| Next changeset 1:2d4444da3087 (2015-01-16) |
|
Commit message:
Imported from capsule None |
|
added:
snap_caller.xml tool_dependencies.xml |
| b |
| diff -r 000000000000 -r b2d889cd87f0 snap_caller.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snap_caller.xml Sat Dec 13 17:20:16 2014 -0500 |
| b |
| b'@@ -0,0 +1,235 @@\n+<tool id="read_alignment" name="SNAP Read Alignment">\n+ <description>Map sequence reads to a reference genome using SNAP</description>\n+ <requirements>\n+ <requirement type="package" version="0.1.5">mimodd</requirement>\n+ </requirements>\n+ <version_command>mimodd version -q</version_command>\n+ <command> \n+\tmimodd snap-batch -s\n+\t## SNAP calls (considering different cases)\n+\n+\t#for $i in $datasets\n+\t\t"snap ${i.mode_choose.mode} $ref_genome\n+\t\t#if $str($i.mode_choose.mode) == "paired" and $str($i.mode_choose.input.iformat) in ("fastq", "gz"):\n+${i.mode_choose.input.ifile1} ${i.mode_choose.input.ifile2}\n+\t\t#else:\n+${i.mode_choose.input.ifile}\n+\t\t#end if\n+--ofile $outputfile --iformat ${i.mode_choose.input.iformat} --oformat $oformat\n+--idx-seedsize $set.seedsize\n+--idx-slack $set.slack --maxseeds $set.maxseeds --maxhits $set.maxhits --clipping=$set.clipping --maxdist $set.maxdist --confdiff $set.confdiff --confadapt $set.confadpt\n+\t\t#if $i.mode_choose.input.header:\n+--header ${i.mode_choose.input.header}\n+\t\t#end if\n+\t\t#if $str($i.mode_choose.mode) == "paired":\n+--spacing $set.sp_min $set.sp_max\n+\t\t#end if\n+\t\t#if $str($set.selectivity) != "off":\n+--selectivity $set.selectivity\n+\t\t#end if\n+\t\t#if $str($set.filter_output) != "off":\n+--filter-output $set.filter_output\n+\t\t#end if\n+\t\t#if $str($set.sort) != "off":\n+--sort $set.sort\n+\t\t#end if\n+\t\t#if $str($set.mmatch_notation) == "general":\n+-M\n+\t\t#end if\n+--max-mate-overlap $set.max_mate_overlap\n+--verbose\n+"\t\t\t\t\t\t\t\n+\t#end for\n+ </command>\n+\n+ <inputs>\n+ ## mandatory arguments (and mode-conditionals)\n+\n+ <param name="ref_genome" type="data" format="fasta" label="reference genome" help="The fasta reference genome that SNAP should align reads against."/>\n+ \n+ <repeat name="datasets" title="datasets" default="1" min="1"> \n+ <conditional name="mode_choose">\n+ <param name="mode" type="select" label="choose mode" help="Reads obtained from single-end sequencing runs should be aligned in \'single\' mode, paired-end reads in \'paired\' mode. **WARNING**: if the read input file is in SAM/BAM format, the current version of this tool will **not** verify the mode and may produce erroneous alignments with wrong settings!">\n+\t <option value="single">single-end</option>\n+\t <option value="paired">paired-end</option>\n+ </param>\n+ \n+ <when value="single">\n+\t <conditional name="input">\n+ <param name="iformat" type="select" label="input file format">\n+ <option value="bam">BAM</option>\n+ <option value="sam">SAM</option>\n+ <option value="gz">gz</option>\n+\t\t <option value="fastq">fastq</option>\n+\t </param>\n+\t <when value="bam">\n+\t\t <param name="ifile" type="data" format="bam" label="input file"/>\n+ <param name="header" type="data" optional="true" format="sam" label="custom header file" />\n+\t </when>\n+\t <when value="sam">\n+\t\t <param name="ifile" type="data" format="sam" label="input file"/>\n+ <param name="header" type="data" optional="true" format="sam" label="custom header file" />\n+\t </when> \n+\t <when value="gz">\n+\t\t <param name="ifile" type="data" label="input file"/>\n+\t\t <param name="header" type="data" format="sam" label="header file" />\n+\t\t </when>\n+\t <when value="fastq">\n+\t\t <param name="ifile" type="data" format="fastq" label="input file"/>\n+\t\t <param name="header" type="data" format="sam" label="header file" />\n+\t\t </when>\n+ </conditional>\n+ </when>\n+ <when value="paired">\t\n+\t <conditional name="input">\n+ <param name="iformat" type="select" label="input file format">\n+ <option value="bam">BAM</option>\n+ <option value="sam">SAM</option>\n+\t\t <option value="gz">gz</option>\n+ <option value="fastq">fastq</option>\n+\t </param>\n+ <when value="bam">\n+\t\t '..b')" help="Indicates whether CIGAR strings in the generated SAM/BAM file should use M (alignment match) rather than = and X (sequence (mis-)match). Warning: Downstream variant calling based on samtools currently relies on the old-style M notation!!" >\n+\t <option value="general">use M for both matches and mismatches</option>\n+\t <option value="differentiate">use = for matches, X for mismatches</option>\n+\t </param>\n+ </when>\n+ </conditional>\n+</inputs>\n+\n+<outputs>\n+ <data name="outputfile" format="bam" label="Aligned reads from MiModd ${tool.name} on ${on_string}">\n+ <change_format>\n+\t <when input="oformat" value="sam" format="sam"/>\n+\t</change_format>\n+ </data>\n+</outputs>\n+\n+<help>\n+.. class:: infomark\n+\n+ **What it does**\n+\n+The tool aligns the sequenced reads in an arbitrary number of input datasets against a common reference genome and stores the results in a single, possibly multi-sample output file. It supports a variety of different sequenced reads input formats, i.e., SAM, BAM, fastq and gzipped fastq, and both single-end and paired-end data.\n+\n+Internally, the tool uses the ultrafast, hashtable-based aligner SNAP (http://snap.cs.berkeley.edu), hence its name. \n+\n+**Notes:**\n+\n+1) In its standard configuration Galaxy will decompress any .gz files during their upload, so the option to align gzipped fastq input is useful only with customized Galaxy instances or by using linked files as explained in our `recipe for using gzipped fastq files in Galaxy`_ from the `MiModD user guide`_.\n+\n+2) To use paired-end fastq data with the tool the read mate information needs to be split over two fastq files in corresponding order.\n+\n+ **TIP:** If your paired-end data is arranged differently, you may look into the *fastq splitter* and *fastq de-interlacer* tools for Galaxy from the `Fastq Manipulation category`_ of the Galaxy Tool Shed to see if they can convert your files to the expected format.\n+\n+3) The tool supports the alignment of reads from the same sequencing run, but distributed across several input files. \n+ \n+ Generally, it expects the reads from each input dataset to belong to one read-group and will abort with an error message if any input dataset declares more than one read group or sample names in its header. Different datasets, however, are allowed to contain reads from the same read-group (as indicated by matching read-group IDs and sample names in their headers), in which case the reads will be combined into one group in the output.\n+\n+4) Read-group information is required for every input dataset!\n+ \n+ We generally recommend to store NGS datasets in SAM/BAM format with run metadata stored in the file header. You can use the *NGS Run Annotation* and *Convert* tools to convert data in fastq format to SAM/BAM with added run information.\n+\n+ While it is not our recommended approach, you can, if you prefer it, align reads from fastq files or SAM/BAM files without header read-group information. To do so, you **must** specify a SAM file that provides the missing information in its header along with the input dataset. You can generate a SAM header file with the *NGS Run Annotation* tool.\n+\n+ Optionally, a SAM header file can also be used to replace existing read-group information in a headered SAM/BAM input file. This can be used to resolve read-group ID conflicts between multiple input files at tool runtime.\n+\n+4) Currently, you cannot configure aligner-specific options separately for specific input files from within this Galaxy tool. If you need this advanced level of control, you should use the command line tool ``mimodd snap-batch``.\n+\n+.. _Fastq Manipulation category: https://toolshed.g2.bx.psu.edu/repository/browse_repositories_in_category?id=310ff67d4caf6531\n+.. _recipe for using gzipped fastq files in Galaxy: http://mimodd.readthedocs.org/en/latest/recipes.html#use-gzipped-fastq-files-in-galaxy\n+.. _MiModD user guide: http://mimodd.readthedocs.org/en/latest\n+\n+</help>\n+</tool>\n+\n' |
| b |
| diff -r 000000000000 -r b2d889cd87f0 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Sat Dec 13 17:20:16 2014 -0500 |
| b |
| @@ -0,0 +1,6 @@ +<?xml version="1.0"?> +<tool_dependency> + <package name="mimodd" version="0.1.5"> + <repository changeset_revision="fbac402764d6" name="package_mimodd_0_1_5" owner="wolma" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> +</tool_dependency> |