Implement param and mod files for MS-GF. User-defined PTMs!

Params previously hardcoded in runMS2.sh. The param file is easier and safer to modify.

params/MSGFplus_mods.txt

@@ -0,0 +1,49 @@
+# This file is used to specify modifications for MS-GF+.
+
+# It is copied and slightly modified from the MS-GF+ example modification file found here:
+#   https://bix-lab.ucsd.edu/download/attachments/13533355/Mods.txt
+
+# Max Number of Modifications per peptide 
+# If this value is large, the search takes long.
+NumMods=3
+
+# To input a modification, use the following command:
+# Mass or CompositionStr, Residues, ModType, Position, Name (all the five fields are required).
+# CompositionStr (C[Num]H[Num]N[Num]O[Num]S[Num]P[Num]Br[Num]Cl[Num]Fe[Num])
+# 	- C (Carbon), H (Hydrogen), N (Nitrogen), O (Oxygen), S (Sulfer), P (Phosphorus), Br (Bromine), Cl (Chlorine), Fe (Iron), and Se (Selenium) are allowed.
+# 	- Negative numbers are allowed.
+# 	- E.g. C2H2O1 (valid), H2C1O1 (invalid) 
+# Mass can be used instead of CompositionStr. It is important to specify accurate masses (integer masses are insufficient).
+# 	- E.g. 15.994915 
+# Residues: affected amino acids (must be upper letters)
+# 	- Must be uppor letters or *
+# 	- Use * if this modification is applicable to any residue. 
+# 	- * should not be "anywhere" modification (e.g. "15.994915, *, opt, any, Oxidation" is not allowed.) 
+# 	- E.g. NQ, *
+# ModType: "fix" for fixed modifications, "opt" for variable modifications (case insensitive)
+# Position: position in the peptide where the modification can be attached. 
+# 	- One of the following five values should be used:
+# 	- any (anywhere), N-term (peptide N-term), C-term (peptide C-term), Prot-N-term (protein N-term), Prot-C-term (protein C-term) 
+# 	- Case insensitive
+# 	- "-" can be omitted
+# 	- E.g. any, Any, Prot-n-Term, ProtNTerm => all valid
+# Name: name of the modification (Unimod PSI-MS name)
+# 	- For proper mzIdentML output, this name should be the same as the Unimod PSI-MS name
+# 	- E.g. Phospho, Acetyl
+# 	- Visit http://www.unimod.org to get PSI-MS names.
+
+57.021464,C,fix,any,Carbamidomethyl  # Fixed Carbamidomethyl C
+#144.102063,*,fix,N-term,iTRAQ4plex   # iTRAQ 4 plex
+#144.102063,K,fix,any,iTRAQ4plex      # iTRAQ 4 plex
+
+# Variable Modifications (default: none)
+15.9949,M,opt,any,Oxidation          # Oxidation M
+#O1,M,opt,any,Oxidation               # Oxidation M (CompositionStr can be used instead of mass)
+#H-1N-1O1,NQ,opt,any,Deamidated       # Negative numbers are allowed.
+#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
+#C2H2O1,K,opt,any,Acetyl              # Acetylation K
+#CH2,K,opt,any,Methyl                 # Methylation K
+#HO3P,STY,opt,any,Phospho             # Phosphorylation STY

params/MSGFplus_params.txt

@@ -0,0 +1,32 @@
+# MS-GF+ parameters
+# Documentation: https://bix-lab.ucsd.edu/pages/viewpage.action?pageId=13533355
+
+# Comments are only allowed on lines starting with # symbol.
+# Make sure there is one space between parameter flag and value.
+# No spaces are allowed within a value.
+
+# Precursor mass tolerance. This can be assymetric, ex. "-t 10ppm,4Da".
+-t 10ppm
+
+# Number of enzyme-specific termini.
+-ntt 2
+
+# Enzyme ID. 0:nonspecific, 1:Trypsin(default), 2:Chymotrypsin, 3:Lys-C, 
+#            4:Lys-N, 5:Glu-C, 6: Arg-C, 7:Asp-N, 8:alphaLP, 9:no cleavage
+-e 1
+
+# Instrument ID. 0:Low-res MS/MS, 1:High-res, 2:TOF (10ppm MS/MS), 3:Q-Exactive HCD
+-inst 0
+
+# Minimum precursor chargem, default 2
+# -minCharge 2
+
+# Maximum precursor charge, default 3
+-maxCharge 6
+
+# Minimum peptide length, default 6
+# -minLength 6
+
+# Maximum peptide length, default 40
+# -maxLength 40
+

runMS2.sh

@@ -129,6 +129,28 @@ if [ ! -f "$MSGFplus_JAR" ]
     echo "msgfplus jar $MSGFplus_JAR not found!"
     exit 0
 fi
+
+### Create MS-GF+ parameter string.
+MSFGplus_MODFILE="${PIPELINEDIR}/params/MSGFplus_mods.txt"
+if [ ! -f "$MSFGplus_MODFILE" ]
+then
+    echo "MSGF+ modification file $MSFGplus_MODFILE not found! Using default of static C+57 and no optional modifications."
+    MSGFplus_MODPARAM=""
+else
+    MSGFplus_MODPARAM=" -mod \"$MSFGplus_MODFILE\""
+fi
+
+# Read and parse MS-GF+ param file. Append modification file parameter.
+MSGFplus_PARAMFILE="${PIPELINEDIR}/params/MSGFplus_params.txt"
+if [ ! -f "$MSGFplus_PARAMFILE" ]
+then
+    echo "MSGF+ parameter file $MSGFplus_PARAMFILE not found!"
+    exit 0
+else
+    MSGFplus_PARAMSTR=$(grep -v "#" "$MSGFplus_PARAMFILE" | tr -s '\n\r' ' ')"$MSGFplus_MODPARAM"
+fi
+
+
 #
 #####
 #Researved for MS1 future analysis
@@ -202,7 +224,7 @@ mkdir -p $TANDEMDIR
         #mv $TANDEMDIR/*tandemK.xml $WORKDIR
 	#MSGF+
 	TBL=${MSGFOUT/.mzid}.tsv
-	time java -Xmx20000M -jar $MSGFplus_JAR -d $FASTAFILE -s $1 -o ${MSGFOUT}.mzid -t 10ppm -tda 0 -ntt 2 -e 1 -inst 3 -maxCharge 6
+	time java -Xmx20000M -jar $MSGFplus_JAR -d $FASTAFILE -s $1 -o ${MSGFOUT}.mzid -tda 0 "$MSGFplus_PARAMSTR"
  	time java -Xmx20000M -cp $MSGFplus_JAR edu.ucsd.msjava.ui.MzIDToTsv -i ${MSGFOUT}.mzid -o $TBL -showQValue 1 -showDecoy 1 -unroll 0