argument is not alowed for `parameter`.") 383 | assertthat::assert_that(transcript_id_column %in% colnames(polya_data_summarized),msg=paste0("Required `transcript`` column is missing from input dataset.")) 384 | assertthat::assert_that("sample_name" %in% colnames(polya_data_summarized),msg=paste0("Required `sample_name` column is missing from input dataset.")) 385 | assertthat::assert_that(parameter %in% colnames(polya_data_summarized),msg=paste0(parameter," is not a column of input dataset.")) 386 | 387 | polya_data_summarized <- polya_data_summarized %>% dplyr::select(!!rlang::sym(transcript_id_column),sample_name,!!rlang::sym(parameter)) %>% tidyr::spread(sample_name,!!rlang::sym(parameter)) %>% as.data.frame() 388 | polya_data_summarized[is.na(polya_data_summarized)] <- 0 389 | sample_names <- colnames(polya_data_summarized[,-1]) 390 | transcript_names <- polya_data_summarized[,1] 391 | polya_data_summarized_t<-t(polya_data_summarized[,-1]) 392 | # step required to remove zero-variance columns (based on https://stackoverflow.com/questions/40315227/how-to-solve-prcomp-default-cannot-rescale-a-constant-zero-column-to-unit-var) 393 | zero_variance_transcripts<-which(apply(polya_data_summarized_t, 2, var)==0) 394 | if (length(zero_variance_transcripts>0)) { 395 | polya_data_summarized_t <- polya_data_summarized_t[ , -zero_variance_transcripts] 396 | colnames(polya_data_summarized_t) <- transcript_names[-zero_variance_transcripts] 397 | } 398 | else { 399 | colnames(polya_data_summarized_t) <- transcript_names 400 | } 401 | pca.test <- prcomp(polya_data_summarized_t,center=T,scale=T) 402 | 403 | return_list <- list(pca = pca.test,sample_names = sample_names) 404 | return(return_list) 405 | } 406 | 407 | 408 | 409 | 410 | 411 | #' Get information about nanopolish processing 412 | #' 413 | #' Process the information returned by \code{nanopolish polya} in the \code{qc_tag} column 414 | #' 415 | #' @param polya_data A data.frame or tibble containig unfiltered polya output from Nanopolish, 416 | #' @param grouping_factor How to group results (e.g. by sample_name) 417 | #' best read with \link[nanotail]{read_polya_single} or \link[nanotail]{read_polya_multiple} 418 | #' @return A \link[tibble]{tibble} with counts for each processing state 419 | 420 | #' @export 421 | #' 422 | get_nanopolish_processing_info <- function(polya_data,grouping_factor=NA) { 423 | 424 | 425 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data.frame provided as an input") 426 | 427 | 428 | if(!is.na(grouping_factor)) { 429 | assertthat::assert_that(grouping_factor %in% colnames(polya_data),msg=paste0(grouping_factor," is not a column of input dataset")) 430 | processing_info <- polya_data %>% dplyr::mutate(qc_tag=forcats::fct_relevel(qc_tag,"PASS", after = Inf)) %>% dplyr::group_by(!!rlang::sym(grouping_factor),qc_tag) %>% dplyr::count() 431 | } 432 | else { 433 | processing_info <- polya_data %>% dplyr::mutate(qc_tag=forcats::fct_relevel(qc_tag,"PASS", after = Inf)) %>% dplyr::group_by(qc_tag) %>% dplyr::count() 434 | } 435 | 436 | return (processing_info) 437 | } 438 | 439 | 440 | 441 | #' Performs differential expression analysis 442 | #' 443 | #' Uses counts for each identified transcript to calculate differential expression between specified groups. 444 | #' This function is a wrapper for \code{\link[edgeR]{binomTest}} from \code{edgeR} package 445 | #' 446 | #' 447 | #' @param polya_data polya_data tibble 448 | #' @param grouping_factor name of column containing factor with groups for comparison 449 | #' @param condition1 first condition to compare 450 | #' @param condition2 second condition to compare 451 | #' @param alpha threshold for a pvalue, to treat the result as significant (default = 0.05) 452 | #' @param summarized_input is input table already summarized? 453 | #' 454 | #' @return a tibble with differential expression results 455 | #' @export 456 | #' 457 | #' @seealso \link[edgeR]{binomTest} 458 | #' 459 | calculate_diff_exp_binom <- function(polya_data,grouping_factor=NA,condition1=NA,condition2=NA,alpha=0.05,summarized_input=FALSE) { 460 | 461 | 462 | 463 | if (missing(polya_data)) { 464 | stop("PolyA data are missing. Please provide a valid polya_data argument", 465 | call. = FALSE) 466 | } 467 | 468 | if (missing(grouping_factor)) { 469 | stop("Grouping factor is missing. Please specify one", 470 | call. = FALSE) 471 | } 472 | 473 | assertthat::assert_that(assertive::is_a_bool(summarized_input),msg="Non-boolean value provided for option summarized_input") 474 | assertthat::assert_that(assertive::has_rows(polya_data),msg = "Empty data.frame provided as an input") 475 | if (!is.na(grouping_factor)) { 476 | assertthat::assert_that(grouping_factor %in% colnames(polya_data),msg=paste0(grouping_factor," is not a column of input dataset")) 477 | if (!is.na(condition1)) { 478 | if(!is.na(condition2)) { 479 | assertthat::assert_that(condition1 %in% levels(polya_data[[grouping_factor]]),msg=paste0(condition1," is not a level of ",grouping_factor," (grouping_factor)")) 480 | assertthat::assert_that(condition2 %in% levels(polya_data[[grouping_factor]]),msg=paste0(condition2," is not a level of ",grouping_factor," (grouping_factor)")) 481 | assertthat::assert_that(condition2 != condition1,msg="condition2 should be different than condition1") 482 | } 483 | else { 484 | stop("Please provide both condition1 and condition2 for comparison") 485 | } 486 | } 487 | else { 488 | stop("Please provide both condition1 and condition2 for comparison") 489 | } 490 | } 491 | else { 492 | stop("Please provide valid grouping_factor") 493 | } 494 | 495 | assertthat::assert_that(is.numeric(alpha),msg = "Non-numeric parameter provided (alpha)") 496 | 497 | if (summarized_input){ 498 | polya_data_summarized <- polya_data 499 | } 500 | else{ 501 | polya_data_summarized <- summarize_polya(polya_data,summary_factors = grouping_factor) 502 | } 503 | 504 | libsizes <- polya_data_summarized %>% dplyr::ungroup() %>% dplyr::group_by(!!rlang::sym(grouping_factor)) %>% dplyr::summarize(lib_size=sum(counts)) %>% dplyr::mutate(sizeFactor=lib_size/mean(lib_size)) 505 | 506 | #sum counts for all samples in given group 507 | polyA_data_counts_summarized<-polya_data_summarized %>% dplyr::group_by(transcript,!!rlang::sym(grouping_factor)) %>% dplyr::summarize(counts_sum=sum(counts)) %>% tidyr::spread(!!rlang::sym(grouping_factor),counts_sum) %>% as.data.frame() 508 | 509 | polyA_data_counts_summarized[is.na(polyA_data_counts_summarized)] <- 0 510 | 511 | polyA_data_counts_summarized <- cbind(polyA_data_counts_summarized$transcript,polyA_data_counts_summarized[,-1]/libsizes$sizeFactor) 512 | colnames(polyA_data_counts_summarized)[1] <- "transcript" 513 | 514 | 515 | binom_test_pvalues<-edgeR::binomTest(y1=polyA_data_counts_summarized[[condition1]],y2=polyA_data_counts_summarized[[condition2]],n1=sum(polyA_data_counts_summarized[[condition1]]),n2=sum(polyA_data_counts_summarized[[condition2]])) 516 | binom_test_adjusted_pvalues <- p.adjust(binom_test_pvalues,method="BH") 517 | 518 | binom_test_results <- 519 | data.frame(transcript = polyA_data_counts_summarized$transcript, 520 | pvalue = binom_test_pvalues, 521 | padj = binom_test_adjusted_pvalues) %>% 522 | dplyr::left_join(polyA_data_counts_summarized) %>% 523 | dplyr::mutate(fold_change = (!! rlang::sym(condition2))/(!! rlang::sym(condition1))) %>% 524 | #dplyr::mutate_(fold_change = ifelse((condition2 > 0 & condition1 > 0), fold_change, 0)) %>% 525 | dplyr::mutate(significance = ifelse(padj < alpha, paste0("FDR<", alpha), "NotSig")) %>% 526 | dplyr::mutate(mean_expr = ((!!rlang::sym(condition1)) + (!!rlang::sym(condition2)))/2) %>% 527 | dplyr::arrange(padj) 528 | 529 | return(binom_test_results) 530 | 531 | } 532 | 533 | 534 | #' Compute Kruskal-Wallis test on poly(A) data 535 | #' 536 | #' @param input_data - input tibble/data.frame with nanopolish output. 537 | #' @param grouping_factor - which column contains group information 538 | #' @param transcript_id column which transcript ids 539 | #' 540 | #' @return data.frame with statistis 541 | #' @export 542 | #' 543 | #' @examples 544 | #' \dontrun{ 545 | #' polya_table <- nanotail::read_polya_single("nanopolish.tsv") 546 | #' kruskal_polya(polya_table,grouping_factor="group",transcript_id="transcript",verbose=T) 547 | #' } 548 | kruskal_polya <- function(input_data,grouping_factor="sample_name",transcript_id="transcript",verbose=F) { 549 | 550 | data_frame_check<-checkmate::assert_data_frame(input_data,min.rows=10) #minimum 10 rows in the input data.frame required 551 | groups_check<-checkmate::assertFactor(input_data[[grouping_factor]],min.levels=2,empty.levels.ok = F) #at least two levels of grouping factor required 552 | 553 | if (verbose) { 554 | message("Correct input data provided") 555 | } 556 | 557 | input_data_split <- split(input_data,input_data[[transcript_id]]) # split data.frame by transcript 558 | if (verbose) { 559 | message("succesfully splitted data by transcripts") 560 | } 561 | 562 | return_stats<-do.call(rbind,lapply(input_data_split,function(x) {.kruskal_polya(x,grouping_factor = grouping_factor,verbose=verbose) })) # compute statistics using helper function 563 | 564 | if (verbose) { 565 | message("Finished statistics computation") 566 | } 567 | 568 | return(return_stats) 569 | } 570 | 571 | #' Compute Kruskal-Wallis test on single poly(A) data 572 | #' 573 | #' @param input_data input data.frame (for single transcript) 574 | #' @param grouping_factor which column contains group information 575 | #' 576 | #' @return data.frame with test statistics 577 | .kruskal_polya <- function(input_data,grouping_factor="sample_name",verbose=F) { 578 | 579 | data_frame_check<-checkmate::check_data_frame(input_data,min.rows=10) #minimum 10 rows (observations) required in the data.frame 580 | groups_check<-checkmate::checkFactor(input_data[[grouping_factor]],min.levels=2,empty.levels.ok = F) #at least 2 factor levels 581 | 582 | # if all asserts are met, do statistics computation 583 | if (is.logical(data_frame_check) & isTRUE(data_frame_check) & is.logical(groups_check) & isTRUE(groups_check)) { 584 | test_formula <- as.formula(paste("polya_length ~ ",grouping_factor,sep="")) 585 | kruskal_stat <- kruskal.test(test_formula,input_data) # kruskal test 586 | test_effectsize <- effectsize::rank_epsilon_squared(test_formula,input_data) #effect size using rank_epsilon_squared 587 | return_data_frame <- data.frame(df=kruskal_stat$parameter,p.value=as.numeric(kruskal_stat$p.value),statistic=kruskal_stat$statistic,effectsize=test_effectsize$rank_epsilon_squared,data_name=kruskal_stat$data.name,data.frame(t(summary(input_data[[grouping_factor]])))) 588 | } 589 | else { 590 | #when asserts where not true, return associated messages (when verbose) and data.frame with NAs instead of statistics values 591 | if (verbose) { 592 | message(paste(data_frame_check,groups_check)) 593 | } 594 | return_data_frame<-data.frame(df=NA,p.value=NA,statistic=NA,data_name=NA,data.frame(t(summary(input_data[[grouping_factor]])))) 595 | } 596 | 597 | } 598 | 599 | 600 | #' Compute Kruskal-Wallis test on poly(A) data 601 | #' 602 | #' @param input_data - input tibble/data.frame with nanopolish output. 603 | #' @param grouping_factor - which column contains group information 604 | #' @param transcript_id column which transcript ids 605 | #' @param verbose verbose output 606 | #' @param verbosity_level how verbose the output should be (levels 1 - little verbosity, or 2 - very verbose) 607 | #' 608 | #' @return data.frame with statistis 609 | #' @export 610 | #' 611 | #' @examples 612 | #' \dontrun{ 613 | #' polya_table <- nanotail::read_polya_single("nanopolish.tsv") 614 | #' kruskal_polya(polya_table,grouping_factor="group",transcript_id="transcript",verbose=T) 615 | #' } 616 | kruskal_polya <- function(input_data,grouping_factor="sample_name",transcript_id="transcript",verbose=F,verbosity_level=1) { 617 | 618 | data_frame_check<-checkmate::assert_data_frame(input_data,min.rows=10) #minimum 10 rows in the input data.frame required 619 | groups_check<-checkmate::assertFactor(input_data[[grouping_factor]],min.levels=2,empty.levels.ok = F) #at least two levels of grouping factor required 620 | 621 | if (verbose) { 622 | message("Correct input data provided") 623 | } 624 | 625 | input_data_split <- split(input_data,input_data[[transcript_id]]) # split data.frame by transcript 626 | if (verbose) { 627 | message("succesfully splitted data by transcripts") 628 | } 629 | 630 | return_stats<-do.call(rbind,future.apply::future_lapply(input_data_split,function(x) {.kruskal_polya(x,grouping_factor = grouping_factor,verbose=verbose,verbosity_level = verbosity_level) })) # compute statistics using helper function 631 | 632 | 633 | return_stats$padj <- p.adjust(return_stats$p.value,method="BH") # adjust p.values 634 | 635 | if (verbose) { 636 | message("Adjusted p.values using Benjamini-Hochberg correction") 637 | } 638 | 639 | return_stats$transcript <- rownames(return_stats) 640 | rownames(return_stats) <- NULL 641 | return_stats <- return_stats[,c("transcript","p.value","padj","statistic","effectsize")] 642 | 643 | if (verbose) { 644 | message("Finished statistics computation") 645 | } 646 | 647 | return(return_stats) 648 | } 649 | 650 | #' Compute Kruskal-Wallis test on single poly(A) data 651 | #' 652 | #' @param input_data input data.frame (for single transcript) 653 | #' @param grouping_factor which column contains group information 654 | #' @param verbose verbose output 655 | #' @param verbosity_level how verbose the output should be (levels 1 - little verbosity, or 2 - very verbose) 656 | #' 657 | #' @return data.frame with test statistics 658 | .kruskal_polya <- function(input_data,grouping_factor="sample_name",verbose=F,verbosity_level=1) { 659 | 660 | data_frame_check<-checkmate::check_data_frame(input_data,min.rows=10) #minimum 10 rows (observations) required in the data.frame 661 | groups_check<-checkmate::checkFactor(input_data[[grouping_factor]],min.levels=2,empty.levels.ok = F) #at least 2 factor levels 662 | 663 | # if all asserts are met, do statistics computation 664 | if (is.logical(data_frame_check) & isTRUE(data_frame_check) & is.logical(groups_check) & isTRUE(groups_check)) { 665 | test_formula <- as.formula(paste("polya_length ~ ",grouping_factor,sep="")) 666 | kruskal_stat <- kruskal.test(test_formula,data=input_data) # kruskal test 667 | test_effectsize <- effectsize::rank_epsilon_squared(test_formula,data=input_data) #effect size using rank_epsilon_squared 668 | return_data_frame <- data.frame(df=kruskal_stat$parameter,p.value=as.numeric(kruskal_stat$p.value),statistic=kruskal_stat$statistic,effectsize=test_effectsize$rank_epsilon_squared,data_name=kruskal_stat$data.name,data.frame(t(summary(input_data[[grouping_factor]])))) 669 | } 670 | else { 671 | #when asserts where not true, return associated messages (when verbose) and data.frame with NAs instead of statistics values 672 | if (verbose & verbosity_level>1) { 673 | message(paste(data_frame_check,groups_check)) 674 | } 675 | return_data_frame<-data.frame(df=NA,p.value=NA,statistic=NA,effectsize=NA,data_name=NA,data.frame(t(summary(input_data[[grouping_factor]])))) 676 | } 677 | 678 | } 679 | 680 | 681 | 682 | #' Normalize counts to sequencingdepth 683 | #' 684 | #' @param summarized_data - output of summarize_polya_per_transcript() 685 | #' @param raw_data - raw polyA data (loaded with read_polya_single() or read_polya_multiple()) 686 | #' @param spike_in_data - spike-in data for normalization (optional) (raw polya data loaded with read_polya_single() or read_polya_multiple(), with the same metadata as raw data) 687 | #' @param groupBy - grouping variable 688 | #' @param force - force recalculation 689 | #' 690 | #' @return data.frame (tibble) with normalized data 691 | #' @export 692 | #' 693 | 694 | normalize_counts_to_depth <- function(summarized_data,raw_data,spike_in_data=NULL,groupBy,force=F) { 695 | 696 | 697 | 698 | if ("norm_counts" %in% colnames(summarized_data) && force==F) { 699 | stop("Input table contains already normalized counts, if you want to rerun normalization on existing data please use force=T") 700 | } 701 | else if ("norm_counts" %in% colnames(summarized_data) && force==T) { 702 | 703 | summarized_data$temp_counts <- summarized_data$counts 704 | } 705 | else if ("counts" %in% colnames(summarized_data)) { 706 | summarized_data$temp_counts <- summarized_data$counts 707 | } 708 | else { 709 | stop("Missing counts column in the input data") 710 | } 711 | 712 | if(!is.null(spike_in_data)) { 713 | spike_in_norm_factors <- spike_in_data %>% dplyr::group_by(across({{groupBy}})) %>% dplyr::count() %>% dplyr::ungroup() %>% dplyr::mutate(norm_factor=n/min(n)) 714 | } 715 | 716 | norm_factors <- raw_data %>% dplyr::group_by(across({{groupBy}})) %>% dplyr::count() %>% dplyr::ungroup() %>% dplyr::mutate(norm_factor=n/min(n)) 717 | 718 | print(norm_factors) 719 | 720 | normalized_data <- summarized_data %>% dplyr::left_join(norm_factors,by={{groupBy}}) %>% dplyr::mutate(norm_counts=temp_counts/norm_factor) %>% dplyr::select(-c(temp_counts,norm_factor,n)) 721 | 722 | 723 | if(!is.null(spike_in_data)) { 724 | normalized_data$temp_counts <- normalized_data$norm_counts 725 | normalized_data <- normalized_data %>% dplyr::left_join(spike_in_norm_factors,by={{groupBy}}) %>% dplyr::mutate(norm_counts=temp_counts/norm_factor) %>% dplyr::select(-c(temp_counts,norm_factor,n)) 726 | } 727 | 728 | return(normalized_data) 729 | } 730 | --------------------------------------------------------------------------------