comparison srst2v2.xml @ 0:ffd5306daa4c draft

planemo upload

0:ffd5306daa4c

<tool id="srst2v2" name="SRST2 - Short Read Sequence Typer (v2)" version="0.2.0">
    <requirements>
        <requirement type="package" version="0.2.0">srst2</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #if $paired_conditional.sPaired == "paired"
           ln -s $paired_conditional.fastq1 sample_1.fastq;
           ln -s $paired_conditional.fastq2 sample_2.fastq;
        #end if

        srst2

        #if $paired_conditional.sPaired == "single"
            --input_se $paired_conditional.fastq1
        #else if $paired_conditional.sPaired == "paired"
            --input_pe sample_1.fastq sample_2.fastq
        #end if

        --output srst2out 
        --save_scores 
        --mlst_definitions "$mlst_definitions" 
        --mlst_db "$mlst_db" 
        --mlst_delimiter $mlstdelim
        --mlst_max_mismatch $mlst_max_mismatch

    ]]></command>
    <inputs>
      <conditional name="paired_conditional">
        <param name="sPaired" type="select" label="Single-End or Paired-End FASTQ?">
          <option value="single">Single-end</option>
          <option value="paired">Paired-end</option>
        </param>
        <when value="single">
          <param name="fastq1" type="data" format="fastq" label="FASTQ file" help="FASTQ" />
        </when>
        <when value="paired">
          <param name="fastq1" type="data" format="fastq" label="Forward FASTQ file" help="FASTQ" />
          <param name="fastq2" type="data" format="fastq" label="Reverse FASTQ file" help="FASTQ" />
        </when>
      </conditional>

        <param type="data" name="mlst_db" label="Fasta file of MLST alleles" format="fasta" />
        <param type="data" name="mlst_definitions" label="ST definitions for MLST scheme" format="tabular" />
        <param type="text" name="mlstdelim" value="_" format="txt" label="Character(s) separating gene name from allele number in MLST database (default &apos;_&apos;)" />
        <param type="integer" name="mlst_max_mismatch" value="10" format="txt" label="Maximum number of mismatches per read for MLST allele calling (default 10)" />
    </inputs>

    <outputs>
      <data format="txt" label="Scores" name="scores" from_work_dir="*.scores"/>
      <data format="bam" label="bam alignment" name="bam" from_work_dir="*.sorted.bam"/>
      <data format="pileup" label="pileup" name="pileup" from_work_dir="*.pileup"/>
      <data format="txt" label="Alleles" name="alleles" from_work_dir="*results.txt"/>
    </outputs>

    <help><![CDATA[

SRST2 - Short Read Sequence Typer (v2)

This program is designed to take Illumina sequence data, a MLST database and/or a database of gene sequences (e.g. resistance genes, virulence genes, etc) and report the presence of STs and/or reference genes.



optional arguments:
  -h, --help            show this help message and exit
  --version             show program's version number and exit
  --input_se INPUT_SE 
                        Single end read file(s) for analysing (may be gzipped)
  --input_pe INPUT_PE 
                        Paired end read files for analysing (may be gzipped)
  --merge_paired        Switch on if all the input read sets belong to a
                        single sample, and you want to merge their data to get
                        a single result
  --forward FORWARD     Designator for forward reads (only used if NOT in
                        MiSeq format sample_S1_L001_R1_001.fastq.gz; otherwise
                        default is _1, i.e. expect forward reads as
                        sample_1.fastq.gz)
  --reverse REVERSE     Designator for reverse reads (only used if NOT in
                        MiSeq format sample_S1_L001_R2_001.fastq.gz; otherwise
                        default is _2, i.e. expect forward reads as
                        sample_2.fastq.gz
  --read_type READ_TYPE
                        Read file type (for bowtie2; default is q=fastq; other
                        options: qseq=solexa, f=fasta).
  --mlst_db MLST_DB     Fasta file of MLST alleles (optional)
  --mlst_delimiter MLST_DELIMITER
                        Character(s) separating gene name from allele number
                        in MLST database (default "-", as in arcc-1)
  --mlst_definitions MLST_DEFINITIONS
                        ST definitions for MLST scheme (required if mlst_db
                        supplied and you want to calculate STs)
  --mlst_max_mismatch MLST_MAX_MISMATCH
                        Maximum number of mismatches per read for MLST allele
                        calling (default 10)
  --gene_db GENE_DB 
                        Fasta file/s for gene databases (optional)
  --no_gene_details     Switch OFF verbose reporting of gene typing
  --gene_max_mismatch GENE_MAX_MISMATCH
                        Maximum number of mismatches per read for gene
                        detection and allele calling (default 10)
  --min_coverage MIN_COVERAGE
                        Minimum %coverage cutoff for gene reporting (default
                        90)
  --max_divergence MAX_DIVERGENCE
                        Maximum %divergence cutoff for gene reporting (default
                        10)
  --min_depth MIN_DEPTH
                        Minimum mean depth to flag as dubious allele call
                        (default 5)
  --min_edge_depth MIN_EDGE_DEPTH
                        Minimum edge depth to flag as dubious allele call
                        (default 2)
  --prob_err PROB_ERR   Probability of sequencing error (default 0.01)
  --truncation_score_tolerance TRUNCATION_SCORE_TOLERANCE
                        % increase in score allowed to choose non-truncated
                        allele
  --stop_after STOP_AFTER
                        Stop mapping after this number of reads have been
                        mapped (otherwise map all)
  --other OTHER        			 
			Other arguments to pass to bowtie2 (must be escaped,
                        e.g. "\\--no-mixed".)
  --max_unaligned_overlap MAX_UNALIGNED_OVERLAP
                        Read discarded from alignment if either of its ends
                        has unaligned overlap with the reference that is
                        longer than this value (default 10)
  --mapq MAPQ           Samtools -q parameter (default 1)
  --baseq BASEQ         Samtools -Q parameter (default 20)
  --samtools_args SAMTOOLS_ARGS
                        Other arguments to pass to samtools mpileup (must be
                        escaped, e.g. "\\-A").
  --output OUTPUT       Prefix for srst2 output files
  --log                 Switch ON logging to file (otherwise log to stdout)
  --save_scores         Switch ON verbose reporting of all scores
  --report_new_consensus
                        If a matching alleles is not found, report the
                        consensus allele. Note, only SNP differences are
                        considered, not indels.
  --report_all_consensus
                        Report the consensus allele for the most likely
                        allele. Note, only SNP differences are considered, not
                        indels.
  --use_existing_bowtie2_sam
                        Use existing SAM file generated by Bowtie2 if
                        available, otherwise they will be generated
  --use_existing_pileup
                        Use existing pileups if available, otherwise they will
                        be generated
  --use_existing_scores
                        Use existing scores files if available, otherwise they
                        will be generated
  --keep_interim_alignment
                        Keep interim files (sam & unsorted bam), otherwise
                        they will be deleted after sorted bam is created
  --threads THREADS     Use multiple threads in Bowtie and Samtools
  --prev_output PREV_OUTPUT 
                        SRST2 results files to compile (any new results from
                        this run will also be incorporated)


    ]]></help>


    <citations>
        <citation type="bibtex">
        @misc{pope_dashnow_zobel_holt_raven_schultz_inouye_tomita_2014, 
        title={SRST2: Rapid genomic surveillance for public health and hospital microbiology labs}, 
        url={https://genomemedicine.biomedcentral.com/articles/10.1186/s13073-014-0090-6}, 
        journal={Genome Medicine}, publisher={BioMed Central}, 
        author={Pope, Bernard J and Dashnow, Harriet and Zobel, Justin and Holt, Kathryn E and Raven, Lesley-Ann and Schultz, Mark B and Inouye, Michael and Tomita, Takehiro}, 
        year={2014}, month={Nov}} ,
       }</citation>
    </citations>
</tool>