annotate spades.xml @ 10:b8d633fbf5f5 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/spades commit 033c31f9e41c2869e195c66e5bf6cc2286062bd9

<tool id="spades" name="SPAdes" version="@TOOL_VERSION@+galaxy1">
    <description>genome assembler for regular and single-cell projects</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">spades</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
        <regex match="Cannot allocate memory"
           source="stdout"
           level="fatal_oom"
           description="Out of memory error occurred" />
        <regex match="The reads contain too many k-mers to fit into available memory"
           source="stdout"
           level="fatal_oom"
           description="Out of memory error occurred" />
    </stdio>
    <command>
    <![CDATA[
    ## A real command looks like: spades.py -k 21,33,55,77,99,127 --careful -1 Y.fastq.gz -2 X.fastq.gz -t 24 -o output

    if [[ -n \$GALAXY_MEMORY_MB ]]; then
        GALAXY_MEMORY_GB=\$(( GALAXY_MEMORY_MB / 1024 ));
    fi &&

    spades.py -o . --disable-gzip-output $sc $onlyassembler $careful -t \${GALAXY_SLOTS:-16} -m \${GALAXY_MEMORY_GB:-250}
    #if not $kmer_choice.auto_kmer_choice:
        -k "$kmer_choice.kmers"
    #end if
    #if $cov.state == "auto":
        --cov-cutoff 'auto'
    #elif $cov.state == "value":
        --cov-cutoff '$cov.cutoff'
    #end if
    $iontorrent
    ## Sequence files, libraries
    #for $i, $library in enumerate( $libraries, start=1 )
        #if str( $library.lib_type ) == "paired_end":
            #set prefix = 'pe'
        #elif str( $library.lib_type ) == "mate_paired":
            #set prefix = 'mp'
        #elif str( $library.lib_type ) == "nxmate_paired":
            #set prefix = 'nxmate'
        #else:
            #set prefix = 'hqmp'
        #end if
        --$prefix$i-$library.orientation
        #for $file in $library.files
            #if $file.file_type.type == "separate"
                --$prefix$i-1 $file.file_type.fwd_reads.extension.replace('fastqsanger', 'fastq'):$file.file_type.fwd_reads
                --$prefix$i-2 $file.file_type.fwd_reads.extension.replace('fastqsanger', 'fastq'):$file.file_type.rev_reads
            #elif $file.file_type.type == "interleaved"
                --$prefix$i-12 $file.file_type.interleaved_reads.extension.replace('fastqsanger', 'fastq'):$file.file_type.interleaved_reads
            #elif $file.file_type.type == "merged"
                --$prefix$i-m $file.file_type.merged_reads.extension.replace('fastqsanger', 'fastq'):$file.file_type.merged_reads
            #elif $file.file_type.type == "unpaired"
                --$prefix$i-s $file.file_type.unpaired_reads.extension.replace('fastqsanger', 'fastq'):$file.file_type.unpaired_reads
            #elif $file.file_type.type == "paired-collection"
                --$prefix$i-1 $file.file_type.fastq_collection.forward.extension.replace('fastqsanger', 'fastq'):$file.file_type.fastq_collection.forward
                --$prefix$i-2 $file.file_type.fastq_collection.reverse.extension.replace('fastqsanger', 'fastq'):$file.file_type.fastq_collection.reverse
            #end if
        #end for
    #end for
    #for $read in $pacbio_reads:
        #if $read:
            --pacbio fastq:$read
        #end if
    #end for
    #for $read in $nanopore_reads:
        #if $read:
            --nanopore fastq:$read
        #end if
    #end for
    #for $read in $sanger_reads:
        #if $read:
            --sanger $read.extension.replace('fastqsanger', 'fastq'):$read
        #end if
    #end for
    #for $contig in $trusted_contigs:
        #if $contig:
            --trusted-contigs $contig.extension.replace('fastqsanger', 'fastq'):$contig
        #end if
    #end for
    #for $contig in $untrusted_contigs:
        #if $contig:
            --untrusted-contigs $contig.extension.replace('fastqsanger', 'fastq'):$contig
        #end if
    #end for
    && python '$write_tsv_script' < contigs.fasta > '$out_contig_stats'
    && python '$write_tsv_script' < scaffolds.fasta > '$out_scaffold_stats'
    ]]>
    </command>

    <configfiles>
        <configfile name="write_tsv_script"><![CDATA[#!/usr/bin/env python
import sys,re
search_str = r'^>(NODE|\S+)_(\d+)(?:_|\s)length_(\d+)_cov_(\d+\.*\d*).*\$'
replace_str = r'\1_\2\t\3\t\4'
cmd = re.compile(search_str)
sys.stdout.write('#name\tlength\tcoverage\n')
for i,line in enumerate(sys.stdin):
    if cmd.match(line):
        sys.stdout.write(cmd.sub(replace_str,line))
]]>
         </configfile>
    </configfiles>

    <inputs>
        <param argument="--sc" falsevalue="" help="This option is required for MDA (single-cell) data." label="Single-cell?" name="sc" truevalue="--sc" type="boolean">
            <option value="false">No</option>
            <option value="true">Yes</option>
        </param>
        <param argument="--only-assembler" checked="False" falsevalue="" label="Run only assembly? (without read error correction)" name="onlyassembler" truevalue="--only-assembler" type="boolean" />
        <param argument="--careful" checked="True" falsevalue="" help="Tries to reduce number of mismatches and short indels. Also runs MismatchCorrector &#8211; a post processing tool, which uses BWA tool (comes with SPAdes)." label="Careful correction?" name="careful" truevalue="--careful" type="boolean" />
        <conditional name="kmer_choice">
            <param checked="False" falsevalue="false" help="k-mer choices can be chosen by SPAdes instead of being entered manually" label="Automatically choose k-mer values" name="auto_kmer_choice" truevalue="true" type="boolean" />
            <when value="false">
                <param help="Comma-separated list of k-mer sizes to be used (all values must be odd, less than 128, listed in ascending order, and smaller than the read length). The default value is 21,33,55." label="K-mers to use, separated by commas" name="kmers" type="text" value="21,33,55" />
            </when>
            <when value="true" />
        </conditional>
        <conditional name="cov">
            <param label="Coverage Cutoff" name="state" type="select">
                <option value="off">Off</option>
                <option value="value">User Specific</option>
                <option value="auto">Auto</option>
            </param>
            <when value="off" />
            <when value="value">
                <param help="coverage cutoff value (a positive float number, or 'auto', or 'off') [default: 'off']" label="Coverage cutoff value" name="cutoff" type="float" value="" />
            </when>
            <when value="auto" />
        </conditional>
        <param checked="False" falsevalue="" label="Libraries are IonTorrent reads?" name="iontorrent" truevalue="--iontorrent" type="boolean" />
        <repeat help="It is not possible to specify only mate-pair libraries. Scaffolds are not produced if neither a paired-end nor a mate-pair library is provided." min="1" max="9" name="libraries" title="Libraries">
            <param label="Library type" name="lib_type" type="select">
                <option value="paired_end">Paired-end / Single reads</option>
                <option value="mate_paired">Mate pairs</option>
                <option value="high_mate_paired">High Quality Mate pairs</option>
                <option value="nxmate_paired">Lucigen NxMate pairs</option>
            </param>
            <param label="Orientation" name="orientation" type="select">
                <option selected="true" value="fr"><![CDATA[-> <- (fr)]]></option>
                <option value="rf"><![CDATA[<- -> (rf)]]></option>
                <option value="ff"><![CDATA[-> -> (ff)]]></option>
            </param>
            <repeat min="1" name="files" title="Files">
                <conditional name="file_type">
                    <param label="Select file format" name="type" type="select">
                        <option value="separate">Separate input files</option>
                        <option value="interleaved">Interleaved files</option>
                        <option value="merged">Merged files</option>
                        <option value="unpaired">Unpaired/Single reads</option>
                        <option value="paired-collection">Paired List Collection</option>
                    </param>
                    <when value="separate">
                        <param format="@INTYPES@" help="FASTQ format" label="Forward reads" name="fwd_reads" type="data" />
                        <param format="@INTYPES@" help="FASTQ format" label="Reverse reads" name="rev_reads" type="data" />
                    </when>
                    <when value="interleaved">
                        <param format="@INTYPES@" help="FASTQ format" label="Interleaved paired reads" name="interleaved_reads" type="data" />
                    </when>
                    <when value="merged">
                        <param format="@INTYPES@" help="FASTQ format" label="Merged paired reads" name="merged_reads" type="data" />
                    </when>
                    <when value="unpaired">
                        <param format="@INTYPES@" help="FASTQ format" label="Unpaired reads" name="unpaired_reads" type="data" />
                    </when>
                    <when value="paired-collection">
                        <param collection_type="paired" format="@INTYPES@" help="FASTQ format" label="Paired-end reads collection" name="fastq_collection" optional="false" type="data_collection" />
                    </when>
                </conditional>
            </repeat>
        </repeat>
        <param optional="true" format="@INTYPES@" label="PacBio CLR reads" multiple="true" name="pacbio_reads" type="data" />
        <param optional="true" format="@INTYPES@" label="Nanopore reads" multiple="true" name="nanopore_reads" type="data" />
        <param optional="true" format="@INTYPES@" label="Sanger reads" multiple="true" name="sanger_reads" type="data" />
        <param optional="true" format="@INTYPES@" label="Trusted contigs" multiple="true" name="trusted_contigs" type="data" />
        <param optional="true" format="@INTYPES@" label="Untrusted contigs" multiple="true" name="untrusted_contigs" type="data" />
        <param name="contig_graph_out" type="boolean" checked="False" label="Output final assembly graph (contigs)?" help="Will output the final assembly graph (contigs) in fastg format for visualisation" />
        <param name="scaffold_graph_out" type="boolean" checked="False" label="Output final assembly graph with scaffolds?" help="Will output the final assembly graph with scaffold information in gfa format for visualisation" />
    </inputs>

    <outputs>
        <data format="tabular" label="${tool.name} on ${on_string}: contig stats" name="out_contig_stats" >
            <actions>
                <action name="column_names" type="metadata" default="name,length,coverage"/>
            </actions>
        </data>
        <data format="tabular" label="${tool.name} on ${on_string}: scaffold stats" name="out_scaffold_stats" >
            <actions>
                <action name="column_names" type="metadata" default="name,length,coverage"/>
            </actions>
        </data>
        <data format="fasta" from_work_dir="contigs.fasta" label="${tool.name} on ${on_string}: contigs (fasta)" name="out_contigs" />
        <data format="fasta" from_work_dir="scaffolds.fasta" label="${tool.name} on ${on_string}: scaffolds (fasta)" name="out_scaffolds" />
        <data format="txt" from_work_dir="spades.log" label="${tool.name} on ${on_string}: log" name="out_log" />
        <data format="txt" from_work_dir="assembly_graph.fastg" label="${tool.name} on ${on_string}: assembly graph" name="contig_graph">
            <filter>contig_graph_out</filter>
        </data>
        <data format="txt" from_work_dir="assembly_graph_with_scaffolds.gfa" label="${tool.name} on ${on_string}: assembly graph with scaffolds" name="scaffold_graph">
            <filter>scaffold_graph_out</filter>
        </data>
    </outputs>
    <tests>
        <test> <!-- Test 1 - basic test with k=33 -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="kmers" value="33" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastq" name="fwd_reads" value="ecoli_1K_1.fq" />
            <param ftype="fastq" name="rev_reads" value="ecoli_1K_2.fq" />
            <output compare="re_match" file="kmer_33_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
            <output name="out_contig_stats">
                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 2 - basic test with k=33 fasta input -->
            <param name="sc" value="false" />
            <param name="onlyassembler" value="true"/>
            <param name="careful" value="false" />
            <param name="kmers" value="33" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fasta" name="fwd_reads" value="ecoli_1K_1.fasta" />
            <param ftype="fasta" name="rev_reads" value="ecoli_1K_2.fasta" />
            <output compare="re_match" file="kmer_33_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
            <output name="out_contig_stats">
                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 3 - basic test with k=33 and gzipped input -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="kmers" value="33" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastq.gz" name="fwd_reads" value="ecoli_1K_1.fq.gz" />
            <param ftype="fastq.gz" name="rev_reads" value="ecoli_1K_2.fq.gz" />
            <output compare="re_match" file="kmer_33_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
            <output name="out_contig_stats">
                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 4 - auto k -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="auto_kmer_choice" value="true" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastq" name="fwd_reads" value="ecoli_1K_1.fq" />
            <param ftype="fastq" name="rev_reads" value="ecoli_1K_2.fq" />
            <output compare="re_match" file="auto_kmer_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
        </test>
        <test> <!-- Test 5 - k=77 -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="kmers" value="77" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastq" name="fwd_reads" value="ecoli_1K_1.fq" />
            <param ftype="fastq" name="rev_reads" value="ecoli_1K_2.fq" />
            <output compare="re_match" file="kmer_77_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
        </test>
        <test> <!-- Test 6 - test for extra graph outputs -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="kmers" value="33" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastq" name="fwd_reads" value="ecoli_1K_1.fq" />
            <param ftype="fastq" name="rev_reads" value="ecoli_1K_2.fq" />
            <param name="contig_graph_out" value="true" />
            <param name="scaffold_graph_out" value="true" />
            <output compare="re_match" file="kmer_33_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
            <output name="out_contig_stats">
                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
            <output name="contig_graph">
                <assert_contents>
                    <has_text text=">EDGE_"/>
                </assert_contents>
            </output>
            <output name="scaffold_graph">
                <assert_contents>
                    <has_text text="NODE_"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 7 - basic test with k=33 and fastsanger input -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="kmers" value="33" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastqsanger" name="fwd_reads" value="ecoli_1K_1.fq" />
            <param ftype="fastqsanger" name="rev_reads" value="ecoli_1K_2.fq" />
            <output compare="re_match" file="kmer_33_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
            <output name="out_contig_stats">
                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 8 - basic test with k=33 and fastsanger.gz input -->
            <param name="sc" value="false" />
            <param name="careful" value="false" />
            <param name="kmers" value="33" />
            <param name="lib_type" value="paired_end" />
            <param ftype="fastqsanger.gz" name="fwd_reads" value="ecoli_1K_1.fq.gz" />
            <param ftype="fastqsanger.gz" name="rev_reads" value="ecoli_1K_2.fq.gz" />
            <output compare="re_match" file="kmer_33_output.fa" ftype="fasta" lines_diff="1" name="out_contigs" />
            <output name="out_contig_stats">
                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

SPAdes – St. Petersburg genome assembler – is intended for both standard isolates and single-cell MDA bacteria assemblies. See http://bioinf.spbau.ru/en/spades for more details on SPAdes.

This wrapper runs SPAdes, collects the output, and throws away all the temporary files. It also produces a tab file with contig names, length and coverage.

**License**

SPAdes is developed by and copyrighted to Saint-Petersburg Academic University, and is released under GPLv2.

This wrapper is copyrighted by Philip Mabon and is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

You should have received a copy of the GNU General Public License along with this program.  If not, see http://www.gnu.org/licenses/.

** Acknowledgments **

Original wrapper developed by Lionel Guy.

Anton Korobeynikov greatlty helped understanding how SPAdes work, and integrated handy features into SPAdes.

Nicola Soranzo fixed various bugs.

Simon Gladman added fastg optional outputs.
]]>
    </help>
    <citations>
        <citation type="doi">10.1089/cmb.2012.0021</citation>
    </citations>
</tool>