1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
|
#!/usr/bin/python3
import sys, os
import string, re
use_message = '''
'''
def extract_pair(RNA):
read_dic = {}
pair_reported = set()
out_file = open("sim_paired.sam", "w")
hits_file = open("sim.sam")
for line in hits_file:
if line.startswith('@'):
continue
fields = line[:-1].split()
read_id, flag, chr1, pos1, mapQ, cigar1, chr2, pos2 = fields[:8]
flag = int(flag)
assert flag & 0x4 == 0
pos1, pos2 = int(pos1), int(pos2)
TI, NM1, Zs1 = "", "", ""
for field in fields[11:]:
if field.startswith("TI"):
TI = "\t" + field
elif field.startswith("NM"):
NM1 = "\t" + field
elif field.startswith("Zs"):
Zs1 = "\t" + field
assert NM1 != ""
assert chr1 == chr2
me = "%s\t%s\t%d" % (read_id, chr1, pos1)
partner = "%s\t%s\t%d" % (read_id, chr2, pos2)
if partner in read_dic:
maps = read_dic[partner]
for map in maps:
if map[0] == me:
cigar2, NM2, Zs2 = map[1:4]
if int(pos2) > int(pos1):
p_str = "%s\t%s\t%d\t%s\t%s\t%d\t%s%s%s%s%s%s" % \
(read_id, chr1, pos1, cigar1, chr2, pos2, cigar2, TI, NM1, NM2, Zs1, Zs2)
else:
p_str = "%s\t%s\t%d\t%s\t%s\t%d\t%s%s%s%s%s%s" % \
(read_id, chr2, pos2, cigar2, chr1, pos1, cigar1, TI, NM2, NM1, Zs2, Zs1)
if p_str not in pair_reported:
pair_reported.add(p_str)
print(p_str, file=out_file)
if not me in read_dic:
read_dic[me] = []
read_dic[me].append([partner, cigar1, NM1, Zs1])
hits_file.close()
out_file.close()
def init_reads(read_dir, RNA):
sim1_file = open("sim_1.sam", 'w')
sim2_file = open("sim_2.sam", 'w')
for line in open("sim.sam"):
if line.startswith('@'):
continue
fields = line[:-1].split('\t')
read_id, flag, chr, pos, _, cigar = fields[:6]
left_read = int(flag) < 128
NM, TI, Zs = "", "", ""
for field in fields:
if field.startswith("NM"):
NM = "\t" + field
elif field.startswith("TI"):
TI = "\t" + field
elif field.startswith("Zs"):
Zs = "\t" + field
print("%s\t%s\t%s\t%s%s%s%s" % (read_id, chr, pos, cigar, TI, NM, Zs), file=(sim1_file if left_read else sim2_file))
sim1_file.close()
sim2_file.close()
extract_pair(RNA)
def to_junction_str(junction):
return "%s-%d-%d" % (junction[0], junction[1], junction[2])
def to_junction(junction_str):
fields = junction_str.split("-")
if len(fields) > 3:
chr, left, right = "-".join(fields[:-2]), fields[-2], fields[-1]
else:
assert len(fields) == 3
chr, left, right = fields
return [chr, int(left), int(right)]
def junction_cmp(a, b):
if a[0] != b[0]:
if a[0] < b[0]:
return -1
else:
return 1
if a[1] != b[1]:
if a[1] < b[1]:
return -1
else:
return 1
if a[2] != b[2]:
if a[2] < b[2]:
return -1
else:
return 1
return 0
def classify_reads(RNA):
if RNA:
readtypes = ["all", "M", "2M_gt_15", "2M_8_15", "2M_1_7", "gt_2M"]
else:
readtypes = ["all" ,"M"]
readtype_order = {}
for i in range(len(readtypes)):
readtype = readtypes[i]
assert readtype not in readtype_order
readtype_order[readtype] = i
for paired in [False, True]:
for readtype in readtypes:
if paired:
base_fname = "sim_paired"
type_sam_fname = base_fname + "_" + readtype + ".sam"
type_read1_fname = base_fname + "_1_" + readtype + ".fa"
type_read2_fname = base_fname + "_2_" + readtype + ".fa"
type_junction_fname = base_fname + "_" + readtype + ".junc"
else:
base_fname = "sim_single"
type_sam_fname = base_fname + "_" + readtype + ".sam"
type_read1_fname = base_fname + "_" + readtype + ".fa"
type_read2_fname = ""
type_junction_fname = base_fname + "_" + readtype + ".junc"
if os.path.exists(type_sam_fname) and \
os.path.exists(type_junction_fname):
continue
read_ids = set()
junctions = []
type_sam_file = open(type_sam_fname, "w")
if paired:
sam_file = open("sim_paired.sam")
else:
sam_file = open("sim_1.sam")
cigar_re = re.compile('\d+\w')
def get_read_type(cigar):
cigars = cigar_re.findall(cigar)
def get_cigar_chars_MN(cigars):
cigars = cigar_re.findall(cigars)
cigar_chars = ""
for cigar in cigars:
cigar_op = cigar[-1]
if cigar_op in "MN":
if cigar_chars == "" or cigar_chars[-1] != cigar_op:
cigar_chars += cigar_op
return cigar_chars
cigar_str = get_cigar_chars_MN(cigar)
if cigar_str == "M":
return cigar_str
elif cigar_str == "MNM":
assert len(cigars) >= 3
left_anchor = 0
for ci in range(len(cigars)):
c = cigars[ci][-1]
c_len = int(cigars[ci][:-1])
if c in "MI":
left_anchor += c_len
else:
break
assert left_anchor > 0
right_anchor = 0
for ci in reversed(list(range(len(cigars)))):
c = cigars[ci][-1]
c_len = int(cigars[ci][:-1])
if c in "MI":
right_anchor += c_len
else:
break
assert right_anchor > 0
min_anchor = min(left_anchor, right_anchor)
if min_anchor > 15:
return "2M_gt_15"
elif min_anchor >= 8 and min_anchor <= 15:
return "2M_8_15"
elif min_anchor >= 1 and min_anchor <= 7:
return "2M_1_7"
else:
assert False
else:
assert cigar_str not in ["M", "MNM"]
return "gt_2M"
# chr and pos are assumed to be integers
def get_junctions(chr, pos, cigar_str):
junctions = []
right_pos = pos
cigars = cigar_re.findall(cigar_str)
cigars = [[int(cigars[i][:-1]), cigars[i][-1]] for i in range(len(cigars))]
for i in range(len(cigars)):
length, cigar_op = cigars[i]
if cigar_op == "N":
left, right = right_pos - 1, right_pos + length
if i > 0 and cigars[i-1][1] in "ID":
if cigars[i-1][1] == "I":
left += cigars[i-1][0]
else:
left -= cigars[i-1][0]
if i + 1 < len(cigars) and cigars[i+1][1] in "ID":
if cigars[i+1][1] == "I":
right -= cigars[i+1][0]
else:
right += cigars[i+1][0]
junctions.append([chr, left, right])
if cigar_op in "MND":
right_pos += length
return junctions
for line in sam_file:
fields = line[:-1].split()
if paired:
read_id, chr, pos, cigar, chr2, pos2, cigar2 = fields[:7]
else:
read_id, chr, pos, cigar = fields[:4]
read_id = int(read_id)
readtype2 = get_read_type(cigar)
if paired:
readtype3 = get_read_type(cigar2)
assert readtype2 in readtype_order
assert readtype3 in readtype_order
if readtype_order[readtype2] < readtype_order[readtype3]:
readtype2 = readtype3
if readtype == "all" or readtype == readtype2:
read_ids.add(read_id)
print(line[:-1], file=type_sam_file)
junctions += get_junctions(chr, int(pos), cigar)
if paired:
junctions += get_junctions(chr2, int(pos2), cigar2)
sam_file.close()
type_sam_file.close()
# make this set non-redundant
junction_set = set()
for junction in junctions:
junction_set.add(to_junction_str(junction))
junctions = []
for junction_str in junction_set:
junctions.append(to_junction(junction_str))
# sort the list of junctions
junctions = sorted(junctions, cmp=junction_cmp)
# write the junctions into a file
type_junction_file = open(type_junction_fname, "w")
for junction in junctions:
print("%s\t%d\t%d" % (junction[0], junction[1], junction[2]), file=type_junction_file)
type_junction_file.close()
def write_reads(read_fname, type_read_fname):
type_read_file = open(type_read_fname, "w")
read_file = open(read_fname)
write = False
for line in read_file:
if line[0] == ">":
read_id = int(line[1:-1])
write = read_id in read_ids
if write:
print(line[:-1], file=type_read_file)
read_file.close()
type_read_file.close()
if paired:
write_reads("sim_1.fa", type_read1_fname)
write_reads("sim_2.fa", type_read2_fname)
else:
write_reads("sim_1.fa", type_read1_fname)
def init():
read_dir_base = "../reads/simulation/"
read_dirs = os.listdir(read_dir_base)
for read_dir in read_dirs:
if os.path.exists(read_dir):
continue
if not os.path.exists(read_dir_base + read_dir + "/sim.sam") or \
not os.path.exists(read_dir_base + read_dir + "/sim_1.fa") or \
not os.path.exists(read_dir_base + read_dir + "/sim_2.fa"):
continue
print("Processing", read_dir, "...", file=sys.stderr)
os.mkdir(read_dir)
os.chdir(read_dir)
os.system("ln -s ../%s%s/* ." % (read_dir_base, read_dir))
os.system("ln -s sim_1.fa 1.fa")
os.system("ln -s sim_2.fa 2.fa")
RNA = (read_dir.find("RNA") != -1)
init_reads(read_dir, RNA)
classify_reads(RNA)
os.system("ln -s ../calculate_read_cost.py .")
os.chdir("..")
if __name__ == "__main__":
init()
|
