Mercurial > repos > nick > duplex

changeset 6:9a0bee12b583 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'9fbe4b8871038d2945fa4b9ee0b5f89cf4e4f494\n'-dirty
author nick
date Mon, 06 Feb 2017 23:39:11 -0500
parents 4bc49a5769ee
children
files align_families.xml correct_barcodes.xml dunovo.xml make_families.xml tool_dependencies.xml
diffstat 5 files changed, 133 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/align_families.xml	Thu Dec 01 23:22:52 2016 -0500
+++ b/align_families.xml	Mon Feb 06 23:39:11 2017 -0500
@@ -1,13 +1,13 @@
 <?xml version="1.0"?>
-<tool id="align_families" name="Du Novo: Align families" version="0.5">
+<tool id="align_families" name="Du Novo: Align families" version="0.6">
   <description>of duplex sequencing reads</description>
   <requirements>
     <requirement type="package" version="7.221">mafft</requirement>
-    <requirement type="package" version="0.5">duplex</requirement>
+    <requirement type="package" version="0.6">duplex</requirement>
     <requirement type="set_environment">DUPLEX_DIR</requirement>
     <!-- TODO: require Python 2.7 -->
   </requirements>
-  <command detect_errors="exit_code">python \$DUPLEX_DIR/align_families.py -p \${GALAXY_SLOTS:-1} $input &gt; $output
+  <command detect_errors="exit_code">python "\$DUPLEX_DIR/align_families.py" -p \${GALAXY_SLOTS:-1} '$input' &gt; '$output'
   </command>
   <inputs>
     <param name="input" type="data" format="tabular" label="Input reads" help="with barcodes, grouped by family"/>
@@ -25,6 +25,22 @@
       <output name="output" file="families.sort.tsv"/>
     </test>
   </tests>
+  <citations>
+    <citation type="bibtex">@article{Stoler2016,
+      author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
+      doi = {10.1186/s13059-016-1039-4},
+      issn = {1474-760X},
+      journal = {Genome biology},
+      number = {1},
+      pages = {180},
+      pmid = {27566673},
+      publisher = {Genome Biology},
+      title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
+      url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
+      volume = {17},
+      year = {2016}
+    }</citation>
+  </citations>
   <help>
 
 **What it does**
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/correct_barcodes.xml	Mon Feb 06 23:39:11 2017 -0500
@@ -0,0 +1,61 @@
+<?xml version="1.0"?>
+<tool id="correct_barcodes" name="Du Novo: Correct barcodes" version="0.6">
+  <description>of duplex sequencing reads</description>
+  <requirements>
+    <requirement type="package" version="2.1.0">bowtie2</requirement>
+    <requirement type="package" version="0.1.18">samtools</requirement>
+    <requirement type="package" version="1.9">networkx</requirement>
+    <requirement type="package" version="0.6">duplex</requirement>
+    <requirement type="set_environment">DUPLEX_DIR</requirement>
+    <!-- TODO: require Python 2.7 -->
+  </requirements>
+  <command detect_errors="exit_code">bash "\$DUPLEX_DIR/baralign.sh" '$input' refdir barcodes.bam
+    &amp;&amp; samtools view -f 256 barcodes.bam
+    | python "\$DUPLEX_DIR/correct.py" -d $dist -m $mapq -p $pos '$input' refdir/barcodes.fa
+    | sort &gt; '$output'
+  </command>
+  <inputs>
+    <param name="input" type="data" format="tabular" label="Input reads" help="with barcodes, grouped by family"/>
+    <param name="dist" type="integer" value="1" min="1" label="Maximum edit distance" help="Only use alignments where the barcodes differ by at most these many errors."/>
+    <param name="mapq" type="integer" value="20" min="0" label="Minimum mapping quality" help="Only use alignments whose MAPQ is at least this."/>
+    <param name="pos" type="integer" value="2" min="0" label="Minimum start offset" help="Ignore alignments where the start positions differ by more than this."/>
+  </inputs>
+  <outputs>
+    <data name="output" format="tabular"/>
+  </outputs>
+  <citations>
+    <citation type="bibtex">@article{Stoler2016,
+      author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
+      doi = {10.1186/s13059-016-1039-4},
+      issn = {1474-760X},
+      journal = {Genome biology},
+      number = {1},
+      pages = {180},
+      pmid = {27566673},
+      publisher = {Genome Biology},
+      title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
+      url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
+      volume = {17},
+      year = {2016}
+    }</citation>
+  </citations>
+  <help>
+
+**What it does**
+
+This is for processing duplex sequencing data. This will correct duplex barcodes and create new, larger families. Errors in barcodes normally prevent them from being recognized as the same as the other barcodes in their family. Correcting these errors allows the original, full families to be reconstructed, saving reads which would otherwise be lost. This tool accomplishes this by doing an all vs. all alignment between the barcodes with bowtie2. This identifies ones which are identical except a few, small differences.
+
+-----
+
+**Input**
+
+This expects the output format of the "Make families" tool.
+
+-----
+
+**Output**
+
+The output format is the same as the input format, ready to be consumed by the "Align families" tool.
+
+    </help>
+</tool>
--- a/dunovo.xml	Thu Dec 01 23:22:52 2016 -0500
+++ b/dunovo.xml	Mon Feb 06 23:39:11 2017 -0500
@@ -1,20 +1,20 @@
 <?xml version="1.0"?>
-<tool id="duplex" name="Du Novo: Make consensus reads" version="0.5">
+<tool id="duplex" name="Du Novo: Make consensus reads" version="0.6">
   <description>from duplex sequencing alignments</description>
   <requirements>
-    <requirement type="package" version="0.5">duplex</requirement>
+    <requirement type="package" version="0.6">duplex</requirement>
     <requirement type="set_environment">DUPLEX_DIR</requirement>
     <!-- TODO: require Python 2.7 -->
   </requirements>
   <command detect_errors="exit_code"><![CDATA[
-    python \$DUPLEX_DIR/dunovo.py -r $min_reads -q $qual_thres -F $qual_format $input
+    python "\$DUPLEX_DIR/dunovo.py" -r $min_reads -q $qual_thres -F $qual_format '$input'
     #if $keep_sscs:
       --sscs-file sscs.fa
     #end if
     > duplex.fa
-    && python \$DUPLEX_DIR/utils/outconv.py duplex.fa -1 $dcs1 -2 $dcs2
+    && python "\$DUPLEX_DIR/utils/outconv.py" duplex.fa -1 '$dcs1' -2 '$dcs2'
     #if $keep_sscs:
-      && python \$DUPLEX_DIR/utils/outconv.py sscs.fa -1 $sscs1 -2 $sscs2
+      && python "\$DUPLEX_DIR/utils/outconv.py" sscs.fa -1 '$sscs1' -2 '$sscs2'
     #end if
   ]]>
   </command>
@@ -45,6 +45,22 @@
       <output name="dcs2" file="families.cons_2.fa"/>
     </test>
   </tests>
+  <citations>
+    <citation type="bibtex">@article{Stoler2016,
+      author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
+      doi = {10.1186/s13059-016-1039-4},
+      issn = {1474-760X},
+      journal = {Genome biology},
+      number = {1},
+      pages = {180},
+      pmid = {27566673},
+      publisher = {Genome Biology},
+      title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
+      url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
+      volume = {17},
+      year = {2016}
+    }</citation>
+  </citations>
   <help>
 
 **What it does**
--- a/make_families.xml	Thu Dec 01 23:22:52 2016 -0500
+++ b/make_families.xml	Mon Feb 06 23:39:11 2017 -0500
@@ -1,16 +1,16 @@
 <?xml version="1.0"?>
-<tool id="make_families" name="Du Novo: Make families" version="0.5">
+<tool id="make_families" name="Du Novo: Make families" version="0.6">
   <description>of duplex sequencing reads</description>
   <requirements>
-    <requirement type="package" version="0.5">duplex</requirement>
+    <requirement type="package" version="0.6">duplex</requirement>
     <requirement type="set_environment">DUPLEX_DIR</requirement>
   </requirements>
   <!-- TODO: Add dependency on coreutils to get paste? -->
-  <command>paste $fastq1 $fastq2
+  <command>paste '$fastq1' '$fastq2'
     | paste - - - -
-    | awk -f \$DUPLEX_DIR/make-barcodes.awk -v TAG_LEN=$taglen -v INVARIANT=$invariant
+    | awk -f "\$DUPLEX_DIR/make-barcodes.awk" -v TAG_LEN=$taglen -v INVARIANT=$invariant
     | sort
-    &gt; $output
+    &gt; '$output'
   </command>
   <inputs>
     <param name="fastq1" type="data" format="fastq" label="Sequencing reads, mate 1"/>
@@ -37,6 +37,22 @@
       <output name="output" file="smoke.families.i0.tsv"/>
     </test>
   </tests>
+  <citations>
+    <citation type="bibtex">@article{Stoler2016,
+      author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
+      doi = {10.1186/s13059-016-1039-4},
+      issn = {1474-760X},
+      journal = {Genome biology},
+      number = {1},
+      pages = {180},
+      pmid = {27566673},
+      publisher = {Genome Biology},
+      title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
+      url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
+      volume = {17},
+      year = {2016}
+    }</citation>
+  </citations>
   <help>
 
 **What it does**
--- a/tool_dependencies.xml	Thu Dec 01 23:22:52 2016 -0500
+++ b/tool_dependencies.xml	Mon Feb 06 23:39:11 2017 -0500
@@ -1,12 +1,21 @@
 <?xml version="1.0"?>
 <tool_dependency>
+  <package name="bowtie2" version="2.1.0">
+    <repository changeset_revision="017a00c265f1" name="package_bowtie2_2_1_0" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
+  </package>
+  <package name="samtools" version="0.1.18">
+    <repository changeset_revision="1409782220c9" name="package_samtools_0_1_18" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+  </package>
   <package name="mafft" version="7.221">
     <repository changeset_revision="15974dd17515" name="mafft" owner="rnateam" toolshed="https://toolshed.g2.bx.psu.edu" />
   </package>
-  <package name="duplex" version="0.5">
+  <package name="networkx" version="1.9">
+    <repository changeset_revision="83df321ad85e" name="package_networkx_1_9" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+  </package>
+  <package name="duplex" version="0.6">
     <install version="1.0">
       <actions>
-        <action type="download_by_url">https://github.com/galaxyproject/dunovo/archive/v0.5.tar.gz</action>
+        <action sha256sum="a3cc378c22fcfc3bcaa11129f27f61bab5ff51cc9185320d53ece273b56e6214" type="download_by_url">https://github.com/galaxyproject/dunovo/archive/v0.6.tar.gz</action>
         <action type="shell_command">make</action>
         <action type="move_directory_files">
           <source_directory>.</source_directory>