Mercurial > repos > wolma > mimodd
diff snap_caller.xml @ 23:5db0545b9004 draft
update to v0.1.7.3
| author | wolma |
|---|---|
| date | Thu, 21 Jul 2016 03:55:49 -0400 |
| parents | c46406466625 |
| children |
line wrap: on
line diff
--- a/snap_caller.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/snap_caller.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="read_alignment" name="SNAP Read Alignment" version="0.1.7.2"> +<tool id="read_alignment" name="SNAP Read Alignment" version="0.1.7.3"> <description>Map sequence reads to a reference genome using SNAP</description> <macros> <import>toolshed_macros.xml</import> </macros> - <expand macro="requirements"/> + <expand macro="requirements" /> <version_command>python3 -m MiModD version -q</version_command> <command> python3 -m MiModD snap-batch -s @@ -50,73 +50,73 @@ <inputs> ## mandatory arguments (and mode-conditionals) - <param name="ref_genome" type="data" format="fasta" label="reference genome" help="The fasta reference genome that SNAP should align reads against."/> + <param format="fasta" help="The fasta reference genome that SNAP should align reads against." label="reference genome" name="ref_genome" type="data" /> - <repeat name="datasets" title="datasets" default="1" min="1"> + <repeat default="1" min="1" name="datasets" title="datasets"> <conditional name="mode_choose"> - <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!"> + <param 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!" label="choose mode" name="mode" type="select"> <option value="single">single-end</option> <option value="paired">paired-end</option> </param> <when value="single"> <conditional name="input"> - <param name="iformat" type="select" label="input file format"> + <param label="input file format" name="iformat" type="select"> <option value="bam">BAM</option> <option value="sam">SAM</option> <option value="gz">gz</option> <option value="fastq">fastq</option> </param> <when value="bam"> - <param name="ifile" type="data" format="bam" label="input file"/> - <param name="header" type="data" optional="true" format="sam" label="custom header file" /> + <param format="bam" label="input file" name="ifile" type="data" /> + <param format="sam" label="custom header file" name="header" optional="true" type="data" /> </when> <when value="sam"> - <param name="ifile" type="data" format="sam" label="input file"/> - <param name="header" type="data" optional="true" format="sam" label="custom header file" /> + <param format="sam" label="input file" name="ifile" type="data" /> + <param format="sam" label="custom header file" name="header" optional="true" type="data" /> </when> <when value="gz"> - <param name="ifile" type="data" label="input file"/> - <param name="header" type="data" format="sam" label="header file" /> + <param label="input file" name="ifile" type="data" /> + <param format="sam" label="header file" name="header" type="data" /> </when> <when value="fastq"> - <param name="ifile" type="data" format="fastq" label="input file"/> - <param name="header" type="data" format="sam" label="header file" /> + <param format="fastq" label="input file" name="ifile" type="data" /> + <param format="sam" label="header file" name="header" type="data" /> </when> </conditional> </when> <when value="paired"> <conditional name="input"> - <param name="iformat" type="select" label="input file format"> + <param label="input file format" name="iformat" type="select"> <option value="bam">BAM</option> <option value="sam">SAM</option> <option value="gz">gz</option> <option value="fastq">fastq</option> </param> <when value="bam"> - <param name="ifile" type="data" format="bam" label="input file"/> - <param name="header" type="data" optional="true" format="sam" label="custom header file" /> + <param format="bam" label="input file" name="ifile" type="data" /> + <param format="sam" label="custom header file" name="header" optional="true" type="data" /> </when> <when value="sam"> - <param name="ifile" type="data" format="sam" label="input file"/> - <param name="header" type="data" optional="true" format="sam" label="custom header file" /> + <param format="sam" label="input file" name="ifile" type="data" /> + <param format="sam" label="custom header file" name="header" optional="true" type="data" /> </when> <when value="fastq"> - <param name="ifile1" type="data" format="fastq" label="inputfile with the first set of reads of paired-end data"/> - <param name="ifile2" type="data" format="fastq" label="inputfile with the second set of reads of paired-end data"/> - <param name="header" type="data" format="sam" label="header file" help="required" /> + <param format="fastq" label="inputfile with the first set of reads of paired-end data" name="ifile1" type="data" /> + <param format="fastq" label="inputfile with the second set of reads of paired-end data" name="ifile2" type="data" /> + <param format="sam" help="required" label="header file" name="header" type="data" /> </when> <when value="gz"> - <param name="ifile1" type="data" label="inputfile with the first set of reads of paired-end data"/> - <param name="ifile2" type="data" label="inputfile with the second set of reads of paired-end data"/> - <param name="header" type="data" format="sam" label="header file" help="required" /> + <param label="inputfile with the first set of reads of paired-end data" name="ifile1" type="data" /> + <param label="inputfile with the second set of reads of paired-end data" name="ifile2" type="data" /> + <param format="sam" help="required" label="header file" name="header" type="data" /> </when> </conditional> </when> </conditional> </repeat> - <param name="oformat" type="select" label="output file format"> + <param label="output file format" name="oformat" type="select"> <option value="bam">BAM</option> <option value="sam">SAM</option> </param> @@ -124,7 +124,7 @@ ## optional arguments <conditional name="set"> - <param name="settings_mode" type="select" label="further parameter settings" help="This section lets you specify the detailed parameter settings for the SNAP aligner. Only change them if you know what you are doing, i.e., read the documentation first."> + <param help="This section lets you specify the detailed parameter settings for the SNAP aligner. Only change them if you know what you are doing, i.e., read the documentation first." label="further parameter settings" name="settings_mode" type="select"> <option value="default">default settings</option> <option value="change">change settings</option> </param> @@ -132,58 +132,58 @@ ## default settings <when value="default"> - <param name="seedsize" type="hidden" value="20"/> - <param name="slack" type="hidden" value="0.3"/> - <param name="sp_min" type="hidden" value="100"/> - <param name="sp_max" type="hidden" value="10000"/> - <param name="maxdist" type="hidden" value="8"/> - <param name="confdiff" type="hidden" value="2"/> - <param name="confadpt" type="hidden" value="7"/> + <param name="seedsize" type="hidden" value="20" /> + <param name="slack" type="hidden" value="0.3" /> + <param name="sp_min" type="hidden" value="100" /> + <param name="sp_max" type="hidden" value="10000" /> + <param name="maxdist" type="hidden" value="8" /> + <param name="confdiff" type="hidden" value="2" /> + <param name="confadpt" type="hidden" value="7" /> - <param name="maxseeds" type="hidden" value="25"/> - <param name="maxhits" type="hidden" value="250"/> - <param name="clipping" type="hidden" value="++"/> + <param name="maxseeds" type="hidden" value="25" /> + <param name="maxhits" type="hidden" value="250" /> + <param name="clipping" type="hidden" value="++" /> - <param name="selectivity" type="hidden" value="off"/> - <param name="filter_output" type="hidden" value="off"/> - <param name="sort" type="hidden" value="0"/> - <param name="mmatch_notation" type="hidden" value="general"/> + <param name="selectivity" type="hidden" value="off" /> + <param name="filter_output" type="hidden" value="off" /> + <param name="sort" type="hidden" value="0" /> + <param name="mmatch_notation" type="hidden" value="general" /> <param name="discard_overlapping_mates" type="hidden" value="" /> </when> ## change settings <when value="change"> - <param name="seedsize" type="integer" value="20" label="seed size (default: 20)" help="Length of the seeds used in the reference genome hash table (SNAP index option -s)."/> - <param name="slack" type="float" value="0.3" label="hash table slack size (default: 0.3)" help="Corresponds to the -h option of SNAP index."/> + <param help="Length of the seeds used in the reference genome hash table (SNAP index option -s)." label="seed size (default: 20)" name="seedsize" type="integer" value="20" /> + <param help="Corresponds to the -h option of SNAP index." label="hash table slack size (default: 0.3)" name="slack" type="float" value="0.3" /> ## paired-end specific options - <param name="sp_min" type="integer" value="100" label="minimum spacing to allow between paired ends (default: 100)" help="Corresponds to the first value of the SNAP option -s. Affects paired-end data only."/> - <param name="sp_max" type="integer" value="10000" label="maximum spacing to allow between paired ends (default: 10000)" help="Corresponds to the second value of the SNAP option -s. Affects paired-end data only."/> - <param name="discard_overlapping_mates" type="text" display="checkboxes" multiple="true" label="discard overlapping read pairs of type" help="Consider overlapping mate pairs of the given orientation type(s) anomalous and discard them; allowed values: RF, FR, FF, RR; multiple types may be specified as a comma-separated list and ALL can be used as a shortcut for discarding all overlapping mate pairs; leave blank to retain all overlapping pairs. Affects paired-end data only." /> - <param name="maxdist" type="integer" value="8" label="edit distance (default: 8)" help="maximum edit distance allowed per read or pair (SNAP option -d); higher values allow more divergent alignments to be found, but increase the rate of misalignments."/> - <param name="maxhits" type="integer" value="250" label="maximum hits per seed (default: 250)" help="Maximum hits to consider per seed (SNAP option -h); don't use a seed region in the alignment process if it matches more than maxhits regions in the reference genome. Higher values reduce the rate of misalignments, but reduce performance."/> - <param name="confdiff" type="integer" value="2" label="confidence threshold (default: 2)" help="Confidence threshold (SNAP option -c); the minimum edit distance difference between two alternate alignments required to reject the poorer alignment as suboptimal; higher values increase the rate of ambiguously aligned reads."/> - <param name="confadpt" type="integer" value="7" label="adaptive confdiff behaviour (default: 7)" help="Specifies how many seeds of a read may be ignored (based on the maximum hits value above) before the confidence threshold above gets increased by one for that read; helps fine-tuning alignment accuracy in repetitive regions of the genome."/> - <param name="maxseeds" type="integer" value="25" label="maximum seeds per read (default: 25)" help="Number of seeds to use per read (SNAP option -n) when trying to match it to the reference genome; higher numbers will increase the rate of aligned reads and reduce the rate of misalignments, but will reduce performance."/> - <param name="clipping" type="select" label="read clipping (default: from back and front)" help="Specifies from which end of a read low-quality bases should be clipped (SNAP option -Cxx)"> + <param help="Corresponds to the first value of the SNAP option -s. Affects paired-end data only." label="minimum spacing to allow between paired ends (default: 100)" name="sp_min" type="integer" value="100" /> + <param help="Corresponds to the second value of the SNAP option -s. Affects paired-end data only." label="maximum spacing to allow between paired ends (default: 10000)" name="sp_max" type="integer" value="10000" /> + <param display="checkboxes" help="Consider overlapping mate pairs of the given orientation type(s) anomalous and discard them; allowed values: RF, FR, FF, RR; multiple types may be specified as a comma-separated list and ALL can be used as a shortcut for discarding all overlapping mate pairs; leave blank to retain all overlapping pairs. Affects paired-end data only." label="discard overlapping read pairs of type" multiple="true" name="discard_overlapping_mates" type="text" /> + <param help="maximum edit distance allowed per read or pair (SNAP option -d); higher values allow more divergent alignments to be found, but increase the rate of misalignments." label="edit distance (default: 8)" name="maxdist" type="integer" value="8" /> + <param help="Maximum hits to consider per seed (SNAP option -h); don't use a seed region in the alignment process if it matches more than maxhits regions in the reference genome. Higher values reduce the rate of misalignments, but reduce performance." label="maximum hits per seed (default: 250)" name="maxhits" type="integer" value="250" /> + <param help="Confidence threshold (SNAP option -c); the minimum edit distance difference between two alternate alignments required to reject the poorer alignment as suboptimal; higher values increase the rate of ambiguously aligned reads." label="confidence threshold (default: 2)" name="confdiff" type="integer" value="2" /> + <param help="Specifies how many seeds of a read may be ignored (based on the maximum hits value above) before the confidence threshold above gets increased by one for that read; helps fine-tuning alignment accuracy in repetitive regions of the genome." label="adaptive confdiff behaviour (default: 7)" name="confadpt" type="integer" value="7" /> + <param help="Number of seeds to use per read (SNAP option -n) when trying to match it to the reference genome; higher numbers will increase the rate of aligned reads and reduce the rate of misalignments, but will reduce performance." label="maximum seeds per read (default: 25)" name="maxseeds" type="integer" value="25" /> + <param help="Specifies from which end of a read low-quality bases should be clipped (SNAP option -Cxx)" label="read clipping (default: from back and front)" name="clipping" type="select"> <option value="++">from back and front</option> <option value="x+">from back only</option> <option value="+x">from front only</option> <option value="xx">no clipping</option> </param> - <param name="selectivity" type="integer" value="1" label="selectivity (default: 1)" help="randomly choose 1/selectivity of the reads to score (SNAP option -S). The tool uses the default of 1 (or a 0 setting) to indicate that all reads should be worked with." /> - <param name="filter_output" type="select" label="filter output (default: no filtering)" help="filter output (SNAP option -F for certain classes of reads."> + <param help="randomly choose 1/selectivity of the reads to score (SNAP option -S). The tool uses the default of 1 (or a 0 setting) to indicate that all reads should be worked with." label="selectivity (default: 1)" name="selectivity" type="integer" value="1" /> + <param help="filter output (SNAP option -F for certain classes of reads." label="filter output (default: no filtering)" name="filter_output" type="select"> <option value="off">no filtering</option> <option value="a">aligned only</option> <option value="s">single-aligned only</option> <option value="u">unaligned only</option> </param> - <param name="sort" type="select" label="output sorting (default: sort by read coordinates)" help="Sort the output file by alignment location (SNAP option --so)."> + <param help="Sort the output file by alignment location (SNAP option --so)." label="output sorting (default: sort by read coordinates)" name="sort" type="select"> <option value="0">sort by read coordinates</option> <option value="off">no sorting</option> </param> - <param name="mmatch_notation" type="select" label="CIGAR symbols for alignment matches/mismatches (default: M notation)" 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!!" > + <param 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!!" label="CIGAR symbols for alignment matches/mismatches (default: M notation)" name="mmatch_notation" type="select"> <option value="general">use M for both matches and mismatches</option> <option value="differentiate">use = for matches, X for mismatches</option> </param> @@ -192,9 +192,9 @@ </inputs> <outputs> - <data name="outputfile" format="bam" label="Aligned reads from MiModd ${tool.name} on ${on_string}"> + <data format="bam" label="Aligned reads from MiModd ${tool.name} on ${on_string}" name="outputfile"> <change_format> - <when input="oformat" value="sam" format="sam"/> + <when format="sam" input="oformat" value="sam" /> </change_format> </data> </outputs> @@ -238,5 +238,4 @@ .. _tool documentation: http://mimodd.readthedocs.org/en/latest/tool_doc.html#snap </help> -</tool> - +</tool> \ No newline at end of file