comparison spades.xml @ 10:b8d633fbf5f5 draft

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

9:24fffa4fee40

<tool id="spades" name="SPAdes" version="@TOOL_VERSION@">
    <description>genome assembler for regular and single-cell projects</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>

           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}

            #set prefix = 'hqmp'
        #end if
        --$prefix$i-$library.orientation
        #for $file in $library.files
            #if $file.file_type.type == "separate"
                --$prefix$i-1 $file.file_type.fwd_reads.extension:$file.file_type.fwd_reads
                --$prefix$i-2 $file.file_type.fwd_reads.extension:$file.file_type.rev_reads
            #elif $file.file_type.type == "interleaved"
                --$prefix$i-12 $file.file_type.interleaved_reads.extension:$file.file_type.interleaved_reads
            #elif $file.file_type.type == "merged"
                --$prefix$i-m $file.file_type.merged_reads.extension:$file.file_type.merged_reads
            #elif $file.file_type.type == "unpaired"
                --$prefix$i-s $file.file_type.unpaired_reads.extension:$file.file_type.unpaired_reads
            #elif $file.file_type.type == "paired-collection"
                --$prefix$i-1 $file.file_type.fastq_collection.forward.extension:$file.file_type.fastq_collection.forward
                --$prefix$i-2 $file.file_type.fastq_collection.reverse.extension:$file.file_type.fastq_collection.reverse
            #end if
        #end for
    #end for
    #for $read in $pacbio_reads:
        #if $read:

            --nanopore fastq:$read
        #end if
    #end for
    #for $read in $sanger_reads:
        #if $read:
            --sanger $read.extension:$read
        #end if
    #end for
    #for $contig in $trusted_contigs:
        #if $contig:
            --trusted-contigs $contig.extension:$contig
        #end if
    #end for
    #for $contig in $untrusted_contigs:
        #if $contig:
            --untrusted-contigs $contig.extension:$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'

    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>

                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 1 - 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" />

                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 1 - 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" />

                <assert_contents>
                    <has_text_matching expression="NODE_1\t1000"/>
                </assert_contents>
            </output>
        </test>
        <test> <!-- Test 2 - 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 3 - 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 4 - 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" />

                </assert_contents>
            </output>
            <output name="scaffold_graph">
                <assert_contents>
                    <has_text text="NODE_"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>

10:b8d633fbf5f5

<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>

           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}

            #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:

            --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'

    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>

                <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" />

                <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" />

                <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" />

                </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>