Mercurial > repos > galaxyp > peptideshaker

changeset 58:07ff622ec007 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/peptideshaker commit 0f6ab8b5647a33b2b051d7aa808ef42546436b23"
author galaxyp
date Sat, 10 Apr 2021 15:57:17 +0000
parents da885ca16cb2
children 943a34df6047
files fasta_cli.xml ident_params.xml macros_basic.xml peptide_shaker.xml searchgui.xml test-data/peptideshaker_reports_output_certificate.txt test-data/peptideshaker_reports_output_extendedpsm.tabular test-data/peptideshaker_reports_output_hierarchical.tabular test-data/peptideshaker_reports_output_peptides.tabular test-data/peptideshaker_reports_output_peptidesnonvalidated.tabular test-data/peptideshaker_reports_output_peptidesphosphorylation.tabular test-data/peptideshaker_reports_output_proteins.tabular test-data/peptideshaker_reports_output_proteinsnonvalidated.tabular test-data/peptideshaker_reports_output_proteinsphosphorylation.tabular test-data/peptideshaker_reports_output_psm.tabular test-data/peptideshaker_reports_output_psmnonvalidated.tabular test-data/peptideshaker_reports_output_psmphosphorylation.tabular
diffstat 9 files changed, 45 insertions(+), 25 deletions(-) [+]
line wrap: on
line diff
--- a/fasta_cli.xml	Tue Mar 16 15:12:03 2021 +0000
+++ b/fasta_cli.xml	Sat Apr 10 15:57:17 2021 +0000
@@ -1,6 +1,6 @@
 <tool id="fasta_cli"
       name="FastaCLI"
-      version="1.0.1"
+      version="@SEARCHGUI_VERSION@+galaxy@SEARCHGUI_VERSION_SUFFIX@"
       profile="20.01"
 >
     <description>
--- a/ident_params.xml	Tue Mar 16 15:12:03 2021 +0000
+++ b/ident_params.xml	Sat Apr 10 15:57:17 2021 +0000
@@ -1,6 +1,6 @@
 <tool id="ident_params"
       name="Identification Parameters"
-      version="1.5.1"
+      version="@SEARCHGUI_VERSION@+galaxy@SEARCHGUI_VERSION_SUFFIX@"
       profile="20.01"
 >
     <description>
--- a/macros_basic.xml	Tue Mar 16 15:12:03 2021 +0000
+++ b/macros_basic.xml	Sat Apr 10 15:57:17 2021 +0000
@@ -11,9 +11,9 @@
         </stdio>
     </xml>
     <token name="@SEARCHGUI_MAJOR_VERSION@">4</token>
-    <token name="@SEARCHGUI_VERSION@">4.0.22</token>
+    <token name="@SEARCHGUI_VERSION@">4.0.25</token>
     <token name="@SEARCHGUI_VERSION_SUFFIX@">0</token>
-    <token name="@PEPTIDESHAKER_VERSION@">2.0.15</token>
+    <token name="@PEPTIDESHAKER_VERSION@">2.0.18</token>
     <token name="@PEPTIDESHAKER_VERSION_SUFFIX@">0</token>
     <xml name="citations">
         <citations>
--- a/peptide_shaker.xml	Tue Mar 16 15:12:03 2021 +0000
+++ b/peptide_shaker.xml	Sat Apr 10 15:57:17 2021 +0000
@@ -570,10 +570,15 @@
 
     <tests>
       <!-- Basic test: default identification parameters, searchgui_tinydb1.fasta, 4 search engines xx-->
-      <test expect_num_outputs="1">
+      <test expect_num_outputs="2">
           <param name="searchgui_input" value="searchgui_tiny_result_default_4engines.zip" ftype="searchgui_archive"/>
-          <param name="mzidentml_creation" value="0"/>
+          <param name="mzidentml_creation" value="1"/>
           <param name="export_psdb" value="1"/>
+          <output name="mzidentML" ftype="mzid">
+              <assert_contents>
+                  <has_text text="MzIdentML"/>
+              </assert_contents>
+          </output>
           <output name="output_psdb" ftype="peptideshaker_archive">
               <assert_contents>
                   <has_size value="122880" delta="3000"/>
--- a/searchgui.xml	Tue Mar 16 15:12:03 2021 +0000
+++ b/searchgui.xml	Sat Apr 10 15:57:17 2021 +0000
@@ -170,7 +170,7 @@
     <inputs>
         <param format="json" name="input_parameters_file" type="data" label="Identification Parameters file"/>
 
-        <param format="fasta" name="input_fasta_file" type="data" label="Fasta file"/>
+        <param format="fasta" name="input_fasta_file" type="data" label="Fasta file" help="For postprocessing with PeptideShaker the sequences must have UniProt style headers and contain decoy sequences (see help)."/>
 
         <param name="peak_lists_files" format="mgf,mzml" type="data" multiple="true" label="Input Peak Lists"
             help="Select appropriate MGF/MZML dataset(s) from history" />
@@ -326,6 +326,21 @@
 
 Optional:     MyriMatch, MS-Amanda, OMSSA (it may not work into isolated environments like containers), Comet, Tide, DirecTag and Novor can be executed.
 
+**Input FASTA**
+
+In order to allow for postprocessing with PeptideShaker the sequences must contain decoy sequences (see _here: https://github.com/compomics/searchgui/wiki/DatabaseHelp#decoy-sequences)
+and the FASTA header must either contain no "|" characters (then the whole header will be used as ID) or have the following format:
+
+    >generic[your tag]|[protein accession]|[protein description]
+
+    or 
+
+    >generic[your tag]|[protein accession]
+
+See _here: https://github.com/compomics/searchgui/wiki/DatabaseHelp#non-standard-fasta.
+
+
+
     </help>
     <expand macro="citations" />
 </tool>
--- a/test-data/peptideshaker_reports_output_certificate.txt	Tue Mar 16 15:12:03 2021 +0000
+++ b/test-data/peptideshaker_reports_output_certificate.txt	Sat Apr 10 15:57:17 2021 +0000
@@ -1,9 +1,9 @@
 
 Project Details
 
-1: PeptideShaker Version: 2.0.2
-2: Date: Thu Nov 19 10:47:40 CET 2020
-3: Experiment: Galaxy_Experiment_2020111910471605779259
+1: PeptideShaker Version: 2.0.18
+2: Date: Fri Apr 02 17:00:43 GMT 2021
+3: Experiment: Galaxy_Experiment_2021040219001617382836
 4: Sample: Not implemented
 5: Replicate Number: Not implemented
 6: Identification Algorithms: OMSSA, X!Tandem and MS-GF+
--- a/test-data/peptideshaker_reports_output_proteins.tabular	Tue Mar 16 15:12:03 2021 +0000
+++ b/test-data/peptideshaker_reports_output_proteins.tabular	Sat Apr 10 15:57:17 2021 +0000
@@ -1,5 +1,5 @@
-	Protein Inference	Main Accession	Description	Protein Group	Secondary Accessions	Chromosome	Gene Name	Taxonomy	Validated Coverage [%]	All Coverage [%]	Possible Coverage [%]	#Peptides	#Validated Peptides	#Unique Peptides	#Validated Unique Peptides	#PSMs	#Validated PSMs	Confidently Localized Modification Sites	#Confidently Localized Modification Sites	Ambiguously Localized Modification Sites	#Ambiguously Localized Modification Sites	Spectrum Counting	MW [kDa]	Confidence [%]	Validation
-1	Single Protein	cds.comp8310_c0_seq2	m.1138 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 22.01 EValue:2.0e-16	cds.comp8310_c0_seq2					3.69	3.69	81.0	1	1	1	1	1	1					12239.035185720222	45.26545451338222	100.0	Doubtful
-2	Single Protein	cds.comp41890_c0_seq1	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20	cds.comp41890_c0_seq1					20.15	20.15	91.04	1	1	1	1	1	1					30798.227885377935	14.802380493830709	100.0	Doubtful
-3	Related Proteins	cds.comp41779_c0_seq1	m.9429 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 30.62 EValue:7.0e-67	cds.comp41779_c0_seq1,cds.comp41779_c0_seq2,cds.comp41779_c0_seq3	cds.comp41779_c0_seq2,cds.comp41779_c0_seq3				3.34	3.34	78.82	1	1	1	1	1	1					7590.674347507289	69.88215380565931	100.0	Doubtful
-4	Single Protein	cds.comp41890_c0_seq1_REVERSED	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20-REVERSED	cds.comp41890_c0_seq1_REVERSED					8.21	8.21	90.3	1	1	1	1	1	1					31052.758694348	14.802380493830709	100.0	Doubtful
+	Protein Inference	Main Accession	Description	Protein Group	Secondary Accessions	Chromosome	Gene Name	Taxonomy	Organism Identifier	Validated Coverage [%]	All Coverage [%]	Possible Coverage [%]	#Peptides	#Validated Peptides	#Unique Peptides	#Validated Unique Peptides	#PSMs	#Validated PSMs	Confidently Localized Modification Sites	#Confidently Localized Modification Sites	Ambiguously Localized Modification Sites	#Ambiguously Localized Modification Sites	Spectrum Counting	MW [kDa]	Confidence [%]	Validation
+1	Single Protein	cds.comp8310_c0_seq2	m.1138 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 22.01 EValue:2.0e-16	cds.comp8310_c0_seq2						3.69	3.69	81.0	1	1	1	1	1	1					12239.035185720222	45.26545451338222	100.0	Doubtful
+2	Single Protein	cds.comp41890_c0_seq1	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20	cds.comp41890_c0_seq1						20.15	20.15	91.04	1	1	1	1	1	1					30798.227885377935	14.802380493830709	100.0	Doubtful
+3	Related Proteins	cds.comp41779_c0_seq1	m.9429 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 30.62 EValue:7.0e-67	cds.comp41779_c0_seq1,cds.comp41779_c0_seq2,cds.comp41779_c0_seq3	cds.comp41779_c0_seq2,cds.comp41779_c0_seq3					3.34	3.34	78.82	1	1	1	1	1	1					7590.674347507289	69.88215380565931	100.0	Doubtful
+4	Single Protein	cds.comp41890_c0_seq1_REVERSED	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20-REVERSED	cds.comp41890_c0_seq1_REVERSED						8.21	8.21	90.3	1	1	1	1	1	1					31052.758694348	14.802380493830709	100.0	Doubtful
--- a/test-data/peptideshaker_reports_output_proteinsnonvalidated.tabular	Tue Mar 16 15:12:03 2021 +0000
+++ b/test-data/peptideshaker_reports_output_proteinsnonvalidated.tabular	Sat Apr 10 15:57:17 2021 +0000
@@ -1,5 +1,5 @@
-	Protein Inference	Main Accession	Description	Protein Group	Secondary Accessions	Chromosome	Gene Name	Taxonomy	Validated Coverage [%]	All Coverage [%]	Possible Coverage [%]	#Peptides	#Validated Peptides	#Unique Peptides	#Validated Unique Peptides	#PSMs	#Validated PSMs	Confidently Localized Modification Sites	#Confidently Localized Modification Sites	Ambiguously Localized Modification Sites	#Ambiguously Localized Modification Sites	Spectrum Counting	MW [kDa]	Confidence [%]	Validation
-1	Single Protein	cds.comp8310_c0_seq2	m.1138 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 22.01 EValue:2.0e-16	cds.comp8310_c0_seq2					3.69	3.69	81.0	1	1	1	1	1	1					12239.035185720222	45.26545451338222	100.0	Doubtful
-2	Single Protein	cds.comp41890_c0_seq1	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20	cds.comp41890_c0_seq1					20.15	20.15	91.04	1	1	1	1	1	1					30798.227885377935	14.802380493830709	100.0	Doubtful
-3	Related Proteins	cds.comp41779_c0_seq1	m.9429 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 30.62 EValue:7.0e-67	cds.comp41779_c0_seq1,cds.comp41779_c0_seq2,cds.comp41779_c0_seq3	cds.comp41779_c0_seq2,cds.comp41779_c0_seq3				3.34	3.34	78.82	1	1	1	1	1	1					7590.674347507289	69.88215380565931	100.0	Doubtful
-4	Single Protein	cds.comp41890_c0_seq1_REVERSED	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20-REVERSED	cds.comp41890_c0_seq1_REVERSED					8.21	8.21	90.3	1	1	1	1	1	1					31052.758694348	14.802380493830709	100.0	Doubtful
+	Protein Inference	Main Accession	Description	Protein Group	Secondary Accessions	Chromosome	Gene Name	Taxonomy	Organism Identifier	Validated Coverage [%]	All Coverage [%]	Possible Coverage [%]	#Peptides	#Validated Peptides	#Unique Peptides	#Validated Unique Peptides	#PSMs	#Validated PSMs	Confidently Localized Modification Sites	#Confidently Localized Modification Sites	Ambiguously Localized Modification Sites	#Ambiguously Localized Modification Sites	Spectrum Counting	MW [kDa]	Confidence [%]	Validation
+1	Single Protein	cds.comp8310_c0_seq2	m.1138 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 22.01 EValue:2.0e-16	cds.comp8310_c0_seq2						3.69	3.69	81.0	1	1	1	1	1	1					12239.035185720222	45.26545451338222	100.0	Doubtful
+2	Single Protein	cds.comp41890_c0_seq1	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20	cds.comp41890_c0_seq1						20.15	20.15	91.04	1	1	1	1	1	1					30798.227885377935	14.802380493830709	100.0	Doubtful
+3	Related Proteins	cds.comp41779_c0_seq1	m.9429 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 30.62 EValue:7.0e-67	cds.comp41779_c0_seq1,cds.comp41779_c0_seq2,cds.comp41779_c0_seq3	cds.comp41779_c0_seq2,cds.comp41779_c0_seq3					3.34	3.34	78.82	1	1	1	1	1	1					7590.674347507289	69.88215380565931	100.0	Doubtful
+4	Single Protein	cds.comp41890_c0_seq1_REVERSED	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20-REVERSED	cds.comp41890_c0_seq1_REVERSED						8.21	8.21	90.3	1	1	1	1	1	1					31052.758694348	14.802380493830709	100.0	Doubtful
--- a/test-data/peptideshaker_reports_output_proteinsphosphorylation.tabular	Tue Mar 16 15:12:03 2021 +0000
+++ b/test-data/peptideshaker_reports_output_proteinsphosphorylation.tabular	Sat Apr 10 15:57:17 2021 +0000
@@ -1,5 +1,5 @@
-	Protein Inference	Main Accession	Description	Protein Group	Secondary Accessions	Chromosome	Gene Name	Taxonomy	Validated Coverage [%]	All Coverage [%]	Possible Coverage [%]	#Peptides	#Validated Peptides	#Unique Peptides	#Validated Unique Peptides	#PSMs	#Validated PSMs	Confident Phosphosites	#Confident Phosphosites	Ambiguous Phosphosites	#Ambiguous Phosphosites	Spectrum Counting NSAF	MW [kDa]	Confidence [%]	Validation
-1	Single Protein	cds.comp8310_c0_seq2	m.1138 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 22.01 EValue:2.0e-16	cds.comp8310_c0_seq2					3.69	3.69	81.0	1	1	1	1	1	1		0		0	0.003257328990228013	45.26545451338222	100.0	Doubtful
-2	Single Protein	cds.comp41890_c0_seq1	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20	cds.comp41890_c0_seq1					20.15	20.15	91.04	1	1	1	1	1	1		0		0	0.00819672131147541	14.802380493830709	100.0	Doubtful
-3	Related Proteins	cds.comp41779_c0_seq1	m.9429 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 30.62 EValue:7.0e-67	cds.comp41779_c0_seq1,cds.comp41779_c0_seq2,cds.comp41779_c0_seq3	cds.comp41779_c0_seq2,cds.comp41779_c0_seq3				3.34	3.34	78.82	1	1	1	1	1	1		0		0	0.00202020202020202	69.88215380565931	100.0	Doubtful
-4	Single Protein	cds.comp41890_c0_seq1_REVERSED	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20-REVERSED	cds.comp41890_c0_seq1_REVERSED					8.21	8.21	90.3	1	1	1	1	1	1		0		0	0.008264462809917356	14.802380493830709	100.0	Doubtful
+	Protein Inference	Main Accession	Description	Protein Group	Secondary Accessions	Chromosome	Gene Name	Taxonomy	Organism Identifier	Validated Coverage [%]	All Coverage [%]	Possible Coverage [%]	#Peptides	#Validated Peptides	#Unique Peptides	#Validated Unique Peptides	#PSMs	#Validated PSMs	Confident Phosphosites	#Confident Phosphosites	Ambiguous Phosphosites	#Ambiguous Phosphosites	Spectrum Counting NSAF	MW [kDa]	Confidence [%]	Validation
+1	Single Protein	cds.comp8310_c0_seq2	m.1138 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 22.01 EValue:2.0e-16	cds.comp8310_c0_seq2						3.69	3.69	81.0	1	1	1	1	1	1		0		0	0.003257328990228013	45.26545451338222	100.0	Doubtful
+2	Single Protein	cds.comp41890_c0_seq1	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20	cds.comp41890_c0_seq1						20.15	20.15	91.04	1	1	1	1	1	1		0		0	0.00819672131147541	14.802380493830709	100.0	Doubtful
+3	Related Proteins	cds.comp41779_c0_seq1	m.9429 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 30.62 EValue:7.0e-67	cds.comp41779_c0_seq1,cds.comp41779_c0_seq2,cds.comp41779_c0_seq3	cds.comp41779_c0_seq2,cds.comp41779_c0_seq3					3.34	3.34	78.82	1	1	1	1	1	1		0		0	0.00202020202020202	69.88215380565931	100.0	Doubtful
+4	Single Protein	cds.comp41890_c0_seq1_REVERSED	m.9546 RecName: Full=70 kDa neurofilament protein; 1051067 GO:0005882 GO:0005198 Identity: 38.58 EValue:4.0e-20-REVERSED	cds.comp41890_c0_seq1_REVERSED						8.21	8.21	90.3	1	1	1	1	1	1		0		0	0.008264462809917356	14.802380493830709	100.0	Doubtful