Skip to content

Update rasusa #7914

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
SaimMomin12 merged 8 commits into from
Apr 22, 2026
+79 −77
Merged

Update rasusa #7914

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
d72e1cb
Update rasusa to 4.0.0
RZ9082 Apr 13, 2026
6f376d9
Updating tools/rasusa from version 3.0.0 to 4.0.0
RZ9082 Apr 20, 2026
c96922b
Bump profile
RZ9082 Apr 21, 2026
56d8e9f
Add a test with sam output
RZ9082 Apr 21, 2026
fb1a41c
rm lint_skip
RZ9082 Apr 21, 2026
9619c08
Remove sam option
RZ9082 Apr 22, 2026
7426714
Delete sam test-data
RZ9082 Apr 22, 2026
58eb1f7
Remove sam from possible input formats
RZ9082 Apr 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion tools/rasusa/.lint_skip
View file
Open in desktop

This file was deleted.

181 changes: 103 additions & 78 deletions tools/rasusa/rasusa.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
<tool id="rasusa" name="rasusa" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
<tool id="rasusa" name="rasusa" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
<description>Randomly subsample reads to a specified coverage</description>
<macros>
<token name="@TOOL_VERSION@">3.0.0</token>
<token name="@TOOL_VERSION@">4.0.0</token>
<token name="@VERSION_SUFFIX@">0</token>
<token name="@PROFILE@">25.0</token>
<token name="@FORMATS@">fastqsanger,fastqsanger.gz,fasta,fasta.gz</token>
<xml name="size_units">
<option value="b">bases</option>
Expand Down Expand Up @@ -52,7 +53,7 @@
--frac $subsample.frac
#end if
#if $r1_ext.endswith(".gz") or $r2_ext.endswith(".gz")
--output-type g
--compress-type g
#end if ]]>
</token>
</macros>
Expand All @@ -65,51 +66,57 @@
</requirements>

<command detect_errors="exit_code"><![CDATA[
#if str( $input.input_selector ) == "aligned":
ln -s '$bam' 'input.bam' &&
ln -s '$bam.metadata.bam_index' 'input.bam.bai' &&
rasusa aln
--coverage $input.coverage
--step-size $input.step_size
#if str($input.input_selector) == "aligned":
#if '$aligned_input.ext' == "bam":
ln -s '$aligned_input.metadata.bam_index' 'input.bam.bai' &&
#end if
ln -s '$aligned_input' input.$aligned_input.ext &&
rasusa aln
--coverage $input.coverage
--step-size $input.step_size
#else:
rasusa reads
rasusa reads
#end if

#if $seed
-s $seed
-s $seed
#end if

#if str( $input.input_selector ) == "paired":
#if str($input.input_selector) == "paired":
#set r1_ext = $input.reads1.extension
#set r2_ext = $input.reads2.extension
-o 'paired_out1.$r1_ext'
-o 'paired_out2.$r2_ext'
@FASTQ_SUBSAMPLE_OPTIONS@
'${input.reads1}'
'${input.reads2}' &&
mv 'paired_out1.$r1_ext' '$paired_output1' &&
mv 'paired_out2.$r2_ext' '$paired_output2'
-o 'paired_out1.$r1_ext'
-o 'paired_out2.$r2_ext'
@FASTQ_SUBSAMPLE_OPTIONS@
'${input.reads1}'
'${input.reads2}' &&
mv 'paired_out1.$r1_ext' '$paired_output1' &&
mv 'paired_out2.$r2_ext' '$paired_output2'

#elif str( $input.input_selector ) == "paired_collection":
#elif str($input.input_selector) == "paired_collection":
#set r1_ext = $input.collection.forward.extension
#set r2_ext = $input.collection.reverse.extension
-o 'paired_out1.$r1_ext'
-o 'paired_out2.$r2_ext'
@FASTQ_SUBSAMPLE_OPTIONS@
'${input.collection.forward}'
'${input.collection.reverse}' &&
mv 'paired_out1.$r1_ext' '${collection_output.forward}' &&
mv 'paired_out2.$r2_ext' '${collection_output.reverse}'
-o 'paired_out1.$r1_ext'
-o 'paired_out2.$r2_ext'
@FASTQ_SUBSAMPLE_OPTIONS@
'${input.collection.forward}'
'${input.collection.reverse}' &&
mv 'paired_out1.$r1_ext' '${collection_output.forward}' &&
mv 'paired_out2.$r2_ext' '${collection_output.reverse}'

#elif str( $input.input_selector ) == "single":
#elif str($input.input_selector) == "single":
#set r1_ext = $input.reads.extension
-o 'single_out.$r1_ext'
@FASTQ_SUBSAMPLE_OPTIONS@
'${input.reads}' &&
mv 'single_out.$r1_ext' '$single_output'
-o 'single_out.$r1_ext'
@FASTQ_SUBSAMPLE_OPTIONS@
'${input.reads}' &&
mv 'single_out.$r1_ext' '$single_output'

#elif str( $input.input_selector ) == "aligned":
'input.bam' | samtools sort --no-PG -@ 1 -T '\${TMPDIR:-.}' -O bam -o '$bam_output' -
#elif str($input.input_selector) == "aligned":
#if str($input.aligned_output_format) == "bam":
--output-format bam 'input.$aligned_input.ext' | samtools sort --no-PG -@ 1 -T '\${TMPDIR:-.}' -O bam -o '$bam_output' -
#elif str($input.aligned_output_format) == "sam":
--output-format sam 'input.$aligned_input.ext' | samtools sort --no-PG -@ 1 -T '\${TMPDIR:-.}' -O sam -o '$sam_output' -
#end if
#end if
]]></command>
<inputs>
Expand All @@ -118,7 +125,7 @@ mv 'single_out.$r1_ext' '$single_output'
<option value="paired">Paired-end FASTQ</option>
<option value="single">Single-end FASTQ</option>
<option value="paired_collection">Paired FASTQ Collection</option>
<option value="aligned">BAM file of aligned reads</option>
<option value="aligned">BAM/SAM file of aligned reads</option>
Comment thread
RZ9082 marked this conversation as resolved.
Outdated
</param>
<when value="paired">
<param name="reads1" type="data" format="@FORMATS@" label="Select first set of reads" help="Specify dataset with forward reads"/>
Expand All @@ -134,10 +141,14 @@ mv 'single_out.$r1_ext' '$single_output'
<expand macro="params_fastq" />
</when>
<when value="aligned">
<param name="bam" format="sam,bam" type="data" label="Select BAM file(s) with alignments"/>
<param name="aligned_input" format="sam,bam" type="data" label="Select BAM/SAM file with alignments"/>
Comment thread
RZ9082 marked this conversation as resolved.
Outdated
<param argument="--coverage" type="integer" min="0" optional="true" value="" label="The desired depth of coverage to subsample the alignment to"/>
<param type="integer" argument="--step-size" value="100" label="When a region has less than the desired coverage, the step size to move along the chromosome to find more reads."
help="The lowest of the step and the minimum end coordinate of the reads in the region will be used. This parameter can have a significant impact on the runtime of the subsampling process."/>
<param type="select" name="aligned_output_format" label="Select desired output format">
<option value="bam" selected="true">BAM</option>
<option value="sam">SAM</option>
</param>
</when>
</conditional>
<param type="integer" argument="--seed" optional="true" label="Random seed to use"/>
Expand All @@ -158,7 +169,10 @@ mv 'single_out.$r1_ext' '$single_output'
<data name="reverse" label="${tool.name} on ${input.collection.reverse.name}: paired-end R2" format_source="collection['reverse']"/>
</collection>
<data name="bam_output" label="${tool.name} on ${on_string}: BAM" format="bam">
<filter>input['input_selector'] == 'aligned'</filter>
<filter>input['input_selector'] == 'aligned' and input['aligned_output_format'] == 'bam'</filter>
</data>
<data name="sam_output" label="${tool.name} on ${on_string}: SAM" format="sam">
<filter>input['input_selector'] == 'aligned' and input['aligned_output_format'] == 'sam'</filter>
</data>
</outputs>
<tests>
Expand All @@ -167,12 +181,12 @@ mv 'single_out.$r1_ext' '$single_output'
<conditional name="input">
<param name="input_selector" value="single"/>
<param name="reads" value="r1.fastq.gz"/>
</conditional>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="b"/>
<param name="genome_size" value="1000"/>
<param name="coverage" value="1"/>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="b"/>
<param name="genome_size" value="1000"/>
<param name="coverage" value="1"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output name="single_output" value="single_by_coverage_b.fastq.gz" ftype="fastqsanger.gz"/>
Expand All @@ -183,12 +197,12 @@ mv 'single_out.$r1_ext' '$single_output'
<param name="input_selector" value="paired"/>
<param name="reads1" value="r1.fastq.gz"/>
<param name="reads2" value="r2.fastq.gz"/>
</conditional>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="k"/>
<param name="genome_size" value="1"/>
<param name="coverage" value="1"/>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="k"/>
<param name="genome_size" value="1"/>
<param name="coverage" value="1"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output name="paired_output1" value="paired1_by_coverage_k.fastq.gz" ftype="fastqsanger.gz"/>
Expand All @@ -204,12 +218,12 @@ mv 'single_out.$r1_ext' '$single_output'
<element name="reverse" value="r2.fastq.gz"/>
</collection>
</param>
</conditional>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="m"/>
<param name="genome_size" value="0.001"/>
<param name="coverage" value="1"/>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="m"/>
<param name="genome_size" value="0.001"/>
<param name="coverage" value="1"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output_collection name="collection_output" type="paired">
Expand All @@ -222,12 +236,12 @@ mv 'single_out.$r1_ext' '$single_output'
<conditional name="input">
<param name="input_selector" value="single"/>
<param name="reads" value="r1.fasta.gz"/>
</conditional>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="g"/>
<param name="genome_size" value="0.001"/>
<param name="coverage" value="0.001"/>
<conditional name="subsample">
<param name="type" value="coverage"/>
<param name="genome_size_unit" value="g"/>
<param name="genome_size" value="0.001"/>
<param name="coverage" value="0.001"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output name="single_output" value="single_end_by_coverage_g.fasta" ftype="fasta.gz"/>
Expand All @@ -238,11 +252,11 @@ mv 'single_out.$r1_ext' '$single_output'
<param name="input_selector" value="paired"/>
<param name="reads1" value="r1.fastq"/>
<param name="reads2" value="r2.fastq"/>
</conditional>
<conditional name="subsample">
<param name="type" value="num_bases"/>
<param name="num_bases_unit" value="k"/>
<param name="bases" value="2"/>
<conditional name="subsample">
<param name="type" value="num_bases"/>
<param name="num_bases_unit" value="k"/>
<param name="bases" value="2"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output name="paired_output1" value="paired1_by_num_bases_k.fastq" ftype="fastqsanger"/>
Expand All @@ -254,10 +268,10 @@ mv 'single_out.$r1_ext' '$single_output'
<param name="input_selector" value="paired"/>
<param name="reads1" value="r1.fasta.gz"/>
<param name="reads2" value="r2.fasta.gz"/>
</conditional>
<conditional name="subsample">
<param name="type" value="num_reads"/>
<param name="num" value="5"/>
<conditional name="subsample">
<param name="type" value="num_reads"/>
<param name="num" value="5"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output name="paired_output1" value="paired1_by_num_reads.fasta.gz" ftype="fasta.gz"/>
Expand All @@ -273,10 +287,10 @@ mv 'single_out.$r1_ext' '$single_output'
<element name="reverse" value="r2.fasta"/>
</collection>
</param>
</conditional>
<conditional name="subsample">
<param name="type" value="frac_reads"/>
<param name="frac" value="0.6"/>
<conditional name="subsample">
<param name="type" value="frac_reads"/>
<param name="frac" value="0.6"/>
</conditional>
</conditional>
<param name="seed" value="1"/>
<output_collection name="collection_output" type="paired">
Expand All @@ -285,15 +299,26 @@ mv 'single_out.$r1_ext' '$single_output'
</output_collection>
</test>
<test expect_num_outputs="1">
<!-- test 8: bam input -->
<!-- test 8: bam input, bam output -->
<conditional name="input">
<param name="input_selector" value="aligned"/>
<param name="bam" value="input.bam" />
<param name="aligned_input" value="input.bam" />
<param name="coverage" value="1"/>
</conditional>
<param name="coverage" value="1"/>
<param name="seed" value="1"/>
<output name="bam_output" value="output.bam" ftype="bam"/>
</test>
<test expect_num_outputs="1">
<!-- test 9: bam input, sam output -->
<conditional name="input">
<param name="input_selector" value="aligned"/>
<param name="aligned_input" value="input.bam" />
<param name="coverage" value="1"/>
<param name="aligned_output_format" value="sam"/>
</conditional>
<param name="seed" value="1"/>
<output name="bam_output" value="output.sam" ftype="sam"/>
</test>
</tests>
<help><![CDATA[

Expand All @@ -306,4 +331,4 @@ specifying the size of the subset:
<citations>
<citation type="doi">10.21105/joss.03941</citation>
</citations>
</tool>
</tool>
Binary file modified tools/rasusa/test-data/output.bam
View file
Open in desktop
Binary file not shown.
Loading
Loading