Integration of Msgfplus

tests/data/params/MSGFPlus_params.txt

@@ -0,0 +1,97 @@
+# Parent mass tolerance 
+#  Examples: 2.5Da or 30ppm
+#  Use comma to set asymmetric values, for example "0.5Da,2.5Da" will set 0.5Da to the left (expMass<theoMass) and 2.5Da to the right (expMass>theoMass)
+PrecursorMassTolerance=5ppm
+
+# Max Number of Modifications per peptide 
+# If this value is large, the search will be slow
+NumMods=3
+
+# Modifications (see below for examples)
+StaticMod=C2H3N1O1,  C, fix, any, Carbamidomethyl           # Fixed Carbamidomethyl C (alkylation)
+
+DynamicMod=O1,       M, opt, any, Oxidation                 # Oxidized methionine
+DynamicMod=C2H2O,    *, opt, Prot-N-term, Acetyl            # Acetylation Protein N-term
+
+# Fragmentation Method
+#  0 means as written in the spectrum or CID if no info (Default)
+#  1 means CID
+#  2 means ETD
+#  3 means HCD
+#  4 means Merge spectra from the same precursor (e.g. CID/ETD pairs, CID/HCD/ETD triplets) 
+FragmentationMethodID=3
+
+# Instrument ID
+#  0 means Low-res LCQ/LTQ (Default for CID and ETD); use InstrumentID=0 if analyzing a dataset with low-res CID and high-res HCD spectra
+#  1 means High-res LTQ (Default for HCD; also appropriate for high res CID); use InstrumentID=1 for Orbitrap, Lumos, and QEHFX instruments
+#  2 means TOF
+#  3 means Q-Exactive
+InstrumentID=0
+
+# Enzyme ID
+#  0 means unspecific cleavage (cleave after any residue)
+#  1 means Trypsin (Default); optionally use this along with NTT=0 for a no-enzyme-specificity search of a tryptically digested sample
+#  2: Chymotrypsin, 3: Lys-C, 4: Lys-N, 5: Glu-C, 6: Arg-C, 7: Asp-N, 8: alphaLP, 9: No Cleavage (for peptidomics)
+EnzymeID=1
+
+# Isotope error range
+#  Takes into account of the error introduced by choosing non-monoisotopic peak for fragmentation.
+#  Useful for accurate precursor ion masses
+#  Ignored if the parent mass tolerance is > 0.5Da or 500ppm
+#  The combination of -t and -ti determins the precursor mass tolerance.
+#  e.g. "-t 20ppm -ti -1,2" tests abs(exp-calc-n*1.00335Da)<20ppm for n=-1, 0, 1, 2.
+IsotopeErrorRange=-1,2
+
+# Number of tolerable termini
+#  The number of peptide termini that must have been cleaved by the enzyme (default 1)
+#  For trypsin, 2 means fully tryptic only, 1 means partially tryptic, and 0 means no-enzyme search
+NTT=2
+
+# Control N-terminal methionine cleavage
+#  0 means to consider protein N-term Met cleavage (Default)
+#  1 means to ignore protein N-term Met cleavage
+IgnoreMetCleavage=0
+
+# Target/Decoy search mode
+#  0 means don't search decoy database (default)
+#  1 means search decoy database to compute FDR (source FASTA file must be forward-only proteins)
+TDA=0
+
+# Number of Threads (by default, uses all available cores)
+NumThreads=1
+
+# Minimum peptide length to consider
+MinPepLength=6
+
+# Maximum peptide length to consider
+MaxPepLength=50
+
+# Minimum precursor charge to consider (if not specified in the spectrum)
+MinCharge=2
+
+# Maximum precursor charge to consider (if not specified in the spectrum)
+MaxCharge=5
+
+# Number of matches per spectrum to be reported
+# If this value is greater than 1, the FDR values computed by MS-GF+ will be skewed by high-scoring 2nd and 3rd hits
+NumMatchesPerSpec=5
+
+# Amino Acid Modification Examples
+# Specify static modifications using one or more StaticMod= entries
+# Specify dynamic modifications using one or more DynamicMod= entries
+# Modification format is:
+# Mass or CompositionString, Residues, ModType, Position, Name (all five fields are required).
+# CompositionString can only contain a limited set of elements, primarily C H N O S or P
+#
+# Examples:
+#   C2H3N1O1,  C,  fix, any,         Carbamidomethyl    # Fixed Carbamidomethyl C (alkylation)
+#   O1,        M,  opt, any,         Oxidation          # Oxidation M
+#   15.994915, M,  opt, any,         Oxidation          # Oxidation M (mass is used instead of CompositionString)
+#   H-1N-1O1,  NQ, opt, any,         Deamidated         # Negative numbers are allowed.
+#   CH2,       K,  opt, any,         Methyl             # Methylation K
+#   C2H2O1,    K,  opt, any,         Acetyl             # Acetylation K
+#   HO3P,      STY,opt, any,         Phospho            # Phosphorylation STY
+#   C2H3NO,    *,  opt, N-term,      Carbamidomethyl    # Variable Carbamidomethyl N-term
+#   H-2O-1,    E,  opt, N-term,      Glu->pyro-Glu      # Pyro-glu from E
+#   H-3N-1,    Q,  opt, N-term,      Gln->pyro-Glu      # Pyro-glu from Q
+#   C2H2O,     *,  opt, Prot-N-term, Acetyl             # Acetylation Protein N-term

tests/data/params/MSGFPlus_params_no_Carbamidomethyl.txt

@@ -0,0 +1,96 @@
+# Parent mass tolerance 
+#  Examples: 2.5Da or 30ppm
+#  Use comma to set asymmetric values, for example "0.5Da,2.5Da" will set 0.5Da to the left (expMass<theoMass) and 2.5Da to the right (expMass>theoMass)
+PrecursorMassTolerance=5ppm
+
+# Max Number of Modifications per peptide 
+# If this value is large, the search will be slow
+NumMods=3
+
+# Modifications (see below for examples)
+
+DynamicMod=O1,       M, opt, any, Oxidation                 # Oxidized methionine
+DynamicMod=C2H2O,    *, opt, Prot-N-term, Acetyl            # Acetylation Protein N-term
+
+# Fragmentation Method
+#  0 means as written in the spectrum or CID if no info (Default)
+#  1 means CID
+#  2 means ETD
+#  3 means HCD
+#  4 means Merge spectra from the same precursor (e.g. CID/ETD pairs, CID/HCD/ETD triplets) 
+FragmentationMethodID=3
+
+# Instrument ID
+#  0 means Low-res LCQ/LTQ (Default for CID and ETD); use InstrumentID=0 if analyzing a dataset with low-res CID and high-res HCD spectra
+#  1 means High-res LTQ (Default for HCD; also appropriate for high res CID); use InstrumentID=1 for Orbitrap, Lumos, and QEHFX instruments
+#  2 means TOF
+#  3 means Q-Exactive
+InstrumentID=0
+
+# Enzyme ID
+#  0 means unspecific cleavage (cleave after any residue)
+#  1 means Trypsin (Default); optionally use this along with NTT=0 for a no-enzyme-specificity search of a tryptically digested sample
+#  2: Chymotrypsin, 3: Lys-C, 4: Lys-N, 5: Glu-C, 6: Arg-C, 7: Asp-N, 8: alphaLP, 9: No Cleavage (for peptidomics)
+EnzymeID=1
+
+# Isotope error range
+#  Takes into account of the error introduced by choosing non-monoisotopic peak for fragmentation.
+#  Useful for accurate precursor ion masses
+#  Ignored if the parent mass tolerance is > 0.5Da or 500ppm
+#  The combination of -t and -ti determins the precursor mass tolerance.
+#  e.g. "-t 20ppm -ti -1,2" tests abs(exp-calc-n*1.00335Da)<20ppm for n=-1, 0, 1, 2.
+IsotopeErrorRange=-1,2
+
+# Number of tolerable termini
+#  The number of peptide termini that must have been cleaved by the enzyme (default 1)
+#  For trypsin, 2 means fully tryptic only, 1 means partially tryptic, and 0 means no-enzyme search
+NTT=2
+
+# Control N-terminal methionine cleavage
+#  0 means to consider protein N-term Met cleavage (Default)
+#  1 means to ignore protein N-term Met cleavage
+IgnoreMetCleavage=0
+
+# Target/Decoy search mode
+#  0 means don't search decoy database (default)
+#  1 means search decoy database to compute FDR (source FASTA file must be forward-only proteins)
+TDA=0
+
+# Number of Threads (by default, uses all available cores)
+NumThreads=1
+
+# Minimum peptide length to consider
+MinPepLength=6
+
+# Maximum peptide length to consider
+MaxPepLength=50
+
+# Minimum precursor charge to consider (if not specified in the spectrum)
+MinCharge=2
+
+# Maximum precursor charge to consider (if not specified in the spectrum)
+MaxCharge=5
+
+# Number of matches per spectrum to be reported
+# If this value is greater than 1, the FDR values computed by MS-GF+ will be skewed by high-scoring 2nd and 3rd hits
+NumMatchesPerSpec=5
+
+# Amino Acid Modification Examples
+# Specify static modifications using one or more StaticMod= entries
+# Specify dynamic modifications using one or more DynamicMod= entries
+# Modification format is:
+# Mass or CompositionString, Residues, ModType, Position, Name (all five fields are required).
+# CompositionString can only contain a limited set of elements, primarily C H N O S or P
+#
+# Examples:
+#   C2H3N1O1,  C,  fix, any,         Carbamidomethyl    # Fixed Carbamidomethyl C (alkylation)
+#   O1,        M,  opt, any,         Oxidation          # Oxidation M
+#   15.994915, M,  opt, any,         Oxidation          # Oxidation M (mass is used instead of CompositionString)
+#   H-1N-1O1,  NQ, opt, any,         Deamidated         # Negative numbers are allowed.
+#   CH2,       K,  opt, any,         Methyl             # Methylation K
+#   C2H2O1,    K,  opt, any,         Acetyl             # Acetylation K
+#   HO3P,      STY,opt, any,         Phospho            # Phosphorylation STY
+#   C2H3NO,    *,  opt, N-term,      Carbamidomethyl    # Variable Carbamidomethyl N-term
+#   H-2O-1,    E,  opt, N-term,      Glu->pyro-Glu      # Pyro-glu from E
+#   H-3N-1,    Q,  opt, N-term,      Gln->pyro-Glu      # Pyro-glu from Q
+#   C2H2O,     *,  opt, Prot-N-term, Acetyl             # Acetylation Protein N-term

tests/integrationtests/wrappers/test_msgfplus.py

@@ -0,0 +1,64 @@
+import xml.etree.ElementTree as ETree
+
+import urgap
+
+
+def test_searchdb_msgfplus_carbamidomethyl_in_usermods():
+    mgf = urgap.UFile(
+        uri=f"file:///{urgap._test_folder}/data/mgfs?uftype={urgap.uftypes.proteomics.converter.PYMZML_MGF}#BSA1.mgf"
+    )
+    fasta = urgap.UFile(
+        uri=f"file:///{urgap._test_folder}/data/fastas?uftype={urgap.uftypes.proteomics.FASTA}#BSA1.fasta"
+    )
+    unimod = urgap.UFile(
+        uri=f"file:///{urgap._test_folder}/data/usermods?uftype={urgap.uftypes.proteomics.MODS_XML}#unimod_no_carbamidomethyl.xml"
+    )
+    usermod = urgap.UFile(
+        uri=f"file:///{urgap._test_folder}/data/usermods?uftype={urgap.uftypes.proteomics.MODS_XML}#usermods_carbamidomethyl.xml"
+    )
+    params1 = urgap.UFile(
+        uri=f"file:///{urgap._test_folder}/data/params?uftype={urgap.uftypes.proteomics.params.MSGFPLUS_TXT}#MSGFPlus_params_no_Carbamidomethyl.txt"
+    )
+    params2 = urgap.UFile(
+        uri=f"file:///{urgap._test_folder}/data/params?uftype={urgap.uftypes.proteomics.params.MSGFPLUS_TXT}#MSGFPlus_params.txt"
+    )
+
+    urd = urgap.URunDict(
+        {
+            "parameters": {
+                "MsgfPlus:20240326": {},
+            },
+            "unode_parameters": {
+                "storage_base_uri": f"file://{urgap._test_folder}/data",
+            },
+        }
+    )
+
+    search_node = urgap.init_node("MsgfPlus:20240326")
+    search_result = search_node.run(
+        [mgf, fasta, params1],
+        urd,
+    )
+    assert search_result[0].path.exists() is True
+
+    tree = ETree.parse(search_result[0].path)
+    root = tree.getroot()
+
+    for ele in root.findall(".//{*}Modification"):
+        assert ele[0].get("name") != "Carbamidomethyl"
+    search_node.remove_output_folder(output_file=search_result[0])
+
+    search_result = search_node.run(
+        [mgf, fasta, params2],
+        urd,
+    )
+    assert search_result[0].path.exists() is True
+    tree = ETree.parse(search_result[0].path)
+    root = tree.getroot()
+
+    C_DETECTED = False
+    for ele in root.findall(".//{*}Modification"):
+        if ele[0].get("name") == "Carbamidomethyl":
+            C_DETECTED = True
+    assert C_DETECTED is True
+    search_node.remove_output_folder(output_file=search_result[0])

urgap/resources/MsgfPlus/2024_03_26/BuildSuffixArray.bat

@@ -0,0 +1 @@
+"C:\Program Files\Java\jre8\bin\java.exe" -Xmx4000M -cp C:\MSGFPlus\MSGFPlus.jar edu.ucsd.msjava.msdbsearch.BuildSA -d C:\SequenceDB\MyDatabase.fasta -tda 2

urgap/resources/MsgfPlus/2024_03_26/Convert_mzid_to_tsv.bat

@@ -0,0 +1,6 @@
+rem Option 1:
+MzidToTsvConverter.exe C:\Work\DatasetName_msgfplus.mzid -mzid:C:\Work\DatasetName_msgfplus.mzid -tsv:C:\Work\DatasetName_msgfplus.tsv -unroll -showDecoy
+
+rem Option 2:
+"C:\Program Files\Java\jre8\bin\java.exe" -Xmx2000M -cp C:\MSGFPlus\MSGFPlus.jar edu.ucsd.msjava.ui.MzIDToTsv -i C:\Work\DatasetName_msgfplus.mzid -o C:\Work\DatasetName_msgfplus.tsv -showQValue 1 -showDecoy 1 -unroll 1
+

urgap/resources/MsgfPlus/2024_03_26/Docs/BuildSA.html

@@ -0,0 +1,77 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+  <head>
+    <title>BuildSA</title>
+    <link type="text/css" rel="stylesheet" href="style.css" />
+  </head>
+
+  <body>
+    <h1 class="pagetitle">BuildSA</h1>
+
+    <p>
+        <a href="index.html">MS-GF+ Documentation home</a>
+    </p>
+
+    <h1>BuildSA</h1>
+
+    <p>
+      Index a protein database (FASTA file) for fast searching.
+    </p>
+    <div class="codePanel">
+      <pre class="code">Usage: java -Xmx3500M -cp MSGFPlus.jar edu.ucsd.msjava.msdbsearch.BuildSA
+	    <span class="code-keyword">-d DatabaseFile</span> (*.fasta or *.fa or *.faa; if a directory path, index all FASTA files)
+	    <span class="code-keyword">[-tda 0/1/2]</span> (0: Target database only, 1: Concatenated target-decoy database only, 2: Both (Default))
+	    <span class="code-keyword">[-o OutputDir]</span> (Directory to save index files; default is the same as the input file)
+	    <span class="code-keyword">[-decoy DecoyPrefix]</span> (Prefix for decoy protein names; default is XXX)
+      </pre>
+    </div>
+
+    <p style="color:#003366;">
+        <b>Parameters:</b>
+    </p>
+    <ul>
+      <li style="margin-bottom: 10px;">
+        <b>-d DatabaseFilePath</b>
+        <ul>
+          <li>Name of a protein database file, or a directory containing one or more protein database files</li>
+          <li>Database file names must end with ".fasta" or ".fa" or ".faa"</li>
+        </ul>
+      </li>
+      <li>
+        <b>-tda 0/1/2</b>
+        <ul>
+          <li>If 0, only "DatabaseFile" will be indexed.</li>
+          <li>If 1, a new database file (*.revConcat.fasta) will be generated by appending reversed proteins. This forward-reverse database will be indexed.</li>
+          <li>If 2, both the original database and the forward-reverse database file will be indexed.</li>
+        </ul>
+      </li>
+      <li>
+        <b>-o OutputDirectory</b>
+        <ul>
+          <li>Path to the output directory (use double quotes if the path contains spaces)</li>
+          <li>By default, the index files are created in the same directory as the Database</li>
+        </ul>
+      </li>
+      <li>
+        <b>-decoy DecoyPrefix</b>
+        <ul>
+          <li>Text to prepend to protein names when including decoy (reverse sequence) proteins in the .revCat.fasta file and related index files</li>
+          <li>Defaults to XXX (though an underscore is also added, giving names like <span class="code-keyword"><code>XXX_Contaminant_TRYP_BOVIN</code></span>)</li>
+          <li>Use <span class="code-keyword"><code>-decoy REV</code></span> to get names like <span class="code-keyword"><code>REV_Contaminant_TRYP_BOVIN</code></span></li>
+          <li>If -decoy is used with BuildSA it should also be used with <a href="MSGFPlus.html">MS-GF+</a></li>
+        </ul>
+      </li>
+
+    </ul>
+
+    <p>BuildSA creates a suffix array of the protein database. For an input database file DBFileName.fasta, BuildSA will generate 4 auxiliary files:</p>
+    <ul>
+        <li>DBFileName.canno</li>
+        <li>DBFileName.cnlcp</li>
+        <li>DBFileName.csarr</li>
+        <li>DBFileName.cseq</li>
+    </ul>
+    <p>BuildSA only needs to be executed once for each protein database file.</p>
+  </body>
+</html>