add info about params to scripts, potential fix for forgebsgenome input

Author: ferenckata

modules/local/cagefightr/enhancercalling/templates/cagefightr_enhancer_calling.R

@@ -20,12 +20,23 @@ source("${projectDir}/bin/qc_plots.R")
 source("${projectDir}/bin/plot_saving.R")
 
 # Variables injected by Nextflow
+# Path to the CAGEexp object with normalized tags and consensus clusters
+# (character)
 ce_path            <- "${cager_obj}"
+# SQLite file with a TxDb genome annotation package (character)
 tx_annotation      <- "${txdb}"
+# Threshold for the cagefightr balance score (double)
 cfBalanceThreshold <- ${params.cfBalanceThreshold}
+# Threshold above which normalized CTSS are considered expressed (double)
 unexpressed        <- ${params.unexpressed}
+# Non inlcusive lower threshold for number of samples supporting enhancers
+# (i.e. where there is bidirectionality) (integer)
 minSamples         <- as.integer(${params.minSamples})
+# Upstream distance to consider into TSS region for ChIPseeker annotation.
+# Should be negative (integer)
 tssregion_up       <- as.integer(${params.tssregion_up})
+# Downstream distance to consider into TSS region for ChIPseeker annotation.
+# Should be positive (integer)
 tssregion_down     <- as.integer(${params.tssregion_down})
 
 # Create output folders

modules/local/cager/processing/templates/cager_processing.R

@@ -19,25 +19,45 @@ suppressPackageStartupMessages({
 })
 
 # Variables injected by Nextflow
+# Path to the CAGEexp object with tags (character)
 ce_path             <- "${cager_obj}"
+# Name of the BSgenome version to be used (takes precedent over file if exists, character)
 bsgenome_name       <- "${bsgenome_name}"
+# File of the BSgenome version to be used (character)
 bsgenome_file       <- "${bsgenome_file}"
+# SQLite file with a TxDb genome annotation package (character)
 tx_annotation       <- "${txdb}"
+# CAGE tag range minimum for normalization calculation (integer)
 range_min           <- as.integer(${params.norm_range_min})
+# CAGE tag range maximum for normalization calculation (integer)
 range_max           <- as.integer(${params.norm_range_max})
+# Method for normalization (character: powerLaw, simpleTpm, or none)
 method              <- "${params.norm_method}"
+# Total number of tags. Setting it to 1 million results
+# in normalized tags per million (tpm) values (integer)
 t_norm              <- as.integer(${params.t_norm})
+# Alpha values from the reverse cumulative distribution fitting (Optional, double)
 alpha_str           <- "${params.alpha}"
 alpha               <- if (alpha_str == "null") NULL else as.double(alpha_str)
+# Number of samples in which the CTSS Tpm threshold (ctss_thr) should be passed (integer)
 sample_num_thr      <- as.integer(${params.sample_num_thr})
+# CTSS Tpm threshold which should be passed in sample_num_thr number of samples (integer)
 ctss_thr            <- as.integer(${params.ctss_thr})
+# Maximum distance parameter for distclu CAGEr function (integer)
 distclu_maxDist     <- as.integer(${params.distclu_maxDist})
+# Threshold above which to keep the singletons during tag clustering (integer)
 keepSingletonsAbove <- as.integer(${params.keepSingletonsAbove})
+# Lower boundary of interquartile range (double)
 iqlow               <- as.double(${params.iq_low})
+# Higher boundary of interquartile range (double)
 iqhigh              <- as.double(${params.iq_high})
+# Tpm threshold for plotting tagcluster IQwidth (integer)
 iqw_tpm_threshold   <- as.integer(${params.iqw_tpm_threshold})
+# CTSS Tpm threshold for consensus clustering (integer)
 consensus_thr       <- as.integer(${params.consensus_thr})
+# Distance threshold for consensus clustering (integer)
 consensus_dist      <- as.integer(${params.consensus_dist})
+# Number of cores to use, (0 = no parallelization, integer)
 num_core            <- as.integer(${task.cpus})
 
 bsgenome <- if (nchar(trimws(bsgenome_name)) > 0) bsgenome_name else bsgenome_file

modules/local/cager/readin/templates/cager_readin.R

@@ -15,10 +15,16 @@ suppressPackageStartupMessages({
 })
 
 # Variables injected by Nextflow
+# Whether BAM or BigWig is provided (character: bam or bigwig)
 data_type         <- "${data_type}"
+# Csv with information from the input channel with columns
+# [id, pairedness, bigwig or bam path, new name]
 sample_table_list <- "${sample_table}"
+# Name of the BSgenome version to be used (takes precedent over file if exists, character)
 bsgenome_name     <- "${bsgenome_name}"
+# File of the BSgenome version to be used (character)
 bsgenome_file     <- "${bsgenome_file}"
+# Number of cores to use, (0 = no parallelization, integer)
 num_core          <- as.integer(${task.cpus})
 
 bsgenome <- if (nchar(trimws(bsgenome_name)) > 0) bsgenome_name else bsgenome_file

modules/local/cager/tag_qc/templates/cager_tag_qc.R

@@ -13,10 +13,15 @@ suppressPackageStartupMessages({
 })
 
 # Variables injected by Nextflow
+# Path to the CAGEexp object with tags (character)
 ce_path                    <- "${cager_obj}"
+# SQLite file with a TxDb genome annotation package (character)
 tx_annotation              <- "${txdb}"
+# Name of the BSgenome version to be used (takes precedent over file if exists, character)
 bsgenome_name              <- "${bsgenome_name}"
+# File of the BSgenome version to be used (character)
 bsgenome_file              <- "${bsgenome_file}"
+# Threshold for considering tags when calculating correlations (integer)
 corrplot_tagCountThreshold <- as.integer(${params.corrplot_tagCountThreshold})
 
 bsgenome <- if (nchar(trimws(bsgenome_name)) > 0) bsgenome_name else bsgenome_file

modules/local/cager/tagcluster_qc/templates/cager_tagcluster_qc.R

@@ -18,15 +18,27 @@ suppressPackageStartupMessages({
 })
 
 # Variables injected by Nextflow
+# Path to the CAGEexp object with tag clusters (character)
 ce_path                    <- "${cager_obj}"
+# SQLite file with a TxDb genome annotation package (character)
 tx_annotation              <- "${txdb}"
+# Name of the BSgenome version to be used (takes precedent over file if exists, character)
 bsgenome_name              <- "${bsgenome_name}"
+# File of the BSgenome version to be used (character)
 bsgenome_file              <- "${bsgenome_file}"
+# Lower boundary of interquartile range (double)
 iqlow                      <- as.double(${params.iq_low})
+# Higher boundary of interquartile range (double)
 iqhigh                     <- as.double(${params.iq_high})
+# Upstream distance to consider into TSS region for ChIPseeker annotation.
+# Should be negative (integer)
 tssregion_up               <- as.integer(${params.tssregion_up})
+# Downstream distance to consider into TSS region for ChIPseeker annotation.
+# Should be positive (integer)
 tssregion_down             <- as.integer(${params.tssregion_down})
+# Upstream nucleotides to consider fot the TSS logo plot (integer)
 tsslogo_upstream           <- as.integer(${params.tsslogo_upstream})
+# Threshold for considering tags when calculating correlations of normalized CTSS (integer)
 corrplot_tagCountThreshold <- as.integer(${params.corrplot_tagCountThreshold})
 
 bsgenome <- if (nchar(trimws(bsgenome_name)) > 0) bsgenome_name else bsgenome_file

modules/local/forgebsgenome/templates/forge_bsgenome.R

@@ -4,7 +4,7 @@ library(BSgenome)
 
 forgeBSgenomeDataPkg(
     "${forge_seed}",
-    ".")
+    "${seqs_fasta}")
 
 pkg_name <- strsplit(readLines("${forge_seed}")[1], " ")[[1]][2]
 system(paste("R CMD build", pkg_name))