Mercurial > repos > iuc > nanoplot
changeset 5:a3c4fe6f49ab draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/nanoplot/ commit 52e462654477b6acf9a087063d3ddb19f66f8b38
| author | iuc |
|---|---|
| date | Thu, 16 Jun 2022 20:08:15 +0000 |
| parents | edbb6c5028f5 |
| children | 0f1c34698076 |
| files | nanoplot.xml test-data/HistogramReadlength.png test-data/NanoStats.txt test-data/NanoStats_post_filtering.txt |
| diffstat | 4 files changed, 126 insertions(+), 76 deletions(-) [+] |
line wrap: on
line diff
--- a/nanoplot.xml Sun Jan 19 19:03:02 2020 -0500 +++ b/nanoplot.xml Thu Jun 16 20:08:15 2022 +0000 @@ -1,38 +1,61 @@ -<tool id="nanoplot" name="NanoPlot" version="@TOOL_VERSION@+galaxy1"> +<tool id="nanoplot" name="NanoPlot" version="@TOOL_VERSION@+galaxy1" profile="20.05"> <description>Plotting suite for Oxford Nanopore sequencing data and alignments</description> <macros> - <token name="@TOOL_VERSION@">1.28.2</token> + <token name="@TOOL_VERSION@">1.36.2</token> </macros> <requirements> <requirement type="package" version="@TOOL_VERSION@">nanoplot</requirement> </requirements> + <stdio> + <regex match="kaleido problem" source="stderr" level="fatal" description="No static plots are saved due to some kaleido problem" /> + </stdio> <version_command>NanoPlot --version</version_command> <command detect_errors="exit_code"><![CDATA[ +## set TMPDIR if not already set by admin +## otherwise kalleido fails with `Less than 64MB of free space in temporary directory for shared memory files: 0` +## export TMPDIR=\${TMPDIR:-\$_GALAXY_JOB_TMP_DIR}; + #set $myfiles = $mode.reads.files - #set reads_temp = [] #if $mode.choice == 'combined': #for $i, $f in enumerate($myfiles) - #if $f.ext == "fastqsanger": + #if $f.ext.startswith("fastq"): #set $extension = 'fastq' #else #set $extension = $f.ext #end if + #if $f.ext.endswith(".gz"): + #set $f = $extension + ".gz" + #else if $f.ext.endswith(".bz"): + #set $extension = $extension + "bz2" + #end if ln -s '$f' './read_${i}.$extension' && + #if "bam" in $extension + ln -s '$f.metadata.bam_index' './read_${i}.${extension}.bai' && + #end if $reads_temp.append("read_" + str($i) + "." + str($extension)) #end for #else - #if $myfiles.ext == "fastqsanger": + #if $myfiles.ext.startswith("fastq"): #set $extension = 'fastq' #else #set $extension = $myfiles.ext #end if - ln -s '$mode.reads.files' './read.$extension' && + #if $myfiles.ext.endswith(".gz"): + #set $extension = $extension + ".gz" + #else if $myfiles.ext.endswith(".bz"): + #set $extension = $extension + "bz2" + #end if + ln -s '$myfiles' './read.$extension' && + #if "bam" in $extension + ln -s '$myfiles.metadata.bam_index' './read.${extension}.bai' && + #end if $reads_temp.append("read." + str($extension)) #end if NanoPlot --threads \${GALAXY_SLOTS:-4} + --tsv_stats --$mode.reads.type ${' '.join($reads_temp)} #if $filter.maxlength --maxlength $filter.maxlength @@ -46,15 +69,15 @@ #if $filter.minqual --minqual $filter.minqual #end if + #if $filter.runtime_until + -- $filter.runtime_until + #end if #if $filter.readtype --readtype $filter.readtype #end if #if $customization.color --color $customization.color #end if - #if $customization.format - --format $customization.format - #end if #if $customization.plots --plots ${str($customization.plots).replace(',', ' ')} #end if @@ -63,8 +86,10 @@ $filter.percentqual $filter.alength $filter.barcoded + $filter.no_supplementary $customization.N50 -o '.' + && >&2 cat *log ]]></command> <inputs> <conditional name="mode"> @@ -190,6 +215,11 @@ optional="true" label="Drop reads with an average quality lower than specified."/> <param + type="integer" + argument="--runtime_until" + optional="true" + label="Only take the N first hours of a run"/> + <param type="select" argument="--readtype" optional="true" @@ -204,6 +234,12 @@ truevalue="--barcoded" falsevalue="" label="Use if you want to split the summary file by barcode."/> + <param + type="boolean" + argument="--no_supplementary" + truevalue="--no_supplementary" + falsevalue="" + label="Use if you want to remove supplementary alignments"/> </section> <section name="customization" @@ -365,23 +401,13 @@ </param> <param type="select" - argument="--format" - optional="true" - label="Specify the output format of the plots."> - <option selected="True" value="png">png</option> - <option value="svg">svg</option> - </param> - <param - type="select" argument="--plots" optional="true" multiple="true" display="checkboxes" label="Specify the bivariate format of the plots."> - <option value="kde">kde</option> - <option value="hex">hex</option> - <option value="dot">dot</option> - <option value="pauvre">pauvre</option> + <option value="kde">kernel density estimation (kde)</option> + <option value="dot">dots (dot)</option> </param> <param type="boolean" @@ -393,18 +419,10 @@ </inputs> <outputs> <data name="output_html" format="html" from_work_dir="NanoPlot-report.html" label="${tool.name} on ${on_string}: HTML report"/> - <data name="nanostats" format="txt" from_work_dir="NanoStats.txt" label="${tool.name} on ${on_string}: NanoStats"/> - <data name="nanostats_post_filtering" format="txt" from_work_dir="NanoStats_post_filtering.txt" label="${tool.name} on ${on_string}: NanoStats post filtering"/> - <data name="read_length" format="png" from_work_dir="HistogramReadlength.*" label="${tool.name} on ${on_string}: Histogram Read Length "> - <change_format> - <when input="customization.format" value="svg" format="svg"/> - </change_format> - </data> - <data name="log_read_length" format="png" from_work_dir="LogTransformed_HistogramReadlength.*" label="${tool.name} on ${on_string}: Log Transformed Histogram Read Length "> - <change_format> - <when input="customization.format" value="svg" format="svg"/> - </change_format> - </data> + <data name="nanostats" format="tabular" from_work_dir="NanoStats.txt" label="${tool.name} on ${on_string}: NanoStats"/> + <data name="nanostats_post_filtering" format="tabular" from_work_dir="NanoStats_post_filtering.txt" label="${tool.name} on ${on_string}: NanoStats post filtering" /> + <data name="read_length" format="png" from_work_dir="Non_weightedHistogramReadlength.png" label="${tool.name} on ${on_string}: Histogram Read Length"/> + <data name="log_read_length" format="png" from_work_dir="Non_weightedLogTransformed_HistogramReadlength.png" label="${tool.name} on ${on_string}: Log Transformed Histogram Read Length"/> </outputs> <tests> <test> @@ -412,18 +430,30 @@ <param name="choice" value="batch"/> <conditional name="reads"> <param name="type" value="fastq_rich"/> - <param name="files" value="reads.fastq.gz" ftype="fastq.gz"/> + <param name="files" value="reads.fastq.gz" ftype="fastqsanger.gz"/> </conditional> </conditional> <section name="filter"> <param name="downsample" value="800"/> </section> <section name="customization"> - <param name="plots" value="hex,kde"/> + <param name="plots" value="kde"/> </section> - <output name="output_html" file="NanoPlot-report.html" ftype="html" lines_diff="8" /> - <output name="nanostats_post_filtering" file="NanoStats_post_filtering.txt" ftype="txt"/> - <output name="read_length" file="HistogramReadlength.png" ftype="png" compare="sim_size" delta="3000"/> + <output name="output_html" ftype="html"> + <assert_contents> + <has_text text="html"/> + <has_text text="mean_qual"/> + </assert_contents> + </output> + <output name="nanostats" file="NanoStats.txt" ftype="tabular"/> + <output name="nanostats_post_filtering" file="NanoStats_post_filtering.txt" ftype="tabular"/> + <output name="read_length" ftype="png" file="HistogramReadlength.png" compare="sim_size"> + </output> + <output name="log_read_length" ftype="png"> + <assert_contents> + <has_text text="PNG"/> + </assert_contents> + </output> </test> <test> <conditional name="mode"> @@ -439,15 +469,18 @@ </section> <section name="customization"> <param name="color" value="yellow"/> - <param name="format" value="svg"/> </section> - <output name="output_html" file="bam-report.html" ftype="html" lines_diff="16"> + <output name="output_html" ftype="html"> <assert_contents> <has_text text="html"/> <has_text text="Aligned read length vs Percent identity plot using dots"/> <!-- bam report specific --> </assert_contents> </output> - <output name="read_length" file="bam-LogTransformed_HistogramReadlength.svg" ftype="svg" compare="sim_size"/> + <output name="read_length" ftype="png"> + <assert_contents> + <has_text text="PNG"/> + </assert_contents> + </output> </test> <test><!-- test with multiple input files --> <conditional name="mode"> @@ -460,8 +493,8 @@ <output name="output_html" ftype="html"> <assert_contents> <has_text text="html"/> - <not_has_text text="Aligned read length vs Percent identity plot using dots"/> <!-- bam report specific --> - <has_text text="<td>9.0</td>"/> <!--check both files were used 4+5 reads --> + <not_has_text text="Aligned read length vs Percent identity plot using dots"/> + <has_text text="<td>9</td>"/> <!--check both files were used 4+5 reads --> </assert_contents> </output> </test>
--- a/test-data/NanoStats.txt Sun Jan 19 19:03:02 2020 -0500 +++ b/test-data/NanoStats.txt Thu Jun 16 20:08:15 2022 +0000 @@ -1,6 +1,25 @@ -General summary: -Mean read length: 2,564.9 -Median read length: 1,910.0 -Number of reads: 9.0 -Read length N50: 4,275.0 -Total bases: 23,084.0 +Metrics dataset +number_of_reads 371 +number_of_bases 8611871.0 +median_read_length 9390.0 +mean_read_length 23212.6 +read_length_stdev 42729.8 +n50 60395.0 +active_channels 169 +mean_qual 10.1 +median_qual 10.3 +longest_read_(with_Q):1 393431 (10.6) +longest_read_(with_Q):2 341725 (11.8) +longest_read_(with_Q):3 320662 (8.0) +longest_read_(with_Q):4 226843 (9.1) +longest_read_(with_Q):5 221901 (10.0) +highest_Q_read_(with_length):1 13.3 (6333) +highest_Q_read_(with_length):2 13.1 (5448) +highest_Q_read_(with_length):3 12.9 (27834) +highest_Q_read_(with_length):4 12.8 (20351) +highest_Q_read_(with_length):5 12.8 (97730) +Reads >Q5: 371 (100.0%) 8.6Mb +Reads >Q7: 371 (100.0%) 8.6Mb +Reads >Q10: 207 (55.8%) 4.7Mb +Reads >Q12: 49 (13.2%) 0.9Mb +Reads >Q15: 0 (0.0%) 0.0Mb
--- a/test-data/NanoStats_post_filtering.txt Sun Jan 19 19:03:02 2020 -0500 +++ b/test-data/NanoStats_post_filtering.txt Thu Jun 16 20:08:15 2022 +0000 @@ -1,27 +1,25 @@ -General summary: -Active channels: 169.0 -Mean read length: 23,212.6 -Mean read quality: 10.1 -Median read length: 9,390.0 -Median read quality: 10.3 -Number of reads: 371.0 -Read length N50: 60,395.0 -Total bases: 8,611,871.0 -Number, percentage and megabases of reads above quality cutoffs ->Q5: 371 (100.0%) 8.6Mb ->Q7: 371 (100.0%) 8.6Mb ->Q10: 207 (55.8%) 4.7Mb ->Q12: 49 (13.2%) 0.9Mb ->Q15: 0 (0.0%) 0.0Mb -Top 5 highest mean basecall quality scores and their read lengths -1: 13.3 (6333) -2: 13.1 (5448) -3: 12.9 (27834) -4: 12.8 (20351) -5: 12.8 (97730) -Top 5 longest reads and their mean basecall quality score -1: 393431 (10.6) -2: 341725 (11.8) -3: 320662 (8.0) -4: 226843 (9.1) -5: 221901 (10.0) +Metrics dataset +number_of_reads 371 +number_of_bases 8611871.0 +median_read_length 9390.0 +mean_read_length 23212.6 +read_length_stdev 42729.8 +n50 60395.0 +active_channels 169 +mean_qual 10.1 +median_qual 10.3 +longest_read_(with_Q):1 393431 (10.6) +longest_read_(with_Q):2 341725 (11.8) +longest_read_(with_Q):3 320662 (8.0) +longest_read_(with_Q):4 226843 (9.1) +longest_read_(with_Q):5 221901 (10.0) +highest_Q_read_(with_length):1 13.3 (6333) +highest_Q_read_(with_length):2 13.1 (5448) +highest_Q_read_(with_length):3 12.9 (27834) +highest_Q_read_(with_length):4 12.8 (20351) +highest_Q_read_(with_length):5 12.8 (97730) +Reads >Q5: 371 (100.0%) 8.6Mb +Reads >Q7: 371 (100.0%) 8.6Mb +Reads >Q10: 207 (55.8%) 4.7Mb +Reads >Q12: 49 (13.2%) 0.9Mb +Reads >Q15: 0 (0.0%) 0.0Mb