# HG changeset patch
# User bornea
# Date 1460480078 14400
# Node ID b688d0dae86b0cc140d4908a727017fd073a09bb
# Parent  1b0547d3c7bc33c71abcac8edad9348bb191db0a
Uploaded

diff -r 1b0547d3c7bc -r b688d0dae86b SAINT_preprocessing.py
--- a/SAINT_preprocessing.py	Tue Mar 29 14:46:04 2016 -0400
+++ b/SAINT_preprocessing.py	Tue Apr 12 12:54:38 2016 -0400
@@ -25,6 +25,7 @@
 
 import sys
 import os.path
+import re
 
 
 infile = sys.argv[1] 
@@ -197,8 +198,10 @@
     for Scaffold_line in data:
         Scaffold_line[4] = Scaffold_line[4].split()[0]
         # Removes the (+##) that sometimes is attached.
-    for protein in data:
-        proteins.append(protein[prot_start])
+    uniprot_re = re.compile("[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}")
+    for protein in data: 
+        prot_id = uniprot_re.match(protein[prot_start])
+        proteins.append(prot_id.group())
     return ReturnValue2(data, proteins, header)