Mercurial > repos > devteam > fastq_combiner

changeset 2:56389130cb63 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/galaxy_sequence_utils/fastq_combiner commit f2582539542b33240234e8ea6093e25d0aee9b6a
author devteam
date Sat, 30 Sep 2017 14:57:41 -0400
parents e711d52c7509
children b05e39b9c170
files fastq_combiner.py fastq_combiner.xml tool_dependencies.xml
diffstat 3 files changed, 70 insertions(+), 126 deletions(-) [+]
line wrap: on
line diff
--- a/fastq_combiner.py	Wed Nov 11 12:40:28 2015 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,49 +0,0 @@
-#Dan Blankenberg
-import sys, os, shutil
-from galaxy_utils.sequence.fastq import fastqWriter, fastqSequencingRead, fastqCombiner, fastqFakeFastaScoreReader
-from galaxy_utils.sequence.fasta import fastaReader, fastaNamedReader
-
-def main():
-    #Read command line arguments
-    fasta_filename = sys.argv[1]
-    fasta_type = sys.argv[2] or 'fasta' #should always be fasta or csfasta? what if txt?
-    qual_filename = sys.argv[3]
-    qual_type = sys.argv[4] or 'qualsanger' #qual454 qualsolid
-    output_filename = sys.argv[5]
-    force_quality_encoding = sys.argv[6]
-    if force_quality_encoding == 'None':
-        force_quality_encoding = None
-    
-    format = 'sanger'
-    if fasta_type == 'csfasta' or qual_type == 'qualsolid':
-        format = 'cssanger'
-    elif qual_type == 'qualsolexa':
-        format = 'solexa'
-    elif qual_type == 'qualillumina':
-        format = 'illumina'
-    
-    out = fastqWriter( open( output_filename, 'wb' ), format = format, force_quality_encoding = force_quality_encoding )
-    if qual_filename == 'None':
-        qual_input = fastqFakeFastaScoreReader( format, quality_encoding = force_quality_encoding )
-    else:
-        qual_input = fastaNamedReader( open( qual_filename, 'rb' )  )
-    
-    fastq_combiner = fastqCombiner( format )
-    i = None
-    skip_count = 0
-    for i, sequence in enumerate( fastaReader( open( fasta_filename, 'rb' ) ) ):
-        quality = qual_input.get( sequence )
-        if quality:
-            fastq_read = fastq_combiner.combine( sequence, quality )
-            out.write( fastq_read )
-        else:
-            skip_count += 1
-    out.close()
-    if i is None:
-        print "Your file contains no valid FASTA sequences."
-    else:
-        print qual_input.has_data()
-        print 'Combined %s of %s sequences with quality scores (%.2f%%).' % ( i - skip_count + 1, i + 1, float( i - skip_count + 1 ) / float( i + 1 ) * 100.0 )
-
-if __name__ == "__main__":
-    main()
--- a/fastq_combiner.xml	Wed Nov 11 12:40:28 2015 -0500
+++ b/fastq_combiner.xml	Sat Sep 30 14:57:41 2017 -0400
@@ -1,67 +1,69 @@
-<tool id="fastq_combiner" name="Combine FASTA and QUAL" version="1.0.1">
-  <description>into FASTQ</description>
-  <requirements>
-    <requirement type="package" version="1.0.0">galaxy_sequence_utils</requirement>
-  </requirements>
-  <command interpreter="python">fastq_combiner.py '$fasta_file' '${fasta_file.extension}' '$qual_file' '${qual_file.extension}' '$output_file' '$force_quality_encoding'</command>
-  <inputs>
-    <param name="fasta_file" type="data" format="fasta,csfasta" label="FASTA File" />
-    <param name="qual_file" type="data" format="qual" label="Quality Score File" optional="True" />
-    <param name="force_quality_encoding" type="select" label="Force Quality Score encoding">
-      <option value="None">Use Source Encoding</option>
-      <option value="ascii" selected="True">ASCII</option>
-      <option value="decimal">Decimal</option>
-    </param>
-  </inputs>
-  <outputs>
-    <data name="output_file" format="fastqsanger">
-      <change_format>
-        <when input_dataset="fasta_file" attribute="extension" value="csfasta" format="fastqcssanger" />
-        <when input_dataset="qual_file" attribute="extension" value="qualsolid" format="fastqcssanger" />
-        <when input_dataset="qual_file" attribute="extension" value="qualsolexa" format="fastqsolexa" />
-        <when input_dataset="qual_file" attribute="extension" value="qualillumina" format="fastqillumina" />
-      </change_format>
-    </data>
-  </outputs>
-  <tests>
-    <test>
-      <param name="fasta_file" value="s2fq_phiX.csfasta" ftype="csfasta" />
-      <param name="qual_file" value="s2fq_phiX.qualsolid" ftype="qualsolid" />
-      <param name="force_quality_encoding" value="None" />
-      <output name="output_file" file="combine_phiX_out_1.fastqcssanger" />
-    </test>
-    <test>
-      <param name="fasta_file" value="s2fq_phiX.csfasta" ftype="csfasta" />
-      <param name="qual_file" value="s2fq_phiX.qualsolid" ftype="qualsolid" />
-      <param name="force_quality_encoding" value="ascii" />
-      <output name="output_file" file="combine_phiX_out_2.fastqcssanger" />
-    </test>
-    <test>
-      <param name="fasta_file" value="fastq_combiner_in_1.fasta" ftype="fasta" />
-      <param name="qual_file" value="fastq_combiner_in_1.qual454" ftype="qual454" />
-      <param name="force_quality_encoding" value="None" />
-      <output name="output_file" file="wrapping_as_sanger.fastqsanger" />
-    </test>
-    <test>
-      <param name="fasta_file" value="fastq_combiner_in_1.fasta" ftype="fasta" />
-      <param name="qual_file" value="fastq_combiner_in_1.qual454" ftype="qual454" />
-      <param name="force_quality_encoding" value="decimal" />
-      <output name="output_file" file="wrapping_as_sanger_decimal.fastqsanger" />
-    </test>
-    <test>
-      <param name="fasta_file" value="fastq_combiner_in_1.fasta" ftype="fasta" />
-      <param name="qual_file" />
-      <param name="force_quality_encoding" value="decimal" />
-      <output name="output_file" file="fastq_combiner_no_qual_decimal_out_1.fastqsanger" />
-    </test>
-    <test>
-      <param name="fasta_file" value="s2fq_phiX.csfasta" ftype="csfasta" />
-      <param name="qual_file" />
-      <param name="force_quality_encoding" value="ascii" />
-      <output name="output_file" file="fastq_combiner_no_qual_ascii_out_1.fastqcssanger" />
-    </test>
-  </tests>
-  <help>
+<tool id="fastq_combiner" name="Combine FASTA and QUAL" version="1.1.1">
+    <description>into FASTQ</description>
+    <requirements>
+        <requirement type="package" version="1.1.1">galaxy_sequence_utils</requirement>
+    </requirements>
+    <command><![CDATA[
+gx-fastq-combiner '$fasta_file' '${fasta_file.extension}' '$qual_file' '${qual_file.extension}' '$output_file' $force_quality_encoding
+    ]]></command>
+    <inputs>
+        <param name="fasta_file" type="data" format="fasta,csfasta" label="FASTA File" />
+        <param name="qual_file" type="data" format="qual" optional="true" label="Quality Score File" />
+        <param name="force_quality_encoding" type="select" label="Force Quality Score encoding">
+            <option value="None">Use Source Encoding</option>
+            <option value="ascii" selected="true">ASCII</option>
+            <option value="decimal">Decimal</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="output_file" format="fastqsanger">
+            <change_format>
+                <when input="fasta_file" value="csfasta" format="fastqcssanger" />
+                <when input="qual_file" value="qualsolid" format="fastqcssanger" />
+                <when input="qual_file" value="qualsolexa" format="fastqsolexa" />
+                <when input="qual_file" value="qualillumina" format="fastqillumina" />
+            </change_format>
+        </data>
+    </outputs>
+    <tests>
+        <test>
+            <param name="fasta_file" value="s2fq_phiX.csfasta" ftype="csfasta" />
+            <param name="qual_file" value="s2fq_phiX.qualsolid" ftype="qualsolid" />
+            <param name="force_quality_encoding" value="None" />
+            <output name="output_file" file="combine_phiX_out_1.fastqcssanger" />
+        </test>
+        <test>
+            <param name="fasta_file" value="s2fq_phiX.csfasta" ftype="csfasta" />
+            <param name="qual_file" value="s2fq_phiX.qualsolid" ftype="qualsolid" />
+            <param name="force_quality_encoding" value="ascii" />
+            <output name="output_file" file="combine_phiX_out_2.fastqcssanger" />
+        </test>
+        <test>
+            <param name="fasta_file" value="fastq_combiner_in_1.fasta" ftype="fasta" />
+            <param name="qual_file" value="fastq_combiner_in_1.qual454" ftype="qual454" />
+            <param name="force_quality_encoding" value="None" />
+            <output name="output_file" file="wrapping_as_sanger.fastqsanger" />
+        </test>
+        <test>
+            <param name="fasta_file" value="fastq_combiner_in_1.fasta" ftype="fasta" />
+            <param name="qual_file" value="fastq_combiner_in_1.qual454" ftype="qual454" />
+            <param name="force_quality_encoding" value="decimal" />
+            <output name="output_file" file="wrapping_as_sanger_decimal.fastqsanger" />
+        </test>
+        <test>
+            <param name="fasta_file" value="fastq_combiner_in_1.fasta" ftype="fasta" />
+            <param name="qual_file" />
+            <param name="force_quality_encoding" value="decimal" />
+            <output name="output_file" file="fastq_combiner_no_qual_decimal_out_1.fastqsanger" />
+        </test>
+        <test>
+            <param name="fasta_file" value="s2fq_phiX.csfasta" ftype="csfasta" />
+            <param name="qual_file" />
+            <param name="force_quality_encoding" value="ascii" />
+            <output name="output_file" file="fastq_combiner_no_qual_ascii_out_1.fastqcssanger" />
+        </test>
+    </tests>
+    <help><![CDATA[
 **What it does**
 
 This tool joins a FASTA file to a Quality Score file, creating a single FASTQ block for each read.
@@ -69,11 +71,8 @@
 Specifying a set of quality scores is optional; when not provided, the output will be fastqsanger or fastqcssanger (when a csfasta is provided) with each quality score being the maximal allowed value (93).
 
 Use this tool, for example, to convert 454-type output to FASTQ.
-
-  </help>
-  
-  <citations>
-    <citation type="doi">10.1093/bioinformatics/btq281</citation>
-  </citations>
-  
+    ]]></help>
+    <citations>
+        <citation type="doi">10.1093/bioinformatics/btq281</citation>
+    </citations>
 </tool>
--- a/tool_dependencies.xml	Wed Nov 11 12:40:28 2015 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,6 +0,0 @@
-<?xml version="1.0"?>
-<tool_dependency>
-  <package name="galaxy_sequence_utils" version="1.0.0">
-      <repository changeset_revision="0643676ad5f7" name="package_galaxy_utils_1_0" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-</tool_dependency>