Mercurial > repos > wolma > mimodd
changeset 23:5db0545b9004 draft
update to v0.1.7.3
| author | wolma |
|---|---|
| date | Thu, 21 Jul 2016 03:55:49 -0400 |
| parents | 24154c580718 |
| children | 3accdbe6503b |
| files | annotate_variants.xml bamsort.xml cloudmap.xml convert.xml covstats.xml deletion_predictor.xml fileinfo.xml reheader.xml sam_header.xml snap_caller.xml snp_caller_caller.xml snpeff_genomes.xml tool_dependencies.xml toolshed_macros.xml varextract.xml vcf_filter.xml |
| diffstat | 16 files changed, 312 insertions(+), 319 deletions(-) [+] |
line wrap: on
line diff
--- a/annotate_variants.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/annotate_variants.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="annotate_variants" name="Variant Annotation" version="0.1.7.2"> +<tool id="annotate_variants" name="Variant Annotation" version="0.1.7.3"> <description>Predict the effects of SNPs and indels on known genes in the reference genome using SnpEff</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 annotate @@ -50,65 +50,65 @@ </command> <inputs> - <param name="inputfile" type="data" format="vcf" label="vcf inputfile to be annotated" /> - <param name="grouping" type="select" label="Group variants by"> + <param format="vcf" label="vcf inputfile to be annotated" name="inputfile" type="data" /> + <param label="Group variants by" name="grouping" type="select"> <option value="">order in the input file</option> <option value="by_sample">sample</option> <option value="by_genes">most affected genes</option> </param> <conditional name="formatting"> - <param name="oformat" type="select" label="Format of the annotation output file"> + <param label="Format of the annotation output file" name="oformat" type="select"> <option value="html">HTML</option> <option value="text">Tab-separated plain text</option> </param> <when value="html"> - <param name="formatter_file" type="data" format="txt" optional="true" label="Optional file with hyperlink formatting instructions" /> - <param name="species" type="text" label="Species" help="Overwrite the species guess from the SnpEff genome, often not necessary" /> + <param format="txt" label="Optional file with hyperlink formatting instructions" name="formatter_file" optional="true" type="data" /> + <param help="Overwrite the species guess from the SnpEff genome, often not necessary" label="Species" name="species" type="text" /> </when> </conditional> <conditional name="annotool"> - <param name="name" type="select" label="Use this tool to annotate the input file" help = "Select SnpEff here, if you want to have the vcf input annotated with genomic feature information. Select None if you do not want additional annotation, if you do not have SnpEff installed, or if you have no appropriate SnpEff annotation file for the input."> + <param help="Select SnpEff here, if you want to have the vcf input annotated with genomic feature information. Select None if you do not want additional annotation, if you do not have SnpEff installed, or if you have no appropriate SnpEff annotation file for the input." label="Use this tool to annotate the input file" name="name" type="select"> <option value="snpeff">SnpEff</option> <option value="None">None</option> </param> <when value="snpeff"> - <param name="genome_list" type="data" format="tabular" label="genome list" /> - <param name="genomeVersion" type="select" label="Genome"> + <param format="tabular" label="genome list" name="genome_list" type="data" /> + <param label="Genome" name="genomeVersion" type="select"> <options from_dataset="genome_list"> - <column name="name" index="0"/> - <column name="value" index="1"/> + <column index="0" name="name" /> + <column index="1" name="value" /> </options> </param> - <param name="ori_output" type="boolean" checked="true" label="Keep the original SnpEff output" /> - <param name="stats" type="boolean" checked="true" label="Produce a summary file of results" /> + <param checked="true" label="Keep the original SnpEff output" name="ori_output" type="boolean" /> + <param checked="true" label="Produce a summary file of results" name="stats" type="boolean" /> <conditional name="snpeff_settings"> - <param name="detail_level" type="select" label="SnpEff-specific parameter settings" help="This section lets you specify the detailed parameter settings for the SnpEff tool."> + <param help="This section lets you specify the detailed parameter settings for the SnpEff tool." label="SnpEff-specific parameter settings" name="detail_level" type="select"> <option value="default">default settings</option> <option value="change">change settings</option> </param> <when value="default"> ## default settings for SnpEff - <param name="chr" type="hidden" value=""/> - <param name="min_cov" type="hidden" value=""/> - <param name="min_qual" type="hidden" value=""/> - <param name="no_ds" type="hidden" value=""/> - <param name="no_us" type="hidden" value=""/> - <param name="no_intron" type="hidden" value=""/> - <param name="no_intergenic" type="hidden" value=""/> - <param name="no_utr" type="hidden" value=""/> - <param name="ud" type="hidden" value=""/> + <param name="chr" type="hidden" value="" /> + <param name="min_cov" type="hidden" value="" /> + <param name="min_qual" type="hidden" value="" /> + <param name="no_ds" type="hidden" value="" /> + <param name="no_us" type="hidden" value="" /> + <param name="no_intron" type="hidden" value="" /> + <param name="no_intergenic" type="hidden" value="" /> + <param name="no_utr" type="hidden" value="" /> + <param name="ud" type="hidden" value="" /> </when> <when value="change"> - <param name="chr" type="boolean" truevalue="-chr" falsevalue="" checked="false" label="prepend 'chr' to chromosome names, e.g., 'chr7' instead of '7'" /> - <param name="min_cov" type="integer" optional="true" label="minimum coverage (default = not used)" help="do not include variants with a coverage lower than this value"/> - <param name="min_qual" type="integer" optional="true" label="minimum quality (default = not used)" help="do not include variants with a quality lower than this value"/> - <param name="no_ds" type="boolean" label="do not show downstream changes" truevalue="--no-downstream" falsevalue="" checked="false" help="annotation of effects on the downstream region of genes can be suppressed"/> - <param name="no_us" type="boolean" label="do not show upstream changes" truevalue="--no-upstream" falsevalue="" checked="false" help="annotation of effects on the upstream region of genes can be suppressed"/> - <param name="no_intron" type="boolean" label="do not show intron changes" truevalue="--no-intron" falsevalue="" checked="false" help="annotation of effects on introns of genes can be suppressed"/> - <param name="no_intergenic" type="boolean" label="do not show intergenic changes" truevalue="--no-intergenic" falsevalue="" checked="false" help="annotation of effects on intergenic regions can be suppressed"/> - <param name="no_utr" type="boolean" label="do not show UTR changes" truevalue="--no-utr" falsevalue="" checked="false" help="annotation of effects on the untranslated regions of genes can be suppressed"/> - <param name="ud" type="integer" optional="true" label="upstream downstream interval length (default = 5000 bases)" help="specify the upstream/downstream interval length, i.e., variants more than INTERVAL nts from the next annotated gene are considered to be intergenic"/> + <param checked="false" falsevalue="" label="prepend 'chr' to chromosome names, e.g., 'chr7' instead of '7'" name="chr" truevalue="-chr" type="boolean" /> + <param help="do not include variants with a coverage lower than this value" label="minimum coverage (default = not used)" name="min_cov" optional="true" type="integer" /> + <param help="do not include variants with a quality lower than this value" label="minimum quality (default = not used)" name="min_qual" optional="true" type="integer" /> + <param checked="false" falsevalue="" help="annotation of effects on the downstream region of genes can be suppressed" label="do not show downstream changes" name="no_ds" truevalue="--no-downstream" type="boolean" /> + <param checked="false" falsevalue="" help="annotation of effects on the upstream region of genes can be suppressed" label="do not show upstream changes" name="no_us" truevalue="--no-upstream" type="boolean" /> + <param checked="false" falsevalue="" help="annotation of effects on introns of genes can be suppressed" label="do not show intron changes" name="no_intron" truevalue="--no-intron" type="boolean" /> + <param checked="false" falsevalue="" help="annotation of effects on intergenic regions can be suppressed" label="do not show intergenic changes" name="no_intergenic" truevalue="--no-intergenic" type="boolean" /> + <param checked="false" falsevalue="" help="annotation of effects on the untranslated regions of genes can be suppressed" label="do not show UTR changes" name="no_utr" truevalue="--no-utr" type="boolean" /> + <param help="specify the upstream/downstream interval length, i.e., variants more than INTERVAL nts from the next annotated gene are considered to be intergenic" label="upstream downstream interval length (default = 5000 bases)" name="ud" optional="true" type="integer" /> </when> </conditional> </when> @@ -116,15 +116,15 @@ </inputs> <outputs> - <data name="outputfile" format="html" > + <data format="html" name="outputfile"> <change_format> - <when input="formatting.oformat" value="text" format="tabular"/> + <when format="tabular" input="formatting.oformat" value="text" /> </change_format> </data> - <data name="snpeff_file" format="vcf" > + <data format="vcf" name="snpeff_file"> <filter>(annotool['name']=="snpeff" and annotool['ori_output'])</filter> </data> - <data name="summary_file" format="html"> + <data format="html" name="summary_file"> <filter>(annotool['name']=="snpeff" and annotool['stats'])</filter> </data> </outputs> @@ -166,5 +166,4 @@ .. _tell us about the problem: mailto:mimodd@googlegroups.com </help> -</tool> - +</tool> \ No newline at end of file
--- a/bamsort.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/bamsort.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="bamsort" name="Sort BAM file" version="0.1.7.2"> +<tool id="bamsort" name="Sort BAM file" version="0.1.7.3"> <description>Sort a BAM file by coordinates (or names) of the mapped reads</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 sort "$input.ifile" -o "$output" --iformat $input.iformat --oformat $oformat $by_name @@ -11,28 +11,28 @@ <inputs> <conditional name="input"> - <param name="iformat" type="select" label = "Input data format"> + <param label="Input data format" name="iformat" type="select"> <option value="bam">bam</option> <option value="sam">sam</option> </param> <when value="bam"> - <param name="ifile" type="data" format="bam" label="BAM input file to sort" /> + <param format="bam" label="BAM input file to sort" name="ifile" type="data" /> </when> <when value="sam"> - <param name="ifile" type="data" format="sam" label="SAM input file to sort" /> + <param format="sam" label="SAM input file to sort" name="ifile" type="data" /> </when> </conditional> - <param name="oformat" type="select" label = "Output format for the sorted data"> + <param label="Output format for the sorted data" name="oformat" type="select"> <option value="bam">bam</option> <option value="sam">sam</option> </param> - <param name="by_name" type="boolean" truevalue = "-n" falsevalue ="" label="Sort by read names instead of coordinates" checked = "false" help="A less common option, but necessary, e.g., if you want to re-align sorted output from a previous run of the Snap Align Tool." /> + <param checked="false" falsevalue="" help="A less common option, but necessary, e.g., if you want to re-align sorted output from a previous run of the Snap Align Tool." label="Sort by read names instead of coordinates" name="by_name" truevalue="-n" type="boolean" /> </inputs> <outputs> - <data name="output" format="bam" label="Sorted output from MiModd ${tool.name} on ${on_string}"> + <data format="bam" label="Sorted output from MiModd ${tool.name} on ${on_string}" name="output"> <change_format> - <when input="oformat" value="sam" format="sam" /> + <when format="sam" input="oformat" value="sam" /> </change_format> </data> </outputs> @@ -49,5 +49,4 @@ The option *Sort by read names instead of coordinates* is useful if you want to re-align coordinate-sorted paired-end data. In *paired-end mode*, the *SNAP Read Alignment* tool expects the reads in the input file to be arranged in read pairs, i.e., the forward read information of a pair must be followed immediately by its reverse mate information, which is typically not the case in coordinate-sorted files. Resorting such files by read names fixes this problem. </help> -</tool> - +</tool> \ No newline at end of file
--- a/cloudmap.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/cloudmap.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,7 +1,6 @@ -<tool id="nacreousmap" name="NacreousMap" version="0.1.7.2"> +<tool id="nacreousmap" name="NacreousMap" version="0.1.7.3"> <description>Map causative mutations by multi-variant linkage analysis.</description> - <expand macro="requirements_rplot"/> - <version_command>python3 -m MiModD version -q</version_command> + <expand macro="requirements_rplot" /> <version_command>python3 -m MiModD version -q</version_command> <command> python3 -m MiModD map ${opt.mode} "${opt.source.ifile}" #if $str($opt.source.sample): @@ -62,16 +61,16 @@ <expand macro="hidden_vaf_algo_params" /> <expand macro="seqdict_param" /> <expand macro="bins" /> - <param name="norm" type="boolean" label="normalize variant counts to bin-width" truevalue="" falsevalue="--no-normalize" checked="true" help="without normalization the tool will just report the number of nucleotides per bin; with normalization the results for different bin-widths will be comparable." /> + <param checked="true" falsevalue="--no-normalize" help="without normalization the tool will just report the number of nucleotides per bin; with normalization the results for different bin-widths will be comparable." label="normalize variant counts to bin-width" name="norm" truevalue="" type="boolean" /> <conditional name="plotopts"> - <param name="plots" type="select" label="graphical output settings"> + <param label="graphical output settings" name="plots" type="select"> <option value="">Do not generate graphs.</option> <option value="-p">Give me graphics.</option> </param> <when value="-p"> <expand macro="scatter_default" /> - <param name="hylim" type="text" label="upper limit for the histogram y-axis (leave blank for automatic scaling)" /> - <param name="xlim" type="select" label="x-axis scaling"> + <param label="upper limit for the histogram y-axis (leave blank for automatic scaling)" name="hylim" type="text" /> + <param label="x-axis scaling" name="xlim" type="select"> <option value="">preserve relative contig sizes</option> <option value="--fit-width">scale each contig to fit the plot width</option> </param> @@ -81,9 +80,9 @@ </macro> <macro name="vaf_unconditional"> <expand macro="bins" /> - <param name="norm" type="boolean" label="normalize variant counts to bin-width" truevalue="" falsevalue="--no-normalize" checked="true" /> + <param checked="true" falsevalue="--no-normalize" label="normalize variant counts to bin-width" name="norm" truevalue="" type="boolean" /> <conditional name="plotopts"> - <param name="plots" type="select" label="graphical output settings"> + <param label="graphical output settings" name="plots" type="select"> <option value="">Do not generate graphs.</option> <option value="--no-scatter -p">Generate only histograms</option> <option value="--no-hist -p">Generate only scatter plots</option> @@ -91,8 +90,8 @@ </param> <when value="--no-scatter -p"> <expand macro="scatter_default" /> - <param name="hylim" type="text" label="upper limit for the histogram y-axis (leave blank for automatic scaling)" /> - <param name="xlim" type="select" label="x-axis scaling"> + <param label="upper limit for the histogram y-axis (leave blank for automatic scaling)" name="hylim" type="text" /> + <param label="x-axis scaling" name="xlim" type="select"> <option value="">preserve relative contig sizes</option> <option value="--fit-width">scale each contig to fit the plot width</option> </param> @@ -100,12 +99,12 @@ </when> <when value="--no-hist -p"> <expand macro="hist_default" /> - <param name="sylim" type="text" label="upper limit for the scatter plot y-axis (default: 1)" /> - <param name="xlim" type="select" label="x-axis scaling"> + <param label="upper limit for the scatter plot y-axis (default: 1)" name="sylim" type="text" /> + <param label="x-axis scaling" name="xlim" type="select"> <option value="">preserve relative contig sizes</option> <option value="--fit-width">scale each contig to fit the plot width</option> </param> - <param name="span" type="text" label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." /> + <param help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" name="span" type="text" /> <expand macro="scatter_colors" /> </when> <when value="-p"> @@ -120,7 +119,7 @@ <param name="infer_missing" type="hidden" value="" /> </macro> <macro name="bins"> - <repeat name="bin_sizes" title="bin sizes to analyze variants in (defaults to: 1Mb and 500Kb)" default="0" min="0" help="Values can be entered in bases (e.g., 1000000), kilobases (e.g., 500Kb) or megabases (e.g., 1Mb), but must be integral, i.e. no decimal numbers are allowed."> + <repeat default="0" help="Values can be entered in bases (e.g., 1000000), kilobases (e.g., 500Kb) or megabases (e.g., 1Mb), but must be integral, i.e. no decimal numbers are allowed." min="0" name="bin_sizes" title="bin sizes to analyze variants in (defaults to: 1Mb and 500Kb)"> <param name="bin_size" type="text" /> </repeat> </macro> @@ -135,39 +134,39 @@ <param name="hcols" type="hidden" value="" /> </macro> <macro name="hist_colors"> - <repeat name="hcols" title="histogram colors" default="0" min="0" help="For each bin size chosen above a histogram will be generated with its color selected from the list provided here (defaults to alternating darkgrey, red)."> + <repeat default="0" help="For each bin size chosen above a histogram will be generated with its color selected from the list provided here (defaults to alternating darkgrey, red)." min="0" name="hcols" title="histogram colors"> <param name="hcolor" type="color" value="darkgrey"> <sanitizer><valid><add value="#" /></valid></sanitizer> </param> </repeat> </macro> <macro name="scatter_colors"> - <param name="pcol" type="color" value="#454545" label="color to be used for the scatter plot data points (default: gray27)"> + <param label="color to be used for the scatter plot data points (default: gray27)" name="pcol" type="color" value="#454545"> <sanitizer><valid><add value="#" /></valid></sanitizer> </param> - <param name="lcol" type="color" value="red" label="color to be used for the regression line (default: red)"> + <param label="color to be used for the regression line (default: red)" name="lcol" type="color" value="red"> <sanitizer><valid><add value="#" /></valid></sanitizer> </param> </macro> <macro name="plot_all"> - <param name="hylim" type="text" label="upper limit for the histogram y-axis (leave blank for automatic scaling)" /> - <param name="sylim" type="text" label="upper limit for the scatter plot y-axis (default: 1)" /> - <param name="xlim" type="select" label="x-axis scaling"> + <param label="upper limit for the histogram y-axis (leave blank for automatic scaling)" name="hylim" type="text" /> + <param label="upper limit for the scatter plot y-axis (default: 1)" name="sylim" type="text" /> + <param label="x-axis scaling" name="xlim" type="select"> <option value="">preserve relative contig sizes</option> <option value="--fit-width">scale each contig to fit the plot width</option> </param> - <param name="span" type="text" label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." /> + <param help="smaller values give a more responsive curve that often picks up local evidence for tight linkage better, but too small values lead to plotting failures (in that case just rerun the tool with a larger value)." label="span value to be used in calculating the Loess regression line through the scatter data (default=0.1, specify 0 to prevent calculation)" name="span" type="text" /> <expand macro="hist_colors" /> <expand macro="scatter_colors" /> </macro> <macro name="seqdict_param"> <conditional name="seqdict_required"> - <param name="required" type="select" label="does this input file require a CloudMap-style sequence dictionary?" help="A sequence dictionary file is required ONLY if the input file does not provide information about the sizes of the chromosomes defined in it. It is NEVER needed for MiModD-generated input files."> + <param help="A sequence dictionary file is required ONLY if the input file does not provide information about the sizes of the chromosomes defined in it. It is NEVER needed for MiModD-generated input files." label="does this input file require a CloudMap-style sequence dictionary?" name="required" type="select"> <option value="no">No</option> <option value="yes">Yes</option> </param> <when value="yes"> - <param name="seqdict" type="data" format="tabular" label="CloudMap-style sequence dictionary file" /> + <param format="tabular" label="CloudMap-style sequence dictionary file" name="seqdict" type="data" /> </when> </conditional> </macro> @@ -175,27 +174,27 @@ <inputs> <conditional name="opt"> - <param name="mode" type="select" label="type of mapping analysis to perform" help="Select Simple Variant Density (SVD) Mapping to map mutations based on linked inheritance in near isogenic populations, Variant Allele Frequency (VAF) Mapping for bulk segregant analysis. Select Reprocess for rapidly replotting the result of a previous VAF analysis."> + <param help="Select Simple Variant Density (SVD) Mapping to map mutations based on linked inheritance in near isogenic populations, Variant Allele Frequency (VAF) Mapping for bulk segregant analysis. Select Reprocess for rapidly replotting the result of a previous VAF analysis." label="type of mapping analysis to perform" name="mode" type="select"> <option value="SVD">Simple Variant Density Mapping</option> <option value="VAF">Variant Allele Frequency Mapping</option> </param> <when value="SVD"> <conditional name="source"> - <param name="inputtype" type="select" label="data source to use"> + <param label="data source to use" name="inputtype" type="select"> <option value="vcf">VCF file of variants (for de-novo mapping)</option> <option value="rep">per-variant report file (for remapping a previous analysis)</option> </param> <when value="vcf"> - <param name="ifile" type="data" format="vcf" label="input file with variants to analyze" /> + <param format="vcf" label="input file with variants to analyze" name="ifile" type="data" /> <expand macro="svd_unconditional" /> - <param name="tabfile" type="select" label="additional per-variant output file" help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap EMS Variant Density Mapping tool as an alternative plotting tool."> + <param help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap EMS Variant Density Mapping tool as an alternative plotting tool." label="additional per-variant output file" name="tabfile" type="select"> <option value="">Do not generate per-variant output</option> <option value="-t">Tabular per-variant report</option> <option value="--cloudmap -t">CloudMap compatibility file</option> </param> </when> <when value="rep"> - <param name="ifile" type="data" format="tabular" label="input file with variants to analyze" /> + <param format="tabular" label="input file with variants to analyze" name="ifile" type="data" /> <param name="tabfile" type="hidden" value="" /> <expand macro="svd_unconditional" /> </when> @@ -203,26 +202,26 @@ </when> <when value="VAF"> <conditional name="source"> - <param name="inputtype" type="select" label="data source to use"> + <param label="data source to use" name="inputtype" type="select"> <option value="vcf">VCF file of variants (for de-novo mapping)</option> <option value="rep">per-variant report file (for remapping a previous analysis)</option> </param> <when value="vcf"> - <param name="ifile" type="data" format="vcf" label="input file with variants to analyze" /> + <param format="vcf" label="input file with variants to analyze" name="ifile" type="data" /> <expand macro="seqdict_param" /> - <param name="sample" type="text" label="mapping sample name" help="the sample to perform mutation mapping for" /> - <param name="related_parent_sample" type="text" label="name of the related parent sample" help="the sample that provides variants present in your original mutant strain or in an ancestor (like the pre-mutagenesis strain); leave blank if not available" /> - <param name="unrelated_parent_sample" type="text" label="name of the unrelated parent sample" help="the sample that provides variants present in the unrelated mapping strain (or in an ancestor of it) used in the mapping cross; leave blank if not available" /> - <param name="infer_missing" type="boolean" checked="false" truevalue="--infer-missing" falsevalue="" label="Infer alleles for missing parent" help="if variant data for either the related or the unrelated parent strain is not available, the tool can try to infer the alleles present in that parent from the allele spectrum found in the mapping sample. Use with caution on carefully filtered variant lists only!" /> + <param help="the sample to perform mutation mapping for" label="mapping sample name" name="sample" type="text" /> + <param help="the sample that provides variants present in your original mutant strain or in an ancestor (like the pre-mutagenesis strain); leave blank if not available" label="name of the related parent sample" name="related_parent_sample" type="text" /> + <param help="the sample that provides variants present in the unrelated mapping strain (or in an ancestor of it) used in the mapping cross; leave blank if not available" label="name of the unrelated parent sample" name="unrelated_parent_sample" type="text" /> + <param checked="false" falsevalue="" help="if variant data for either the related or the unrelated parent strain is not available, the tool can try to infer the alleles present in that parent from the allele spectrum found in the mapping sample. Use with caution on carefully filtered variant lists only!" label="Infer alleles for missing parent" name="infer_missing" truevalue="--infer-missing" type="boolean" /> <expand macro="vaf_unconditional" /> - <param name="tabfile" type="select" label="additional per-variant output file" help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap Hawaiian Variant Mapping tool as an alternative plotting tool."> + <param help="You can either choose to produce a tabular per-variant report, which is useful for fast replotting with different plot settings or a vcf-like CloudMap-compatibility file that can be used as input for the CloudMap Hawaiian Variant Mapping tool as an alternative plotting tool." label="additional per-variant output file" name="tabfile" type="select"> <option value="">Do not generate per-variant output</option> <option value="-t">Tabular per-variant report</option> <option value="--cloudmap -t">CloudMap compatibility file</option> </param> </when> <when value="rep"> - <param name="ifile" type="data" format="tabular" label="input file with variants to analyze" /> + <param format="tabular" label="input file with variants to analyze" name="ifile" type="data" /> <expand macro="seqdict_param" /> <param name="tabfile" type="hidden" value="" /> <expand macro="hidden_vaf_algo_params" /> @@ -234,11 +233,11 @@ </inputs> <outputs> - <data name="ofile" format="tabular" label="MiModD ${opt.mode} Mapping - binned variant counts for ${on_string}" /> - <data name="tfile" format="tabular" label="MiModD ${opt.mode} Mapping - per-variant report for ${on_string}"> + <data format="tabular" label="MiModD ${opt.mode} Mapping - binned variant counts for ${on_string}" name="ofile" /> + <data format="tabular" label="MiModD ${opt.mode} Mapping - per-variant report for ${on_string}" name="tfile"> <filter>(opt['source']['tabfile'])</filter> </data> - <data name="pfile" format="pdf" label="MiModD ${opt.mode} Mapping - linkage plots for ${on_string}"> + <data format="pdf" label="MiModD ${opt.mode} Mapping - linkage plots for ${on_string}" name="pfile"> <filter>(opt['source']['plotopts']['plots'])</filter> </data> </outputs> @@ -337,4 +336,4 @@ .. _CloudMap: https://usegalaxy.org/u/gm2123/p/cloudmap .. _mapping-by-sequencing analysis workflows in MiModD: http://mimodd.readthedocs.org/en/latest/cloudmap.html </help> -</tool> +</tool> \ No newline at end of file
--- a/convert.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/convert.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,13 +1,13 @@ -<tool id="convert" name="Convert" version="0.1.7.2"> +<tool id="convert" name="Convert" version="0.1.7.3"> <description>between different sequence data formats</description> <macros> <import>toolshed_macros.xml</import> </macros> - <expand macro="requirements"/> + <expand macro="requirements" /> <version_command>python3 -m MiModD version -q</version_command> <command> #if $str($mode.split_on_rgs) or $str($mode.oformat)=="fastq" or $str($mode.oformat)=="gz": - echo "Your input data is now getting processed by MiModD. The output will be split into several files based on the read groups found in the input.\nThis history item will remain in the busy state until the job is finished.\nAfter the job is showing as finished, Galaxy will start adding the results files to your history one by one.\n\nThis may take a while to complete! \n\nYou should refresh your history to see if new files have arrived.\n\nThis message is for your information only and can be deleted from the history once the job has finished." > $output_split_on_read_groups; + echo "Your input data is now getting processed by MiModD. The output will be split into several files based on the read groups found in the input.\nThis history item will remain in the busy state until the job is finished.\nAfter the job is showing as finished, Galaxy will start adding the results files to your history one by one.\n\nThis may take a while to complete! \n\nYou should refresh your history to see if new files have arrived.\n\nThis message is for your information only and can be deleted from the history once the job has finished." > $output_split_on_read_groups; mkdir converted_data; #end if @@ -36,7 +36,7 @@ <inputs> <conditional name="mode"> - <param name="iformat" type="select" label="input file format" help="Your choice will update the interface to display further choices appropriate for your type of input data."> + <param help="Your choice will update the interface to display further choices appropriate for your type of input data." label="input file format" name="iformat" type="select"> <option value="fastq">fastq: single-end (one file)</option> <option value="fastq_pe">fastq: paired-end (two files)</option> <option value="gz">gzip compressed fastq: single-end (one file)</option> @@ -45,95 +45,95 @@ <option value="bam">bam</option> </param> <when value="fastq"> - <param name="oformat" type="select" label="output file format"> + <param label="output file format" name="oformat" type="select"> <option value="sam">sam</option> <option value="bam">bam</option> </param> - <repeat name="input_list" title="fastq input dataset" default="1" min="1"> - <param name="file1" format="fastq" type="data" label="inputfile"/> + <repeat default="1" min="1" name="input_list" title="fastq input dataset"> + <param format="fastq" label="inputfile" name="file1" type="data" /> </repeat> - <param name="header" type="data" format="sam" label="Use Header File" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file."/> - <param name="split_on_rgs" type="hidden" value=""/> + <param format="sam" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file." label="Use Header File" name="header" type="data" /> + <param name="split_on_rgs" type="hidden" value="" /> </when> <when value="fastq_pe"> - <param name="oformat" type="select" label="output file format"> + <param label="output file format" name="oformat" type="select"> <option value="sam">sam</option> <option value="bam">bam</option> </param> - <repeat name="input_list" title="fastq input datasets" default="1" min="1"> - <param format="fastq" name="file1" type="data" label="inputfile with the first set of reads of paired-end data"/> - <param format="fastq" name="file2" type="data" label="inputfile with the second set of reads of paired-end data"/> + <repeat default="1" min="1" name="input_list" title="fastq input datasets"> + <param format="fastq" label="inputfile with the first set of reads of paired-end data" name="file1" type="data" /> + <param format="fastq" label="inputfile with the second set of reads of paired-end data" name="file2" type="data" /> </repeat> - <param name="header" type="data" format="sam" label="Use Header File" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file."/> - <param name="split_on_rgs" type="hidden" value=""/> + <param format="sam" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file." label="Use Header File" name="header" type="data" /> + <param name="split_on_rgs" type="hidden" value="" /> </when> <when value="gz"> - <param name="oformat" type="select" label="output file format"> + <param label="output file format" name="oformat" type="select"> <option value="sam">sam</option> <option value="bam">bam</option> </param> - <repeat name="input_list" title="fastq.gz input dataset" default="1" min="1"> - <param name="file1" format="data" type="data" label="inputfile"/> + <repeat default="1" min="1" name="input_list" title="fastq.gz input dataset"> + <param format="data" label="inputfile" name="file1" type="data" /> </repeat> - <param name="header" type="data" format="sam" label="Use Header File" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file."/> - <param name="split_on_rgs" type="hidden" value=""/> + <param format="sam" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file." label="Use Header File" name="header" type="data" /> + <param name="split_on_rgs" type="hidden" value="" /> </when> <when value="gz_pe"> - <param name="oformat" type="select" label="output file format"> + <param label="output file format" name="oformat" type="select"> <option value="sam">sam</option> <option value="bam">bam</option> </param> - <repeat name="input_list" title="fastq.gz input datasets" default="1" min="1"> - <param format="data" name="file1" type="data" label="inputfile with the first set of reads of paired-end data"/> - <param format="data" name="file2" type="data" label="inputfile with the second set of reads of paired-end data"/> + <repeat default="1" min="1" name="input_list" title="fastq.gz input datasets"> + <param format="data" label="inputfile with the first set of reads of paired-end data" name="file1" type="data" /> + <param format="data" label="inputfile with the second set of reads of paired-end data" name="file2" type="data" /> </repeat> - <param name="header" type="data" format="sam" label="Use Header File" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file."/> - <param name="split_on_rgs" type="hidden" value=""/> + <param format="sam" help="A SAM file with header information, as generated, for example, by the NGS Run Annotation Tool, that will be used to attach metainformation to the results file." label="Use Header File" name="header" type="data" /> + <param name="split_on_rgs" type="hidden" value="" /> </when> <when value="sam"> - <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> <option value="fastq">fastq</option> <option value="gz">gzipped fastq</option> </param> - <repeat name="input_list" title="sam input dataset" default="1" min="1" max="1"> - <param name="file1" format="sam" type="data" label="inputfile"/> + <repeat default="1" max="1" min="1" name="input_list" title="sam input dataset"> + <param format="sam" label="inputfile" name="file1" type="data" /> </repeat> - <param name="header" type="hidden" value="None"/> - <param name="split_on_rgs" type="boolean" truevalue="--split-on-rgs" falsevalue="" checked="false" label="Split output based on read group IDs" help="If the input file contains reads from different read groups, write them to separate output files; implied automatically for conversions to fastq and gzipped fastq format"/> + <param name="header" type="hidden" value="None" /> + <param checked="false" falsevalue="" help="If the input file contains reads from different read groups, write them to separate output files; implied automatically for conversions to fastq and gzipped fastq format" label="Split output based on read group IDs" name="split_on_rgs" truevalue="--split-on-rgs" type="boolean" /> </when> <when value="bam"> - <param name="oformat" type="select" label="output file format"> + <param label="output file format" name="oformat" type="select"> <option value="sam">sam</option> <option value="bam">bam</option> <option value="fastq">fastq</option> <option value="gz">gzipped fastq</option> </param> - <repeat name="input_list" title="bam input dataset" default="1" min="1" max="1"> - <param name="file1" format="bam" type="data" label="inputfile"/> + <repeat default="1" max="1" min="1" name="input_list" title="bam input dataset"> + <param format="bam" label="inputfile" name="file1" type="data" /> </repeat> - <param name="header" type="hidden" value="None"/> - <param name="split_on_rgs" type="boolean" truevalue="--split-on-rgs" falsevalue="" checked="false" label="Split output based on read group IDs" help="If the input file contains reads from different read groups, write them to separate output files; implied automatically for conversions to fastq and gzipped fastq format"/> + <param name="header" type="hidden" value="None" /> + <param checked="false" falsevalue="" help="If the input file contains reads from different read groups, write them to separate output files; implied automatically for conversions to fastq and gzipped fastq format" label="Split output based on read group IDs" name="split_on_rgs" truevalue="--split-on-rgs" type="boolean" /> </when> </conditional> </inputs> <outputs> - <data name="outputname" format="bam" label="Converted reads from MiModd ${tool.name} on ${on_string}"> + <data format="bam" label="Converted reads from MiModd ${tool.name} on ${on_string}" name="outputname"> <change_format> - <when input="mode.oformat" value="sam" format="sam" /> + <when format="sam" input="mode.oformat" value="sam" /> </change_format> <filter> (not mode['split_on_rgs'] and mode['oformat'] not in ("fastq", "gz")) </filter> </data> - <data name="output_split_on_read_groups" format="txt" label="MiModD ${tool.name} run on ${on_string}"> + <data format="txt" label="MiModD ${tool.name} run on ${on_string}" name="output_split_on_read_groups"> <filter> (mode['split_on_rgs'] or mode['oformat'] in ("fastq", "gz")) </filter> - <discover_datasets pattern="__designation_and_ext__" directory="converted_data" visible="true" /> + <discover_datasets directory="converted_data" pattern="__designation_and_ext__" visible="true" /> </data> </outputs> @@ -167,5 +167,4 @@ .. _MiModD user guide: http://mimodd.readthedocs.org/en/latest </help> -</tool> - +</tool> \ No newline at end of file
--- a/covstats.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/covstats.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,19 +1,19 @@ -<tool id="coverage_stats" name="Coverage Statistics" version="0.1.7.2"> +<tool id="coverage_stats" name="Coverage Statistics" version="0.1.7.3"> <description>Calculate coverage statistics for a BCF file as generated by the Variant Calling tool</description> <macros> <import>toolshed_macros.xml</import> </macros> - <expand macro="requirements"/> + <expand macro="requirements" /> <version_command>python3 -m MiModD version -q</version_command> <command> python3 -m MiModD covstats "$ifile" --ofile "$output_vcf" </command> <inputs> - <param name="ifile" type="data" format="bcf" label="BCF input file" help="Use the Variant Calling tool to generate input for this tool."/> + <param format="bcf" help="Use the Variant Calling tool to generate input for this tool." label="BCF input file" name="ifile" type="data" /> </inputs> <outputs> - <data name="output_vcf" format="tabular" label="Coverage Statistics for ${on_string}"/> + <data format="tabular" label="Coverage Statistics for ${on_string}" name="output_vcf" /> </outputs> <help> @@ -28,4 +28,4 @@ The tool treats genome positions missing from the BCF input as zero coverage, so it is safe to use ONLY with BCF files produced by the *Variant Calling* tool or through other commands that keep the information for all sites. </help> -</tool> +</tool> \ No newline at end of file
--- a/deletion_predictor.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/deletion_predictor.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="deletion_prediction" name="Deletion Prediction for paired-end data" version="0.1.7.2"> +<tool id="deletion_prediction" name="Deletion Prediction for paired-end data" version="0.1.7.3"> <description>Predicts deletions in one or more aligned read samples based on coverage of the reference genome and on insert sizes</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 delcall @@ -15,18 +15,18 @@ </command> <inputs> - <repeat name="list_input" title="Aligned reads input source" default="1" min="1"> - <param name="bamfile" type="data" format="bam" label="input BAM file" /> + <repeat default="1" min="1" name="list_input" title="Aligned reads input source"> + <param format="bam" label="input BAM file" name="bamfile" type="data" /> </repeat> - <param name="covfile" type="data" format="bcf" label="BCF variant call file to extract coverage from" help="Use the Variant Calling tool to generate this file."/> - <param name="group_by_id" type="boolean" label="group reads based on read group id only" truevalue="-i" falsevalue="" checked="false" help="If selected, reads from different read groups will be treated strictly separate. If turned off, read groups with identical sample names are used together for identifying uncovered regions, but are still treated separately for the prediction of deletions." /> - <param name="include_uncovered" type="boolean" label="include low-coverage regions" truevalue="-u" falsevalue="" checked="false" help="If selected, regions that fulfill the coverage criteria below, but are not statistically significant deletions, will be included in the output." /> - <param name="max_cov" type="integer" value="0" label="maximal coverage allowed inside a low-coverage region (default: 0)" help="The maximal coverage at a site allowed to consider it as part of a low-coverage region" /> - <param name="min_size" type="integer" value="100" label="minimal deletion size (default: 100)" help="A low-coverage region must consist of at least this number of consecutive bases below the maximal coverage to consider it in further analyses."/> + <param format="bcf" help="Use the Variant Calling tool to generate this file." label="BCF variant call file to extract coverage from" name="covfile" type="data" /> + <param checked="false" falsevalue="" help="If selected, reads from different read groups will be treated strictly separate. If turned off, read groups with identical sample names are used together for identifying uncovered regions, but are still treated separately for the prediction of deletions." label="group reads based on read group id only" name="group_by_id" truevalue="-i" type="boolean" /> + <param checked="false" falsevalue="" help="If selected, regions that fulfill the coverage criteria below, but are not statistically significant deletions, will be included in the output." label="include low-coverage regions" name="include_uncovered" truevalue="-u" type="boolean" /> + <param help="The maximal coverage at a site allowed to consider it as part of a low-coverage region" label="maximal coverage allowed inside a low-coverage region (default: 0)" name="max_cov" type="integer" value="0" /> + <param help="A low-coverage region must consist of at least this number of consecutive bases below the maximal coverage to consider it in further analyses." label="minimal deletion size (default: 100)" name="min_size" type="integer" value="100" /> </inputs> <outputs> - <data name="outputfile" format="gff" /> + <data format="gff" name="outputfile" /> </outputs> <help> @@ -62,4 +62,4 @@ </help> -</tool> +</tool> \ No newline at end of file
--- a/fileinfo.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/fileinfo.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,26 +1,26 @@ -<tool id="fileinfo" name="Retrieve File Information" version="0.1.7.2"> +<tool id="fileinfo" name="Retrieve File Information" version="0.1.7.3"> <description>for supported data formats.</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 info "$ifile" -o "$outputfile" --verbose --oformat $oformat </command> <inputs> - <param name="ifile" type="data" format="bam,sam,vcf,bcf,fasta" label="input file" /> - <param name="oformat" type="select" label="output format"> + <param format="bam,sam,vcf,bcf,fasta" label="input file" name="ifile" type="data" /> + <param label="output format" name="oformat" type="select"> <option value="txt">text</option> <option value="html">html</option> </param> </inputs> <outputs> - <data name="outputfile" format="txt" label="Sample Info on ${on_string}"> + <data format="txt" label="Sample Info on ${on_string}" name="outputfile"> <change_format> - <when input="oformat" value="html" format="html"/> + <when format="html" input="oformat" value="html" /> </change_format> </data> </outputs> @@ -35,4 +35,4 @@ It autodetects and works with most file formats produced by MiModD, i.e., **SAM / BAM, vcf / bcf and fasta**, and produces a standardized report for all of them. </help> -</tool> +</tool> \ No newline at end of file
--- a/reheader.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/reheader.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,6 +1,6 @@ -<tool id="reheader" name="Reheader BAM file" version="0.1.7.2"> +<tool id="reheader" name="Reheader BAM file" version="0.1.7.3"> <description>From a BAM file generate a new file with the original header (if any) replaced or modified by that found in a second SAM file</description> - <expand macro="requirements"/> + <expand macro="requirements" /> <version_command>python3 -m MiModD version -q</version_command> <command> #if ($str($rg.treat_rg) != "ignore" and $str($rg.rginfo.source) == "from_form") or $str($co.treat_co) != "ignore": @@ -103,29 +103,29 @@ <import>toolshed_macros.xml</import> <macro name="getreadgroupinfo"> <conditional name="rginfo"> - <param name="source" type="select" label="source of new read-group information" help=""> + <param help="" label="source of new read-group information" name="source" type="select"> <option value="from_file">existing SAM file</option> <option value="from_form">input form</option> </param> <when value="from_file"> - <param name="data" type="data" format="sam" label="read-group template file in SAM format" help="use the read group information found in this file" /> - <repeat name="rg" title="custom read-group mapping" default="0" min="0" help="read-group information found in the input file, by default, gets updated / replaced with information from template file read-groups with matching IDs. Alternatively, you may specify explicit read-group mappings below."> - <param name="source_id" type="text" label="modify input file information for read-group ID (will create the read-group if it does not exist)" /> - <param name="rg_id" type="text" label="with template file information for read-group ID" /> + <param format="sam" help="use the read group information found in this file" label="read-group template file in SAM format" name="data" type="data" /> + <repeat default="0" help="read-group information found in the input file, by default, gets updated / replaced with information from template file read-groups with matching IDs. Alternatively, you may specify explicit read-group mappings below." min="0" name="rg" title="custom read-group mapping"> + <param label="modify input file information for read-group ID (will create the read-group if it does not exist)" name="source_id" type="text" /> + <param label="with template file information for read-group ID" name="rg_id" type="text" /> </repeat> </when> <when value="from_form"> - <repeat name="rg" title="new read-group info" default="1" min="1"> - <param name="source_id" type="text" label="read-group ID (will create the read-group if it does not exist)" help="required field" /> + <repeat default="1" min="1" name="rg" title="new read-group info"> + <param help="required field" label="read-group ID (will create the read-group if it does not exist)" name="source_id" type="text" /> <param name="rg_id" type="hidden" value="" /> - <param name="rg_sm" type="text" label="sample name" help="required field" /> - <param name="rg_ds" type="text" label="description" /> - <param name="rg_date" type="text" label="date (YY-MM-DD format) the run was produced" /> - <param name="rg_cn" type="text" label="name of sequencing center" /> - <param name="rg_lb" type="text" label="read-group library" /> - <param name="rg_pl" type="text" label="platform/technology used to produce the reads" /> - <param name="rg_pi" type="text" label="predicted median insert size" /> - <param name="rg_pu" type="text" label="platform unit; unique identifier" /> + <param help="required field" label="sample name" name="rg_sm" type="text" /> + <param label="description" name="rg_ds" type="text" /> + <param label="date (YY-MM-DD format) the run was produced" name="rg_date" type="text" /> + <param label="name of sequencing center" name="rg_cn" type="text" /> + <param label="read-group library" name="rg_lb" type="text" /> + <param label="platform/technology used to produce the reads" name="rg_pl" type="text" /> + <param label="predicted median insert size" name="rg_pi" type="text" /> + <param label="platform unit; unique identifier" name="rg_pu" type="text" /> </repeat> </when> </conditional> @@ -134,10 +134,10 @@ <inputs> - <param name="inputfile" type="data" format="bam" label="input file in BAM format" help="the file to reheader." /> + <param format="bam" help="the file to reheader." label="input file in BAM format" name="inputfile" type="data" /> <conditional name="rg"> - <param name="treat_rg" type="select" label="modify read-group information ?" help="Replace mode will ignore ALL existing read group information in the input file and use ONLY template information, Update mode will COPY existing input file information and UPDATE it with template information; choose No, ... to leave read-group information alone."> + <param help="Replace mode will ignore ALL existing read group information in the input file and use ONLY template information, Update mode will COPY existing input file information and UPDATE it with template information; choose No, ... to leave read-group information alone." label="modify read-group information ?" name="treat_rg" type="select"> <option value="ignore">No, do not change read-groups.</option> <option value="update">Yes, update existing information</option> <option value="replace">Yes, replace existing information</option> @@ -151,37 +151,37 @@ </conditional> <conditional name="co"> - <param name="treat_co" type="select" label="modify comments in the input file ?" help=""> + <param help="" label="modify comments in the input file ?" name="treat_co" type="select"> <option value="ignore">No, do not change comments.</option> <option value="update">Yes, append new comments to existing ones</option> <option value="replace">Yes, replace all existing comments</option> </param> <when value="update"> - <repeat name="coinfo" title="comment line" default="0" min="0"> - <param name="line" type="text" size="80" /> + <repeat default="0" min="0" name="coinfo" title="comment line"> + <param name="line" size="80" type="text" /> </repeat> </when> <when value="replace"> - <repeat name="coinfo" title="comment line" default="0" min="0"> - <param name="line" type="text" size="80" /> + <repeat default="0" min="0" name="coinfo" title="comment line"> + <param name="line" size="80" type="text" /> </repeat> </when> </conditional> - <repeat name="rg_renaming" title="rename read-group" default="0" min="0" help="Warning: changing read-group IDs may increase job runtime substantially."> - <param name="from" type="text" size="30" label="old name" help="as it appears in the current input file header"/> - <param name="to" type="text" size="30" label="new name" /> + <repeat default="0" help="Warning: changing read-group IDs may increase job runtime substantially." min="0" name="rg_renaming" title="rename read-group"> + <param help="as it appears in the current input file header" label="old name" name="from" size="30" type="text" /> + <param label="new name" name="to" size="30" type="text" /> </repeat> - <repeat name="sq_renaming" title="rename sequence" default="0" min="0" help="Warning: changing sequence names may increase job runtime substantially."> - <param name="from" type="text" size="30" label="old name" help="as it appears in the current input file header"/> - <param name="to" type="text" size="30" label="new name" /> + <repeat default="0" help="Warning: changing sequence names may increase job runtime substantially." min="0" name="sq_renaming" title="rename sequence"> + <param help="as it appears in the current input file header" label="old name" name="from" size="30" type="text" /> + <param label="new name" name="to" size="30" type="text" /> </repeat> </inputs> <outputs> - <data name="output" format="bam" label="(Re)headered bam file from MiModd ${tool.name} on ${on_string}"> + <data format="bam" label="(Re)headered bam file from MiModd ${tool.name} on ${on_string}" name="output"> </data> </outputs> @@ -199,5 +199,4 @@ The template information used to modify or replace the input file metadata is provided through forms or, in the case of read-group information, can be taken from an existing SAM file as can be generated, for example, with the *NGS Run Annotation* tool. </help> -</tool> - +</tool> \ No newline at end of file
--- a/sam_header.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/sam_header.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="ngs_run_annotation" name="NGS Run Annotation" version="0.1.7.2"> +<tool id="ngs_run_annotation" name="NGS Run Annotation" version="0.1.7.3"> <description>Create a SAM format header from run metadata for sample annotation.</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 header @@ -38,73 +38,73 @@ </command> <inputs> - <param name="rg_id" type="text" size="80" label="read-group ID (required)"> + <param label="read-group ID (required)" name="rg_id" size="80" type="text"> <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value=""" /> </valid> <mapping initial="none"> - <add source=""" target="\""/> + <add source=""" target="\"" /> </mapping> </sanitizer> </param> - <param name="rg_sm" type="text" size="80" label="sample name (required)"> + <param label="sample name (required)" name="rg_sm" size="80" type="text"> <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value=""" /> </valid> <mapping initial="none"> - <add source=""" target="\""/> + <add source=""" target="\"" /> </mapping> </sanitizer> </param> - <param name="rg_ds" type="text" size="80" label="description"> + <param label="description" name="rg_ds" size="80" type="text"> <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value=""" /> </valid> <mapping initial="none"> - <add source=""" target="\""/> + <add source=""" target="\"" /> </mapping> </sanitizer> </param> - <param name="rg_date" type="text" label="date (YYYY-MM-DD) the run was produced" /> - <param name="rg_cn" type="text" size="80" label="name of sequencing center"> + <param label="date (YYYY-MM-DD) the run was produced" name="rg_date" type="text" /> + <param label="name of sequencing center" name="rg_cn" size="80" type="text"> <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value=""" /> </valid> <mapping initial="none"> - <add source=""" target="\""/> + <add source=""" target="\"" /> </mapping> </sanitizer> </param> - <param name="rg_lb" type="text" size="80" label="read-group library"> + <param label="read-group library" name="rg_lb" size="80" type="text"> <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value=""" /> </valid> <mapping initial="none"> - <add source=""" target="\""/> + <add source=""" target="\"" /> </mapping> </sanitizer> </param> - <param name="rg_pl" type="text" label="platform/technology used to produce the reads" /> - <param name="rg_pi" type="text" label="predicted median insert size" /> - <param name="rg_pu" type="text" size="80" label="platform unit; unique identifier"> + <param label="platform/technology used to produce the reads" name="rg_pl" type="text" /> + <param label="predicted median insert size" name="rg_pi" type="text" /> + <param label="platform unit; unique identifier" name="rg_pu" size="80" type="text"> <sanitizer invalid_char=""> <valid initial="string.printable"> <remove value=""" /> </valid> <mapping initial="none"> - <add source=""" target="\""/> + <add source=""" target="\"" /> </mapping> </sanitizer> </param> </inputs> <outputs> - <data name="outputfile" format="sam" label="${rg_sm} (${rg_id}) header information from MiModd ${tool.name} on ${on_string}"/> + <data format="sam" label="${rg_sm} (${rg_id}) header information from MiModd ${tool.name} on ${on_string}" name="outputfile" /> </outputs> <help> @@ -125,5 +125,4 @@ While you can do Alignments from fastq file format by providing a custom header file directly to the *SNAP Read Alignment* tool, we **recommend** you to first convert all input files to and archive all datasets in SAM/BAM format with appropriate header information prior to any downstream analysis. Although a bit more time-consuming, this practice protects against information loss and ensures that the input datasets will remain useful for others in the future. </help> -</tool> - +</tool> \ No newline at end of file
--- 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
--- a/snp_caller_caller.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/snp_caller_caller.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="variant_calling" name="Variant Calling" version="0.1.7.2"> +<tool id="variant_calling" name="Variant Calling" version="0.1.7.3"> <description>From a reference and aligned reads generate a BCF file with position-specific variant likelihoods and coverage information</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 varcall @@ -21,17 +21,17 @@ </command> <inputs> - <param name="ref_genome" type="data" format="fasta" label="reference genome" /> - <repeat name="list_input" title="Aligned reads input source" default="1" min="1"> - <param name="inputfile" type="data" format="bam" label="input file" /> + <param format="fasta" label="reference genome" name="ref_genome" type="data" /> + <repeat default="1" min="1" name="list_input" title="Aligned reads input source"> + <param format="bam" label="input file" name="inputfile" type="data" /> </repeat> - <param name="group_by_id" type="boolean" label="group reads based on read group id only" truevalue="-i" falsevalue="" checked="false" help="If selected, this option ensures that only the read group id (but not the sample name) is considered in grouping reads in the input file(s). If turned off, read groups with identical sample names are automatically pooled and analyzed together even if they come from different NGS runs." /> - <param name="no_md5_check" type="boolean" label="turn off md5 sum verification" truevalue="-x" falsevalue="" checked="false" help="leave turned on to avoid accidental variant calling against a wrong reference genome version (see the tool help below)." /> - <param name="depth" type="integer" value="250" label="maximum per-BAM depth (default: 250)" help="to avoid excessive use of memory"/> + <param checked="false" falsevalue="" help="If selected, this option ensures that only the read group id (but not the sample name) is considered in grouping reads in the input file(s). If turned off, read groups with identical sample names are automatically pooled and analyzed together even if they come from different NGS runs." label="group reads based on read group id only" name="group_by_id" truevalue="-i" type="boolean" /> + <param checked="false" falsevalue="" help="leave turned on to avoid accidental variant calling against a wrong reference genome version (see the tool help below)." label="turn off md5 sum verification" name="no_md5_check" truevalue="-x" type="boolean" /> + <param help="to avoid excessive use of memory" label="maximum per-BAM depth (default: 250)" name="depth" type="integer" value="250" /> </inputs> <outputs> - <data name="output_vcf" format="bcf" label="Variant Calls from MiModd Variant Calling on ${on_string}"/> + <data format="bcf" label="Variant Calls from MiModd Variant Calling on ${on_string}" name="output_vcf" /> </outputs> <help> @@ -63,4 +63,4 @@ It exposes just a single configuration parameter of these tools - the *maximum per-BAM depth*. Through this parameter, the maximum number of reads considered for variant calling at any site can be controlled. Its default value of 250 is taken from *samtools mpileup* and usually suitable. Consider, however, that this gives the maximum read number per input file, so if you have a large number of samples in one input file, it could become necessary to increase the value to get sufficient reads considered per sample. </help> -</tool> +</tool> \ No newline at end of file
--- a/snpeff_genomes.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/snpeff_genomes.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,15 +1,15 @@ -<tool id="snpeff_genomes" name="List Installed SnpEff Genomes" version="0.1.7.2"> +<tool id="snpeff_genomes" name="List Installed SnpEff Genomes" version="0.1.7.3"> <description>Checks the local SnpEff installation to compile a list of currently installed genomes</description> <macros> <import>toolshed_macros.xml</import> </macros> - <expand macro="requirements"/> + <expand macro="requirements" /> <version_command>python3 -m MiModD version -q</version_command> <command> python3 -m MiModD snpeff-genomes -o "$outputfile" </command> <outputs> - <data name="outputfile" format="tabular" /> + <data format="tabular" name="outputfile" /> </outputs> <help> .. class:: infomark @@ -21,4 +21,4 @@ </help> -</tool> +</tool> \ No newline at end of file
--- a/tool_dependencies.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/tool_dependencies.xml Thu Jul 21 03:55:49 2016 -0400 @@ -13,7 +13,7 @@ <repository changeset_revision="83407422ec16" name="package_python_3_4_x_lean" owner="wolma" prior_installation_required="True" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> - <package name="mimodd" version="0.1.7.2"> + <package name="mimodd" version="0.1.7.3"> <install version="1.0"> <actions> <!-- prepare a python3 venv to install into --> @@ -62,9 +62,9 @@ <!-- download and install MiModD --> <action type="change_directory">$TMP_WORK_DIR</action> - <action type="download_file">http://sourceforge.net/projects/mimodd/files/MiModD-0.1.7.2.tar.gz</action> - <action type="shell_command">tar -xzf MiModD-0.1.7.2.tar.gz</action> - <action type="change_directory">MiModD-0.1.7.2</action> + <action type="download_file">http://sourceforge.net/projects/mimodd/files/MiModD-0.1.7.3/MiModD-0.1.7.3.tar.gz</action> + <action type="shell_command">tar -xzf MiModD-0.1.7.3.tar.gz</action> + <action type="change_directory">MiModD-0.1.7.3</action> <action type="set_environment_for_install"> <repository changeset_revision="63a4a902cda2" name="package_zlib_1_2_8" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"> <package name="zlib" version="1.2.8" />
--- a/toolshed_macros.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/toolshed_macros.xml Thu Jul 21 03:55:49 2016 -0400 @@ -2,13 +2,13 @@ <xml name="requirements"> <requirements> <requirement type="package" version="3.4">python3</requirement> - <requirement type="package" version="0.1.7.2">mimodd</requirement> + <requirement type="package" version="0.1.7.3">mimodd</requirement> </requirements> </xml> <xml name="requirements_rplot"> <requirements> <requirement type="package" version="3.4">python3</requirement> - <requirement type="package" version="0.1.7.2">mimodd</requirement> + <requirement type="package" version="0.1.7.3">mimodd</requirement> <requirement type="package" version="3.2.1">R</requirement> <requirement type="package" version="6.3">readline</requirement> </requirements>
--- a/varextract.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/varextract.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,11 +1,11 @@ -<tool id="extract_variants" name="Extract Variant Sites" version="0.1.7.2"> +<tool id="extract_variants" name="Extract Variant Sites" version="0.1.7.3"> <description>from a BCF file</description> <macros> <import>toolshed_macros.xml</import> </macros> - <expand macro="requirements"/> + <expand macro="requirements" /> <version_command>python3 -m MiModD version -q</version_command> - <command> + <command> python3 -m MiModD varextract "$ifile" #if $len($sitesinfo) -p @@ -19,14 +19,14 @@ </command> <inputs> - <param name="ifile" type="data" format="bcf" label="BCF input file" help="Use the Variant Calling tool to generate the input for this tool."/> - <repeat name="sitesinfo" title="include information from pre-calculated vcf file" default="0"> - <param name="pre_vcf" type="data" format="vcf" label="independently generated vcf file" /> + <param format="bcf" help="Use the Variant Calling tool to generate the input for this tool." label="BCF input file" name="ifile" type="data" /> + <repeat default="0" name="sitesinfo" title="include information from pre-calculated vcf file"> + <param format="vcf" label="independently generated vcf file" name="pre_vcf" type="data" /> </repeat> - <param name="keep_alts" type="boolean" label="keep all sites with alternate bases" truevalue="-a" falsevalue="" checked="false" help="If selected, the VCF output will include ALL sites for which non-reference bases have been observed, i.e., even those not considered allelic sites by the variant caller." /> + <param checked="false" falsevalue="" help="If selected, the VCF output will include ALL sites for which non-reference bases have been observed, i.e., even those not considered allelic sites by the variant caller." label="keep all sites with alternate bases" name="keep_alts" truevalue="-a" type="boolean" /> </inputs> <outputs> - <data name="output_vcf" format="vcf" label="Variants extracted with MiModd from ${on_string}"/> + <data format="vcf" label="Variants extracted with MiModd from ${on_string}" name="output_vcf" /> </outputs> <help> @@ -98,4 +98,4 @@ </help> -</tool> +</tool> \ No newline at end of file
--- a/vcf_filter.xml Sun Jun 12 07:39:46 2016 -0400 +++ b/vcf_filter.xml Thu Jul 21 03:55:49 2016 -0400 @@ -1,9 +1,9 @@ -<tool id="vcf_filter" name="VCF Filter" version="0.1.7.2"> +<tool id="vcf_filter" name="VCF Filter" version="0.1.7.3"> <description>Extracts lines from a vcf variant file based on field-specific filters</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 vcf-filter @@ -52,29 +52,29 @@ </command> <inputs> - <param name="inputfile" type="data" format="vcf" label="VCF input file" /> - <repeat name="datasets" title="Sample-specific Filter" default="0" min="0"> - <param name="sample" type="text" label="sample" help="name of a sample as it appears in the VCF input file and that indicates the sample that this filter should be applied to." /> - <param name="GT" type="text" label="genotype pattern(s) for the inclusion of variants" help="keep only variants for which the genotype of the sample matches the specified pattern; format: x/x where x = 0 is wildtype and x = 1 is mutant. Multiple genotypes can be specified as a comma-separated list." /> - <param name="DP" type="integer" label="depth of coverage for the sample at the variant site" value = "0" help="keep only variants with at least this sample-specific coverage at the variant site" /> - <param name="GQ" type="integer" label="genotype quality for the variant in the sample" value = "0" help="keep only variants for which the genotype prediction for the sample has at least this quality" /> - <param name="AF" type="text" label="allelic fraction filter" help="expected format: [allele number]:[minimal fraction]:[maximal fraction]; keep only variants for which the fraction of sample-specific reads supporting a given allele number is between minimal and maximal fraction; if allele number is omitted, the filter operates on the most frequent non-reference allele instead" /> + <param format="vcf" label="VCF input file" name="inputfile" type="data" /> + <repeat default="0" min="0" name="datasets" title="Sample-specific Filter"> + <param help="name of a sample as it appears in the VCF input file and that indicates the sample that this filter should be applied to." label="sample" name="sample" type="text" /> + <param help="keep only variants for which the genotype of the sample matches the specified pattern; format: x/x where x = 0 is wildtype and x = 1 is mutant. Multiple genotypes can be specified as a comma-separated list." label="genotype pattern(s) for the inclusion of variants" name="GT" type="text" /> + <param help="keep only variants with at least this sample-specific coverage at the variant site" label="depth of coverage for the sample at the variant site" name="DP" type="integer" value="0" /> + <param help="keep only variants for which the genotype prediction for the sample has at least this quality" label="genotype quality for the variant in the sample" name="GQ" type="integer" value="0" /> + <param help="expected format: [allele number]:[minimal fraction]:[maximal fraction]; keep only variants for which the fraction of sample-specific reads supporting a given allele number is between minimal and maximal fraction; if allele number is omitted, the filter operates on the most frequent non-reference allele instead" label="allelic fraction filter" name="AF" type="text" /> </repeat> - <repeat name="regions" title="Region Filter" default="0" min="0" help = "Filter variant sites by their position in the genome. If multiple Region Filters are specified, all variants that fall in ONE of the regions are reported."> - <param name="chrom" type="text" label="Chromosome" /> - <param name="start" type="text" label="Region Start" /> - <param name="stop" type="text" label="Region End" /> + <repeat default="0" help="Filter variant sites by their position in the genome. If multiple Region Filters are specified, all variants that fall in ONE of the regions are reported." min="0" name="regions" title="Region Filter"> + <param label="Chromosome" name="chrom" type="text" /> + <param label="Region Start" name="start" type="text" /> + <param label="Region End" name="stop" type="text" /> </repeat> - <param name="vartype" type="select" label="Select the types of variants to include in the output"> + <param label="Select the types of variants to include in the output" name="vartype" type="select"> <option value="">all types of variants</option> <option value="--no-indels">exclude indels</option> <option value="--indels-only">only indels</option> </param> - <param name="vfilter" type="text" label="sample" help="Filter output by sample name; only the sample-specific columns with their sample name matching any of the comma separated filters will be retained in the output." /> + <param help="Filter output by sample name; only the sample-specific columns with their sample name matching any of the comma separated filters will be retained in the output." label="sample" name="vfilter" type="text" /> </inputs> <outputs> - <data name="outputfile" format="vcf" /> + <data format="vcf" name="outputfile" /> </outputs> <help> @@ -105,21 +105,21 @@ *Simple genotype pattern* -genotype pattern: 1/1 ==> keep all variants in the vcf input file for which the specified sample's genotype is homozygous mutant +genotype pattern: 1/1 ==> keep all variants in the vcf input file for which the specified sample's genotype is homozygous mutant *Complex genotype pattern* -genotype pattern: 0/1, 0/0 ==> keep all variants for which the sample's genotype is either heterozygous or homozygous wildtype +genotype pattern: 0/1, 0/0 ==> keep all variants for which the sample's genotype is either heterozygous or homozygous wildtype *Multiple sample-specific filters* Filter 1: genotype pattern: 0/0, Filter 2: genotype pattern 1/1: -==> keep all variants for which the first sample's gentoype is homozygous wildtype **and** the second sample's genotype is homozygous mutant +==> keep all variants for which the first sample's gentoype is homozygous wildtype **and** the second sample's genotype is homozygous mutant *Combining sample-specific filter criteria* genotype pattern: 1/1, depth of coverage: 3, genotype quality: 9 -==> keep variants for which the sample's genotype is homozygous mutant **and** for which this genotype assignment is corroborated by a genotype quality score of at least 9 +==> keep variants for which the sample's genotype is homozygous mutant **and** for which this genotype assignment is corroborated by a genotype quality score of at least 9 **and** at least three reads from the sample cover the variant site **TIP:** @@ -130,4 +130,4 @@ </help> -</tool> +</tool> \ No newline at end of file