diff read2mut.xml @ 43:d21960b45a6b draft

planemo upload for repository https://github.com/Single-Molecule-Genetics/VariantAnalyzerGalaxy/tree/master/tools/variant_analyzer commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8
author mheinzl
date Tue, 02 Mar 2021 15:32:41 +0000
parents da224c392a54
children 8fbe6aba07e5
line wrap: on
line diff
--- a/read2mut.xml	Wed Feb 24 14:20:17 2021 +0000
+++ b/read2mut.xml	Tue Mar 02 15:32:41 2021 +0000
@@ -1,12 +1,16 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<tool id="read2mut" name="Call specific mutations in reads:" version="2.0.4" profile="17.01">
+<tool id="read2mut" name="Call specific mutations in reads:" version="2.1.0" profile="19.01">
     <description>Looks for reads with mutation at known positions and calculates frequencies and stats.</description>
     <macros>
         <import>va_macros.xml</import>
     </macros>
-    <expand macro="requirements">
+    <requirements>
+        <requirement type="package" version="2.7">python</requirement>
+        <requirement type="package" version="1.4.0">matplotlib</requirement>
+        <requirement type="package" version="0.15">pysam</requirement>
         <requirement type="package" version="1.1.0">xlsxwriter</requirement>
-    </expand>
+        <requirement type="package" version="0.11.6">cyvcf2</requirement>
+    </requirements>
     <command><![CDATA[
         ln -s '$file2' bam_input.bam &&
         ln -s '${file2.metadata.bam_index}' bam_input.bam.bai &&
@@ -17,11 +21,11 @@
         --sscsJson '$file4'
         --thresh '$thresh'
         --phred '$phred'
-        --trim5 '$trim5'
-        --trim3 '$trim3'
+        --trim '$trim'
         $chimera_correction
+        --softclipping_dist '$softclipping_dist'
+        --reads_threshold '$reads_threshold'
         --outputFile '$output_xlsx'
-        --outputFile_csv '$outputFile_csv'
         --outputFile2 '$output_xlsx2'
         --outputFile3 '$output_xlsx3'
     ]]>
@@ -33,13 +37,13 @@
         <param name="file4" type="data" format="json" label="JSON File with SSCS tag stats" optional="false" help="JSON file generated by DCS mutations to SSCS stats."/>
         <param name="thresh" type="integer" label="Tag count threshold" value="0" help="Integer threshold for displaying mutations. Only mutations occuring in DCS of less than thresh tags are displayed. Default of 0 displays all."/>
         <param name="phred" type="integer" label="Phred quality score threshold" min="0" max="41" value="20" help="Integer threshold for Phred quality score. Only reads higher than this threshold are considered. Default = 20."/>
-        <param name="trim5" type="integer" label="Trimming threshold at 5' end of reads" value="10" help="Integer threshold for assigning mutations at the beginning of reads to a lower tier. Default 10."/>
-        <param name="trim3" type="integer" label="Trimming threshold at 3' end of reads" value="10" help="Integer threshold for assigning mutations at the end of reads to a lower tier. Default 10."/>
+        <param name="trim" type="integer" label="Trimming threshold" value="10" help="Integer threshold for assigning mutations at start and end of reads to lower tier. Default 10."/>
         <param name="chimera_correction" type="boolean" label="Apply chimera correction?" truevalue="--chimera_correction" falsevalue="" checked="False" help="Count chimeric variants and correct the variant frequencies."/>
+        <param name="softclipping_dist" type="integer" label="Distance between artifact and softclipping of the reads" min="1" value="15" help="Count mutation as an artifact if mutation lies within this parameter away from the softclipping part of the reads. Default = 20"/>
+<param name="reads_threshold" type="float" label="Minimum percentage of softclipped reads in a family" min="0.0" max="1.0" value="1.0" help="Float number which specifies the minimum percentage of softclipped reads in a family to be considered in the softclipping tiers. Default: 1.0, means all reads of a family have to be softclipped."/>
     </inputs>
     <outputs>
         <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/>
-        <data name="outputFile_csv" format="csv" label="${tool.name} on ${on_string}: CSV summary"/>
         <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/>
         <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/>
     </outputs>
@@ -51,10 +55,11 @@
             <param name="file4" value="SSCS_counts_test.json"/>
             <param name="thresh" value="0"/>
             <param name="phred" value="20"/>
-            <param name="trim5" value="10"/>
-            <param name="trim3" value="10"/>
+            <param name="trim" value="10"/>
+            <param name="chimera_correction"/>
+            <param name="softclipping_dist" value="15"/>
+            <param name="reads_threshold" value="1.0"/>
             <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/>
-            <output name="outputFile_csv" file="Variant_Analyzer_summary_test.csv" decompress="true" lines_diff="10"/>
             <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/>
             <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/>
         </test>
@@ -70,7 +75,7 @@
 **Input** 
 
 **Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g. 
-generated by the `FreeBayes <https://arxiv.org/abs/1207.3907>`_ or `LoFreq <https://academic.oup.com/nar/article/40/22/11189/1152727>`_ variant caller.
+generated by the `FreeBayes variant caller <https://arxiv.org/abs/1207.3907>`_.
 
 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the 
 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_.
@@ -86,7 +91,7 @@
 **Output**
 
 The output are three XLSX files containing frequencies stats for DCS mutations based 
-on information from the raw reads and a CSV file containing the summary information without color-coding. In addition to that a tier based 
+on information from the raw reads. In addition to that a tier based 
 classification is provided based on the amout of support for a true variant call.
 
     ]]>