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
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
|
Description: Use 2to3 to port to Python3
Bug-Debian: https://bugs.debian.org/936281
Author: Andreas Tille <tille@debian.org>
Last-Update: Tue, 10 Sep 2019 08:02:24 +0200
--- a/Makefile
+++ b/Makefile
@@ -364,11 +364,11 @@ centrifuge.bat:
centrifuge-build.bat:
echo "@echo off" > centrifuge-build.bat
- echo "python %~dp0/centrifuge-build %*" >> centrifuge-build.bat
+ echo "python3 %~dp0/centrifuge-build %*" >> centrifuge-build.bat
centrifuge-inspect.bat:
echo "@echo off" > centrifuge-inspect.bat
- echo "python %~dp0/centrifuge-inspect %*" >> centrifuge-inspect.bat
+ echo "python3 %~dp0/centrifuge-inspect %*" >> centrifuge-inspect.bat
.PHONY: centrifuge-src
--- a/centrifuge-build
+++ b/centrifuge-build
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
"""
Copyright 2014, Daehwan Kim <infphilo@gmail.com>
--- a/centrifuge-inspect
+++ b/centrifuge-inspect
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
"""
Copyright 2014, Daehwan Kim <infphilo@gmail.com>
--- a/evaluation/centrifuge_evaluate.py
+++ b/evaluation/centrifuge_evaluate.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
import sys, os, subprocess, inspect
import platform, multiprocessing
@@ -25,7 +25,7 @@ def read_taxonomy_tree(tax_file):
"""
def compare_scm(centrifuge_out, true_out, taxonomy_tree, rank):
ancestors = set()
- for tax_id in taxonomy_tree.keys():
+ for tax_id in list(taxonomy_tree.keys()):
if tax_id in ancestors:
continue
while True:
@@ -106,7 +106,7 @@ def compare_scm(centrifuge_out, true_out
unclassified += 1
raw_unique_classified = 0
- for value in db_dic.values():
+ for value in list(db_dic.values()):
if len(value) == 1:
raw_unique_classified += 1
return classified, unique_classified, unclassified, len(db_dic), raw_unique_classified
@@ -152,7 +152,7 @@ def compare_abundance(centrifuge_out, tr
if tax_id in db_dic:
SSR += (abundance - db_dic[tax_id]) ** 2;
if debug:
- print >> sys.stderr, "\t\t\t\t{:<10}: {:.6} vs. {:.6} (truth vs. centrifuge)".format(tax_id, abundance, db_dic[tax_id])
+ print("\t\t\t\t{:<10}: {:.6} vs. {:.6} (truth vs. centrifuge)".format(tax_id, abundance, db_dic[tax_id]), file=sys.stderr)
else:
SSR += (abundance) ** 2
@@ -179,7 +179,7 @@ def sql_execute(sql_db, sql_query):
"""
def create_sql_db(sql_db):
if os.path.exists(sql_db):
- print >> sys.stderr, sql_db, "already exists!"
+ print(sql_db, "already exists!", file=sys.stderr)
return
columns = [
@@ -316,7 +316,7 @@ def evaluate(index_base,
os.mkdir(index_path)
index_fnames = ["%s/%s.%d.cf" % (index_path, index_base, i+1) for i in range(3)]
if not check_files(index_fnames):
- print >> sys.stderr, "Downloading indexes: %s" % ("index")
+ print("Downloading indexes: %s" % ("index"), file=sys.stderr)
os.system("cd %s; wget ftp://ftp.ccb.jhu.edu/pub/infphilo/centrifuge/data/%s.tar.gz; tar xvzf %s.tar.gz; rm %s.tar.gz; ln -s %s/%s* .; cd -" % \
(index_path, index_base, index_base, index_base, index_base, index_base))
assert check_files(index_fnames)
@@ -356,7 +356,7 @@ def evaluate(index_base,
scm_fname = "%s/%s.scm" % (read_path, read_base)
read_fnames = [read1_fname, read2_fname, truth_fname, scm_fname]
if not check_files(read_fnames):
- print >> sys.stderr, "Simulating reads %s_1.fq %s_2.fq ..." % (read_base, read_base)
+ print("Simulating reads %s_1.fq %s_2.fq ..." % (read_base, read_base), file=sys.stderr)
centrifuge_simulate = os.path.join(path_base, "centrifuge_simulate_reads.py")
simulate_cmd = [centrifuge_simulate,
"--num-fragment", str(num_fragment)]
@@ -377,11 +377,11 @@ def evaluate(index_base,
else:
base_fname = read_base + "_single"
- print >> sys.stderr, "Database: %s" % (index_base)
+ print("Database: %s" % (index_base), file=sys.stderr)
if paired:
- print >> sys.stderr, "\t%d million pairs" % (num_fragment / 1000000)
+ print("\t%d million pairs" % (num_fragment / 1000000), file=sys.stderr)
else:
- print >> sys.stderr, "\t%d million reads" % (num_fragment / 1000000)
+ print("\t%d million reads" % (num_fragment / 1000000), file=sys.stderr)
program_bin_base = "%s/.." % path_base
def get_program_version(program, version):
@@ -428,7 +428,7 @@ def evaluate(index_base,
if version:
program_name += ("_%s" % version)
- print >> sys.stderr, "\t%s\t%s" % (program_name, str(datetime.now()))
+ print("\t%s\t%s" % (program_name, str(datetime.now())), file=sys.stderr)
if paired:
program_dir = program_name + "_paired"
else:
@@ -449,7 +449,7 @@ def evaluate(index_base,
program_cmd = get_program_cmd(program, version, read1_fname, read2_fname, out_fname)
start_time = datetime.now()
if verbose:
- print >> sys.stderr, "\t", start_time, " ".join(program_cmd)
+ print("\t", start_time, " ".join(program_cmd), file=sys.stderr)
if program in ["centrifuge"]:
proc = subprocess.Popen(program_cmd, stdout=open(out_fname, "w"), stderr=subprocess.PIPE)
else:
@@ -462,7 +462,7 @@ def evaluate(index_base,
if duration < 0.1:
duration = 0.1
if verbose:
- print >> sys.stderr, "\t", finish_time, "finished:", duration
+ print("\t", finish_time, "finished:", duration, file=sys.stderr)
results = {"strain" : [0, 0, 0],
"species" : [0, 0, 0],
@@ -484,21 +484,21 @@ def evaluate(index_base,
# if rank == "strain":
# assert num_cases == num_fragment
- print >> sys.stderr, "\t\t%s" % rank
- print >> sys.stderr, "\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(classified, num_cases, float(classified) / num_cases)
- print >> sys.stderr, "\t\t\tprecision : {:,} / {:,} ({:.2%})".format(classified, raw_classified, float(classified) / raw_classified)
- print >> sys.stderr, "\n\t\t\tfor uniquely classified ",
+ print("\t\t%s" % rank, file=sys.stderr)
+ print("\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(classified, num_cases, float(classified) / num_cases), file=sys.stderr)
+ print("\t\t\tprecision : {:,} / {:,} ({:.2%})".format(classified, raw_classified, float(classified) / raw_classified), file=sys.stderr)
+ print("\n\t\t\tfor uniquely classified ", end=' ', file=sys.stderr)
if paired:
- print >> sys.stderr, "pairs"
+ print("pairs", file=sys.stderr)
else:
- print >> sys.stderr, "reads"
- print >> sys.stderr, "\t\t\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(unique_classified, num_cases, float(unique_classified) / num_cases)
- print >> sys.stderr, "\t\t\t\t\tprecision : {:,} / {:,} ({:.2%})".format(unique_classified, raw_unique_classified, float(unique_classified) / raw_unique_classified)
+ print("reads", file=sys.stderr)
+ print("\t\t\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(unique_classified, num_cases, float(unique_classified) / num_cases), file=sys.stderr)
+ print("\t\t\t\t\tprecision : {:,} / {:,} ({:.2%})".format(unique_classified, raw_unique_classified, float(unique_classified) / raw_unique_classified), file=sys.stderr)
# Calculate sum of squared residuals in abundance
if rank == "strain":
abundance_SSR = compare_abundance("centrifuge_report.tsv", truth_fname, taxonomy_tree, debug)
- print >> sys.stderr, "\t\t\tsum of squared residuals in abundance: {}".format(abundance_SSR)
+ print("\t\t\tsum of squared residuals in abundance: {}".format(abundance_SSR), file=sys.stderr)
if runtime_only:
os.chdir("..")
--- a/evaluation/centrifuge_simulate_reads.py
+++ b/evaluation/centrifuge_simulate_reads.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
#
# Copyright 2015, Daehwan Kim <infphilo@gmail.com>
@@ -156,7 +156,7 @@ def read_transcript(genomes_seq, gtf_fil
transcripts[transcript_id][2].append([left, right])
# Sort exons and merge where separating introns are <=5 bps
- for tran, [chr, strand, exons] in transcripts.items():
+ for tran, [chr, strand, exons] in list(transcripts.items()):
exons.sort()
tmp_exons = [exons[0]]
for i in range(1, len(exons)):
@@ -167,7 +167,7 @@ def read_transcript(genomes_seq, gtf_fil
transcripts[tran] = [chr, strand, tmp_exons]
tmp_transcripts = {}
- for tran, [chr, strand, exons] in transcripts.items():
+ for tran, [chr, strand, exons] in list(transcripts.items()):
exon_lens = [e[1] - e[0] + 1 for e in exons]
transcript_len = sum(exon_lens)
if transcript_len >= frag_len:
@@ -444,8 +444,8 @@ def getSamAlignment(dna, exons, genome_s
MD += ("{}".format(MD_match_len))
if len(read_seq) != read_len:
- print >> sys.stderr, "read length differs:", len(read_seq), "vs.", read_len
- print >> sys.stderr, pos, "".join(cigars), cigar_descs, MD, XM, NM, Zs
+ print("read length differs:", len(read_seq), "vs.", read_len, file=sys.stderr)
+ print(pos, "".join(cigars), cigar_descs, MD, XM, NM, Zs, file=sys.stderr)
assert False
return pos, cigars, cigar_descs, MD, XM, NM, Zs, read_seq
@@ -575,8 +575,8 @@ def samRepOk(genome_seq, read_seq, chr,
tMD += ("{}".format(match_len))
if tMD != MD or tXM != XM or tNM != NM or XM > max_mismatch or XM != NM:
- print >> sys.stderr, chr, pos, cigar, MD, XM, NM, Zs
- print >> sys.stderr, tMD, tXM, tNM
+ print(chr, pos, cigar, MD, XM, NM, Zs, file=sys.stderr)
+ print(tMD, tXM, tNM, file=sys.stderr)
assert False
@@ -631,7 +631,7 @@ def simulate_reads(index_fname, base_fna
# Read genome sequences into memory
genomes_fname = index_fname + ".fa"
if not os.path.exists(genomes_fname):
- print >> sys.stderr, "Extracting genomes from Centrifuge index to %s, which may take a few hours ..." % (genomes_fname)
+ print("Extracting genomes from Centrifuge index to %s, which may take a few hours ..." % (genomes_fname), file=sys.stderr)
extract_cmd = [centrifuge_inspect,
index_fname]
extract_proc = subprocess.Popen(extract_cmd, stdout=open(genomes_fname, 'w'))
@@ -660,15 +660,15 @@ def simulate_reads(index_fname, base_fna
assert num_frag == sum(expr_profile)
if dna:
- genome_ids = genome_seqs.keys()
+ genome_ids = list(genome_seqs.keys())
else:
- transcript_ids = transcripts.keys()
+ transcript_ids = list(transcripts.keys())
random.shuffle(transcript_ids)
assert len(transcript_ids) >= len(expr_profile)
# Truth table
truth_file = open(base_fname + ".truth", "w")
- print >> truth_file, "taxID\tgenomeLen\tnumReads\tabundance\tname"
+ print("taxID\tgenomeLen\tnumReads\tabundance\tname", file=truth_file)
truth_list = []
normalized_sum = 0.0
debug_num_frag = 0
@@ -695,19 +695,19 @@ def simulate_reads(index_fname, base_fna
if can_tax_id in names:
name = names[can_tax_id]
abundance = raw_abundance / genome_len / normalized_sum
- print >> truth_file, "{}\t{}\t{}\t{:.6}\t{}".format(tax_id, genome_len, t_num_frags, abundance, name)
+ print("{}\t{}\t{}\t{:.6}\t{}".format(tax_id, genome_len, t_num_frags, abundance, name), file=truth_file)
truth_file.close()
# Sequence Classification Map (SCM) - something I made up ;-)
scm_file = open(base_fname + ".scm", "w")
# Write SCM header
- print >> scm_file, "@HD\tVN:1.0\tSO:unsorted"
- for tax_id in genome_seqs.keys():
+ print("@HD\tVN:1.0\tSO:unsorted", file=scm_file)
+ for tax_id in list(genome_seqs.keys()):
name = ""
if tax_id in names:
name = names[tax_id]
- print >> scm_file, "@SQ\tTID:%s\tSN:%s\tLN:%d" % (tax_id, name, len(genome_seqs[tax_id]))
+ print("@SQ\tTID:%s\tSN:%s\tLN:%d" % (tax_id, name, len(genome_seqs[tax_id])), file=scm_file)
read_file = open(base_fname + "_1.fa", "w")
if paired_end:
@@ -718,11 +718,11 @@ def simulate_reads(index_fname, base_fna
t_num_frags = expr_profile[t]
if dna:
tax_id = genome_ids[t]
- print >> sys.stderr, "TaxID: %s, num fragments: %d" % (tax_id, t_num_frags)
+ print("TaxID: %s, num fragments: %d" % (tax_id, t_num_frags), file=sys.stderr)
else:
transcript_id = transcript_ids[t]
chr, strand, transcript_len, exons = transcripts[transcript_id]
- print >> sys.stderr, transcript_id, t_num_frags
+ print(transcript_id, t_num_frags, file=sys.stderr)
genome_seq = genome_seqs[tax_id]
genome_len = len(genome_seq)
@@ -763,14 +763,14 @@ def simulate_reads(index_fname, base_fna
XS = "\tXS:A:{}".format(strand)
TI = "\tTI:Z:{}".format(transcript_id)
- print >> read_file, ">{}".format(cur_read_id)
- print >> read_file, read_seq
+ print(">{}".format(cur_read_id), file=read_file)
+ print(read_seq, file=read_file)
output = "{}\t{}\t{}\t{}\tNM:i:{}\tMD:Z:{}".format(cur_read_id, tax_id, pos + 1, cigar_str, NM, MD)
if paired_end:
- print >> read2_file, ">{}".format(cur_read_id)
- print >> read2_file, reverse_complement(read2_seq)
+ print(">{}".format(cur_read_id), file=read2_file)
+ print(reverse_complement(read2_seq), file=read2_file)
output += "\t{}\t{}\tNM2:i:{}\tMD2:Z:{}".format(pos2 + 1, cigar2_str, NM2, MD2)
- print >> scm_file, output
+ print(output, file=scm_file)
cur_read_id += 1
@@ -865,7 +865,7 @@ if __name__ == '__main__':
parser.print_help()
exit(1)
if not args.dna:
- print >> sys.stderr, "Error: --rna is not implemented."
+ print("Error: --rna is not implemented.", file=sys.stderr)
exit(1)
# if args.dna:
# args.expr_profile = "constant"
--- a/evaluation/test/centrifuge_evaluate_mason.py
+++ b/evaluation/test/centrifuge_evaluate_mason.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/python3
import sys, os, subprocess, inspect
import platform, multiprocessing
@@ -27,7 +27,7 @@ def compare_scm(centrifuge_out, true_out
higher_ranked = {}
ancestors = set()
- for tax_id in taxonomy_tree.keys():
+ for tax_id in list(taxonomy_tree.keys()):
if tax_id in ancestors:
continue
while True:
@@ -82,7 +82,7 @@ def compare_scm(centrifuge_out, true_out
fields = line.strip().split('\t')
if len(fields) != 3:
- print >> sys.stderr, "Warning: %s missing" % (line.strip())
+ print("Warning: %s missing" % (line.strip()), file=sys.stderr)
continue
read_name, tax_id = fields[1:3]
# Traverse up taxonomy tree to match the given rank parameter
@@ -117,7 +117,7 @@ def compare_scm(centrifuge_out, true_out
# print read_name
raw_unique_classified = 0
- for read_name, maps in db_dic.items():
+ for read_name, maps in list(db_dic.items()):
if len(maps) == 1 and read_name not in higher_ranked:
raw_unique_classified += 1
return classified, unique_classified, unclassified, len(db_dic), raw_unique_classified
@@ -184,7 +184,7 @@ def evaluate(index_base,
read_fname]
if verbose:
- print >> sys.stderr, ' '.join(centrifuge_cmd)
+ print(' '.join(centrifuge_cmd), file=sys.stderr)
out_fname = "centrifuge.output"
proc = subprocess.Popen(centrifuge_cmd, stdout=open(out_fname, "w"), stderr=subprocess.PIPE)
@@ -208,12 +208,12 @@ def evaluate(index_base,
# if rank == "strain":
# assert num_cases == num_fragment
- print >> sys.stderr, "\t\t%s" % rank
- print >> sys.stderr, "\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(classified, num_cases, float(classified) / num_cases)
- print >> sys.stderr, "\t\t\tprecision : {:,} / {:,} ({:.2%})".format(classified, raw_classified, float(classified) / raw_classified)
- print >> sys.stderr, "\n\t\t\tfor uniquely classified "
- print >> sys.stderr, "\t\t\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(unique_classified, num_cases, float(unique_classified) / num_cases)
- print >> sys.stderr, "\t\t\t\t\tprecision : {:,} / {:,} ({:.2%})".format(unique_classified, raw_unique_classified, float(unique_classified) / raw_unique_classified)
+ print("\t\t%s" % rank, file=sys.stderr)
+ print("\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(classified, num_cases, float(classified) / num_cases), file=sys.stderr)
+ print("\t\t\tprecision : {:,} / {:,} ({:.2%})".format(classified, raw_classified, float(classified) / raw_classified), file=sys.stderr)
+ print("\n\t\t\tfor uniquely classified ", file=sys.stderr)
+ print("\t\t\t\t\tsensitivity: {:,} / {:,} ({:.2%})".format(unique_classified, num_cases, float(unique_classified) / num_cases), file=sys.stderr)
+ print("\t\t\t\t\tprecision : {:,} / {:,} ({:.2%})".format(unique_classified, raw_unique_classified, float(unique_classified) / raw_unique_classified), file=sys.stderr)
# Calculate sum of squared residuals in abundance
"""
@@ -252,12 +252,12 @@ def evaluate(index_base,
if rank_taxID not in true_abundance:
true_abundance[rank_taxID] = 0.0
true_abundance[rank_taxID] += (reads / float(genomeSize))
- for taxID, reads in true_abundance.items():
+ for taxID, reads in list(true_abundance.items()):
true_abundance[taxID] /= total_sum
- print >> sys.stderr, "number of genomes:", num_genomes
- print >> sys.stderr, "number of species:", num_species
- print >> sys.stderr, "number of uniq species:", len(true_abundance)
+ print("number of genomes:", num_genomes, file=sys.stderr)
+ print("number of species:", num_species, file=sys.stderr)
+ print("number of uniq species:", len(true_abundance), file=sys.stderr)
read_fname = "centrifuge_data/bacteria_sim10M/bacteria_sim10M.fa"
summary_fname = "centrifuge.summary"
@@ -271,14 +271,14 @@ def evaluate(index_base,
read_fname]
if verbose:
- print >> sys.stderr, ' '.join(centrifuge_cmd)
+ print(' '.join(centrifuge_cmd), file=sys.stderr)
out_fname = "centrifuge.output"
proc = subprocess.Popen(centrifuge_cmd, stdout=open(out_fname, "w"), stderr=subprocess.PIPE)
proc.communicate()
calc_abundance = {}
- for taxID in true_abundance.keys():
+ for taxID in list(true_abundance.keys()):
calc_abundance[taxID] = 0.0
first = True
for line in open(summary_fname):
@@ -296,12 +296,12 @@ def evaluate(index_base,
"""
abundance_file = open("abundance.cmp", 'w')
- print >> abundance_file, "taxID\ttrue\tcalc\trank"
+ print("taxID\ttrue\tcalc\trank", file=abundance_file)
for rank in ranks:
if rank == "strain":
continue
true_abundance_rank, calc_abundance_rank = {}, {}
- for taxID in true_abundance.keys():
+ for taxID in list(true_abundance.keys()):
assert taxID in calc_abundance
rank_taxID = taxID
while True:
@@ -322,11 +322,11 @@ def evaluate(index_base,
calc_abundance_rank[rank_taxID] += calc_abundance[taxID]
ssr = 0.0 # Sum of Squared Residuals
- for taxID in true_abundance_rank.keys():
+ for taxID in list(true_abundance_rank.keys()):
assert taxID in calc_abundance_rank
ssr += (true_abundance_rank[taxID] - calc_abundance_rank[taxID]) ** 2
- print >> abundance_file, "%s\t%.6f\t%.6f\t%s" % (taxID, true_abundance_rank[taxID], calc_abundance_rank[taxID], rank)
- print >> sys.stderr, "%s) Sum of squared residuals: %.6f" % (rank, ssr)
+ print("%s\t%.6f\t%.6f\t%s" % (taxID, true_abundance_rank[taxID], calc_abundance_rank[taxID], rank), file=abundance_file)
+ print("%s) Sum of squared residuals: %.6f" % (rank, ssr), file=sys.stderr)
abundance_file.close()
|
