Mercurial > repos > galaxyp > openms_epifany
diff Epifany.xml @ 5:e8c52c1d6f98 draft default tip
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 5c080b1e2b99f1c88f4557e9fec8c45c9d23b906
author | galaxyp |
---|---|
date | Fri, 14 Jun 2024 21:32:01 +0000 |
parents | f3096a586de8 |
children |
line wrap: on
line diff
--- a/Epifany.xml Thu Dec 01 19:13:55 2022 +0000 +++ b/Epifany.xml Fri Jun 14 21:32:01 2024 +0000 @@ -1,8 +1,7 @@ -<?xml version='1.0' encoding='UTF-8'?> <!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTDConverter.--> -<!--Proposed Tool Section: [Utilities]--> +<!--Proposed Tool Section: [Identification Processing]--> <tool id="Epifany" name="Epifany" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05"> - <description>Runs a Bayesian protein inference.</description> + <description>Runs a Bayesian protein inference</description> <macros> <token name="@EXECUTABLE@">Epifany</token> <import>macros.xml</import> @@ -17,13 +16,13 @@ mkdir in_cond.in && #if $in_cond.in_select == "no" mkdir ${' '.join(["'in_cond.in/%s'" % (i) for i, f in enumerate($in_cond.in) if f])} && -${' '.join(["ln -s '%s' 'in_cond.in/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_cond.in) if f])} +${' '.join(["cp '%s' 'in_cond.in/%s/%s.%s' && " % (f, i, re.sub('[^\w\-_]', '_', f.element_identifier), $gxy2omsext(f.ext)) for i, f in enumerate($in_cond.in) if f])} #else -ln -s '$in_cond.in' 'in_cond.in/${re.sub("[^\w\-_]", "_", $in_cond.in.element_identifier)}.$gxy2omsext($in_cond.in.ext)' && +cp '$in_cond.in' 'in_cond.in/${re.sub("[^\w\-_]", "_", $in_cond.in.element_identifier)}.$gxy2omsext($in_cond.in.ext)' && #end if #if $exp_design: mkdir exp_design && - ln -s '$exp_design' 'exp_design/${re.sub("[^\w\-_]", "_", $exp_design.element_identifier)}.$gxy2omsext($exp_design.ext)' && + cp '$exp_design' 'exp_design/${re.sub("[^\w\-_]", "_", $exp_design.element_identifier)}.$gxy2omsext($exp_design.ext)' && #end if mkdir out && @@ -62,56 +61,57 @@ <option value="yes">Yes: process each dataset in an independent job</option> </param> <when value="no"> - <param argument="-in" type="data" format="consensusxml,idxml" multiple="true" optional="false" label="Input: identification results" help=" select consensusxml,idxml data sets(s)"/> + <param argument="-in" type="data" format="consensusxml,idxml" multiple="true" label="Input: identification results" help=" select consensusxml,idxml data sets(s)"/> </when> <when value="yes"> - <param argument="-in" type="data" format="consensusxml,idxml" multiple="false" optional="false" label="Input: identification results" help=" select consensusxml,idxml data sets(s)"/> + <param argument="-in" type="data" format="consensusxml,idxml" label="Input: identification results" help=" select consensusxml,idxml data sets(s)"/> </when> </conditional> <param argument="-exp_design" type="data" format="tabular" optional="true" label="(Currently unused) Input: experimental design" help=" select tabular data sets(s)"/> - <param argument="-out_type" display="radio" type="select" optional="false" label="Output type: auto detected by file extension but can be overwritten here" help=""> + <param argument="-out_type" type="select" label="Output type: auto detected by file extension but can be overwritten here" help=""> <option value="consensusXML">consensusxml</option> <option value="idXML">idxml</option> + <validator type="expression" message="A value needs to be selected">value != "select a value"</validator> <expand macro="list_string_san" name="out_type"/> </param> <param argument="-protein_fdr" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Additionally calculate the target-decoy FDR on protein-level based on the posteriors" help=""/> - <param argument="-greedy_group_resolution" type="select" optional="true" label="Post-process inference output with greedy resolution of shared peptides based on the parent protein probabilities" help="Also adds the resolved ambiguity groups to output"> + <param argument="-greedy_group_resolution" type="select" label="Post-process inference output with greedy resolution of shared peptides based on the parent protein probabilities" help="Also adds the resolved ambiguity groups to output"> <option value="none" selected="true">none</option> <option value="remove_associations_only">remove_associations_only</option> <option value="remove_proteins_wo_evidence">remove_proteins_wo_evidence</option> <expand macro="list_string_san" name="greedy_group_resolution"/> </param> - <param argument="-max_psms_extreme_probability" type="float" optional="true" value="1.0" label="Set PSMs with probability higher than this to this maximum probability" help=""/> + <param argument="-max_psms_extreme_probability" type="float" value="1.0" label="Set PSMs with probability higher than this to this maximum probability" help=""/> <section name="algorithm" title="Parameters for the Algorithm section" help="" expanded="false"> - <param name="psm_probability_cutoff" argument="-algorithm:psm_probability_cutoff" type="float" optional="true" min="0.0" max="1.0" value="0.001" label="Remove PSMs with probabilities less than this cutoff" help=""/> - <param name="top_PSMs" argument="-algorithm:top_PSMs" type="integer" optional="true" min="0" value="1" label="Consider only top X PSMs per spectrum" help="0 considers all"/> + <param name="psm_probability_cutoff" argument="-algorithm:psm_probability_cutoff" type="float" min="0.0" max="1.0" value="0.001" label="Remove PSMs with probabilities less than this cutoff" help=""/> + <param name="top_PSMs" argument="-algorithm:top_PSMs" type="integer" min="0" value="1" label="Consider only top X PSMs per spectrum" help="0 considers all"/> <param name="keep_best_PSM_only" argument="-algorithm:keep_best_PSM_only" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Epifany uses the best PSM per peptide for inference" help="Discard the rest (true) or keepe.g. for quantification/reporting?"/> <param name="update_PSM_probabilities" argument="-algorithm:update_PSM_probabilities" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(Experimental:) Update PSM probabilities with their posteriors under consideration of the protein probabilities" help=""/> <param name="user_defined_priors" argument="-algorithm:user_defined_priors" type="boolean" truevalue="true" falsevalue="false" checked="false" label="(Experimental:) Uses the current protein scores as user-defined priors" help=""/> <param name="annotate_group_probabilities" argument="-algorithm:annotate_group_probabilities" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Annotates group probabilities for indistinguishable protein groups (indistinguishable by experimentally observed PSMs)" help=""/> <param name="use_ids_outside_features" argument="-algorithm:use_ids_outside_features" type="boolean" truevalue="true" falsevalue="false" checked="false" label="(Only consensusXML) Also use IDs without associated features for inference?" help=""/> <section name="model_parameters" title="Model parameters for the Bayesian network" help="" expanded="false"> - <param name="prot_prior" argument="-algorithm:model_parameters:prot_prior" type="float" optional="true" min="-1.0" max="1.0" value="-1.0" label="Protein prior probability ('gamma' parameter)" help="Negative values enable grid search for this param"/> - <param name="pep_emission" argument="-algorithm:model_parameters:pep_emission" type="float" optional="true" min="-1.0" max="1.0" value="-1.0" label="Peptide emission probability ('alpha' parameter)" help="Negative values enable grid search for this param"/> - <param name="pep_spurious_emission" argument="-algorithm:model_parameters:pep_spurious_emission" type="float" optional="true" min="-1.0" max="1.0" value="-1.0" label="Spurious peptide identification probability ('beta' parameter)" help="Usually much smaller than emission from proteins. Negative values enable grid search for this param"/> - <param name="pep_prior" argument="-algorithm:model_parameters:pep_prior" type="float" optional="true" min="0.0" max="1.0" value="0.1" label="Peptide prior probability (experimental, should be covered by combinations of the other params)" help=""/> + <param name="prot_prior" argument="-algorithm:model_parameters:prot_prior" type="float" min="-1.0" max="1.0" value="-1.0" label="Protein prior probability ('gamma' parameter)" help="Negative values enable grid search for this param"/> + <param name="pep_emission" argument="-algorithm:model_parameters:pep_emission" type="float" min="-1.0" max="1.0" value="-1.0" label="Peptide emission probability ('alpha' parameter)" help="Negative values enable grid search for this param"/> + <param name="pep_spurious_emission" argument="-algorithm:model_parameters:pep_spurious_emission" type="float" min="-1.0" max="1.0" value="-1.0" label="Spurious peptide identification probability ('beta' parameter)" help="Usually much smaller than emission from proteins. Negative values enable grid search for this param"/> + <param name="pep_prior" argument="-algorithm:model_parameters:pep_prior" type="float" min="0.0" max="1.0" value="0.1" label="Peptide prior probability (experimental, should be covered by combinations of the other params)" help=""/> <param name="regularize" argument="-algorithm:model_parameters:regularize" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Regularize the number of proteins that produce a peptide together (experimental, should be activated when using higher p-norms)" help=""/> <param name="extended_model" argument="-algorithm:model_parameters:extended_model" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Uses information from different peptidoforms also across runs (automatically activated if an experimental design is given!)" help=""/> </section> <section name="loopy_belief_propagation" title="Settings for the loopy belief propagation algorithm" help="" expanded="false"> - <param name="scheduling_type" argument="-algorithm:loopy_belief_propagation:scheduling_type" type="select" optional="true" label="(Not used yet) How to pick the next message: priority = based on difference to last message (higher = more important)" help="fifo = first in first out. subtree = message passing follows a random spanning tree in each iteration"> + <param name="scheduling_type" argument="-algorithm:loopy_belief_propagation:scheduling_type" type="select" label="(Not used yet) How to pick the next message: priority = based on difference to last message (higher = more important)" help="fifo = first in first out. subtree = message passing follows a random spanning tree in each iteration"> <option value="priority" selected="true">priority</option> <option value="fifo">fifo</option> <option value="subtree">subtree</option> <expand macro="list_string_san" name="scheduling_type"/> </param> - <param name="convergence_threshold" argument="-algorithm:loopy_belief_propagation:convergence_threshold" type="float" optional="true" min="0.0" max="1.0" value="1e-05" label="Initial threshold under which MSE difference a message is considered to be converged" help=""/> - <param name="dampening_lambda" argument="-algorithm:loopy_belief_propagation:dampening_lambda" type="float" optional="true" min="0.0" max="0.49999" value="0.001" label="Initial value for how strongly should messages be updated in each step" help="0 = new message overwrites old completely (no dampening; only recommended for trees),0.5 = equal contribution of old and new message (stay below that),In-between it will be a convex combination of both. Prevents oscillations but hinders convergence"/> - <param name="max_nr_iterations" argument="-algorithm:loopy_belief_propagation:max_nr_iterations" type="integer" optional="true" value="2147483647" label="(Usually auto-determined by estimated but you can set a hard limit here)" help="If not all messages converge, how many iterations should be done at max per connected component?"/> - <param name="p_norm_inference" argument="-algorithm:loopy_belief_propagation:p_norm_inference" type="float" optional="true" value="1.0" label="P-norm used for marginalization of multidimensional factors" help="1 == sum-product inference (all configurations vote equally) (default),<= 0 == infinity = max-product inference (only best configurations propagate)The higher the value the more important high probability configurations get"/> + <param name="convergence_threshold" argument="-algorithm:loopy_belief_propagation:convergence_threshold" type="float" min="0.0" max="1.0" value="1e-05" label="Initial threshold under which MSE difference a message is considered to be converged" help=""/> + <param name="dampening_lambda" argument="-algorithm:loopy_belief_propagation:dampening_lambda" type="float" min="0.0" max="0.49999" value="0.001" label="Initial value for how strongly should messages be updated in each step" help="0 = new message overwrites old completely (no dampening; only recommended for trees),0.5 = equal contribution of old and new message (stay below that),In-between it will be a convex combination of both. Prevents oscillations but hinders convergence"/> + <param name="max_nr_iterations" argument="-algorithm:loopy_belief_propagation:max_nr_iterations" type="integer" value="2147483647" label="(Usually auto-determined by estimated but you can set a hard limit here)" help="If not all messages converge, how many iterations should be done at max per connected component?"/> + <param name="p_norm_inference" argument="-algorithm:loopy_belief_propagation:p_norm_inference" type="float" value="1.0" label="P-norm used for marginalization of multidimensional factors" help="1 == sum-product inference (all configurations vote equally) (default),<= 0 == infinity = max-product inference (only best configurations propagate)The higher the value the more important high probability configurations get"/> </section> <section name="param_optimize" title="Settings for the parameter optimization" help="" expanded="false"> - <param name="aucweight" argument="-algorithm:param_optimize:aucweight" type="float" optional="true" min="0.0" max="1.0" value="0.3" label="How important is target decoy AUC vs calibration of the posteriors" help="0 = maximize calibration only, 1 = maximize AUC only, between = convex combination"/> + <param name="aucweight" argument="-algorithm:param_optimize:aucweight" type="float" min="0.0" max="1.0" value="0.3" label="How important is target decoy AUC vs calibration of the posteriors" help="0 = maximize calibration only, 1 = maximize AUC only, between = convex combination"/> <param name="conservative_fdr" argument="-algorithm:param_optimize:conservative_fdr" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Use (D+1)/(T) instead of (D+1)/(T+D) for parameter estimation" help=""/> <param name="regularized_fdr" argument="-algorithm:param_optimize:regularized_fdr" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Use a regularized FDR for proteins without unique peptides" help=""/> </section> @@ -122,14 +122,14 @@ <param argument="-picked_decoy_string" type="text" optional="true" value="" label="If using picked protein FDRs, which decoy string was used" help="Leave blank for auto-detection"> <expand macro="list_string_san" name="picked_decoy_string"/> </param> - <param argument="-picked_decoy_prefix" type="select" optional="true" label="If using picked protein FDRs, was the decoy string a prefix or suffix" help="Ignored during auto-detection"> + <param argument="-picked_decoy_prefix" type="select" label="If using picked protein FDRs, was the decoy string a prefix or suffix" help="Ignored during auto-detection"> <option value="prefix" selected="true">prefix</option> <option value="suffix">suffix</option> <expand macro="list_string_san" name="picked_decoy_prefix"/> </param> - <param argument="-min_psms_extreme_probability" type="float" optional="true" value="0.0" label="Set PSMs with probability lower than this to this minimum probability" help=""/> + <param argument="-min_psms_extreme_probability" type="float" value="0.0" label="Set PSMs with probability lower than this to this minimum probability" help=""/> <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> - <param argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> + <param argument="-test" type="hidden" value="False" label="Enables the test mode (needed for internal use only)" help="" optional="true"> <expand macro="list_string_san" name="test"/> </param> </expand> @@ -147,7 +147,8 @@ <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter> </data> </outputs> - <tests><!-- UTILS_Epifany_1 --> + <tests> + <!-- TOPP_Epifany_1 --> <test expect_num_outputs="2"> <section name="adv_opts"> <param name="conservative_fdr" value="true"/> @@ -161,7 +162,7 @@ <conditional name="in_cond"> <param name="in" value="FidoAdapter_1_input.idXML"/> </conditional> - <output name="out" file="Epifany_1_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="out" value="Epifany_1_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> <param name="out_type" value="idXML"/> <param name="protein_fdr" value="false"/> <param name="greedy_group_resolution" value="none"/> @@ -201,8 +202,11 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> - <!-- UTILS_Epifany_2 --> + <!-- TOPP_Epifany_2 --> <test expect_num_outputs="2"> <section name="adv_opts"> <param name="conservative_fdr" value="true"/> @@ -216,7 +220,7 @@ <conditional name="in_cond"> <param name="in" value="Epifany_2_input.consensusXML"/> </conditional> - <output name="out" file="Epifany_2_out.consensusXML" compare="sim_size" delta_frac="0.7" ftype="consensusxml"/> + <output name="out" value="Epifany_2_out.consensusXML" compare="sim_size" delta_frac="0.7" ftype="consensusxml"/> <param name="out_type" value="consensusXML"/> <param name="protein_fdr" value="false"/> <param name="greedy_group_resolution" value="none"/> @@ -256,8 +260,11 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> - <!-- UTILS_Epifany_3 --> + <!-- TOPP_Epifany_3 --> <test expect_num_outputs="2"> <section name="adv_opts"> <param name="conservative_fdr" value="true"/> @@ -271,7 +278,7 @@ <conditional name="in_cond"> <param name="in" value="Epifany_2_input.consensusXML"/> </conditional> - <output name="out" file="Epifany_3_out.consensusXML" compare="sim_size" delta_frac="0.7" ftype="consensusxml"/> + <output name="out" value="Epifany_3_out.consensusXML" compare="sim_size" delta_frac="0.7" ftype="consensusxml"/> <param name="out_type" value="consensusXML"/> <param name="protein_fdr" value="false"/> <param name="greedy_group_resolution" value="none"/> @@ -311,8 +318,11 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> - <!-- UTILS_Epifany_4 --> + <!-- TOPP_Epifany_4 --> <test expect_num_outputs="2"> <section name="adv_opts"> <param name="conservative_fdr" value="true"/> @@ -326,7 +336,7 @@ <conditional name="in_cond"> <param name="in" value="FidoAdapter_1_input_singlerun.idXML"/> </conditional> - <output name="out" file="Epifany_4_out_singlerun.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="out" value="Epifany_4_out_singlerun.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> <param name="out_type" value="idXML"/> <param name="protein_fdr" value="false"/> <param name="greedy_group_resolution" value="remove_proteins_wo_evidence"/> @@ -366,8 +376,11 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> - <!-- UTILS_Epifany_5 --> + <!-- TOPP_Epifany_5 --> <test expect_num_outputs="2"> <section name="adv_opts"> <param name="conservative_fdr" value="true"/> @@ -381,7 +394,7 @@ <conditional name="in_cond"> <param name="in" value="FidoAdapter_1_input_singlerun.idXML"/> </conditional> - <output name="out" file="Epifany_4_out_singlerun_fdr.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="out" value="Epifany_4_out_singlerun_fdr.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> <param name="out_type" value="idXML"/> <param name="protein_fdr" value="true"/> <param name="greedy_group_resolution" value="remove_proteins_wo_evidence"/> @@ -421,11 +434,14 @@ <is_valid_xml/> </assert_contents> </output> + <assert_stdout> + <has_text_matching expression="@EXECUTABLE@ took .* \(wall\), .* \(CPU\), .* \(system\), .* \(user\)(; Peak Memory Usage: 32 MB)?."/> + </assert_stdout> </test> </tests> <help><![CDATA[Runs a Bayesian protein inference. -For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/UTILS_Epifany.html]]></help> +For more information, visit https://openms.de/doxygen/release/3.1.0/html/TOPP_Epifany.html]]></help> <expand macro="references"/> </tool>