Mercurial > repos > rreumerman > snptools

comparison trams.py @ 7:8de0ffc2166f draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author rreumerman
date Mon, 10 Jun 2013 09:40:54 -0400
parents bd5692103d5b
children
comparison
equal deleted inserted replaced
6:e711f63e99ff 7:8de0ffc2166f
2 transl_table = 11 2 transl_table = 11
3 intro_message = ''' +------------------------------------------------------------------+ 3 intro_message = ''' +------------------------------------------------------------------+
4 | Tool for Rapid Annotation of Microbial SNPs (TRAMS): a simple | 4 | Tool for Rapid Annotation of Microbial SNPs (TRAMS): a simple |
5 | program for rapid annotation of genomic variation in prokaryotes | 5 | program for rapid annotation of genomic variation in prokaryotes |
6 | | 6 | |
7 | Developed by: Richard A. Reumerman, Paul R. Herron, | 7 | Developed by: Richard A. Reumerman, Nick P. Tucker, Paul R. |
8 | Paul A. Hoskisson and Vartul Sangal | 8 | Herron, Paul A. Hoskisson and Vartul Sangal |
9 +------------------------------------------------------------------+\n''' 9 +------------------------------------------------------------------+\n'''
10 ################# 10 #################
11 11
12 import sys 12 import sys
13 import time 13 import time
193 straininfo[j][codon[i][j+2][0]] += 1# Counting; 193 straininfo[j][codon[i][j+2][0]] += 1# Counting;
194 elif strain[1] in ['a','g','c','t']: 194 elif strain[1] in ['a','g','c','t']:
195 codon[i][j+2] = ['MNP',strain[1],'',''] 195 codon[i][j+2] = ['MNP',strain[1],'','']
196 straininfo[j]['mnps'] += 1 196 straininfo[j]['mnps'] += 1
197 new_codons[j] = new_codon_calc(new_codons[j],strain[1],pos_in_cod) 197 new_codons[j] = new_codon_calc(new_codons[j],strain[1],pos_in_cod)
198 elif strain[0] == 'Allele missing': codon[i][j+2] = strain 198 elif strain[0] == 'Missing allele':
199 codon[i][j+2] = strain
199 else: codon[i][j+2] = ['']*4 200 else: codon[i][j+2] = ['']*4
200 201
201 for line in codon[1:-1]: 202 for line in codon[1:-1]:
202 if line != '': write_output(line) 203 if line != '': write_output(line)
203 204
287 288
288 # Loop through SNPs from array and process them; 289 # Loop through SNPs from array and process them;
289 props = {}# Properties of a feature; 290 props = {}# Properties of a feature;
290 prev_snp = ''# Position of previous SNP; 291 prev_snp = ''# Position of previous SNP;
291 to_write = []# Information of current SNP; 292 to_write = []# Information of current SNP;
293 allowed_chars = ['g','a','t','c','','-']
292 compl_bases = {'a':'t','t':'a','g':'c','c':'g'} 294 compl_bases = {'a':'t','t':'a','g':'c','c':'g'}
293 firstsnp = True# First snp of region, or of codon in cases of 3 positions in codon mutated; 295 firstsnp = True# First snp of region, or of codon in cases of 3 positions in codon mutated;
294 prev_start=j=k=0 296 prev_start=j=k=0
295 overlap_snps = [] 297 overlap_snps = []
296 codon = ['']*5# Array of codon positions. First item is position of first base of codon in the gene; 298 codon = ['']*5# Array of codon positions. First item is position of first base of codon in the gene;
327 329
328 330
329 snp_entry[-1] = snp_entry[-1].rstrip()# Remove newline character at end of line; 331 snp_entry[-1] = snp_entry[-1].rstrip()# Remove newline character at end of line;
330 332
331 # Prevent crash upon encounter nonstandard base character; 333 # Prevent crash upon encounter nonstandard base character;
332 if snp_entry[1] not in ['a','g','c','t']:# Ref base 334 if snp_entry[1].lower() not in allowed_chars:# Ref base
333 i += 1 335 i += 1
334 continue 336 continue
335 for m,base in enumerate(snp_entry[2:],2): 337 for m,base in enumerate(snp_entry[2:],2):
336 if base.lower() not in ['a','g','c','t']: 338 if base.lower() not in allowed_chars:
337 snp_entry[m] = '' 339 snp_entry[m] = ''
338 # Crash prevented 340 # Crash prevented
339 341
340 mnp=in_feat=False 342 mnp=in_feat=False
341 snp_feat = region[2] 343 snp_feat = region[2]
407 409
408 for l, snp in enumerate(snp_entry[2:]):# Loop through SNPs/strains; 410 for l, snp in enumerate(snp_entry[2:]):# Loop through SNPs/strains;
409 411
410 snp = snp.lower() 412 snp = snp.lower()
411 if snp == '':# Empty cell; 413 if snp == '':# Empty cell;
412 to_write.append(['','','','']) 414 to_write.append(['']*4)
413 continue 415 continue
414 416
415 if snp == '-': # Feature not present in this strain; 417 if snp == '-': # Feature not present in this strain;
416 to_write.append(['Allele missing','','','']) 418 to_write.append(['Missing allele','','',''])
417 continue 419 continue
418 420
419 if snp_feat == -1:# Intergenic; 421 if snp_feat == -1:# Intergenic;
420 if snp == ref_base.lower(): 422 if snp == ref_base.lower():
421 to_write.append(['']*4) 423 to_write.append(['']*4)