Mercurial > repos > simon-gladman > velvetoptimiser
diff velvetoptimiser.xml @ 5:82398ba86ba7 draft default tip
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/velvetoptimiser commit 87fc41195cd9d05d431e8363c31898ce07369ed3"
| author | iuc |
|---|---|
| date | Sat, 27 Nov 2021 10:38:38 +0000 |
| parents | 4a53b89fa703 |
| children |
line wrap: on
line diff
--- a/velvetoptimiser.xml Wed Jan 13 15:31:18 2021 +0000 +++ b/velvetoptimiser.xml Sat Nov 27 10:38:38 2021 +0000 @@ -1,5 +1,8 @@ -<tool id="velvetoptimiser" name="VelvetOptimiser" version="2.2.6+galaxy1"> +<tool id="velvetoptimiser" name="VelvetOptimiser" version="2.2.6+galaxy2"> <description>Automatically optimize Velvet assemblies</description> + <xrefs> + <xref type="bio.tools">velvetoptimiser</xref> + </xrefs> <requirements> <requirement type="package" version="1.2.10">velvet</requirement> <requirement type="package" version="2.2.6">perl-velvetoptimiser</requirement> @@ -15,6 +18,7 @@ -t "\${GALAXY_SLOTS:-1}" -s $start_kmer -e $end_kmer + -x $kmer_step -d out -f " #for $i in $files: @@ -61,22 +65,26 @@ #end for " - ##if str($advanced.advanced_select) == "advanced" - $advanced.verbose - -k '$advanced.optFuncKmer' - -c '$advanced.optFuncCov' - #if str($advanced.velvetg_opts) != "" - -o '$advanced.velvetg_opts' - #end if - -m $advanced.minCutoff - -z $advanced.maxCutoff - ##end if + $advanced.verbose + -k '$advanced.optFuncKmer' + -c '$advanced.optFuncCov' + #if str($advanced.velvetg_opts) != "" + -o '$advanced.velvetg_opts' + #end if + -m $advanced.minCutoff + -z $advanced.maxCutoff ]]></command> <inputs> - <param name="start_kmer" type="integer" value="31" label="Start k-mer size" help="Odd integer, Lower limit of k-mer size range to search for optimum value" /> - <param name="end_kmer" type="integer" value="191" label="End k-mer size" help="Odd integer, Upper limit of k-mer size range to search for optimum value" /> - <param name="kmer_step" type="integer" value="2" label="K-mer search step size" help="Even integer, the k-mer value step size when searching the range" /> + <param name="start_kmer" argument="-s" type="integer" value="31" min="11" max="191" label="Start k-mer size" help="Odd integer, Lower limit of k-mer size range to search for optimum value"> + <validator type="expression" message="Value needs to be odd">int(value) % 2 == 1</validator> + </param> + <param name="end_kmer" argument="-e" type="integer" value="191" min="11" max="191" label="End k-mer size" help="Odd integer, Upper limit of k-mer size range to search for optimum value"> + <validator type="expression" message="Value needs to be odd">int(value) % 2 == 1</validator> + </param> + <param name="kmer_step" argument="-x" type="integer" value="2" min="2" max="189" label="K-mer search step size" help="Even integer, the k-mer value step size when searching the range"> + <validator type="expression" message="Value needs to be even">int(value) % 2 == 0</validator> + </param> <repeat name="files" title="Input files" min="1"> <param name="filetype" label="Input file type" type="select" help="Input file type"> @@ -108,12 +116,12 @@ </repeat> <section name="advanced" title="Advanced Options" expanded="false"> - <param name="verbose" type="boolean" checked="false" truevalue="-v" falsevalue="" label="Verbose" help="Include verbose velvet output in log file" /> - <param name="optFuncKmer" type="text" value="n50" label="K-mer optimisation function" help="See help below for possibilities!"/> - <param name="optFuncCov" type="text" value="Lbp" label="Coverage cutoff optimisation function" help="See help below for possibilities!"/> - <param name="velvetg_opts" type="text" value="" label="Other velvetg options" help="Add any other required velvetg options from the advanced set"/> - <param name="minCutoff" type="integer" value="0" label="Minimum coverage cutoff" help="The minimum coverage cutoff to consider in the optimisation"/> - <param name="maxCutoff" type="float" value="0.8" label="Maximum coverage cutoff" help="The maximum coverage cutoff to consider expressed as a fraction of the calculated expected coverage."/> + <param name="verbose" argument="-v" type="boolean" checked="false" truevalue="-v" falsevalue="" label="Verbose" help="Include verbose velvet output in log file" /> + <param name="optFuncKmer" argument="-k" type="text" value="n50" label="K-mer optimisation function" help="See help below for possibilities!"/> + <param name="optFuncCov" argument="-c" type="text" value="Lbp" label="Coverage cutoff optimisation function" help="See help below for possibilities!"/> + <param name="velvetg_opts" argument="-o" type="text" value="" label="Other velvetg options" help="Add any other required velvetg options from the advanced set"/> + <param name="minCutoff" argument="-m" type="integer" value="0" label="Minimum coverage cutoff" help="The minimum coverage cutoff to consider in the optimisation"/> + <param name="maxCutoff" argument="-z" type="float" value="0.8" label="Maximum coverage cutoff" help="The maximum coverage cutoff to consider expressed as a fraction of the calculated expected coverage."/> </section> </inputs> @@ -236,10 +244,12 @@ The hash length, also known as k-mer length, corresponds to the length, in base pairs, of the words being hashed. - The hash length is the length of the k-mers being entered in the hash table. Firstly, you must observe three technical constraints:: - - it must be an odd number, to avoid palindromes. If you put in an even number, Velvet will just decrement it and proceed. - - it must be below or equal to MAXKMERHASH length (cf. 2.3.3, by default 31bp), because it is stored on 64 bits - - it must be strictly inferior to read length, otherwise you simply will not observe any overlaps between reads, for obvious reasons. + The hash length is the length of the k-mers being entered in the hash table. Firstly, you must observe three technical constraints: + + - it must be an odd number, to avoid palindromes. If you put in an even number, Velvet will just decrement it and proceed. + - it must be below or equal to MAXKMERHASH length (cf. 2.3.3, by default 31bp), because it is stored on 64 bits + - it must be strictly inferior to read length, otherwise you simply will not observe any overlaps between reads, for obvious reasons. + Now you still have quite a lot of possibilities. As is often the case, it's a trade-off between specificity and sensitivity. Longer kmers bring you more specificity (i.e. less spurious overlaps) but lowers coverage (cf. below)... so there's a sweet spot to be found with time and experience. We like to think in terms of "k-mer coverage", i.e. how many times has a k-mer been seen among the reads. The relation between k-mer coverage Ck and standard (nucleotide-wise) coverage C is Ck = C * (L - k + 1)/L where k is your hash length, and L you read length. @@ -274,21 +284,15 @@ Velvet works mainly with fasta and fastq formats. For paired-end reads, the assumption is that each read is next to its mate read. In other words, if the reads are indexed from 0, then reads 0 and 1 are paired, 2 and 3, 4 and 5, etc. - Supported file formats are:: - - fasta - fastq - bam - - Read categories are:: + Supported file formats are: fasta, fastq, bam - short (default) - shortPaired - long (for Sanger, 454 or even reference sequences) - longPaired - reference (for pre-mapped sam or bam files - see Velvet manual for details on how to use this option) - - + Read categories are: + + - short (default) + - shortPaired + - long (for Sanger, 454 or even reference sequences) + - longPaired + - reference (for pre-mapped sam or bam files - see Velvet manual for details on how to use this option) ]]></help> <citations> <citation type="bibtex">@UNPUBLISHED{GLADMAN2012,