Changed editConfJET to editConfJETpython to reduce bash dependency.

esgemme.py

@@ -19,6 +19,7 @@ import glob
 
 from prody import *
 from scipy.stats import rankdata
+from Bio import AlignIO
 
 #from gemmeAnal import *
 
@@ -50,17 +51,29 @@ def extractQuerySeq(filename):
 	fOUT.close()
 	return prot,seq,i-1
 
-def getNbSeq(filename):
-	#TODO: Remove bash dependency and count the sequences within Python!
-	"""
-		# Get the number of sequences in a multi-fasta file
-		
-	"""
-	if filename!='':
-		proc=subprocess.Popen("grep -c '^>' "+filename,stdout=subprocess.PIPE,shell=True)
-		return int(proc.stdout.read())
-	else:
-		return 0
+# def getNbSeq(filename):
+# 	#TODO: Remove bash dependency and count the sequences within Python!
+# 	"""
+# 		# Get the number of sequences in a multi-fasta file
+		
+# 	"""
+# 	if filename!='':
+# 		proc=subprocess.Popen("grep -c '^>' "+filename,stdout=subprocess.PIPE,shell=True)
+# 		return int(proc.stdout.read())
+# 	else:
+# 		return 0
+
+# def getNbSeqPython(filename):
+#     #TODO: Remove bash dependency and count the sequences within Python!
+#     """
+#     	Get the number of sequences in a multi-fasta file using only Python functions.	
+#     """
+#     if ((filename != '') or (filename != None)):
+#         alignment = AlignIO.read(filename, "fasta")
+#         return int(len(alignment))
+#     else:
+#         print("ERROR: Could not find MSA file!")
+#         return 0
 
 def createPDB(prot,seq):
 	"""
@@ -80,12 +93,27 @@ def createPDB(prot,seq):
 			i += 1
 		
 	fOUT.close()
-def editConfJET(N):
+# def editConfJET(N):
+# 	"""
+# 		# Edit JET configuration file with correct number of Seqs & MSA
+# 	"""
+# 	reCode=subprocess.call("sed -i 's/results\t\t5000/results\t\t"+str(N)+"/' default.conf",shell=True)
+# 	return(reCode)
+
+def editConfJETpython(N):
     """
     	# Edit JET configuration file with correct number of Seqs & MSA
     """
-	reCode=subprocess.call("sed -i 's/results\t\t5000/results\t\t"+str(N)+"/' default.conf",shell=True)
-	return(reCode)
+    with open("default.conf", "r+" ) as file:
+        fileContents = file.read()
+        textPattern = re.compile( re.escape("results\t\t5000"))
+        fileContents = textPattern.sub("results\t\t"+str(N), fileContents)
+        file.seek( 0 )
+        file.truncate()
+        file.write(fileContents)
+
+    #reCode=subprocess.call("sed -i 's/results\t\t5000/results\t\t"+str(N)+"/' default.conf",shell=True)
+    return 0
 
 def minMaxNormalization(data):
     """
@@ -147,7 +175,7 @@ def launchJET(prot, retMet, bFile, fFile, pdbfile, chains, n, N, nl):
 		if bFile!='':
 			#TODO: I think these two lines must be here as well but I am not sure. 
 			# print(N)
-			# editConfJET(N)
+			# editConfJETpython(N)
 
 			if(bFile == prot+"_"+chainID+".psiblast"):
 				shutil.copy2(bFile, bFile+".orig")
@@ -166,7 +194,7 @@ def launchJET(prot, retMet, bFile, fFile, pdbfile, chains, n, N, nl):
 
 		else:
 			print(N)
-			editConfJET(N)
+			editConfJETpython(N)
 
 			if(fFile == prot+"_"+chainID+".fasta"):
 				shutil.copy2(fFile, fFile+".orig")

example/example-sgemme-script.sh

@@ -15,34 +15,38 @@ elif [ "$1" == "jetoff" ]
 then
     # If you have your own JET2 score file, you can turn off JET2 as follows:
     # In ../tests folder, you can find a sample JET2 file called BLAT_jet.res 
-    echo "Running SGEMME with a user-provided alignment file."
+    echo "Running ESGEMME with a user-provided alignment file."
     echo "Using a previously produced prot_jet.res file to check reproducibility!"
     cp ../tests/BLAT_jet.res .
-    python $SGEMME_PATH/sgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --jetfile BLAT_jet.res
+    python $ESGEMME_PATH/esgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --jetfile BLAT_jet.res
 
 elif [ "$1" == "withpdb" ]
 then
 
     #Please note that CV isa structural feature and it can not be calculated if you don't specify a pdb file.
     echo "Using blat-af2.pdb for the structural feature calculations!"
-    python $SGEMME_PATH/sgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --pdbfile blat-af2.pdb --normweightmode maxhalftracepchalftracecvhalfcvpc
+    echo "Entire mutational map of the protein will be calculated!"
+    python $ESGEMME_PATH/esgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --pdbfile blat-af2.pdb --normweightmode maxhalftracepchalftracecvhalfcvpc
 
 elif [ "$1" == "withpdb-withmutfile" ]
 then
 
     #Please note that CV isa structural feature and it can not be calculated if you don't specify a pdb file.
     echo "Using blat-af2.pdb for the structural feature calculations!"
-    python $SGEMME_PATH/sgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --pdbfile blat-af2.pdb --normweightmode maxhalftracepchalftracecvhalfcvpc -m Stiffler_2015_BLAT_ECOLX.mut
+    echo "Only effects of mutations specified in the Stiffler_2015_BLAT_ECOLX.mut file will be calculated!"
+    python $ESGEMME_PATH/esgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --pdbfile blat-af2.pdb --normweightmode maxhalftracepchalftracecvhalfcvpc -m Stiffler_2015_BLAT_ECOLX.mut
 
 elif [ "$1" == "ssjetormax" ]
 then
 
     #Please note that CV isa structural feature and it can not be calculated if you don't specify a pdb file.
     echo "Using blat-af2.pdb for the secondary structure based calculations!"
-    python $SGEMME_PATH/sgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --pdbfile blat-af2.pdb --normweightmode ssjetormax -m Stiffler_2015_BLAT_ECOLX.mut
+    echo "Only effects of mutations specified in the Stiffler_2015_BLAT_ECOLX.mut file will be calculated!"
+    python $ESGEMME_PATH/esgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta --pdbfile blat-af2.pdb --normweightmode ssjetormax -m Stiffler_2015_BLAT_ECOLX.mut
     
 else
-    echo "Running SGEMME with a user-provided alignment file."
-    python $SGEMME_PATH/sgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta
+    echo "Running EGEMME with a user-provided alignment file."
+    echo "Since a pdb file is not provided, only evolutionary information will be used!"
+    python $ESGEMME_PATH/esgemme.py aliBLAT.fasta -r input -f aliBLAT.fasta
     
 fi