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
|
Description: Use 2to3 to port to Python3
Bug-Debian: https://bugs.debian.org/938565
Author: Andreas Tille <tille@debian.org>
Last-Update: Wed, 04 Sep 2019 16:44:45 +0200
--- a/tools/TQS.py
+++ b/tools/TQS.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
__doc__ = """
TQS
@@ -53,18 +53,18 @@ def main():
f = open(opts.seqfile)
seq = f.readlines()
f.close()
- except Exception, e:
- print "ERROR: Could not read from %s: %s" % (opts.seqfile, e)
- print usage % (sys.argv[0:])
+ except Exception as e:
+ print("ERROR: Could not read from %s: %s" % (opts.seqfile, e))
+ print(usage % (sys.argv[0:]))
sys.exit()
try:
f = open(opts.qualfile)
qual = f.readlines()
f.close()
- except Exception, e:
- print "ERROR: Could not read from %s: %s" % (opts.qualfile, e)
- print usage % (sys.argv[0:])
+ except Exception as e:
+ print("ERROR: Could not read from %s: %s" % (opts.qualfile, e))
+ print(usage % (sys.argv[0:]))
sys.exit()
@@ -75,22 +75,22 @@ def main():
try:
FASTA = open(fasta, 'w')
except:
- print "ERROR: Can not write to %s" % fasta
+ print("ERROR: Can not write to %s" % fasta)
sys.exit()
try:
LOG = open(log, 'w')
except:
- print "ERROR: Can not write to %s" % log
+ print("ERROR: Can not write to %s" % log)
sys.exit()
if opts.mer < 15 or opts.mer > 200:
- print "ERROR: -l must be a number between 15 and 200."
+ print("ERROR: -l must be a number between 15 and 200.")
sys.exit()
if opts.consec < 16 or opts.consec > opts.mer:
- print "ERROR: -c must be a number between 16 and -l."
+ print("ERROR: -c must be a number between 16 and -l.")
sys.exit()
LOG.write("""
@@ -130,7 +130,7 @@ def parseQualFile(threshold, difference,
read_number = 0
if verbose:
- print "Printing trimming pattern for all reads passing the set threshold values...\n"
+ print("Printing trimming pattern for all reads passing the set threshold values...\n")
for line in qual:
read_number += 1 ### this keeps track of the read order, respected between the prb and seq files
@@ -156,7 +156,7 @@ def parseQualFile(threshold, difference,
if head_match != None:
ok_read += 1
col = head_match.span()
- if not trim_info.has_key(read_number):
+ if read_number not in trim_info:
trim_info[read_number] = {}
start = int(col[0])
@@ -167,7 +167,7 @@ def parseQualFile(threshold, difference,
if verbose:
sub = concat[trim_info[read_number]['start']:trim_info[read_number]['end']]
- print "passed seqs:%i line#%i %s (start trim:%i,length:%i) %s\n" % (ok_read, read_number, concat, start, end, sub)
+ print("passed seqs:%i line#%i %s (start trim:%i,length:%i) %s\n" % (ok_read, read_number, concat, start, end, sub))
LOG.write("%i out of %i sequences passed your filter (I >= %i and D >= %i and L >= %i)\n" % (ok_read, read_number, threshold, difference, consecutive))
@@ -191,7 +191,7 @@ def readNTrim(trim_info, seq, verbose, F
gDNAlinker2_field = re.compile('^ATCTAACAG')
if verbose:
- print "Printing trimmed sequences for all reads passing the set threshold values minus, excluding sequence containing linkers...\n"
+ print("Printing trimmed sequences for all reads passing the set threshold values minus, excluding sequence containing linkers...\n")
for line in seq:
read_number += 1 ### tracks read number / will match order in prb file
@@ -199,7 +199,7 @@ def readNTrim(trim_info, seq, verbose, F
info = line.split("\t") ### split line, the seq file lists: lane tile xcoord y coord DNAseq
dna_string = info[4]
- if trim_info.has_key(read_number):
+ if read_number in trim_info:
trim_seq = dna_string[trim_info[read_number]['start']:trim_info[read_number]['end']]
if re.match(dna_sequence_field, trim_seq): ### no ambiguous bases?
if re.match(gDNAlinker1_field, trim_seq) or re.match(gDNAlinker2_field,trim_seq): ### matches gDNA linker?
@@ -208,7 +208,7 @@ def readNTrim(trim_info, seq, verbose, F
usable_reads += 1
FASTA.write(">%s-%s-%s-%s\n%s\n" % (info[0],info[1],info[2],info[3],trim_seq))
if verbose:
- print "line#%i %s (start trim:%i,length:%i) %s" % (read_number,info[4],trim_info[read_number]['start'],trim_info[read_number]['end'],trim_seq)
+ print("line#%i %s (start trim:%i,length:%i) %s" % (read_number,info[4],trim_info[read_number]['start'],trim_info[read_number]['end'],trim_seq))
LOG.write("%i out of %i sequences appear to be usable, after filtering out sequences hard-coded in this program * %i gDNA linker sequences*\n" % (usable_reads, read_number,gDNAlinker_count))
return
--- a/tools/TQS.readme
+++ b/tools/TQS.readme
@@ -24,12 +24,12 @@ __version__ = '1.0'
Execution example
==================
-python TQS.py -f test_seq.txt -q test_prb.txt -l 36 -t 5 -d 5 -c 20
+python3 TQS.py -f test_seq.txt -q test_prb.txt -l 36 -t 5 -d 5 -c 20
Options
=======
-python TQS.py --help
+python3 TQS.py --help
Usage: TQS.py [options]
--- a/tools/TQSexport.py
+++ b/tools/TQSexport.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
__doc__ = """
TQS
@@ -47,9 +47,9 @@ def main():
f = open(opts.exportfile)
seq = f.readlines()
f.close()
- except Exception, e:
- print "ERROR: Could not read from %s: %s" % (opts.exportfile, e)
- print usage % (sys.argv[0:])
+ except Exception as e:
+ print("ERROR: Could not read from %s: %s" % (opts.exportfile, e))
+ print(usage % (sys.argv[0:]))
sys.exit()
@@ -61,17 +61,17 @@ def main():
try:
FASTA = open(fasta, 'w')
except:
- print "ERROR: Can not write to %s" % fasta
+ print("ERROR: Can not write to %s" % fasta)
sys.exit()
try:
LOG = open(log, 'w')
except:
- print "ERROR: Can not write to %s" % log
+ print("ERROR: Can not write to %s" % log)
sys.exit()
if opts.consec < minimum_length:
- print "ERROR: -c must be a number larger than %i." % (minimum_length)
+ print("ERROR: -c must be a number larger than %i." % (minimum_length))
sys.exit()
LOG.write("""
@@ -106,7 +106,7 @@ YYYYRYYYYYYYYYYYTTTTTOOOMOOOMMOOOOOG chr
read_number = 0
if verbose:
- print "Printing trimming pattern for all reads passing the set threshold values...\n"
+ print("Printing trimming pattern for all reads passing the set threshold values...\n")
for line in export:
read_number += 1
@@ -134,7 +134,7 @@ YYYYRYYYYYYYYYYYTTTTTOOOMOOOMMOOOOOG chr
if head_match != None:
ok_read += 1
col = head_match.span()
- if not trim_info.has_key(read_number):
+ if read_number not in trim_info:
trim_info[read_number] = {}
start = int(col[0])
@@ -150,7 +150,7 @@ YYYYRYYYYYYYYYYYTTTTTOOOMOOOMMOOOOOG chr
FASTA.write(">%s-%s-%s-%s%s\n%s\n" % (info[1],info[2],info[3],info[4],pair,trim_seq))
if verbose:
- print "passed seqs:%i line#%i %s (start trim:%i,end trim:%i) %s\n" % (ok_read, read_number, concat, start, end, trim_seq)
+ print("passed seqs:%i line#%i %s (start trim:%i,end trim:%i) %s\n" % (ok_read, read_number, concat, start, end, trim_seq))
LOG.write("%i out of %i sequences passed your filter (-t >= %i and -c >= %i)\n" % (ok_read, read_number, threshold, consecutive))
--- a/tools/TQSfastq.py
+++ b/tools/TQSfastq.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
__doc__ = """
TQS
@@ -52,9 +52,9 @@ def main():
f = open(opts.fastqfile)
seq = f.readlines()
f.close()
- except Exception, e:
- print "ERROR: Could not read from %s: %s" % (opts.fastqfile, e)
- print usage % (sys.argv[0:])
+ except Exception as e:
+ print("ERROR: Could not read from %s: %s" % (opts.fastqfile, e))
+ print(usage % (sys.argv[0:]))
sys.exit()
@@ -66,21 +66,21 @@ def main():
try:
FASTA = open(fasta, 'w')
except:
- print "ERROR: Can not write to %s" % fasta
+ print("ERROR: Can not write to %s" % fasta)
sys.exit()
try:
LOG = open(log, 'w')
except:
- print "ERROR: Can not write to %s" % log
+ print("ERROR: Can not write to %s" % log)
sys.exit()
if opts.consec < minimum_length:
- print "ERROR: -c must be a number larger than %i." % (minimum_length)
+ print("ERROR: -c must be a number larger than %i." % (minimum_length))
sys.exit()
if opts.encoding != 33 and opts.encoding != 64:
- print "ERROR: -e must be either 33 or 64."
+ print("ERROR: -e must be either 33 or 64.")
sys.exit()
LOG.write("""
@@ -114,7 +114,7 @@ def readNtrim(fastq, threshold, consecut
record_line = 0
if verbose:
- print "Printing trimming pattern for all reads passing the set threshold values...\n"
+ print("Printing trimming pattern for all reads passing the set threshold values...\n")
for line in fastq:
record_line += 1
@@ -150,7 +150,7 @@ def readNtrim(fastq, threshold, consecut
if head_match != None:
ok_read += 1
col = head_match.span()
- if not trim_info.has_key(read_number):
+ if read_number not in trim_info:
trim_info[read_number] = {}
start = int(col[0])
@@ -160,7 +160,7 @@ def readNtrim(fastq, threshold, consecut
FASTA.write(">%s\n%s\n" % (read_id, trim_seq))
if verbose:
- print "%s\n%s\n%s\n passed seqs:%i line#%i %s (start trim:%i,end trim:%i) %s\n" % (read_id,seq,qual,ok_read, read_number, concat, start, end, trim_seq)
+ print("%s\n%s\n%s\n passed seqs:%i line#%i %s (start trim:%i,end trim:%i) %s\n" % (read_id,seq,qual,ok_read, read_number, concat, start, end, trim_seq))
LOG.write("%i out of %i sequences passed your filter (-t >= %i and -c >= %i)\n" % (ok_read, read_number, threshold, consecutive))
|
