view skesa.xml @ 22:9448df7c25a0 draft

Uploaded
author estrain
date Mon, 15 Oct 2018 17:12:13 -0400
parents 8bafd3d18864
children e2b708d5c0d3
line wrap: on
line source

<tool id="skesa" name="skesa" version="0.23">
    <requirements>
      <requirement type="package" version="2.3.0">skesa</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[

      skesa

      #if $jobtype.select == "fasta_single"
        #set outname = $jobtype.fasta.name
        --fasta $jobtype.fasta 
      #else if $jobtype.select == "fastq_single"
        #set outname = $jobtype.fastq1.name
        --fastq $jobtype.fastq1 
      #else if $jobtype.select == "fastq_fr"
        #set outname = $jobtype.fastq1.name
        --fastq $jobtype.fastq1 --fastq $jobtype.fastq2
      #else if $jobtype.select == "fastq_pair"
        #set outname = $jobtype.coll.name
        --fastq $jobtype.coll.forward --fastq $jobtype.coll.reverse
      #end if

      #if $options.select=="advanced"
        #if $options.cores
          --cores $options.cores
        #end if
        #if $options.memory
          --memory $options.memory
        #end if
        #if $options.hash_count
          --hash_count
        #end if
        #if $options.estimated_kmers
          --estimated_kmers $options.estimated.kmers
        #end if
        #if $options.skip
         --skip_bloom_filter
        #end if
        #if $options.kmer
         --kmer $options.kmer 
        #end if
        #if $options.min_count
         --min_count $options.min_count 
        #end if
        #if $options.max_kmer_count
         --max_kmer_count $options.max_kmer_count 
        #end if
        #if $options.vector_percent
         --vector_percent $options.vector_percent 
        #end if
        #if $options.insert_size
         --insert_size $options.insert.size 
        #end if
        #if $options.steps
         --steps $options.steps 
        #end if
        #if $options.fraction
         --fraction $options.fraction 
        #end if
        #if $options.max_snp_len
         --max_snp_len $options.max_snp_len 
        #end if
        #if $options.min_contig
         --min_contig $options.min_contig 
        #end if
        #if $options.allow_snps
         --allow_snps 
        #end if
      #else if $options.select =="basic"
        --cores \${GALAXY_SLOTS:-4} 
        --memory 16
      #end if

      > ${outname}.fasta 

    ]]></command>
    <inputs>
      <conditional name="jobtype">
        <param name="select" type="select" label="Select Input">
          <option value="fasta_single">Single FASTA</option>
          <option value="fastq_single">Single FASTQ</option>
          <option value="fastq_fr">Forward and Reverse FASTQ</option>
          <option value="fastq_pair">Paired FASTQ Collection</option>
        </param>
        <when value="fasta_single">
          <param name="fasta" type="data" format="fasta" label="FASTA" />
        </when>
        <when value="fastq_single">
          <param name="fastq1" type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" label="FASTQ" />
        </when>
        <when value="fastq_fr">
          <param name="fastq1" type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" label="Forward FASTQ" />
          <param name="fastq2" type="data" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" label="Reverse FASTQ" />
        </when>
        <when value="fastq_pair">
          <param name="coll" label="Paired FASTQ" type="data_collection" format="fastq,fastqsanger,fastq.gz,fastqsanger.gz,fastq.bz2,fastqsanger.bz2" collection_type="paired" />
        </when>
      </conditional>
  
      <conditional name="options">
        <param name="select" type="select" label="Options Type">
          <option value="basic">Basic</option>
          <option value="advanced">Advanced</option>
        </param>
        <when value="advanced">
          <param name="cores" type="integer" label="Number of cores to use" value="1"/>
          <param name="memory" type="integer" label="Memory available (GB, only for sorted counter)" value="16"/>
          <param name="hash_count" type="boolean" label="hash counter"/>
          <param name="estimated_kmers" type="integer" label="Estimated number of unique kmers for bloom filter" value="100"/>
          <param name="skip" type="boolean" label="skip bloom filter, use estimate kmers as the hash"/>
          <param name="kmer" type="integer" label="Minimal kmer length for assembly" value="21"/>
          <param name="min_count" type="integer" label="Minimal count for kmers retained for comparing alternate choices" value=""/>
          <param name="max_kmer_count" type="integer" label="Minimum acceptable average count for estimating the maximal kmer length in reads" value=""/>
          <param name="vector_percent" type="float" label="Count for  vectors as a fraction of the read number (1=disabled)" value="1">
            <validator type="in_range" message="Must be float(0,1)." min="0" max="1"/>
          </param>
          <param name="insert_size" type="integer" label="Expected insert size for paired reads (if not provided, it will be estimated)" value=""/>
          <param name="steps" type="integer" label="Number of assembly iterations from minimal to maximal kmer length in reads" value="11"/>
          <param name="fraction" type="float" label="Maximum noise to signal ratio acceptable for extension" value="0.1">
            <validator type="in_range" message="Must be float(0,1)." min="0" max="1"/>
          </param>
          <param name="max_snp_len" type="integer" label="Maximal snp length" value="150"/>
          <param name="min_contig" type="integer" label="Minimal contig length reported in output" value="200"/>
          <param name="allow_snps" type="boolean" label="Turn SNP discovery" value="false"/>
        </when>
        <when value="basic"/>
      </conditional>
    </inputs>
    <outputs>
      <data format="fasta" name="results.skesa.fasta" label="${tool.name} on ${on_string}: Contigs" from_work_dir="*.fasta"/>
    </outputs>

    <help><![CDATA[

    ]]></help>
     <citations>
        <citation type="bibtex">
        @misc{pope_dashnow_zobel_holt_raven_schultz_inouye_tomita_2014,
        title={skesa: eSKESA is a de-novo sequence read assembler for cultured single isolate genomes
    based on DeBruijn graphs. It uses conservative heuristics and is designed to
    create breaks at repeat regions in the genome. This leads to excellent sequence
    quality but not necessarily a large N50 statistic. It is a multi-threaded
    application that scales well with the number of processors. For different runs
    with the same inputs, including the order of reads, the order and orientation
    of contigs in the output is deterministic. },
        url={https://github.com/ncbi/ngs-tools/tree/master/tools/skesa/},
        author={National Center for Biotechnology Information },
       }</citation>
    </citations>
</tool>