Mercurial > repos > iuc > ribowaltz_process
changeset 1:042cab870a39 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ribowaltz commit 416063685092b818a398e00d5027f7fe742230f1
| author | iuc |
|---|---|
| date | Mon, 23 Oct 2023 12:10:31 +0000 |
| parents | 6d4c94373bba |
| children | |
| files | macros.xml ribowaltz.R ribowaltz.xml ribowaltz_plot.R |
| diffstat | 4 files changed, 70 insertions(+), 26 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Thu Sep 22 20:30:54 2022 +0000 +++ b/macros.xml Mon Oct 23 12:10:31 2023 +0000 @@ -6,6 +6,7 @@ </requirements> </xml> <token name="@TOOL_VERSION@">1.2.0</token> + <token name="@VERSION_SUFFIX@">0</token> <token name="@PROFILE@">21.05</token> <xml name="edam_ontology"> <edam_topics>
--- a/ribowaltz.R Thu Sep 22 20:30:54 2022 +0000 +++ b/ribowaltz.R Mon Oct 23 12:10:31 2023 +0000 @@ -21,6 +21,7 @@ "cds_coverage_info", "Z", 1, "character", "psite_info_rdata", "O", 0, "character", "refseq_sep", "s", 0, "character", + "indel_threshold", "t", 0, "integer", "params_duplicate_filterting", "d", 0, "character", "params_peridiocity_filterting", "l", 0, "character", "params_custom_filterting", "c", 0, "character", @@ -48,7 +49,7 @@ sep <- NULL } # convert alignments in BAM files into list of data tables -reads_list <- bamtolist(bamfolder = opt$bamdir, annotation = annotation_dt, refseq_sep = sep) +reads_list <- bamtolist(bamfolder = opt$bamdir, annotation = annotation_dt, refseq_sep = sep, indel_threshold = opt$indel_threshold) library("jsonlite") # remove duplicate reads @@ -63,21 +64,21 @@ # selection of read lengths - periodicity filtering if (!is.null(opt$params_peridiocity_filterting)) { - json_peridiocity_filterting <- fromJSON(opt$params_peridiocity_filterting) - reads_list <- length_filter( - data = reads_list, - length_filter_mode = "periodicity", - periodicity_threshold = json_peridiocity_filterting$periodicity_threshold - ) + json_peridiocity_filterting <- fromJSON(opt$params_peridiocity_filterting) + reads_list <- length_filter( + data = reads_list, + length_filter_mode = "periodicity", + periodicity_threshold = json_peridiocity_filterting$periodicity_threshold + ) } # selection of read lengths - length range filtering if (!is.null(opt$params_custom_filterting)) { - json_custom_filterting <- fromJSON(opt$params_custom_filterting) - reads_list <- length_filter( - data = reads_list, - length_filter_mode = "custom", - length_range = json_custom_filterting$length_range - ) + json_custom_filterting <- fromJSON(opt$params_custom_filterting) + reads_list <- length_filter( + data = reads_list, + length_filter_mode = "custom", + length_range = json_custom_filterting$length_range + ) } # compute P-site offset
--- a/ribowaltz.xml Thu Sep 22 20:30:54 2022 +0000 +++ b/ribowaltz.xml Mon Oct 23 12:10:31 2023 +0000 @@ -1,16 +1,16 @@ -<tool id="ribowaltz_process" name="riboWaltz" version="@VERSION@" profile="@PROFILE@"> +<tool id="ribowaltz_process" name="riboWaltz" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> <description>calculation of optimal P-site offsets and diagnostic analysis</description> <macros> <import>macros.xml</import> </macros> - <expand macro='requirements'/> <expand macro='edam_ontology' /> <expand macro='xrefs'/> + <expand macro='requirements'/> <command detect_errors="exit_code"><![CDATA[ #for $i, $sample in enumerate($rep_samples): ln -s $sample.bam_file $sample.sample_name'.bam' && #end for - Rscript '${__tool_directory__}/ribowaltz.R' -b . -g '$gtf' --refseq_sep '$refseq_sep' + Rscript '${__tool_directory__}/ribowaltz.R' -b . -g '$gtf' --refseq_sep '$refseq_sep' --indel_threshold $indel_threshold #import json #if $filtering.duplicates.filter == 'yes': #set params_duplicate_filterting = [] @@ -59,6 +59,8 @@ <param name="gtf" type="data" format="gtf,gff" label="Annotation in GTF format"/> <param name="refseq_sep" type="text" optional="true" label="Separator between reference sequences' name and additional information to discard" help=" All characters before the first occurrence of the specified separator are kept"/> + <param name="indel_threshold" type="integer" value="5" min="0" + label="Positive integer value specifying the maximum number of indels allowed for each read."/> <param name="save_rdata" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Save p-site info RDATA file?" help="Useful for advanced plotting using riboWaltz-plot tool"/> @@ -198,6 +200,46 @@ </assert_contents> </output> </test> + <test expect_num_outputs="5"> + <param name="gtf" value="rep1_annot.gtf.gz"/> + <param name="refseq_sep" value="."/> + <param name="indel_threshold" value="3"/> + <param name="save_rdata" value="true"/> + <repeat name="rep_samples"> + <param name="sample_name" value="Replicate1"/> + <param name="bam_file" value="rep1.bam"/> + </repeat> + <section name="filtering"/> + <section name="psite_additional"> + <param name="flanking" value="3"/> + <param name="use_start" value="true"/> + <param name="psite_extrimity" value="auto"/> + <param name="cl" value="99"/> + </section> + <section name="coverage_additional"> + <param name="psites_per_region" value="true"/> + <param name="min_overlap" value="1"/> + <param name="start_nts" value="0"/> + <param name="stop_nts" value="0"/> + </section> + <output name="codon_coverage_out"> + <assert_contents> + <has_text_matching expression="transcript\tstart\tend\tfrom_cds_start\tfrom_cds_stop\tregion\tReplicate1"/> + <has_text_matching expression="ENSMUST00000000137\t2656\t2659\t865\t471\t3utr\t0"/> + </assert_contents> + </output> + <output name="cds_coverage_out"> + <assert_contents> + <has_text_matching expression="transcript\tlength_cds\tReplicate1"/> + <has_text_matching expression="ENSMUST00000019109\t741\t5"/> + </assert_contents> + </output> + <output name="psite_rdata_out"> + <assert_contents> + <has_size value="169141" delta="1000"/> + </assert_contents> + </output> + </test> </tests> <help><![CDATA[ riboWaltz is an R package for calculation of optimal P-site offsets, diagnostic analysis and visual inspection of ribosome profiling data. Taking advantage of a two-step algorithm where offset information is passed through populations of reads with different length in order to maximize offset coherence, riboWaltz computes with high precision the P-site offset. riboWaltz also provides a variety of graphical representations, laying the foundations for further accurate RiboSeq analyses and improved interpretation of positional information. More information can be found here: https://github.com/LabTranslationalArchitectomics/riboWaltz
--- a/ribowaltz_plot.R Thu Sep 22 20:30:54 2022 +0000 +++ b/ribowaltz_plot.R Mon Oct 23 12:10:31 2023 +0000 @@ -118,7 +118,7 @@ print(metaprofile) sample_list <- list() for (sample_name in names(reads_psite_list)) { - sample_list[[sample_name]] <- c(sample_name) + sample_list[[sample_name]] <- c(sample_name) } metaheatmap <- metaheatmap_psite( reads_psite_list, @@ -138,15 +138,15 @@ pdf("codon_usage.pdf", height = 6, width = 16) json_codon_usage_psite <- fromJSON(opt$params_codon_usage_psite) for (sample_name in names(reads_psite_list)) { - cu_barplot <- codon_usage_psite( - reads_psite_list, - annotation_dt, - sample = sample_name, - fastapath = json_codon_usage_psite$fastapath, - fasta_genome = FALSE, - frequency_normalization = json_codon_usage_psite$frequency - ) - print(cu_barplot[["plot"]]) + cu_barplot <- codon_usage_psite( + reads_psite_list, + annotation_dt, + sample = sample_name, + fastapath = json_codon_usage_psite$fastapath, + fasta_genome = FALSE, + frequency_normalization = json_codon_usage_psite$frequency + ) + print(cu_barplot[["plot"]]) } dev.off() }