Mercurial > repos > cstrittmatter > skesa
changeset 5:b82a1b3c5b61 draft
planemo upload commit cd1454c40a43ad9da3d59e6ba8359318fc772c43-dirty
author | cstrittmatter |
---|---|
date | Wed, 15 Aug 2018 17:35:46 -0400 |
parents | 15be58c254f5 |
children | f9b8095f18fe |
files | skesa.xml |
diffstat | 1 files changed, 31 insertions(+), 14 deletions(-) [+] |
line wrap: on
line diff
--- a/skesa.xml Wed Aug 15 09:33:27 2018 -0400 +++ b/skesa.xml Wed Aug 15 17:35:46 2018 -0400 @@ -5,20 +5,29 @@ <command detect_errors="exit_code"><![CDATA[ #if $jobtype.select != "cl" skesa - #if $jobtype.select == "asm" - -i $draft + #if $jobtype.select == "srr" + -sra_run $srrnum + #else if $jobtype.select == "asm" + --fasta $draft #else if $jobtype.select == "se" --fastq $fastq1 #else if $jobtype.select == "pe" --fastq $fastq1,$fastq2 --use_paired_ends #end if - > results.skesa.fasta + #if $cores != 0 + --cores $cores + #end if + --memory $memory > results.skesa.fasta #end if ]]></command> <inputs> <conditional name="jobtype"> + <when value="srr"> + <param name="srrnum" type="text" label="Sra run number"/> + </when> <param name="select" type="select" label="Assembly or FASTQ Reads?"> + <option value="sra">SRR number</option> <option value="asm">Genome Assembly</option> <option value="se">Single-End Reads</option> <option value="pe">Paired-End Reads</option> @@ -38,9 +47,10 @@ <param type="data_collection" name="collection_files" format="fastq" collection_type="list" label="FASTQS: Must be a Data Set list built from multiple fastq files" /> </when> </conditional> - - <param name="percent_identity" type="integer" label="Percent identity required for an allele match [default 90]" value="90" /> - <param name="percent_length" type="integer" label="Percent length required for an allele match [default 50]" value="50" /> + <param name="memory" type="integer" label="Memory available (GB) [integer]" value="16" /> + <param name="cores" type="integer" label="Number of cores to use (default all) [integer]" value="0" /> + <param name="kmer" type="integer" label="Minimal kmer length for assembly [default 21] if non are specified " value="0" /> + <param name="min_count" type="integer" label="Minimal count for kmers retained for comparing alternate choices [integer]" value="0" /> </inputs> <outputs> @@ -55,23 +65,30 @@ A fasta assembly or single or paired end reads test or data set list of fastqs -**PERCENTIDENTITY** +**Memory available** -Percentage of identity wanted to use against the database. From 0 to 100, default is 90%. +--memory arg (=32) Memory available (GB) [integer] + -**PERCENTLENGTH** +**Number of cores** -Percentage of length wanted to use against the database. From 0 to 100, default is 50%. +--cores arg (=0) Number of cores to use (default all) [integer] -https://github.com/phac-nml/ecoli_serotyping +https://github.com/ncbi/ngs-tools/tree/master/tools/skesa/ ]]></help> <citations> <citation type="bibtex"> @misc{pope_dashnow_zobel_holt_raven_schultz_inouye_tomita_2014, - title={SRST2: ecyper wraps a standalone serotyping module for Escherichia coli. Supports fasta and fastq file formats.}, - url={https://www.nml-lnm.gc.ca/}, - author={National Microbiology Laboratory }, + 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>