Mercurial > repos > galaxyp > idpassemble
changeset 8:e0ff9e45c273 draft
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/bumbershoot
| author | galaxyp |
|---|---|
| date | Fri, 06 Oct 2017 13:56:47 -0400 |
| parents | 393e129b02e2 |
| children | bf4693df2605 |
| files | idpassemble.xml idpquery.xml |
| diffstat | 2 files changed, 121 insertions(+), 137 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/idpassemble.xml Fri Oct 06 13:56:47 2017 -0400 @@ -0,0 +1,121 @@ +<?xml version="1.0"?> +<tool id="idpassemble" name="idpAssemble" version="@VERSION@.0"> + <description>Merge IDPicker databases from single files into a merged database, and filters the result at PSM/spectrum/peptide/protein/gene levels.</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <stdio> + <exit_code range="1:" level="fatal" description="Job Failed" /> + <regex match="^Error:.*$" source="both" level="fatal" /> + </stdio> + <command> +<![CDATA[ + #if len($input) < 2 + cp '${input}' output && + #end if + + idpAssemble + -MaxFDRScore $MaxFDRScore + -MinDistinctPeptides $filter_at_gene_level_condition.MinDistinctPeptides + -MinSpectra $filter_at_gene_level_condition.MinSpectra + -MinAdditionalPeptides $filter_at_gene_level_condition.MinAdditionalPeptides + -MinSpectraPerDistinctMatch $MinSpectraPerDistinctMatch + -MinSpectraPerDistinctPeptide $MinSpectraPerDistinctPeptide + -MaxProteinGroupsPerPeptide $MaxProteinGroupsPerPeptide + #if $filter_at_gene_level_condition.FilterAtGeneLevel + -FilterAtGeneLevel 1 + #end if + -SummarizeSources 1 + #if len($input) > 1 + -MergedOutputFilepath output + #for $i in $input + '${i.file_name}' + #end for + #else + output + #end if +]]> + </command> + <inputs> + <param name="input" type="data" format="idpdb" label="Input idpDB(s)" multiple="true"/> + <param argument="-MaxFDRScore" type="float" label="Max FDR Score" min="0.00000001" value="0.05" help="Peptide-spectrum-matches (PSMs) with an FDR score (interpolated Q-value) higher than this will be excluded from the filtered data set." /> + <conditional name="filter_at_gene_level_condition"> + <param argument="-FilterAtGeneLevel" type="boolean" truevalue="1" falsevalue="0" label="Filter at Gene Level" help="Apply filters at the gene level (i.e. 'min distinct peptides per gene group' instead of 'min distinct peptides per protein group')"/> + <when value="1"> + <param argument="-MinDistinctPeptides" type="integer" label="Min Distinct Peptides per Gene Group" min="1" value="2" help="Gene groups with fewer than this number of peptides will be excluded from the filtered data set." /> + <param argument="-MinSpectra" type="integer" label="Min Filtered Spectra per Gene Group" min="1" value="2" help="Gene groups with fewer than this number of spectra will be excluded from the filtered data set." /> + <param argument="-MinAdditionalPeptides" type="integer" label="Min Additional Peptides per Gene Group" min="0" value="1" help="Gene groups that are not necessary to explain the presence of at least this many extra peptides will be from the filtered data set. A value of 1 means that each gene group must explain at least 1 peptide that other gene groups do not explain." /> + </when> + <when value="0"> + <param argument="-MinDistinctPeptides" type="integer" label="Min Distinct Peptides per Protein Group" min="1" value="2" help="Protein groups with fewer than this number of peptides will be excluded from the filtered data set." /> + <param argument="-MinSpectra" type="integer" label="Min Filtered Spectra per Protein Group" min="1" value="2" help="Protein groups with fewer than this number of spectra will be excluded from the filtered data set." /> + <param argument="-MinAdditionalPeptides" type="integer" label="Min Additional Peptides per Protein Group" min="0" value="1" help="Protein groups that are not necessary to explain the presence of at least this many extra peptides will be from the filtered data set. A value of 1 means that each protein group must explain at least 1 peptide that other protein groups do not explain." /> + </when> + </conditional> + <param argument="-MinSpectraPerDistinctMatch" type="integer" label="Min Filtered Spectra per Distinct Match" min="1" value="1" help="Distinct matches with fewer than this number of spectra will be excluded from the filtered data set." /> + <param argument="-MinSpectraPerDistinctPeptide" type="integer" label="Min Filtered Spectra per Distinct Peptide" min="1" value="1" help="Distinct peptides with fewer than this number of spectra will be excluded from the filtered data set." /> + <param argument="-MaxProteinGroupsPerPeptide" type="integer" label="Max Protein Groups per Distinct Peptide" min="0" value="10" help="Peptides that map to more than this number of protein groups will be excluded from the filtered data set. Highly ambiguous peptides are not very useful for quantitation." /> + </inputs> + <outputs> + <data format="idpdb" name="output" from_work_dir="output" /> + </outputs> + <tests> + <test> + <param name="input" value="201208-378803-mm.idpDB" /> + <param name="MaxFDRScore" value="0.05" /> + <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" /> + <param name="filter_at_gene_level_condition.MinSpectra" value="2" /> + <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" /> + <param name="MinSpectraPerDistinctMatch" value="1" /> + <param name="MinSpectraPerDistinctPeptide" value="1" /> + <param name="MaxProteinGroupsPerPeptide" value="10" /> + <output name="output" file="201208-378803-mm-filtered.idpDB" compare="sim_size" delta="500000" /> + </test> + <test> + <param name="input" value="201208-378803-msgf.idpDB" /> + <param name="MaxFDRScore" value="0.05" /> + <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" /> + <param name="filter_at_gene_level_condition.MinSpectra" value="2" /> + <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" /> + <param name="MinSpectraPerDistinctMatch" value="1" /> + <param name="MinSpectraPerDistinctPeptide" value="1" /> + <param name="MaxProteinGroupsPerPeptide" value="10" /> + <output name="output" file="201208-378803-msgf-filtered.idpDB" compare="sim_size" delta="500000" /> + </test> + <test> + <param name="input" value="201208-378803-cm.idpDB" /> + <param name="MaxFDRScore" value="0.05" /> + <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" /> + <param name="filter_at_gene_level_condition.MinSpectra" value="2" /> + <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" /> + <param name="MinSpectraPerDistinctMatch" value="1" /> + <param name="MinSpectraPerDistinctPeptide" value="1" /> + <param name="MaxProteinGroupsPerPeptide" value="10" /> + <output name="output" file="201208-378803-cm-filtered.idpDB" compare="sim_size" delta="500000" /> + </test> + <test> + <param name="input" value="201208-378803-mm.idpDB,201208-378803-msgf.idpDB,201208-378803-cm.idpDB" /> + <param name="MaxFDRScore" value="0.05" /> + <param name="filter_at_gene_level_condition.MinDistinctPeptides" value="2" /> + <param name="filter_at_gene_level_condition.MinSpectra" value="2" /> + <param name="filter_at_gene_level_condition.MinAdditionalPeptides" value="1" /> + <param name="MinSpectraPerDistinctMatch" value="1" /> + <param name="MinSpectraPerDistinctPeptide" value="1" /> + <param name="MaxProteinGroupsPerPeptide" value="10" /> + <output name="output" file="201208-378803.idpDB" compare="sim_size" delta="500000" /> + </test> + </tests> + <help> +<![CDATA[ +**What it does** + +Merges and filters one or more IDPicker 3 idpDB files into a combined idpDB file. Protein assembly (e.g. parsimony) is conducted on the combined set of proteins. +]]> + </help> + <citations> + <citation type="doi">10.1021/pr900360j</citation> + <citation type="bibtex">@misc{toolsGalaxyP, author = {Chilton, J, Chambers MC, et al.}, title = {Galaxy Proteomics Tools}, publisher = {GitHub}, journal = {GitHub repository}, + year = {2015}, url = {https://github.com/galaxyproteomics/tools-galaxyp}}</citation> <!-- TODO: fix substitution of commit ", commit = {$sha1$}" --> + </citations> +</tool>
--- a/idpquery.xml Fri Oct 06 13:55:15 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,137 +0,0 @@ -<?xml version="1.0"?> -<tool id="idpquery" name="idpQuery" version="@VERSION@.0"> - <description>Creates text reports from idpDB files.</description> - <macros> - <import>macros.xml</import> - <xml name="proteinGroupByColumns"> - <param name="report_columns" type="select" label="Select report columns" display="checkboxes" multiple="true"> - <option value="Accession" selected="true">Accession</option> - <option value="GeneId">Gene Id</option> - <option value="GeneGroup">Gene Group</option> - <option value="DistinctPeptides">Distinct Peptides</option> - <option value="DistinctMatches">Distinct Matches</option> - <option value="FilteredSpectra">Filtered Spectra</option> - <option value="IsDecoy">Is Decoy</option> - <option value="Cluster">Cluster</option> - <option value="ProteinGroup">Protein Group</option> - <option value="Length">Length</option> - <option value="PercentCoverage">Percent Coverage</option> - <option value="Sequence">Sequence</option> - <option value="Description">Description</option> - <option value="TaxonomyId">Taxonomy Id</option> - <option value="GeneName">Gene Name</option> - <option value="GeneFamily">Gene Family</option> - <option value="Chromosome">Chromosome</option> - <option value="GeneDescription">Gene Description</option> - <option value="PrecursorIntensity">Precursor Intensity</option> - <option value="PrecursorArea">Precursor Area</option> - <option value="PrecursorBestSNR">Precursor Best SNR</option> - <option value="PrecursorMeanSNR">Precursor Mean SNR</option> - <option value="iTRAQ4plex">iTRAQ 4-plex</option> - <option value="iTRAQ8plex">iTRAQ 8-plex</option> - <option value="TMT2plex">TMT 2-plex</option> - <option value="TMT6plex">TMT 6-plex</option> - <option value="TMT10plex">TMT 10-plex</option> - <option value="PivotMatchesByGroup">Pivot Matches By Group</option> - <option value="PivotMatchesBySource">Pivot Matches By Source</option> - <option value="PivotPeptidesByGroup">Pivot Peptides By Group</option> - <option value="PivotPeptidesBySource">Pivot Peptides By Source</option> - <option value="PivotSpectraByGroup">Pivot Spectra By Group</option> - <option value="PivotSpectraBySource">Pivot Spectra By Source</option> - <option value="PivotPrecursorIntensityByGroup">Pivot Precursor Intensity By Group</option> - <option value="PivotPrecursorIntensityBySource">Pivot Precursor Intensity By Source</option> - <option value="PivotPrecursorAreaByGroup">Pivot Precursor Area By Group</option> - <option value="PivotPrecursorAreaBySource">Pivot Precursor Area By Source</option> - <option value="PivotPrecursorBestSNRByGroup">Pivot Precursor Best SNR By Group</option> - <option value="PivotPrecursorBestSNRBySource">Pivot Precursor Best SNR By Source</option> - <option value="PivotPrecursorMeanSNRByGroup">Pivot Precursor Mean SNR By Group</option> - <option value="PivotPrecursorMeanSNRBySource">Pivot Precursor Mean SNR By Source</option> - <option value="PivotITRAQByGroup">Pivot iTRAQ By Group</option> - <option value="PivotITRAQBySource">Pivot iTRAQ By Source</option> - <option value="PivotTMTByGroup">Pivot TMT By Group</option> - <option value="PivotTMTBySource">Pivot TMT By Source</option> - <option value="PeptideGroups">Peptide Groups</option> - <option value="PeptideSequences">Peptide Sequences</option> - </param> - </xml> - </macros> - <expand macro="requirements" /> - <stdio> - <exit_code range="1:" level="fatal" description="Job Failed" /> - <regex match="^Error:.*$" source="both" level="fatal" /> - </stdio> - <command> -<![CDATA[ - #set $input_name = $input.display_name - #set $output_name = $input_name.split(".")[0] + ".tsv" - ln -s '$input' '${input_name}' && - - idpQuery $group_by.group_by_value $group_by.report_columns '${input_name}' && - mv '$output_name' output -]]> - </command> - <inputs> - <param name="input" type="data" format="idpdb" label="Input idpDB" multiple="false" /> - <conditional name="group_by"> - <param name="group_by_value" type="select" label="What proteomic entity do you want to group by?" help="Only protein- and gene-centric entities are currently supported."> - <option value="Protein" selected="true">Protein</option> - <option value="ProteinGroup">Protein Group</option> - <option value="Gene">Gene</option> - <option value="GeneGroup">Gene Group</option> - </param> - <when value="Protein"> - <expand macro="proteinGroupByColumns" /> - </when> - <when value="ProteinGroup"> - <expand macro="proteinGroupByColumns" /> - </when> - <when value="Gene"> - <expand macro="proteinGroupByColumns" /> - </when> - <when value="GeneGroup"> - <expand macro="proteinGroupByColumns" /> - </when> - </conditional> - </inputs> - <outputs> - <data format="tabular" name="output" from_work_dir="output" /> - </outputs> - <tests> - <test> - <param name="input" value="201203-624176-12-mm-gui-test.idpDB" /> - <param name="group_by_value" value="Protein" /> - <param name="report_columns" value="Accession,FilteredSpectra,Description" /> - <output name="output" file="201203-624176-12-mm-gui-test-Protein-Accession,FilteredSpectra,Description.tsv" /> - </test> - <test> - <param name="input" value="201203-624176-12-mm-gui-test.idpDB" /> - <param name="group_by_value" value="ProteinGroup" /> - <param name="report_columns" value="ProteinGroup,Accession,PercentCoverage" /> - <output name="output" file="201203-624176-12-mm-gui-test-ProteinGroup-ProteinGroup,Accession,PercentCoverage.tsv" /> - </test> - <test> - <param name="input" value="201203-624176-12-mm-gui-test.idpDB" /> - <param name="group_by_value" value="Gene" /> - <param name="report_columns" value="GeneId,Accession,DistinctPeptides" /> - <output name="output" file="201203-624176-12-mm-gui-test-Gene-GeneId,Accession,DistinctPeptides.tsv" /> - </test> - <test> - <param name="input" value="201203-624176-12-mm-gui-test.idpDB" /> - <param name="group_by_value" value="GeneGroup" /> - <param name="report_columns" value="GeneGroup,GeneId,DistinctMatches" /> - <output name="output" file="201203-624176-12-mm-gui-test-GeneGroup-GeneGroup,GeneId,DistinctMatches.tsv" /> - </test> - </tests> - <help> -<![CDATA[ -**What it does** - -Creates user-configurable text reports from IDPicker 3 idpDB files. -]]> - </help> - <citations> - <citation type="doi">10.1021/pr900360j</citation> - <citation type="bibtex">@misc{toolsGalaxyP, author = {Chilton, J, Chambers MC, et al.}, title = {Galaxy Proteomics Tools}, publisher = {GitHub}, journal = {GitHub repository}, - year = {2015}, url = {https://github.com/galaxyproteomics/tools-galaxyp}}</citation> <!-- TODO: fix substitution of commit ", commit = {$sha1$}" --> - </citations> -</tool>