Mercurial > repos > bornea > saint_preprocessing

comparison SAINT_preprocessing.py @ 51:09b89febcf98 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bornea
date Thu, 19 May 2016 12:12:00 -0400
parents 61b792d17660
children 26b5bd96332e
comparison
equal deleted inserted replaced
50:61b792d17660 51:09b89febcf98
240 # Remake inter file without protein errors from Uniprot. 240 # Remake inter file without protein errors from Uniprot.
241 err = readtab("error proteins.txt") 241 err = readtab("error proteins.txt")
242 bait = readtab(baitfile) 242 bait = readtab(baitfile)
243 data = read_Scaffold(Scaffold_input).data 243 data = read_Scaffold(Scaffold_input).data
244 header = read_Scaffold(Scaffold_input).header 244 header = read_Scaffold(Scaffold_input).header
245 header = [MQ_var.replace(r"\"", "") for MQ_var in header]
246 header = [MQ_var.replace(r"Intensity.", r"") for MQ_var in header]
247 header = [MQ_var.replace(r".", r"-") for MQ_var in header]
248 bait_index = [] 245 bait_index = []
249 for bait_item in bait: 246 for bait_line in bait:
250 bait_index.append(header.index(bait_item[0])) 247 bait_index.append(header.index(bait_line[0]))
251 proteins = read_Scaffold(Scaffold_input).proteins 248 proteins = read_Scaffold(Scaffold_input).proteins
252 errors = [] 249 errors = []
253 valid_prots = []
254 for e in err: 250 for e in err:
255 errors.append(e[0]) 251 errors.append(e[0])
256 for a in proteins: 252 with open('inter.txt', 'w') as y:
257 a = a.replace("\n", "")
258 # Remove \n for input into function.
259 a = a.replace("\r", "")
260 # Ditto for \r.
261 seq = get_info(a).seqlength
262 GN = get_info(a).genename
263 if seq != 'NA':
264 if GN != 'NA':
265 valid_prots.append(a)
266 with open('inter.txt', 'w') as input_file:
267 l = 0; a = 0 253 l = 0; a = 0
268 for bb in bait: 254 for bb in bait:
269 for lst in data: 255 for lst in data:
270 print lst 256 if proteins[a] not in errors:
271 if lst[0] in valid_prots: 257 y.write(header[bait_index[l]] + '\t' + bb[1] + '\t' + proteins[a] + '\t'
272 input_file.write(header[bait_index[l]] + '\t' + bb[1] + '\t' + lst[0] + '\t' + lst[bait_index[l]] + '\n') 258 + lst[bait_index[l]] + '\n')
273 a += 1 259 a += 1
274 if a == len(proteins): 260 if a == len(proteins):
275 l += 1; a = 0 261 l += 1; a = 0
276
277 262
278 263
279 def bait_check(bait, Scaffold_input): 264 def bait_check(bait, Scaffold_input):
280 # Check that bait names share Scaffold header titles. 265 # Check that bait names share Scaffold header titles.
281 bait_in = readtab(bait) 266 bait_in = readtab(bait)