I've been using re.sub() to try and take the below pattern1 and convert it
to pattern2 (which are below) below that is mycode1. Does anyone have any
suggestions as to how I can figure this out?
pattern1
NTR+A0001 0.01
GLU-A0003 8.21
GLU-A0008 3.619
ARG+A0010 14
ARG+A0023 14
ARG+A0024 14
ASP-A0028 0.01
ARG+A0034 13.193
ASP-A0039 2.973
LYS+A0040 10.634
LYS+A0043 12.693
ASP-A0051 3.994
ASP-A0055 0.01
GLU-A0057 9.017
ARG+A0062 14
TYR-A0064 13.028
GLU-A0066 4.081
LYS+A0073 11.193
ASP-A0076 0.01
TYR-A0084 14
HIS+A0086 0.01
TYR-A0087 14
LYS+A0091 11.193
LYS+A0092 10.275
LYS+A0095 11.193
ASP-A0097 2.96
TYR-A0098 14
ASP-A0101 0.01
LYS+A0114 14
TYR-A0116 14
ASP-A0123 0.01
HIS+A0125 7.15
GLU-A0126 3.269
LYS+A0127 11.693
ASP-A0128 2.324
HIS+A0129 7.15
GLU-A0134 3.612
LYS+A0137 12.134
GLU-A0150 2.546
ASP-A0153 0.01
HIS+A0162 9.547
ARG+A0166 14
LYS+A0167 11.693
TYR-A0169 13.641
LYS+A0177 9.547
GLU-A0184 2.952
LYS+A0185 10.634
LYS+A0188 10.634
GLU-A0193 4.078
ARG+A0199 14
ASP-A0201 1.973
LYS+A0209 11.693
GLU-A0213 3.279
GLU-A0219 4.706
LYS+A0223 11.693
ARG+A0226 13.193
GLU-A0227 4.377
GLU-A0228 9.459
GLU-A0230 4.274
ARG+A0232 14
TYR-A0234 14
ASP-A0239 2.317
GLU-A0248 3.982
LYS+A0253 10.547
ASP-A0261 2.335
ARG+A0267 14
LYS+A0272 14
TYR-A0275 10.21
HIS+A0276 7.15
ASP-A0280 3.317
LYS+A0281 11.193
ARG+A0292 12.693
ASP-A0294 2.473
ASP-A0304 2.3
LYS+A0305 11.693
GLU-A0308 2.083
LYS+A0312 11.193
GLU-A0314 4.517
LYS+A0315 11.693
GLU-A0322 15.177
ASP-A0327 0.01
LYS+A0328 10.298
ASP-A0330 0.01
HIS+A0331 0.01
LYS+A0341 6.65
ASP-A0344 0.01
ASP-A0346 2.03
GLU-A0347 3.149
ARG+A0351 14
GLU-A0354 4.52
LYS+A0357 11.193
LYS+A0358 11.634
GLU-A0359 3.945
ASP-A0369 5.467
HIS+A0370 0.01
HIS+A0372 14
ASP-A0380 0.751
LYS+A0382 13.193
LYS+A0393 12.693
ASP-A0394 2.724
TYR-A0402 14
GLU-A0406 3.551
GLU-A0407 4.924
ASP-A0408 1.824
GLU-A0411 5.186
HIS+A0412 6.852
ARG+A0418 23.69
TYR-A0422 14
HIS+A0425 6.65
ASP-A0434 0.01
ASP-A0437 0.01
TYR-A0440 10.555
LYS+A0443 11.155
LYS+A0449 11.693
CTR-A0449 3.014
_MG+A0452 5.257
NTR+B0001 8.547
GLU-B0003 4.312
GLU-B0008 2.577
ARG+B0010 14
ARG+B0023 14
ARG+B0024 14
ASP-B0028 0.724
ARG+B0034 13.193
ASP-B0039 3.21
LYS+B0040 11.193
LYS+B0043 12.377
ASP-B0051 8.766
ASP-B0055 0.01
GLU-B0057 1.955
ARG+B0062 14
TYR-B0064 12.243
GLU-B0066 3.279
LYS+B0073 12.193
ASP-B0076 0.01
TYR-B0084 14
HIS+B0086 0.01
TYR-B0087 14
LYS+B0091 11.693
LYS+B0092 10.547
LYS+B0095 11.134
ASP-B0097 1.839
TYR-B0098 14
ASP-B0101 0.01
LYS+B0114 14
TYR-B0116 14
ASP-B0123 0.01
HIS+B0125 7.15
GLU-B0126 4.746
LYS+B0127 11.693
ASP-B0128 2.457
HIS+B0129 6.65
GLU-B0134 2.737
LYS+B0137 12.193
GLU-B0150 3.33
ASP-B0153 0.611
HIS+B0162 9.664
ARG+B0166 14
LYS+B0167 10.599
TYR-B0169 14
LYS+B0177 10.547
GLU-B0184 3.501
LYS+B0185 11.693
LYS+B0188 12.634
GLU-B0193 3.281
ARG+B0199 14.134
ASP-B0201 1.52
LYS+B0209 10.547
GLU-B0213 3.073
GLU-B0219 3.317
LYS+B0223 11.134
ARG+B0226 12.634
GLU-B0227 4.577
GLU-B0228 7.332
GLU-B0230 3.865
ARG+B0232 14
TYR-B0234 14
ASP-B0239 1.797
GLU-B0248 4.706
LYS+B0253 10.275
ASP-B0261 2.68
ARG+B0267 14
LYS+B0272 10.547
TYR-B0275 10.988
HIS+B0276 7.65
ASP-B0280 3.077
LYS+B0281 12.193
ARG+B0292 13.193
ASP-B0294 2.473
ASP-B0304 2.77
LYS+B0305 11.193
GLU-B0308 3.108
LYS+B0312 12.193
GLU-B0314 3.568
LYS+B0315 11.693
GLU-B0322 9.138
ASP-B0327 13.172
LYS+B0328 10.24
ASP-B0330 0.01
HIS+B0331 4.598
LYS+B0341 6.15
ASP-B0344 0.01
ASP-B0346 1.247
GLU-B0347 2.911
ARG+B0351 14
GLU-B0354 4.113
LYS+B0357 11.134
LYS+B0358 11.693
GLU-B0359 4.509
ASP-B0369 4.63
HIS+B0370 0.01
HIS+B0372 0.01
ASP-B0380 2.097
LYS+B0382 11.693
LYS+B0393 11.693
ASP-B0394 0.473
TYR-B0402 14
GLU-B0406 2.85
GLU-B0407 4.328
ASP-B0408 2.562
GLU-B0411 5.428
HIS+B0412 2.554
ARG+B0418 14
TYR-B0422 14
HIS+B0425 7.15
ASP-B0434 0.01
ASP-B0437 0.01
TYR-B0440 10.199
LYS+B0443 12.693
LYS+B0449 12.693
CTR-B0449 3.18
_MG+B0452 8.86
pattern2
pKaRes NTR 1 A,value= 0.01
pKaRes GLU 3 A,value= 8.21
pKaRes GLU 8 A,value= 3.619
pKaRes ARG 10 A,value= 14
mycode1
from __future__ import with_statement
import re
dict={"NTR":"NTR","CTR":"CTR","_MG":"_MG","PHE":"PHE",
"LEU":"LEU","SER":"SER","TYR":"TYR","CYS":"CYS",
"TRP":"TRP","LEU":"LEU","PRO":"PRO","HIS":"HIS",
"GLN":"GLN","ARG":"ARG","ILE":"ILE","MET":"MET",
"THR":"THR","ASN":"ASN","LYS":"LYS","SER":"SER",
"ARG":"ARG","VAL":"VAL","ALA":"ALA","ASP":"ASP",
"GLU":"GLU","GLY":"GLY"}
# in google search for '''re python search print pattern'''
def new1():
#this takes...#
with open('C:/Documents and
Settings/Administrator/Desktop/Northeastern/Research2/python/E341K.txt') as
fil:
print fil
contents = fil.read()
letter = contents
letter=str(letter)
#list1=list(letter)
x= len(contents)
#''.join(contents)
#splitted=letter.split("-")
AA='AA'
xx=dict.keys()
NTR1='NTR1'
#for B in letter and dict.keys():
for A in letter:
if re.sub(' ',' ', letter):
letter=re.sub('\t','\t',letter) #'value= '
#print letter
#print re.sub('\t' and r'\+','',letter), re.sub(r'\+',' ',letter),
re.sub('A0','A',letter)
break
for A in letter:
if re.sub(r'\+',' ',letter):
letter=re.sub(r'\+',' ',letter)
#print letter
break
for A in letter:
if re.sub(r'\-',' ',letter):
letter=re.sub(r'\-',' ',letter)
#print letter
break
for A in letter:
if re.sub('[0-9]','',letter):
letter2=re.sub('[0-9]','',letter)
#print letter2, 'letter2'
break
for A in letter2:
if re.sub(r'\.','',letter2):
letter1=re.sub(r'\.','',letter2)
#print letter1, 'letter1'
break
for A in letter:
if re.sub('A000?', 'A', letter):
letter3=re.sub('A000?', 'A', letter)
#print letter3
break
for A in letter:
if re.sub('A010?','A',letter3):
letter4=re.sub('A010?','A',letter3)
print letter4
break
re.purge()
#digs=re.compile(r'\+A')
#for line in letter:
#if digs.search(line):
#splitted=line.split(' ') #print line
#line=list(line)
#print line
**************A Good Credit Score is 700 or Above. See yours in just 2 easy
steps!
(http://pr.atwola.com/promoclk/100126575x1220685763x1201394209/aol?redir=http:%2F%2Fwww.freecreditreport.com%2Fpm%2Fdefault.aspx%3Fsc%3D668072%26hmpgID
%3D62%26bcd%3DMarchfooterNO62)
_______________________________________________
Tutor maillist - Tutor@python.org
http://mail.python.org/mailman/listinfo/tutor
