Skip to content
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

Updating tools/rseqc from version 5.0.1 to 5.0.3 #5618

Closed
wants to merge 4 commits into from
Closed

Updating tools/rseqc from version 5.0.1 to 5.0.3 #5618

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
75be0bb
Updating tools/rseqc from version 5.0.1 to 5.0.3
Nov 7, 2023
87ea68e
fix linting
bgruening Nov 12, 2023
0449e4b
add citations
bgruening Feb 25, 2024
f2839f2
add expect_num_outputs and reformat all tools
bgruening Mar 6, 2024
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
31 changes: 10 additions & 21 deletions tools/rseqc/FPKM_count.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,10 @@
<macros>
<import>rseqc_macros.xml</import>
</macros>

<expand macro="bio_tools"/>

<expand macro="requirements" />

<expand macro="stdio" />

<expand macro="requirements"/>
<expand macro="stdio"/>
<version_command><![CDATA[FPKM_count.py --version]]></version_command>

<command><![CDATA[
@BAM_SAM_INPUTS@
FPKM_count.py -i 'input.${extension}' -o output -r '${refgene}'
Expand All @@ -36,31 +31,28 @@
--single-read="${singleread}"
]]>
</command>

<inputs>
<expand macro="bam_param" />
<expand macro="refgene_param" />
<expand macro="strand_type_param" />
<expand macro="multihits_param" />
<expand macro="bam_param"/>
<expand macro="refgene_param"/>
<expand macro="strand_type_param"/>
<expand macro="multihits_param"/>
<param name="onlyexonic" type="boolean" value="false" truevalue="--only-exonic" falsevalue="" label="Only use exonic (UTR exons and CDS exons) reads, otherwise use all reads" help="(--only-exonic)"/>
<param name="singleread" type="select" label="How should read-pairs that only have one end mapped be counted?" help="(--single-read)">
<option value="1" selected="true">Treat it as a whole fragment (1)</option>
<option value="0.5">Treat it as a half fragment (0.5)</option>
<option value="0">Ignore it (0)</option>
</param>
</inputs>

<outputs>
<data format="tabular" name="output" from_work_dir="output.FPKM.xls" label="${tool.name} on ${on_string}: FPKM counts"/>
</outputs>

<tests>
<test>
<test expect_num_outputs="1">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" ftype="bed12"/>
<output name="output" file="output01.tab"/>
</test>
<test>
<test expect_num_outputs="1">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" ftype="bed12"/>
<conditional name="multihits_type">
Expand All @@ -69,11 +61,10 @@
</conditional>
<output name="output" file="output02.tab"/>
<assert_command>
<has_text text="--mapq=20" />
<has_text text="--mapq=20"/>
</assert_command>
</test>
</tests>

<help><![CDATA[
FPKM_count.py
+++++++++++++
Expand Down Expand Up @@ -134,7 +125,5 @@ chr1 32479294 32509482 NM_006559 2891.0 ‘+’ 2151.0

]]>
</help>

<expand macro="citations" />

<expand macro="citations"/>
</tool>
46 changes: 18 additions & 28 deletions tools/rseqc/RNA_fragment_size.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,49 +6,41 @@
<import>rseqc_macros.xml</import>
</macros>
<expand macro="bio_tools"/>

<expand macro="requirements" />

<expand macro="stdio" />

<expand macro="requirements"/>
<expand macro="stdio"/>
<version_command><![CDATA[RNA_fragment_size.py --version]]></version_command>

<command><![CDATA[
@BAM_SAM_INPUTS@
RNA_fragment_size.py -i 'input.${extension}' --refgene='${refgene}' --mapq=${mapq} --frag-num=${fragnum} > '${output}'
]]>
</command>

<inputs>
<expand macro="bam_param" />
<expand macro="refgene_param" />
<expand macro="mapq_param" />
<param name="fragnum" type="integer" value="3" label="Minimum number of fragments (default: 3)" help="(--frag-num)" />
<expand macro="bam_param"/>
<expand macro="refgene_param"/>
<expand macro="mapq_param"/>
<param name="fragnum" type="integer" value="3" label="Minimum number of fragments (default: 3)" help="(--frag-num)"/>
</inputs>

<outputs>
<data format="tabular" name="output" />
<data format="tabular" name="output"/>
</outputs>

<tests>
<test>
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
<test expect_num_outputs="1">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" ftype="bed12"/>
<output name="output">
<assert_contents>
<has_line_matching expression="^chrom\ttx_start\ttx_end\tsymbol\tfrag_count\tfrag_mean\tfrag_median\tfrag_std$" />
<has_line_matching expression="^chr1\t11873\t14409\tNR_046018\t1\t0\t0\t0$" />
<has_line_matching expression="^chr1\t14361\t29370\tNR_024540\t14\t66.5\t51.0\t41.119599080\d+$" />
<has_line_matching expression="^chr1\t17368\t17436\tNR_106918\t0\t0\t0\t0$" />
<has_line_matching expression="^chr1\t17368\t17436\tNR_107062\t0\t0\t0\t0$" />
<has_line_matching expression="^chr1\t34610\t36081\tNR_026818\t0\t0\t0\t0$" />
<has_line_matching expression="^chr1\t34610\t36081\tNR_026820\t0\t0\t0\t0$" />
<has_line_matching expression="^chr1\t69090\t70008\tNM_001005484\t0\t0\t0\t0$" />
<has_line_matching expression="^chrom\ttx_start\ttx_end\tsymbol\tfrag_count\tfrag_mean\tfrag_median\tfrag_std$"/>
<has_line_matching expression="^chr1\t11873\t14409\tNR_046018\t1\t0\t0\t0$"/>
<has_line_matching expression="^chr1\t14361\t29370\tNR_024540\t14\t66.5\t51.0\t41.119599080\d+$"/>
<has_line_matching expression="^chr1\t17368\t17436\tNR_106918\t0\t0\t0\t0$"/>
<has_line_matching expression="^chr1\t17368\t17436\tNR_107062\t0\t0\t0\t0$"/>
<has_line_matching expression="^chr1\t34610\t36081\tNR_026818\t0\t0\t0\t0$"/>
<has_line_matching expression="^chr1\t34610\t36081\tNR_026820\t0\t0\t0\t0$"/>
<has_line_matching expression="^chr1\t69090\t70008\tNM_001005484\t0\t0\t0\t0$"/>
</assert_contents>
</output>
</test>
</tests>

<help><![CDATA[
RNA_fragment_size.py
++++++++++++++++++++
Expand Down Expand Up @@ -80,7 +72,5 @@ Minimum number of fragments
]]>

</help>

<expand macro="citations" />

<expand macro="citations"/>
</tool>
66 changes: 28 additions & 38 deletions tools/rseqc/RPKM_saturation.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,13 +4,9 @@
<import>rseqc_macros.xml</import>
</macros>
<expand macro="bio_tools"/>

<expand macro="requirements" />

<expand macro="stdio" />

<expand macro="requirements"/>
<expand macro="stdio"/>
<version_command><![CDATA[RPKM_saturation.py --version]]></version_command>

<command><![CDATA[
@BAM_SAM_INPUTS@
RPKM_saturation.py -i 'input.${extension}' -o output -r '${refgene}'
Expand All @@ -36,53 +32,49 @@
-l ${percentileFloor} -u ${percentileCeiling} -s ${percentileStep} -c ${rpkmCutoff}
--mapq $mapq
]]></command>

<inputs>
<expand macro="bam_sam_param" />
<expand macro="refgene_param" />
<expand macro="strand_type_param" />
<expand macro="bam_sam_param"/>
<expand macro="refgene_param"/>
<expand macro="strand_type_param"/>
<param name="percentileFloor" type="integer" value="5" label="Begin sampling from this percentile (default=5)" help="(--percentile-floor)"/>
<param name="percentileCeiling" type="integer" value="100" label="End sampling at this percentile (default=100)" help="(--percentile-ceiling)" />
<param name="percentileStep" type="integer" value="5" label="Sampling step size (default=5)" help="(--percentile-step)" />
<param name="rpkmCutoff" type="text" value="0.01" label="Ignore transcripts with RPKM smaller than this number (default=0.01)" help="(--rpkm-cutoff)" />
<expand macro="mapq_param" />
<expand macro="rscript_output_param" />
<param name="percentileCeiling" type="integer" value="100" label="End sampling at this percentile (default=100)" help="(--percentile-ceiling)"/>
<param name="percentileStep" type="integer" value="5" label="Sampling step size (default=5)" help="(--percentile-step)"/>
<param name="rpkmCutoff" type="text" value="0.01" label="Ignore transcripts with RPKM smaller than this number (default=0.01)" help="(--rpkm-cutoff)"/>
<expand macro="mapq_param"/>
<expand macro="rscript_output_param"/>
</inputs>

<outputs>
<expand macro="pdf_output_data" filename="output.saturation.pdf" />
<expand macro="pdf_output_data" filename="output.saturation.pdf"/>
<data format="tabular" name="outputxls" from_work_dir="output.eRPKM.xls" label="${tool.name} on ${on_string}: RPKM"/>
<data format="tabular" name="outputrawxls" from_work_dir="output.rawCount.xls" label="${tool.name} on ${on_string}: raw count"/>
<expand macro="rscript_output_data" filename="output.saturation.r" />
<expand macro="rscript_output_data" filename="output.saturation.r"/>
</outputs>

<tests>
<test>
<test expect_num_outputs="4">
<param name="input" value="pairend_strandspecific_51mer_hg19_random.bam"/>
<param name="refgene" value="hg19.HouseKeepingGenes_30.bed"/>
<param name="rscript_output" value="true" />
<param name="rscript_output" value="true"/>
<output name="outputxls">
<assert_contents>
<has_n_columns n="26" />
<has_line_matching expression="chr1\t16174358\t16266950\tNM_015001.*" />
</assert_contents>
<assert_contents>
<has_n_columns n="26"/>
<has_line_matching expression="chr1\t16174358\t16266950\tNM_015001.*"/>
</assert_contents>
</output>
<output name="outputrawxls">
<assert_contents>
<has_n_columns n="26" />
<has_line_matching expression="chr1\t16174358\t16266950\tNM_015001.*" />
</assert_contents>
<assert_contents>
<has_n_columns n="26"/>
<has_line_matching expression="chr1\t16174358\t16266950\tNM_015001.*"/>
</assert_contents>
</output>
<output name="outputr">
<assert_contents>
<has_text text="pdf('output.saturation.pdf')" />
<has_line_matching expression="S5=c\(\d+\.\d+\)" />
</assert_contents>
<assert_contents>
<has_text text="pdf('output.saturation.pdf')"/>
<has_line_matching expression="S5=c\(\d+\.\d+\)"/>
</assert_contents>
</output>
<output name="outputpdf" file="output.saturation.pdf" compare="sim_size" />
<output name="outputpdf" file="output.saturation.pdf" compare="sim_size"/>
</test>
</tests>

<help><![CDATA[
RPKM_saturation.py
++++++++++++++++++
Expand Down Expand Up @@ -163,7 +155,5 @@ Output

]]>
</help>

<expand macro="citations" />

<expand macro="citations"/>
</tool>
32 changes: 11 additions & 21 deletions tools/rseqc/bam2wig.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,19 +1,14 @@
<tool id="rseqc_bam2wig" name="BAM to Wiggle" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@GALAXY_VERSION@">
<description>
converts all types of RNA-seq data from .bam to .wig
converts all types of RNA-seq data from BAM to Wiggle
</description>
<macros>
<import>rseqc_macros.xml</import>
</macros>

<expand macro="bio_tools"/>

<expand macro="requirements" />

<expand macro="stdio" />

<expand macro="requirements"/>
<expand macro="stdio"/>
<version_command><![CDATA[bam2wig.py --version]]></version_command>

<command><![CDATA[
@BAM_SAM_INPUTS@
bam2wig.py -i 'input.${extension}' -s '${chromsize}' -o outfile
Expand Down Expand Up @@ -44,9 +39,9 @@
]]>
</command>
<inputs>
<expand macro="bam_param" />
<expand macro="bam_param"/>
<param name="chromsize" type="data" label="Chromosome size file (tab or space separated)" format="txt,tabular" help="(--chromSize)"/>
<expand macro="multihits_param" />
<expand macro="multihits_param"/>
<conditional name="wigsum_type">
<param name="wigsum_type_selector" type="select" label="Normalization">
<option value="normalize">Normalize to specified sum</option>
Expand All @@ -57,9 +52,8 @@
</when>
<when value="raw"/>
</conditional>
<expand macro="strand_type_param" />
<expand macro="strand_type_param"/>
</inputs>

<outputs>
<data format="wig" name="output" from_work_dir="outfile.wig">
<filter>strand_type['strand_specific'] == 'none'</filter>
Expand All @@ -71,37 +65,35 @@
<filter>strand_type['strand_specific'] != 'none'</filter>
</data>
</outputs>

<tests>
<test>
<test expect_num_outputs="1">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="chromsize" value="hg19.chrom.sizes"/>
<output name="output" file="testwig.wig"/>
</test>
<test>
<test expect_num_outputs="1">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="chromsize" value="hg19.chrom.sizes"/>
<param name="multihits_type_selector" value="skip_multihits"/>
<param name="mapq" value="20"/>
<output name="output" file="testwig.wig"/>
</test>
<test>
<test expect_num_outputs="2">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="chromsize" value="hg19.chrom.sizes"/>
<param name="strand_specific" value="pair"/>
<param name="pair_type" value="sd"/>
<output name="outputfwd" file="testwig.Forward.wig"/>
<output name="outputrv" file="testwig.Reverse.wig"/>
</test>
<test>
<test expect_num_outputs="1">
<param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
<param name="chromsize" value="hg19.chrom.sizes"/>
<param name="wigsum_type_selector" value="normalize"/>
<param name="totalwig" value="100"/>
<output name="output" file="testwig_wigsum100.wig"/>
</test>
</tests>

<help><![CDATA[
bam2wig.py
++++++++++
Expand Down Expand Up @@ -149,7 +141,5 @@ is strand specific, two wig files corresponding to Forward and Reverse will be g
.. _bigwig: http://genome.ucsc.edu/FAQ/FAQformat.html#format6.1
]]>
</help>

<expand macro="citations" />

<expand macro="citations"/>
</tool>
Loading
Loading