Mercurial > repos > jobucher > bbtools_clumpify
changeset 0:4db4aa29dca7 draft default tip
planemo upload commit bea844bbbf7c1ccbfe60af62697f89708e00522a
| author | jobucher |
|---|---|
| date | Thu, 07 Nov 2024 13:05:53 +0000 |
| parents | |
| children | |
| files | clumpify.xml test-data/2.fastq test-data/clumped_2.fastq |
| diffstat | 3 files changed, 211 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/clumpify.xml Thu Nov 07 13:05:53 2024 +0000 @@ -0,0 +1,187 @@ +<tool id="clumpify" name="BBMap Clumpify: Deduplication" version="0.1.0+galaxy0" python_template_version="3.5" profile="21.05"> + <requirements> + <requirement type="package" version="38.84">bbmap</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + + #import re + + #if $singlePaired.sPaired == "single" + #set read1 = re.sub('[^\w\-_.]', '_', str($singlePaired.input_singles.element_identifier)) + ln -s '${singlePaired.input_singles}' '${read1}' && + ##set output1 = 'clumpified_' + read1 + #set output1 = 'clumpified_read.fastq.gz' + ##ln -s '${ouput_single}' '${output1}' && + clumpify.sh in='${read1}' out='${output1}' groups=auto + #if $parameter_selection.use_sequencing_platform == "true" + $parameter_selection.sequencing_platform + #else + dupedist='$parameter_selection.dupedist' + #if $parameter_selection.spany == "true" + spany=t + #else + spany=f + #end if + #if $parameter_selection.adjacent == "true" + adjacent=t + #else + adjacent=f + #end if + #end if + + #if $advanced_parameters.use_advanced_options == "true" + #if $advanced_parameters.dedupe == "true" + dedupe=t + #else + dedupe=f + #end if + #if $advanced_parameters.optical == "true" + optical=t + #else + optical=f + #end if + #end if + #else + #set read1 = re.sub('[^\w\-_.]', '_', str($singlePaired.input_mate1.element_identifier)) + #set read2 = re.sub('[^\w\-_.]', '_', str($singlePaired.input_mate2.element_identifier)) + ln -s '${singlePaired.input_mate1}' '${read1}' && + ln -s '${singlePaired.input_mate2}' '${read2}' && + #set output1 = 'clumpified_read1.fastq.gz' + #set output2 = 'clumpified_read2.fastq.gz' + clumpify.sh in='${read1}' in2='${read2}' out='${output1}' out2='${output2}' groups=auto + #if $parameter_selection.use_sequencing_platform == "true" + $parameter_selection.sequencing_platform + #else + dupedist='$parameter_selection.dupedist' + #if $parameter_selection.spany == "true" + spany=t + #else + spany=f + #end if + #if $parameter_selection.adjacent == "true" + adjacent=t + #else + adjacent=f + #end if + #end if + + #if $advanced_parameters.use_advanced_options == "true" + #if $advanced_parameters.dedupe == "true" + dedupe=t + #else + dedupe=f + #end if + #if $advanced_parameters.optical == "true" + optical=t + #else + optical=f + #end if + #end if + #end if + + + ]]></command> + <inputs> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single"> + Single-end + </option> + <option value="paired"> + Paired-end + </option> + </param> + <when value="single"> + <param name="input_singles" type="data" + format="fastqsanger,fastqillumina,fastq,fasta,fastq.gz,fastqsanger.gz" label="FASTQ/FASTA file" + help="FASTQ or FASTA files."/> + </when> + <when value="paired"> + <param name="input_mate1" type="data" format="fastqsanger,fastqillumina,fastq,fasta,fastq.gz,fastqsanger.gz" label="Mate pair 1" help="FASTQ or FASTA files."/> + <param name="input_mate2" type="data" format="fastqsanger,fastqillumina,fastq,fasta,fastq.gz,fastqsanger.gz" label="Mate pair 2" help="FASTQ or FASTA files."/> + </when> + </conditional> + <conditional name="parameter_selection"> + <param name="use_sequencing_platform" type="select" label="Specify sequencing platform?" value="true" help="Check this box to specify the sequencing platform, or uncheck to manually set individual parameters." > + <option value="true">Yes</option> + <option value="false">No</option> + </param> + <when value="true"> + <param name="sequencing_platform" type="select" label="Specify sequencing platform used to obtain data"> + <option value="dupedist=40" selected="true">HiSeq 1T / HiSeq 2500</option> + <option value="dupedist=2500">HiSeq 3k / HiSeq 4k</option> + <option value="spany=t adjacent=t dupedist=12000">Novaseq / X-patterned flowcell</option> + <option value="spany=t adjacent=t dupedist=40">NextSeq</option> + <option value="dupedist=40">Other</option> + </param> + </when> + <when value="false"> + <param name="dupedist" type="integer" label="Duplication Distance (dupedist)" value="40" help="Specify the duplication distance." /> + <param name="spany" type="boolean" label="Spany" value="false" help="Enable spany (spany=t)." /> + <param name="adjacent" type="boolean" label="Adjacent" value="false" help="Enable adjacent (adjacent=t)." /> + </when> + </conditional> + <conditional name="advanced_parameters"> + <param name="use_advanced_options" type="select" label="Show additional options?" value="false" help="Check this box to set additional advanced parameters." > + <option value="false">No</option> + <option value="true">Yes</option> + </param> + <when value="true"> + <param name="dedupe" type="boolean" label="Dedupe" value="true" help="Specify whether to perform deduplication." /> + <param name="optical" type="boolean" label="Optical" value="true" help="Specify whether to consider optical duplicates." /> + </when> + <when value="false"> + <!-- No additional parameters needed when smooth is false --> + </when> + </conditional> + </inputs> + <outputs> + <!-- Define possible single-end output --> + <data name="output_single" format="fastq.gz" from_work_dir="clumpified_read.fastq.gz" + label="Clumpify Output: ${singlePaired.input_singles.element_identifier}" > + <filter> + singlePaired['sPaired'] == "single" + </filter> + </data> + + <!-- Define possible paired-end outputs --> + <data name="paired_output1" format="fastq.gz" from_work_dir="clumpified_read1.fastq.gz" + label="Clumpify Output: ${singlePaired.input_mate1.element_identifier}"> + <filter> + singlePaired['sPaired'] == "paired" + </filter> + </data> + <data name="paired_output2" format="fastq.gz" from_work_dir="clumpified_read2.fastq.gz" + label="Clumpify Output: ${singlePaired.input_mate2.element_identifier}"> + <filter> + singlePaired['sPaired'] == "paired" + </filter> + </data> + </outputs> + <tests> + <!-- Test for single-end input --> + <test expect_num_outputs="1"> + <param name="sPaired" value="single"/> + <param name="input_singles" value="test-data/single_end.fastq.gz"/> + <param name="use_sequencing_platform" value="true"/> + <param name="sequencing_platform" value="dupedist=40"/> + <param name="use_advanced_options" value="false"/> + <output name="output_single" file="clumpify_output_input1.fastq.gz" count="1" /> + </test> + + </tests> + <help><![CDATA[ + dedup test update + ]]></help> + <citations> + <citation type="bibtex"> + @misc{githubclumpify.sh, + author = {LastTODO, FirstTODO}, + year = {TODO}, + title = {clumpify.sh}, + publisher = {GitHub}, + journal = {GitHub repository}, + url = {https://github.com/BioInfoTools/BBMap/blob/master/sh/clumpify.sh}, + }</citation> + </citations> +</tool> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/2.fastq Thu Nov 07 13:05:53 2024 +0000 @@ -0,0 +1,12 @@ +@EAS54_6_R1_2_1_413_324 +CCCTTCTTGTCTTCAGCGTTTCTCC ++ +;;3;;;;;;;;;;;;7;;;;;;;88 +@EAS54_6_R1_2_1_540_792 +TTGGCAGGCCAAGGCCGATGGATCA ++ +;;;;;;;;;;;7;;;;;-;;;3;83 +@EAS54_6_R1_2_1_443_348 +GTTGCTTCTGGCGTGGGTGGGGGGG ++EAS54_6_R1_2_1_443_348 +;;;;;;;;;;;9;7;;.7;393333 \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/clumped_2.fastq Thu Nov 07 13:05:53 2024 +0000 @@ -0,0 +1,12 @@ +@EAS54_6_R1_2_1_540_792 +TTGGCAGGCCAAGGCCGATGGATCA ++ +;;;;;;;;;;;7;;;;;-;;;3;83 +@EAS54_6_R1_2_1_413_324 +CCCTTCTTGTCTTCAGCGTTTCTCC ++ +;;3;;;;;;;;;;;;7;;;;;;;88 +@EAS54_6_R1_2_1_443_348 +GTTGCTTCTGGCGTGGGTGGGGGGG ++ +;;;;;;;;;;;9;7;;.7;393333