|
4
|
1 #################
|
|
|
2 transl_table = 11
|
|
|
3 intro_message = ''' +------------------------------------------------------------------+
|
|
|
4 | Tool for Rapid Annotation of Microbial SNPs (TRAMS): a simple |
|
|
|
5 | program for rapid annotation of genomic variation in prokaryotes |
|
|
|
6 | |
|
|
7
|
7 | Developed by: Richard A. Reumerman, Nick P. Tucker, Paul R. |
|
|
|
8 | Herron, Paul A. Hoskisson and Vartul Sangal |
|
|
4
|
9 +------------------------------------------------------------------+\n'''
|
|
|
10 #################
|
|
|
11
|
|
|
12 import sys
|
|
|
13 import time
|
|
|
14 start = time.clock()
|
|
|
15
|
|
|
16 # Command line files: SNP REF REF-TYPE ANNOT OVERL SUM;
|
|
|
17 if len(sys.argv) < 7:
|
|
|
18 exit("\nNot enough arguments given.\nUsage: TRAMS_Galaxy.py [SNP.] [REF.] [ANNOT.] [OVERL.] [SUM.]")
|
|
|
19 try:
|
|
|
20 file_snps = open(sys.argv[1], "rU")
|
|
|
21 except IOError as e:
|
|
|
22 exit("Error trying to open '"+sys.argv[1]+"': {1}".format(e.errno, e.strerror))
|
|
|
23 try:
|
|
|
24 file_ref = open(sys.argv[2], "rU")
|
|
|
25 except IOError as e:
|
|
|
26 exit("Error trying to open '"+sys.argv[2]+"': {1}".format(e.errno, e.strerror))
|
|
|
27
|
|
|
28 filetype_reference = sys.argv[3]
|
|
|
29
|
|
|
30 try:
|
|
|
31 file_out = open(sys.argv[4], "w")
|
|
|
32 except IOError as e:
|
|
|
33 exit("Error trying to open '"+sys.argv[4]+"': {1}".format(e.errno, e.strerror))
|
|
|
34 try:
|
|
|
35 file_overlap = open(sys.argv[5], "w")
|
|
|
36 except IOError as e:
|
|
|
37 exit("Error trying to open '"+sys.argv[5]+"': {1}".format(e.errno, e.strerror))
|
|
|
38 try:
|
|
|
39 file_summary = open(sys.argv[6], "w")
|
|
|
40 except IOError as e:
|
|
|
41 exit("Error trying to open '"+sys.argv[6]+"': {1}".format(e.errno, e.strerror))
|
|
|
42
|
|
|
43 import Bio
|
|
|
44 from Bio import SeqIO, SeqFeature
|
|
|
45 from Bio.SeqRecord import SeqRecord
|
|
|
46 from Bio.Seq import Seq
|
|
|
47 from Bio.Alphabet import generic_dna, IUPAC
|
|
|
48 from Bio.Data import CodonTable
|
|
|
49
|
|
|
50 modules_loaded = time.clock()
|
|
|
51
|
|
|
52 def non_coding_calc(gene, pos = 0):
|
|
|
53 '''This function takes a pseudogene and returns the number of bases
|
|
|
54 located in between the sub-features before 'pos'. Returns 0 if 'pseudo' = False.
|
|
|
55 Input: {start, subfeats, pseudo}, pos (default = 0)'''
|
|
|
56 if not gene['pseudo']: return 0
|
|
|
57
|
|
|
58 non_coding_bases = 0
|
|
|
59 prev_subfeat_end = gene['start']
|
|
|
60 if gene['strand'] == -1:
|
|
|
61 for subfeature in gene['subfeats']:
|
|
|
62 if subfeature.location._start.position < pos:
|
|
|
63 prev_subfeat_end = subfeature.location._end.position
|
|
|
64 continue
|
|
|
65 non_coding_bases += (subfeature.location._start.position - prev_subfeat_end)
|
|
|
66 prev_subfeat_end = subfeature.location._end.position
|
|
|
67 else:
|
|
|
68 for subfeature in gene['subfeats']:
|
|
|
69 non_coding_bases += (subfeature.location._start.position - prev_subfeat_end)
|
|
|
70 prev_subfeat_end = subfeature.location._end.position
|
|
|
71 if prev_subfeat_end >= pos and pos != 0: break
|
|
|
72
|
|
|
73 return non_coding_bases
|
|
|
74
|
|
|
75
|
|
|
76 def region_calc(bounds,length):
|
|
|
77 regions = []
|
|
|
78 lastend=i=0
|
|
|
79 while i < len(bounds):
|
|
|
80 if bounds[i]['start'] > lastend:# Intergenic region present;
|
|
|
81 regions.append([lastend,bounds[i]['start'],-1])
|
|
|
82 lastend = bounds[i]['start']
|
|
|
83 else:
|
|
|
84 regions.append([bounds[i]['start'],bounds[i]['end'],i])
|
|
|
85 if bounds[i]['end'] > lastend:
|
|
|
86 lastend = bounds[i]['end']
|
|
|
87 i += 1
|
|
|
88
|
|
|
89 if regions[-1][1] < length:# Final tail of genome;
|
|
|
90 regions.append([lastend,length,-1])
|
|
|
91
|
|
|
92 return regions
|
|
|
93
|
|
|
94
|
|
|
95 def overlap_calc(bounds):
|
|
|
96 '''This function takes an array of feature starts and ends and
|
|
|
97 returns an array of starts and ends of all overlapping regions.
|
|
|
98 Input: [{start,end}]'''
|
|
|
99 i = 0
|
|
|
100 overlaps = []
|
|
|
101 while i < len(bounds) - 1:
|
|
|
102 for downstr in bounds[i+1:]:
|
|
|
103 if downstr[0] < bounds[i][1]:# Features overlap;
|
|
|
104 if downstr[1] < bounds[i][1]:# Complete overlap;
|
|
|
105 overlaps.append([downstr[0],downstr[1],bounds[i][2],downstr[2],[0,0]])
|
|
|
106 else:# Partial overlap;
|
|
|
107 overlaps.append([downstr[0],bounds[i][1],bounds[i][2],downstr[2],[0,0]])
|
|
|
108 else:# No use looking further;
|
|
|
109 break
|
|
|
110
|
|
|
111 i += 1
|
|
|
112
|
|
|
113 return overlaps
|
|
|
114
|
|
|
115
|
|
|
116 def match_feature(bounds,pos,prev=0):
|
|
|
117 '''This function checks if a position is located inside a feature and
|
|
|
118 returns the feature's number if found or -1 if none is found.
|
|
|
119 Input: {start,end},pos,prev_feat (default = 0)'''
|
|
|
120 for i in range(prev, len(bounds)):
|
|
|
121 if (pos >= bounds[i]['start']) and (pos < bounds[i]['end']):
|
|
|
122 return i
|
|
|
123 elif pos < bounds[i]['start']:# No use looking further
|
|
|
124 return -1
|
|
|
125
|
|
|
126 return -1
|
|
|
127
|
|
|
128
|
|
|
129 def write_output(line,target=file_out):
|
|
|
130 '''This function takes the 2 dimensional array containing all the SNP
|
|
|
131 data. It contains an array of information on the feature and an array
|
|
|
132 for each strain for which SNPs are given.
|
|
|
133 Input: [[pos],[ref],[cells],[cells],etc]'''
|
|
|
134 target.write('\n'+str(line[0][0]))
|
|
|
135 for cell in line[1]:
|
|
|
136 target.write('\t'+str(cell))
|
|
|
137 for strain in line[2:]:
|
|
|
138 target.write('\t')
|
|
|
139 for cell in strain:
|
|
|
140 target.write('\t'+str(cell))
|
|
|
141
|
|
|
142 target.flush()
|
|
|
143
|
|
|
144
|
|
|
145 def new_codon_calc(ref_codon, new_base, pos_in_cod):
|
|
|
146 return str(ref_codon[0:pos_in_cod-1]+new_base+ref_codon[pos_in_cod:len(ref_codon)])
|
|
|
147
|
|
|
148
|
|
|
149 def mut_type_check(ref_res, ref_codon, pos_in_gene, new_base, new_codon):
|
|
|
150 if str(new_codon).lower() == str(ref_codon).lower():
|
|
|
151 return ['','','','']
|
|
|
152 new_residue = Seq(new_codon).translate(table=transl_table)
|
|
|
153 if str(new_residue) == str(ref_res):
|
|
|
154 mut_type = 'synonymous'
|
|
|
155 elif (pos_in_gene / 3) < 1 and str(ref_codon).upper() in CodonTable.unambiguous_dna_by_id[transl_table].start_codons:# position 0,1 or 2 and SNP is in start codon;
|
|
|
156 if str(new_codon).upper() in CodonTable.unambiguous_dna_by_id[transl_table].start_codons: mut_type = 'nonsynonymous'
|
|
|
157 else: mut_type = 'nonstart'
|
|
|
158 elif str(new_residue) == '*': mut_type = 'nonsense'
|
|
|
159 elif str(ref_res) == '*': mut_type = 'nonstop'
|
|
|
160 else: mut_type = 'nonsynonymous'
|
|
|
161
|
|
|
162 return [mut_type,new_base,new_codon,new_residue]
|
|
|
163
|
|
|
164
|
|
|
165 def codon_process(codon):
|
|
|
166 '''This function processes a codon. It loops through it 3 times,
|
|
|
167 once to determine which is the highest position mutated, once to
|
|
|
168 fill in the cells for the output file and once to output all lines.
|
|
|
169 Input: [empty,start_pos,[line1],[line2],[line3],strand]
|
|
|
170 It also uses global variable strain_nr'''
|
|
|
171 lastposition = [-1]*(strain_nr-1)
|
|
|
172 new_codons = ['']*(strain_nr-1)
|
|
|
173 if codon[-1] == -1:# Change codon position order for -1 features;
|
|
|
174 temp = codon [1:-1]
|
|
|
175 temp.reverse()
|
|
|
176 codon[1:-1] = temp
|
|
|
177 for i,line in enumerate(codon[1:-1],1):
|
|
|
178 if line == '': continue
|
|
|
179 for j,strain in enumerate(line[2:]):
|
|
|
180 if strain[1] in ['a','g','c','t']:
|
|
|
181 lastposition[j] = i
|
|
|
182 new_codons[j] = codon[i][1][8]
|
|
|
183
|
|
|
184 for i,line in enumerate(codon[1:-1],1):
|
|
|
185 if codon[-1] == -1: pos_in_cod = 4-i
|
|
|
186 else: pos_in_cod = i
|
|
|
187
|
|
|
188 if line == '': continue
|
|
|
189 for j,strain in enumerate(line[2:]):
|
|
|
190 if i == lastposition[j]: # Check for synonymous etc.;
|
|
|
191 new_codons[j] = new_codon_calc(new_codons[j],strain[1],pos_in_cod)
|
|
|
192 codon[i][j+2] = mut_type_check(line[1][9],line[1][8],codon[0],strain[1],new_codons[j])
|
|
|
193 straininfo[j][codon[i][j+2][0]] += 1# Counting;
|
|
|
194 elif strain[1] in ['a','g','c','t']:
|
|
|
195 codon[i][j+2] = ['MNP',strain[1],'','']
|
|
|
196 straininfo[j]['mnps'] += 1
|
|
|
197 new_codons[j] = new_codon_calc(new_codons[j],strain[1],pos_in_cod)
|
|
7
|
198 elif strain[0] == 'Missing allele':
|
|
|
199 codon[i][j+2] = strain
|
|
4
|
200 else: codon[i][j+2] = ['']*4
|
|
|
201
|
|
|
202 for line in codon[1:-1]:
|
|
|
203 if line != '': write_output(line)
|
|
|
204
|
|
|
205 def feature_props(feature):
|
|
|
206 properties = {'type':feature.type,'strand':feature.location._strand,
|
|
|
207 'sequence':feature.extract(seq_record.seq),'pseudo': False,
|
|
|
208 'locus_tag':'','gene_name':'','product':'',
|
|
|
209 'start':int(feature.location._start.position),
|
|
|
210 'end':int(feature.location._end.position)}
|
|
|
211 if 'pseudo' in feature.qualifiers:
|
|
|
212 properties['pseudo'] = True
|
|
|
213 properties['type'] = 'pseudogene'
|
|
|
214 properties['pure_seq'] = properties['sequence']
|
|
|
215 if properties['strand'] == -1:
|
|
|
216 properties['sequence'] = seq_record.seq[feature.location._start.position:feature.location._end.position].reverse_complement()
|
|
|
217 else:
|
|
|
218 properties['sequence'] = seq_record.seq[feature.location._start.position:feature.location._end.position]
|
|
|
219 if feature.sub_features: properties['subfeats'] = feature.sub_features
|
|
|
220 if 'locus_tag' in feature.qualifiers: properties['locus_tag'] = feature.qualifiers['locus_tag'][0]
|
|
|
221 if 'gene' in feature.qualifiers: properties['gene_name']= feature.qualifiers['gene'][0]
|
|
|
222 if feature.type in ['tRNA','rRNA','CDS']: properties['product'] = feature.qualifiers['product'][0]
|
|
|
223
|
|
|
224 return properties
|
|
|
225
|
|
|
226 # Read embl/genbank file for information on sequence features;
|
|
|
227 try:
|
|
|
228 seq_record = SeqIO.parse(file_ref, filetype_reference).next()
|
|
|
229 except:
|
|
|
230 file_ref.close()
|
|
|
231 quit("Error reading "+sys.argv[2]+", please check file for errors.")
|
|
|
232 file_ref.close()
|
|
|
233
|
|
|
234 # Loop through genome features and save relevant properties;
|
|
|
235 feats = []# Dictionary of properties;
|
|
|
236
|
|
|
237 feature_types = {'intergenic':0,'gene':0,'pseudogene':0}
|
|
|
238 feat_temp_store = ''
|
|
|
239 for feature in seq_record.features:
|
|
|
240 # Check if gene is defined as other feature (e.g. CDS). Else, save info from 'gene';
|
|
|
241 if feat_temp_store != '':
|
|
|
242 if (feature.location._start.position == feat_temp_store.location._start.position and
|
|
|
243 feature.location._end.position == feat_temp_store.location._end.position):# Gene also defined as other feature;
|
|
|
244 feat_temp_store = ''
|
|
|
245 else:# Gene not also defined as CDS;
|
|
|
246 feats.append(feature_props(feat_temp_store))
|
|
|
247 feat_temp_store = ''
|
|
|
248 elif feature.type == 'gene':
|
|
|
249 feat_temp_store = feature
|
|
|
250
|
|
|
251 if not feature.type in ['source','gene','misc_feature']:
|
|
|
252 if not feature.type in feature_types and feature.type != 'CDS': feature_types[feature.type] = 0
|
|
|
253 feats.append(feature_props(feature))
|
|
|
254
|
|
|
255
|
|
|
256 feat_props = sorted(feats, key=lambda cells:int(cells['start']))
|
|
|
257 feat_boundaries = [{'start':item['start'],'end':item['end']} for item in feat_props]
|
|
|
258 regions = region_calc(feat_boundaries,len(seq_record.seq))
|
|
|
259 feat_overlap = overlap_calc(regions)
|
|
|
260
|
|
|
261 reference_loaded = time.clock()
|
|
|
262
|
|
|
263 # Create array of SNPs from input file for processing;
|
|
|
264 lines = [line.split('\t') for line in file_snps if line.strip()]
|
|
|
265 file_snps.close()
|
|
|
266 # First line contains headers, extract number of strains etc;
|
|
|
267 headers = lines[0]
|
|
|
268 snp_table = sorted(lines[1:], key=lambda cells:int(cells[0]))
|
|
|
269
|
|
|
270 snps_loaded = time.clock()
|
|
|
271
|
|
|
272 # Print output file headers;
|
|
|
273 headers[-1] = headers[-1].rstrip()# Remove newline character;
|
|
|
274 strain_nr = len(headers)-1
|
|
|
275 strains_found = 'Found '+str(strain_nr)+' strains: '+headers[1]+' (reference)'
|
|
|
276 first_line = '\t'+headers[1]+'\t'*9
|
|
|
277 second_line = 'Position\tFeature\tLocus tag\tGene\tProduct\tStart\tEnd\tStrand\tRef. base\tRef. codon\tRef. res.'
|
|
|
278 straininfo = [0]*(len(headers[2:]))
|
|
|
279 for i,strain in enumerate(headers[2:]):
|
|
|
280 straininfo[i] = {'snps':0,'mnps':0,'synonymous':0,'nonsynonymous':0,'nonstart':0,'nonstop':0,'nonsense':0}
|
|
|
281 straininfo[i].update(feature_types)
|
|
|
282 strains_found += ', '+strain
|
|
|
283 first_line += '\t\t'+strain+'\t'*3
|
|
|
284 second_line += '\t\tSNP type\tNew base\tNew codon\tNew res.'
|
|
|
285
|
|
|
286 file_out.write(first_line+'\n'+second_line)
|
|
|
287 file_out.flush()
|
|
|
288
|
|
|
289 # Loop through SNPs from array and process them;
|
|
|
290 props = {}# Properties of a feature;
|
|
|
291 prev_snp = ''# Position of previous SNP;
|
|
|
292 to_write = []# Information of current SNP;
|
|
7
|
293 allowed_chars = ['g','a','t','c','','-']
|
|
4
|
294 compl_bases = {'a':'t','t':'a','g':'c','c':'g'}
|
|
|
295 firstsnp = True# First snp of region, or of codon in cases of 3 positions in codon mutated;
|
|
|
296 prev_start=j=k=0
|
|
|
297 overlap_snps = []
|
|
|
298 codon = ['']*5# Array of codon positions. First item is position of first base of codon in the gene;
|
|
|
299
|
|
|
300 for region in regions:
|
|
|
301 firstsnp = True
|
|
|
302 i = prev_start
|
|
|
303 while i < len(snp_table):# Loop through SNPs
|
|
|
304 snp_entry = snp_table[i]
|
|
|
305 if not str(snp_entry[0]).isdigit():# Not a valid line, skip;
|
|
|
306 i += 1
|
|
|
307 continue
|
|
|
308
|
|
|
309 pos = int(snp_entry[0])-1
|
|
|
310 if pos < region[0]:# Not inside region yet;
|
|
|
311 i += 1
|
|
|
312 continue
|
|
|
313 elif firstsnp and pos < region[1]:
|
|
|
314 prev_start = i
|
|
|
315 elif pos >= region[1]:# End of region, process and next;
|
|
|
316 if not firstsnp and codon != ['','','','','']:
|
|
|
317 codon_process(codon)
|
|
|
318 break
|
|
|
319
|
|
|
320 # Documentation of SNPs in feature overlaps;
|
|
|
321 while j < len(feat_overlap)-1 and pos > feat_overlap[j][1]: j += 1
|
|
|
322 k = j
|
|
|
323 while k < len(feat_overlap) and pos >= feat_overlap[k][0]:
|
|
|
324 if pos < feat_overlap[k][1]:
|
|
|
325 if feat_overlap[k][4][0] == 0:
|
|
|
326 feat_overlap[k][4][0] = pos
|
|
|
327 feat_overlap[k][4][1] = pos
|
|
|
328 k += 1
|
|
|
329
|
|
|
330
|
|
|
331 snp_entry[-1] = snp_entry[-1].rstrip()# Remove newline character at end of line;
|
|
|
332
|
|
|
333 # Prevent crash upon encounter nonstandard base character;
|
|
7
|
334 if snp_entry[1].lower() not in allowed_chars:# Ref base
|
|
4
|
335 i += 1
|
|
|
336 continue
|
|
|
337 for m,base in enumerate(snp_entry[2:],2):
|
|
7
|
338 if base.lower() not in allowed_chars:
|
|
4
|
339 snp_entry[m] = ''
|
|
|
340 # Crash prevented
|
|
|
341
|
|
|
342 mnp=in_feat=False
|
|
|
343 snp_feat = region[2]
|
|
|
344 ref_base = snp_entry[1]
|
|
|
345
|
|
|
346 to_write = [[pos+1]]
|
|
|
347
|
|
|
348 # Output feature properties and reference situation;
|
|
|
349 if snp_feat == -1:
|
|
|
350 codon = ['']*5
|
|
|
351 to_write.append(['intergenic','','','','','','',ref_base.upper(),'',''])
|
|
|
352 elif feat_props[snp_feat]['type'] not in ['CDS','gene','pseudogene']:# In feature, but non-coding;
|
|
|
353 codon = ['']*5
|
|
|
354 props = feat_props[snp_feat]
|
|
|
355 if props['strand'] == -1: ref_base = (compl_bases[snp_entry[1].lower()])
|
|
|
356 else: ref_base = snp_entry[1]
|
|
|
357 to_write.append([props['type'],props['locus_tag'],props['gene_name'],
|
|
|
358 props['product'],props['start']+1,props['end'],
|
|
|
359 '',ref_base.upper(),'',''])
|
|
|
360 else:# in CDS/gene feature, check codon etc;
|
|
|
361 props = feat_props[snp_feat]
|
|
|
362 sequence = props['sequence']
|
|
|
363 if props['strand'] == -1:
|
|
|
364 pos_in_gene = props['end'] - pos - 1# Python counting
|
|
|
365 ref_base = (compl_bases[snp_entry[1].lower()])
|
|
|
366 else:
|
|
|
367 pos_in_gene = pos - props['start']# Python counting
|
|
|
368 ref_base = snp_entry[1]
|
|
|
369
|
|
|
370 in_feat = True
|
|
|
371 if props['pseudo'] and 'subfeats' in props:# Pseudogene that needs special attention;
|
|
|
372 in_feat = False
|
|
|
373 subfeat_boundaries = [{'start':item.location._start.position,'end':item.location._end.position}
|
|
|
374 for item in props['subfeats']]
|
|
|
375 snp_subfeat = match_feature(subfeat_boundaries,pos)
|
|
|
376 if snp_subfeat != -1:
|
|
|
377 in_feat = True
|
|
|
378 pos_in_gene -= non_coding_calc({'start':props['start'],'subfeats':props['subfeats'],
|
|
|
379 'pseudo':True,'strand':props['strand']},pos)
|
|
|
380 sequence = props['pure_seq']
|
|
|
381
|
|
|
382 if not in_feat:# In pseudogene non-coding region;
|
|
|
383 codon = ['']*5
|
|
|
384 to_write.append(['non coding',props['locus_tag'],props['gene_name'],props['product'],
|
|
|
385 props['start']+1,props['end'],props['strand'],ref_base.upper(),
|
|
|
386 '',''])
|
|
|
387 else:# In coding region;
|
|
|
388 pos_in_cod = (pos_in_gene+1)%3
|
|
|
389 if pos_in_cod == 0: pos_in_cod = 3# Remainder of division 0 means 3rd place in codon;
|
|
|
390
|
|
|
391 old_codon = sequence[pos_in_gene-pos_in_cod+1:pos_in_gene-pos_in_cod+4].upper()
|
|
|
392 old_residue = old_codon.translate(table=transl_table)
|
|
|
393 to_write.append([props['type'],props['locus_tag'],props['gene_name'],props['product'],
|
|
|
394 props['start']+1,props['end'],props['strand'],ref_base.upper(),
|
|
|
395 old_codon,old_residue])
|
|
|
396
|
|
|
397 if in_feat and not firstsnp and (pos >= prev_snp):# Check if snp is in same codon as previous snp. Position check for overlapping features;
|
|
|
398 if props['strand'] == 1 and (pos - prev_snp + 1) < pos_in_cod:# Same codon (Positive strand);
|
|
|
399 mnp = True
|
|
|
400 elif props['strand'] == -1 and (pos - prev_snp + 1) <= (3 - pos_in_cod):# Same codon (negative strand);
|
|
|
401 mnp = True
|
|
|
402
|
|
|
403 # Process previous codon if not MNP;
|
|
|
404 if in_feat and not mnp:
|
|
|
405 if not firstsnp:
|
|
|
406 codon_process(codon)
|
|
|
407 codon = [pos_in_gene-pos_in_cod+1,'','','',props['strand']]
|
|
|
408
|
|
|
409
|
|
|
410 for l, snp in enumerate(snp_entry[2:]):# Loop through SNPs/strains;
|
|
|
411
|
|
|
412 snp = snp.lower()
|
|
|
413 if snp == '':# Empty cell;
|
|
7
|
414 to_write.append(['']*4)
|
|
4
|
415 continue
|
|
|
416
|
|
|
417 if snp == '-': # Feature not present in this strain;
|
|
7
|
418 to_write.append(['Missing allele','','',''])
|
|
4
|
419 continue
|
|
|
420
|
|
|
421 if snp_feat == -1:# Intergenic;
|
|
|
422 if snp == ref_base.lower():
|
|
|
423 to_write.append(['']*4)
|
|
|
424 else:
|
|
|
425 to_write.append(['',snp,'',''])
|
|
|
426 straininfo[l]['intergenic'] += 1
|
|
|
427 straininfo[l]['snps'] += 1
|
|
|
428 continue
|
|
|
429
|
|
|
430 if props['strand'] == -1:
|
|
|
431 snp = compl_bases[snp]
|
|
|
432
|
|
|
433 if snp == ref_base.lower():
|
|
|
434 to_write.append(['']*4)
|
|
|
435 else:
|
|
|
436 to_write.append(['',snp,'',''])
|
|
|
437 straininfo[l]['snps'] += 1
|
|
|
438 if props['type'] != 'CDS':
|
|
|
439 straininfo[l][props['type']] += 1
|
|
|
440
|
|
|
441
|
|
|
442
|
|
|
443 if props['type'] in ['CDS','gene','pseudogene'] and in_feat:
|
|
|
444 codon[pos_in_cod] = to_write
|
|
|
445 else:
|
|
|
446 write_output(to_write)
|
|
|
447
|
|
|
448 if firstsnp: firstsnp = False
|
|
|
449 prev_snp = pos+1
|
|
|
450 i += 1
|
|
|
451
|
|
|
452
|
|
|
453 if codon != ['','','','','']: codon_process(codon)
|
|
|
454
|
|
|
455 file_out.close()
|
|
|
456
|
|
|
457 end = time.clock()
|
|
|
458
|
|
|
459 file_summary.write("\n")
|
|
|
460 file_summary.write(intro_message)
|
|
|
461 file_summary.write('\n'+strains_found+'.\n')
|
|
|
462
|
|
|
463 file_summary.write("\nFinished annotation. Total time: %s s\n\n" % round(end-start,1))
|
|
|
464
|
|
|
465
|
|
|
466 file_overlap.write('SNP start\tSNP end\tFeature 1\tLocus tag\tProduct\t\tFeature 2\tLocus tag\tProduct')
|
|
|
467 for overlap in feat_overlap:
|
|
|
468 if overlap[4] != [0,0]:
|
|
|
469 overlap[4][0]+=1
|
|
|
470 overlap[4][1]+=1
|
|
|
471 if overlap[4][0] == overlap[4][1]: overlap[4][1] = ''
|
|
|
472 write_output([[str(overlap[4][0])],[str(overlap[4][1]),feat_props[overlap[2]]['type'],feat_props[overlap[2]]['locus_tag'],feat_props[overlap[2]]['product']],
|
|
|
473 [feat_props[overlap[3]]['type'],feat_props[overlap[3]]['locus_tag'],feat_props[overlap[3]]['product']]],
|
|
|
474 file_overlap)
|
|
|
475
|
|
|
476
|
|
|
477 for i,strain in enumerate(headers[2:]):
|
|
|
478 file_summary.write("\n")
|
|
|
479 info = straininfo[i]
|
|
|
480 file_summary.write("+ Strain %s:\n" % strain)
|
|
|
481 file_summary.write(" %s SNPs found\n" % info['snps'])
|
|
|
482 file_summary.write(" Number of SNPs found CDS features: %s\n" % (info['mnps']+info['nonstart']+info['nonstop']+info['nonsense']+
|
|
|
483 info['synonymous']+info['nonsynonymous']))
|
|
|
484 file_summary.write(" (of which in pseudogenes: %s)\n" % info['pseudogene'])
|
|
|
485 file_summary.write(" - MNPs: %s\n" % info['mnps'])
|
|
|
486 file_summary.write(" - Synonymous: %s\n" % info['synonymous'])
|
|
|
487 file_summary.write(" - Nonsynonymous: %s\n" % info['nonsynonymous'])
|
|
|
488 file_summary.write(" - Nonsense: %s\n" % info['nonsense'])
|
|
|
489 file_summary.write(" - Nonstart: %s\n" % info['nonstart'])
|
|
|
490 file_summary.write(" - Nonstop: %s\n" % info['nonstop'])
|
|
|
491 file_summary.write(" Intergenic: %s\n" % info['intergenic'])
|
|
|
492
|
|
|
493 for typ in feature_types:
|
|
|
494 if typ not in ['intergenic','pseudogene'] and info[typ] != 0:
|
|
|
495 file_summary.write(" %s: %s\n" % (typ,info[typ]))
|
|
|
496 file_summary.flush()
|
|
|
497
|
|
|
498 file_overlap.close()
|
|
|
499 file_summary.close()
|
