Repository 'fragpipe'
hg clone https://toolshed.g2.bx.psu.edu/repos/galaxyp/fragpipe

Changeset 4:e969a182e3cb (2024-12-13)
Previous changeset 3:da9ebef968bd (2024-09-12)
Commit message:
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/fragpipe commit f98d62a3e8aef1dd26fa64eff5c19f5773652d43
modified:
fragpipe.xml
macros.xml
added:
test-data/default/outputs/workflow_msbooster_percolator.txt
b
diff -r da9ebef968bd -r e969a182e3cb fragpipe.xml
--- a/fragpipe.xml Thu Sep 12 08:06:44 2024 +0000
+++ b/fragpipe.xml Fri Dec 13 15:17:28 2024 +0000
b
@@ -200,6 +200,57 @@
         </output_collection>
       </test>
       <test expect_num_outputs="11">
+        <param name="inputs" value="default/test1.mzML,default/test2.mzML" ftype="mzml"/>
+        <param name="database_name" value="default/test.fasta" ftype="fasta"/>
+        <param name="manifest" value="default/test.manifest" ftype="tabular"/>
+        <param name="workflow_name" value="Default"/>
+        <param name="label_free_quantification_run" value="ionquant"/>
+        <param name="output_options" value="workflow,log,combined_outputs,concatenated_outputs"/>
+        <param name="license_agreements" value="true"/>
+        <param name="run_psm_validation" value="msbooster_percolator"/>
+        <output name="concat_psm_tsv" ftype="tabular">
+            <assert_contents>
+                <has_text text="Experiment&#x9;Spectrum&#x9;Spectrum File&#x9;Peptide&#x9;Modified Peptide&#x9;Extended Peptide&#x9;Prev AA&#x9;Next AA&#x9;Peptide Length&#x9;Charge&#x9;Retention&#x9;Observed Mass&#x9;Calibrated Observed Mass&#x9;Observed M/Z&#x9;Calibrated Observed M/Z&#x9;Calculated Peptide Mass&#x9;Calculated M/Z&#x9;Delta Mass&#x9;SpectralSim&#x9;RTScore&#x9;Expectation&#x9;Hyperscore&#x9;Nextscore&#x9;PeptideProphet Probability&#x9;Number of Enzymatic Termini&#x9;Number of Missed Cleavages&#x9;Protein Start&#x9;Protein End&#x9;Intensity&#x9;Assigned Modifications&#x9;Observed Modifications&#x9;Purity&#x9;Is Unique&#x9;Protein&#x9;Protein ID&#x9;Entry Name&#x9;Gene&#x9;Protein Description&#x9;Mapped Genes&#x9;Mapped Proteins"/>
+                <has_text text="sample1"/>
+            </assert_contents>
+        </output>
+        <output name="concat_ion_tsv" ftype="tabular">
+            <assert_contents>
+                <has_text text="Experiment&#x9;Peptide Sequence&#x9;Modified Sequence&#x9;Prev AA&#x9;Next AA&#x9;Peptide Length&#x9;Protein Start&#x9;Protein End&#x9;M/Z&#x9;Charge&#x9;Observed Mass&#x9;Probability&#x9;Expectation&#x9;Spectral Count&#x9;Intensity&#x9;Assigned Modifications&#x9;Observed Modifications&#x9;Protein&#x9;Protein ID&#x9;Entry Name&#x9;Gene&#x9;Protein Description&#x9;Mapped Genes&#x9;Mapped Proteins"/>
+                <has_text text="sample1"/>
+            </assert_contents>
+        </output>
+        <output name="concat_peptide_tsv" ftype="tabular">
+            <assert_contents>
+                <has_text text="Experiment&#x9;Peptide&#x9;Prev AA&#x9;Next AA&#x9;Peptide Length&#x9;Protein Start&#x9;Protein End&#x9;Charges&#x9;Probability&#x9;Spectral Count&#x9;Intensity&#x9;Assigned Modifications&#x9;Observed Modifications&#x9;Protein&#x9;Protein ID&#x9;Entry Name&#x9;Gene&#x9;Protein Description&#x9;Mapped Genes&#x9;Mapped Proteins"/>
+                <has_text text="sample1"/>
+            </assert_contents>
+        </output>
+        <output name="concat_protein_tsv" ftype="tabular">
+            <assert_contents>
+                <has_text text="Experiment&#x9;Protein&#x9;Protein ID&#x9;Entry Name&#x9;Gene&#x9;Length&#x9;Organism&#x9;Protein Description&#x9;Protein Existence&#x9;Coverage&#x9;Protein Probability&#x9;Top Peptide Probability&#x9;Total Peptides&#x9;Unique Peptides&#x9;Razor Peptides&#x9;Total Spectral Count&#x9;Unique Spectral Count&#x9;Razor Spectral Count&#x9;Total Intensity&#x9;Unique Intensity&#x9;Razor Intensity&#x9;Razor Assigned Modifications&#x9;Razor Observed Modifications&#x9;Indistinguishable Proteins"/>
+                <has_text text="sample1"/>
+            </assert_contents>
+        </output>
+        <output name="output_workflow" ftype="txt" file="default/outputs/workflow_msbooster_percolator.txt" compare="contains">
+            <assert_contents>
+                <has_text text="crystalc.run-crystalc=false"/>
+            </assert_contents>
+        </output>
+        <output name="log" ftype="txt">
+            <assert_contents>
+                <has_text text="FragPipe version 20.0"/>
+            </assert_contents>
+        </output>
+        <output_collection name="combined_outputs" type="list">
+            <element name="combined_protein.tsv" ftype="tabular">
+                <assert_contents>
+                    <has_text text="Protein&#x9;Protein ID&#x9;Entry Name&#x9;Gene&#x9;Protein Length&#x9;Organism&#x9;Protein Existence&#x9;Description&#x9;Protein Probability&#x9;Top Peptide Probability&#x9;Combined Total Peptides&#x9;Combined Spectral Count&#x9;Combined Unique Spectral Count&#x9;Combined Total Spectral Count&#x9;sample1 Spectral Count&#x9;sample2 Spectral Count&#x9;sample1 Intensity&#x9;sample2 Intensity&#x9;Indistinguishable Proteins"/>
+                </assert_contents>
+            </element>
+        </output_collection>
+      </test>
+      <test expect_num_outputs="11">
         <param name="inputs" value="tmt11/test1.mzML,tmt11/test2.mzML" ftype="mzml"/>
         <param name="database_name" value="tmt11/test.fasta" ftype="fasta"/>
         <param name="manifest" value="tmt11/test.manifest" ftype="tabular"/>
b
diff -r da9ebef968bd -r e969a182e3cb macros.xml
--- a/macros.xml Thu Sep 12 08:06:44 2024 +0000
+++ b/macros.xml Fri Dec 13 15:17:28 2024 +0000
[
@@ -1,7 +1,7 @@
 <macros>
     <import>msfragger_macros.xml</import>
     <token name="@TOOL_VERSION@">20.0</token>
-    <token name="@VERSION_SUFFIX@">3</token>
+    <token name="@VERSION_SUFFIX@">4</token>
     <xml name="requirements">
         <requirements>
             <requirement type="package" version="@TOOL_VERSION@">fragpipe</requirement>
@@ -350,13 +350,27 @@
     <!-- Set Percolator workflow options -->
     <token name="@PERCOLATOR@"><![CDATA[
         #set $prc = $wf.validation.validation_tab.psm_validation.percolator
-        #set $wfdict['run-validation-tab'] = $wf.validation.validation_tab.run_validation
-        #set $wfdict['peptide-prophet.run-peptide-prophet'] = 'false'
         #set $wfdict['percolator.run-percolator'] = 'true'
         #set $wfdict['percolator.keep-tsv-files'] = str($prc.keep_tsv_files)
         #set $wfdict['percolator.min-prob'] = str($prc.min_prob)
     ]]></token>
 
+    <xml name="msbooster">
+        <section name="msbooster" expanded="true" title="MSBooster">
+            <param name="predict_rt" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Predict RT"/>
+            <param name="predict_spectra" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Predict spectra"/>
+            <param name="use_correlated_features" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use correlated features"/>
+        </section>
+    </xml>
+    <token name="@MSBOOSTER@"><![CDATA[
+        #set $prfx = $wf.validation.validation_tab.psm_validation.msbooster
+        #set $wfdict['msbooster.run-msbooster'] = 'true'
+        #set $wfdict['msbooster.predict-rt'] = str($prfx.predict_rt)
+        #set $wfdict['msbooster.predict-spectra'] = str($prfx.predict_spectra)
+        #set $wfdict['msbooster.use-correlated-features'] = str($prfx.use_correlated_features)
+    ]]></token>
+
+
     <!-- Philosopher Report (phi-report) options -->
     <xml name="phi_report">
         <conditional name="phi_report">
@@ -424,16 +438,6 @@
         <param name="run_crystalc" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Run Crystal-C" help="Recommend for open searches for additional resuts cleanup"/>
     </xml>
 
-    <!-- MSBooster options. Disabled until DIA-NN integrated.
-    <xml name="msbooster">
-        <section name="msbooster" expanded="false" title="MSBooster">
-            <param name="predict_rt" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Predict RT"/>
-            <param name="predict_spectra" type="boolean" truevalue="true" falsevalue="false" checked="true" label="Predict spectra"/>
-            <param name="use_correlated_features" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use correlated features"/>
-        </section>
-    </xml>
-     -->
-
     <!-- Protein Prophet options -->
     <xml name="protein_prophet" token_minprob="0.05">
         <conditional name="protein_prophet">
@@ -484,9 +488,7 @@
                         <param name="run_psm_validation" type="select" label="PSM Validation">
                             <option value="peptide_prophet" selected="@PEP@">Run PeptideProphet</option>
                             <option value="percolator" selected="@PERC@">Run Percolator</option>
-                            <!-- MSBooster disabled until DIA-NN integrated
                             <option value="msbooster_percolator" selected="@BOOST@">Run MSBooster and Percolator</option>
-                            -->
                             <option value="no" selected="@NO@">Use workflow values</option>
                         </param>
                         <when value="peptide_prophet">
@@ -495,12 +497,10 @@
                         <when value="percolator">
                             <expand macro="percolator"/>
                         </when>
-                        <!-- MSBooster disabled until DIA-NN integrated
                         <when value="msbooster_percolator">
                             <expand macro="msbooster"/>
                             <expand macro="percolator"/>
                         </when>
-                        -->
                         <when value="no">
                         </when>
                     </conditional>
@@ -524,9 +524,13 @@
         #elif $prfx.run_psm_validation == 'percolator'
             #set $wfdict['run-psm-validation'] = 'true'
             #set $wfdict['msbooster.run-msbooster'] = 'false'
+            #set $wfdict['peptide-prophet.run-peptide-prophet=false'] = 'false'
             @PERCOLATOR@
-        ##elif $prfx.run_psm_validation == 'msbooster_percolator'
-        # MSBooster disabled until DIA-NN integrated.
+        #elif $prfx.run_psm_validation == 'msbooster_percolator'
+            #set $wfdict['run-psm-validation'] = 'true'
+            #set $wfdict['peptide-prophet.run-peptide-prophet=false'] = 'false'
+            @MSBOOSTER@
+            @PERCOLATOR@
         #end if
         @PROTEINPROPHET@
         @PHIREPORT@
b
diff -r da9ebef968bd -r e969a182e3cb test-data/default/outputs/workflow_msbooster_percolator.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/default/outputs/workflow_msbooster_percolator.txt Fri Dec 13 15:17:28 2024 +0000
b
b'@@ -0,0 +1,308 @@\n+database.decoy-tag=rev_\n+diann.fragpipe.cmd-opts=\n+diann.heavy=\n+diann.library=\n+diann.light=\n+diann.medium=\n+diann.q-value=0.01\n+diann.quantification-strategy=3\n+diann.run-dia-nn=false\n+diann.run-dia-plex=false\n+diann.run-specific-protein-q-value=false\n+diann.unrelated-runs=false\n+diann.use-predicted-spectra=true\n+diaumpire.AdjustFragIntensity=true\n+diaumpire.BoostComplementaryIon=false\n+diaumpire.CorrThreshold=0\n+diaumpire.DeltaApex=0.2\n+diaumpire.ExportPrecursorPeak=false\n+diaumpire.Q1=true\n+diaumpire.Q2=true\n+diaumpire.Q3=true\n+diaumpire.RFmax=500\n+diaumpire.RPmax=25\n+diaumpire.RTOverlap=0.3\n+diaumpire.SE.EstimateBG=false\n+diaumpire.SE.IsoPattern=0.3\n+diaumpire.SE.MS1PPM=10\n+diaumpire.SE.MS2PPM=20\n+diaumpire.SE.MS2SN=1.1\n+diaumpire.SE.MassDefectFilter=true\n+diaumpire.SE.MassDefectOffset=0.1\n+diaumpire.SE.NoMissedScan=1\n+diaumpire.SE.SN=1.1\n+diaumpire.run-diaumpire=false\n+freequant.mz-tol=10\n+freequant.rt-tol=0.4\n+freequant.run-freequant=false\n+ionquant.excludemods=\n+ionquant.heavy=\n+ionquant.imtol=0.05\n+ionquant.ionfdr=0.01\n+ionquant.light=\n+ionquant.locprob=0.75\n+ionquant.maxlfq=1\n+ionquant.mbr=1\n+ionquant.mbrimtol=0.05\n+ionquant.mbrmincorr=0\n+ionquant.mbrrttol=1\n+ionquant.mbrtoprun=10\n+ionquant.medium=\n+ionquant.minfreq=0\n+ionquant.minions=2\n+ionquant.minisotopes=2\n+ionquant.minscans=3\n+ionquant.mztol=10\n+ionquant.normalization=1\n+ionquant.peptidefdr=1\n+ionquant.proteinfdr=1\n+ionquant.requantify=1\n+ionquant.rttol=0.4\n+ionquant.run-ionquant=true\n+ionquant.tp=0\n+ionquant.uniqueness=0\n+ionquant.use-labeling=false\n+ionquant.use-lfq=true\n+ionquant.writeindex=0\n+msbooster.predict-rt=true\n+msbooster.predict-spectra=true\n+msbooster.run-msbooster=true\n+msbooster.use-correlated-features=false\n+msfragger.Y_type_masses=\n+msfragger.activation_types=all\n+msfragger.add_topN_complementary=0\n+msfragger.allowed_missed_cleavage_1=2\n+msfragger.allowed_missed_cleavage_2=2\n+msfragger.calibrate_mass=2\n+msfragger.check_spectral_files=true\n+msfragger.clip_nTerm_M=true\n+msfragger.deisotope=1\n+msfragger.delta_mass_exclude_ranges=(-1.5,3.5)\n+msfragger.deneutralloss=1\n+msfragger.diagnostic_fragments=\n+msfragger.diagnostic_intensity_filter=0\n+msfragger.digest_max_length=50\n+msfragger.digest_min_length=7\n+msfragger.fragment_ion_series=b,y\n+msfragger.fragment_mass_tolerance=20\n+msfragger.fragment_mass_units=1\n+msfragger.group_variable=0\n+msfragger.intensity_transform=0\n+msfragger.ion_series_definitions=\n+msfragger.isotope_error=0/1/2/3\n+msfragger.labile_search_mode=off\n+msfragger.localize_delta_mass=false\n+msfragger.mass_diff_to_variable_mod=0\n+msfragger.mass_offsets=0\n+msfragger.max_fragment_charge=2\n+msfragger.max_variable_mods_combinations=5000\n+msfragger.max_variable_mods_per_peptide=3\n+msfragger.min_fragments_modelling=2\n+msfragger.min_matched_fragments=4\n+msfragger.min_sequence_matches=2\n+msfragger.minimum_peaks=15\n+msfragger.minimum_ratio=0.01\n+msfragger.misc.fragger.clear-mz-hi=0.0\n+msfragger.misc.fragger.clear-mz-lo=0.0\n+msfragger.misc.fragger.digest-mass-hi=5000\n+msfragger.misc.fragger.digest-mass-lo=500\n+msfragger.misc.fragger.enzyme-dropdown-1=stricttrypsin\n+msfragger.misc.fragger.enzyme-dropdown-2=null\n+msfragger.misc.fragger.precursor-charge-hi=4\n+msfragger.misc.fragger.precursor-charge-lo=1\n+msfragger.misc.fragger.remove-precursor-range-hi=1.5\n+msfragger.misc.fragger.remove-precursor-range-lo=-1.5\n+msfragger.misc.slice-db=1\n+msfragger.num_enzyme_termini=2\n+msfragger.output_format=pepXML_pin\n+msfragger.output_max_expect=50.0\n+msfragger.output_report_topN=1\n+msfragger.output_report_topN_dia1=5\n+msfragger.output_report_topN_dia2=3\n+msfragger.override_charge=false\n+msfragger.precursor_mass_lower=-20\n+msfragger.precursor_mass_mode=selected\n+msfragger.precursor_mass_units=1\n+msfragger.precursor_mass_upper=20\n+msfragger.precursor_true_tolerance=20\n+msfragger.precursor_true_units=1\n+msfragger.remainder_fragment_masses=\n+msfragger.remove_precursor_peak=1\n+msfragger.report_alternative_proteins=true\n+msfragger.require_precursor='..b'1\n+ptmshepherd.cap_y_ions=\n+ptmshepherd.decoy_type=1\n+ptmshepherd.diag_ions=\n+ptmshepherd.diagextract_mode=false\n+ptmshepherd.diagmine_diagMinFoldChange=3.0\n+ptmshepherd.diagmine_diagMinSpecDiff=00.2\n+ptmshepherd.diagmine_fragMinFoldChange=3.0\n+ptmshepherd.diagmine_fragMinPropensity=00.1\n+ptmshepherd.diagmine_fragMinSpecDiff=00.1\n+ptmshepherd.diagmine_minIonsPerSpec=2\n+ptmshepherd.diagmine_minPeps=25\n+ptmshepherd.diagmine_mode=false\n+ptmshepherd.diagmine_pepMinFoldChange=3.0\n+ptmshepherd.diagmine_pepMinSpecDiff=00.2\n+ptmshepherd.glyco_adducts=\n+ptmshepherd.glyco_fdr=1.00\n+ptmshepherd.glyco_isotope_max=3\n+ptmshepherd.glyco_isotope_min=-1\n+ptmshepherd.glyco_mode=false\n+ptmshepherd.glyco_ppm_tol=50\n+ptmshepherd.glycodatabase=\n+ptmshepherd.histo_smoothbins=2\n+ptmshepherd.iontype_a=false\n+ptmshepherd.iontype_b=true\n+ptmshepherd.iontype_c=true\n+ptmshepherd.iontype_x=false\n+ptmshepherd.iontype_y=true\n+ptmshepherd.iontype_z=true\n+ptmshepherd.localization_allowed_res=\n+ptmshepherd.localization_background=4\n+ptmshepherd.max_adducts=0\n+ptmshepherd.n_glyco=true\n+ptmshepherd.normalization-psms=true\n+ptmshepherd.normalization-scans=false\n+ptmshepherd.output_extended=false\n+ptmshepherd.peakpicking_mass_units=0\n+ptmshepherd.peakpicking_minPsm=10\n+ptmshepherd.peakpicking_promRatio=0.3\n+ptmshepherd.peakpicking_width=0.002\n+ptmshepherd.precursor_mass_units=0\n+ptmshepherd.precursor_tol=0.01\n+ptmshepherd.print_decoys=false\n+ptmshepherd.prob_dhexOx=2,0.5,0.1\n+ptmshepherd.prob_dhexY=2,0.5\n+ptmshepherd.prob_neuacOx=2,0.05,0.2\n+ptmshepherd.prob_neugcOx=2,0.05,0.2\n+ptmshepherd.prob_phosphoOx=2,0.05,0.2\n+ptmshepherd.prob_regY=5,0.5\n+ptmshepherd.prob_sulfoOx=2,0.05,0.2\n+ptmshepherd.remainder_masses=\n+ptmshepherd.remove_glycan_delta_mass=true\n+ptmshepherd.run-shepherd=false\n+ptmshepherd.spectra_maxfragcharge=2\n+ptmshepherd.spectra_ppmtol=20\n+ptmshepherd.varmod_masses=\n+quantitation.run-label-free-quant=false\n+run-psm-validation=true\n+run-validation-tab=true\n+saintexpress.fragpipe.cmd-opts=\n+saintexpress.max-replicates=10\n+saintexpress.run-saint-express=false\n+saintexpress.virtual-controls=100\n+speclibgen.easypqp.extras.max_delta_ppm=15\n+speclibgen.easypqp.extras.max_delta_unimod=0.02\n+speclibgen.easypqp.extras.rt_lowess_fraction=0\n+speclibgen.easypqp.fragment.a=false\n+speclibgen.easypqp.fragment.b=true\n+speclibgen.easypqp.fragment.c=false\n+speclibgen.easypqp.fragment.x=false\n+speclibgen.easypqp.fragment.y=true\n+speclibgen.easypqp.fragment.z=false\n+speclibgen.easypqp.im-cal=Automatic selection of a run as reference IM\n+speclibgen.easypqp.neutral_loss=false\n+speclibgen.easypqp.rt-cal=ciRT\n+speclibgen.easypqp.select-file.text=\n+speclibgen.easypqp.select-im-file.text=\n+speclibgen.keep-intermediate-files=false\n+speclibgen.run-speclibgen=false\n+tab-run.delete_calibrated_mzml=false\n+tab-run.delete_temp_files=false\n+tab-run.sub_mzml_prob_threshold=0.5\n+tab-run.write_sub_mzml=false\n+tmtintegrator.add_Ref=-1\n+tmtintegrator.aggregation_method=0\n+tmtintegrator.allow_overlabel=true\n+tmtintegrator.allow_unlabeled=true\n+tmtintegrator.best_psm=true\n+tmtintegrator.channel_num=TMT-6\n+tmtintegrator.dont-run-fq-lq=false\n+tmtintegrator.glyco_qval=-1\n+tmtintegrator.groupby=0\n+tmtintegrator.log2transformed=true\n+tmtintegrator.max_pep_prob_thres=0\n+tmtintegrator.min_ntt=0\n+tmtintegrator.min_pep_prob=0.9\n+tmtintegrator.min_percent=0.05\n+tmtintegrator.min_purity=0.5\n+tmtintegrator.min_site_prob=-1\n+tmtintegrator.mod_tag=none\n+tmtintegrator.ms1_int=true\n+tmtintegrator.outlier_removal=true\n+tmtintegrator.print_RefInt=false\n+tmtintegrator.prot_exclude=none\n+tmtintegrator.prot_norm=0\n+tmtintegrator.psm_norm=false\n+tmtintegrator.quant_level=2\n+tmtintegrator.ref_tag=Bridge\n+tmtintegrator.run-tmtintegrator=false\n+tmtintegrator.tolerance=20\n+tmtintegrator.top3_pep=true\n+tmtintegrator.unique_gene=0\n+tmtintegrator.unique_pep=false\n+tmtintegrator.use_glycan_composition=false\n+workflow.input.data-type.im-ms=false\n+workflow.input.data-type.regular-ms=true\n+workflow.saved-with-ver=20.0-build5\n'