diff split_libraries_fastq.xml @ 0:20194da2549d draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/qiime/ commit a9d1e0debcd357d8080a1c6c5f1d206dd45a7a4d

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/split_libraries_fastq.xml	Fri May 19 03:54:05 2017 -0400
@@ -0,0 +1,152 @@
+<tool id="qiime_split_libraries_fastq" name="Split fastq libraries" version="@WRAPPER_VERSION@.0">
+    <description>to performs demultiplexing of Fastq sequence data</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <version_command>split_libraries_fastq.py --version</version_command>
+    <command detect_errors="aggressive"><![CDATA[
+        split_libraries_fastq.py
+            #set $seq_files = ''
+            #set $sep = ''
+            #for $file in $sequence_read_fps
+                #set $seq_files += $sep + str($file)
+                #set $sep = ','
+            #end for
+            --sequence_read_fps '$seq_files'
+
+            -o split_libraries
+
+            #set $mapping_files = ''
+            #set $sep = ''
+            #for $file in $mapping_fps
+                #set $mapping_files += $sep + str($file)
+                #set $sep = ','
+            #end for
+            --mapping_fps '$mapping_files'
+
+            #set $barcode_files = ''
+            #set $sep = ''
+            #for $file in $barcode_read_fps
+                #set $barcode_files += $sep + str($file)
+                #set $sep = ','
+            #end for
+            --barcode_read_fps '$barcode_files'
+
+            $store_qual_scores
+            #if str($sample_ids):
+                --sample_ids '$sample_ids'
+            #end if
+            $store_demultiplexed_fastq
+            $retain_unassigned_reads
+
+            --max_bad_run_length '$max_bad_run_length'
+            --min_per_read_length_fraction '$min_per_read_length_fraction'
+            --sequence_max_n '$sequence_max_n'
+            --start_seq_id '$start_seq_id'
+            $rev_comp_barcode
+            $rev_comp_mapping_barcodes
+            $rev_comp
+            --phred_quality_threshold '$phred_quality_threshold'
+            #if str( $barcode.barcode_type ) != "custom_length"
+                --barcode_type '$barcode.barcode_type'
+            #else
+                --barcode_type '$barcode.barcode_length'
+            #end if
+            --max_barcode_errors '$max_barcode_errors'
+            $phred_offset
+    ]]></command>
+    <inputs>
+        <param argument="--sequence_read_fps" type="data" format="fastq,fastqsanger,fastqsolexa" label="Input fastq files" multiple="True"/>
+        <param argument="--mapping_fps" type="data" format="txt,tabular,tsv,csv" label="Metadata mapping files (optional)" multiple="True" optional="True"/>
+        <param argument="--barcode_read_fps" type="data" format="fastq,fastqsanger,fastqsolexa" label="Barcode read files (optional)" multiple="True" optional="True"/>
+        <param argument="--store_qual_scores" type="boolean" label="Store quality strings in files?" truevalue="--store_qual_scores" falsevalue="" checked="False"/>
+        <param argument="--sample_ids" type="text" label="Comma-separated list of samples ids to be applied to all sequences (optional)" optional="True" help="It must be one per input file path (used when data is not multiplexed)"/>
+        <param argument="--store_demultiplexed_fastq" type="boolean" label="Write demultiplexed fastq files?" truevalue="--store_demultiplexed_fastq" falsevalue="" checked="False"/>
+        <param argument="--retain_unassigned_reads" type="boolean" label="Retain sequences which don’t map to a barcode in the mapping file?" truevalue="--retain_unassigned_reads" falsevalue="" checked="False" help="Sample ID will be 'Unassigned'"/>
+        <param argument="--max_bad_run_length" type="integer" value="3" label="Maximum number of consecutive low quality base calls allowed before truncating a read"/>
+        <param argument="--min_per_read_length_fraction" type="float" value="0.75" label="Minimum number of consecutive high quality base calls to include a read (per single end read) as a fraction of the input read length"/>
+        <param argument="--sequence_max_n" type="integer" value="0" label="Maximum number of N characters allowed in a sequence to retain it" help="This is applied after quality trimming, and is total over combined paired end reads if applicable"/>
+        <param argument="--start_seq_id" type="integer" value="0" label="Start seq_ids as ascending integers beginning with start_seq_id"/>
+        <param argument="--rev_comp_barcode" type="boolean" label="Reverse complement barcode reads before lookup?" truevalue="--rev_comp_barcode" falsevalue="" checked="False"/>
+        <param argument="--rev_comp_mapping_barcodes" type="boolean" label="Reverse complement barcode in mapping before lookup?" truevalue="--rev_comp_mapping_barcodes" falsevalue="" checked="False" help="It is useful if barcodes in mapping file are reverse complements of golay codes"/>
+        <param argument="--rev_comp" type="boolean" label="Reverse omplement sequence before writing to output file?" truevalue="--rev_comp" falsevalue="" checked="False"/>
+        <param argument="--phred_quality_threshold" type="integer" value="3" label="Maximum unacceptable Phred quality score" help="E.g., for Q20 and better, 19 must be specified"/>
+        <conditional name="barcode">
+            <param argument="--barcode_type" type="select" label="Type of barcode">
+                <option value="hamming_8">hamming_8</option>
+                <option value="golay_12" selected="true">golay_12</option>
+                <option value="variable_length">variable_length (disable any barcode correction)</option>
+                <option value="custom_length">Custom length</option>
+                <option value="not-barcoded">Data not barcoded</option>
+            </param>
+            <when value="hamming_8"/>
+            <when value="golay_12"/>
+            <when value="variable_length"/>
+            <when value="custom_length">
+                <param name="barcode_length" type="integer" value="4" label="Barcode length"/>
+            </when>
+            <when value="not-barcoded"/>
+        </conditional>
+        <param argument="--max_barcode_errors" type="float" value="1.5" label="Maximum number of errors in barcode"/>
+        <param argument="--phred_offset" type="select" label="Ascii offset to use when decoding phred scores">
+            <option value="--phred_offset 33">33</option>
+            <option value="--phred_offset 64">64</option>
+            <option value="" selected="true">Automatically determined</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="log" format="txt" from_work_dir="split_libraries/split_library_log.txt" label="${tool.name} on ${on_string}: log"/>
+        <data name="histograms" format="tabular" from_work_dir="split_libraries/histograms.txt" label="${tool.name} on ${on_string}: histograms"/>
+        <data name="seqs" format="fasta" from_work_dir="split_libraries/seqs.fna" label="${tool.name} on ${on_string}: sequences"/>
+        <data name="seqs_qual" format="qual" from_work_dir="split_libraries/seqs.qual" label="${tool.name} on ${on_string}: sequence qualities">
+            <filter>store_qual_scores is True</filter>
+        </data>
+        <data name="seqs_fastq" format="fastq" from_work_dir="split_libraries/seqs.fastq" label="${tool.name} on ${on_string}: demultiplexed sequences (fastq)">
+            <filter>store_demultiplexed_fastq is True</filter>
+        </data>
+    </outputs>
+    <tests>
+        <test>
+            <param name="sequence_read_fps" value="split_libraries_fastq/forward_reads.fastq"/>
+            <param name="mapping_fps" value="split_libraries_fastq/map.tsv"/>
+            <param name="barcode_read_fps" value="split_libraries_fastq/barcodes.fastq"/>
+            <param name="store_qual_scores" value="--store_qual_scores"/>
+            <param name="store_demultiplexed_fastq" value="--store_demultiplexed_fastq"/>
+            <param name="retain_unassigned_reads" value=""/>
+            <param name="max_bad_run_length" value="3"/>
+            <param name="min_per_read_length_fraction" value="0.75"/>
+            <param name="sequence_max_n" value="0"/>
+            <param name="start_seq_id" value="0"/>
+            <param name="rev_comp_barcode" value=""/>
+            <param name="rev_comp_mapping_barcodes" value=""/>
+            <param name="rev_comp" value=""/>
+            <param name="barcode_selector" value="golay_12"/>
+            <param name="max_barcode_errors" value="1.5"/>
+            <param name="phred_offset" value=""/>
+            <output name="log">
+                <assert_contents>
+                    <has_line line="Median sequence length: 132.50"></has_line>
+                    <has_text text="L1S76"></has_text>
+                    <has_text text="L1S281"></has_text>
+                    <has_text text="L1S8"></has_text>
+                </assert_contents>
+            </output>
+            <output name="seqs" file="split_libraries_fastq/sequences.fasta"/>
+            <output name="histograms" file="split_libraries_fastq/histograms.tabular"/>
+            <output name="seqs_qual" file="split_libraries_fastq/sequence_qualities.qual"/>
+            <output name="seqs_fastq" file="split_libraries_fastq/demultiplexed_sequences.fastq"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+**What it does**
+
+This tool performs demultiplexing of Fastq sequence data where barcodes and sequences are contained in two separate fastq files (common on Illumina runs).
+
+More information about this tool is available on
+`QIIME documentation <http://qiime.org/scripts/split_libraries_fastq.html>`_.
+    ]]></help>
+    <citations>
+        <expand macro="citations"/>
+    </citations>
+</tool>