-
Notifications
You must be signed in to change notification settings - Fork 0
/
improved_indel_snp.py
352 lines (324 loc) · 15.6 KB
/
improved_indel_snp.py
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
#!/usr/bin/python
import os
import subprocess
# General information - modify appropriately for each experiment
# sample_base = "3612-DC-1" # Naming scheme of samples without the sample number
number_of_samples = '4' # Number of sequencing samples
species = 'human' # Valid options: mouse or human
read_type = 'PE' # Valid options: "SE" or "PE"
read_length = 150
sample_suffix = 'fastq'
compression_suffix = 'gz'
n_cpus = 8
pc = 'goku'
# experiment_name = '20160816_rnaseq' # Name of experiment, also name of the output folder for all files
entity_searched = 'snp' # Valid options include 'indel', 'snp', or 'none'
confidence_threshold = 20
elif pc == 'goku': # Setting up programs
flexbar = '/usr/bin/flexbar'
hisat2 = '/home/pinojc/RNASeq_sources/Software/hisat2-2.0.4/hisat2'
samtools = '/home/pinojc/RNASeq_sources/Software/samtools-1.3.1/samtools'
samstat = '/usr/local/bin/samstat'
featurecounts = '/home/pinojc/RNASeq_sources/Software/subread-1.5.1-source/bin/featureCounts'
output_directory = "/media/pinojc/68f7ba6a-cdf6-4761-930d-9c1bb724e40d/home/LP_data"
fasta_directory = "/home/pinojc/LisaData/E65_rna_fasta"
gatk = '/home/pinojc/RNASeq_sources/Software/GenomeAnalysisTK.jar'
picard = '/home/pinojc/RNASeq_sources/Software/picard.jar'
STAR = '/home/pinojc/RNASeq_sources/Software/STAR'
# experiment specific information
adaptors = '/home/pinojc/RNASeq_sources/illumina_truseq.fasta'
if species == 'mouse':
transcripts = '/Users/temporary/genomes/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf'
hisat2_index = '/Users/temporary/genomes/Mus_musculus/UCSC/mm10/Sequence/HISAT2_index/mm10.genome'
reference_genome = '/Users/temporary/genomes/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome_indel.fa'
elif species == 'human':
transcripts = '/media/pinojc/68f7ba6a-cdf6-4761-930d-9c1bb724e40d/home/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf'
hisat2_index = '/media/pinojc/68f7ba6a-cdf6-4761-930d-9c1bb724e40d/home/Homo_sapiens/UCSC/hg38/Sequence/HISAT2Index/genome'
reference_genome = '/media/pinojc/68f7ba6a-cdf6-4761-930d-9c1bb724e40d/home/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/genome.fa'
snp_vcf_file = '/media/pinojc/68f7ba6a-cdf6-4761-930d-9c1bb724e40d/home/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/1000G_phase1.snps.high_confidence.hg38.vcf'
indel_vcf_file = '/Users/temporary/genomes/Homo_sapiens_hg38/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/Mills_and_1000G_gold_standard.indels.hg38.vcf'
genome_directory = '/media/pinojc/68f7ba6a-cdf6-4761-930d-9c1bb724e40d/home/Homo_sapiens/UCSC/hg38/Sequence/STARIndex'
else:
print(
"Error - invalid species. Valid arguments are 'human' or 'mouse'")
quit() # Adaptor Trimming via Flexbar
def flexbar_trim(sample_base):
# Flexbar options
# '-a' = adaptor sequences (fasta format)
# '-n' = number of threads
# '-u' = max uncalled bases for each read to pass filtering
# '-m' = min read length to remain after filtering/trimming
# '-t' = prefix for output file names
# '-ao' = adapter min overlap
# '-ae' = adapter trim end
print("Start trimming {}".format(sample_base))
path_to_executable = flexbar
suffix_for_output = '-t {}/{}-trimmed'.format(fasta_directory, sample_base)
adaptor_trim_end = '-ae ANY'
adaptor_overlap = '-ao 5'
path_to_adaptors = "-a {}".format(adaptors)
number_max_uncalled_bases_pass = '-u {}'.format(read_length)
main_read_length_to_remain = '-m 18'
threads = '-n {}'.format(n_cpus)
if read_type not in ('SE', 'PE'):
print("Error. Invalid read type. Valid options are SE or PE Aborting.")
quit()
elif read_type == 'SE':
reads = '-r {}/{}.{}.{}'.format(fasta_directory, sample_base, sample_suffix, compression_suffix)
elif read_type == 'PE':
reads = ' -r {}/{}_1.{}.{} -p {}/{}_2.{}.{}'.format(fasta_directory, sample_base, sample_suffix,
compression_suffix, fasta_directory, sample_base,
sample_suffix, compression_suffix)
command = [path_to_executable, reads, path_to_adaptors, threads, suffix_for_output, adaptor_overlap,
adaptor_trim_end, number_max_uncalled_bases_pass, main_read_length_to_remain]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done trimming {}".format(sample_base))
# # STAR 2-pass alignemnt Alignment
# def star_file_read_in(sample_base):
# path_to_executable = STAR
# genome_dir = '--genomeDir {}'.format(genome_directory)
# if read_type == 'SE':
# reads = '--readFilesIn {}/{}-trimmed.{}'.format(fasta_directory,
# sample_base, sample_suffix)
# elif read_type == 'PE':
# reads = '--readFilesIn {}/{}-trimmed_1.{} {}/{}-trimmed_2.{}'.format(fasta_directory, sample_base, sample_suffix,
# fasta_directory, sample_base, sample_suffix)
# threads = '--runThreadN {}'.format(n_cpus)
# command = [path_to_executable, genome_dir, reads, threads]
# call_code = ' '.join(command)
# print(call_code)
# process = subprocess.Popen([call_code], shell=True,
# stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
# while True:
# output = process.stdout.readline()
# if output == '' and process.poll() is not None:
# break
# if output:
# print output.strip()
# rc = process.poll()
# print("Done aligning {}".format(sample_base))
#
#
# def star_initial_alignment(sample_base):
# print("Starting aligning {}".format(sample_base))
# if not os.path.exists('BAM_files'):
# os.mkdir('BAM_files')
#
# path_to_executable = STAR
# run_mode = '--runMode genomeGenerate'
# genome_dir = '--genomeDir {}'.format(genome_directory)
# ref_genome = '--genomeFastaFiles {}'.format(reference_genome)
# options = '--sjdbFileChrStartEnd {}/BAM_files --sjdbOverhang 75 --runThreadN {}'.format(output_directory, n_cpus)
#
# output_name = '-S ./BAM_files/{}.sam'.format(sample_base)
# threads = '-p {}'.format(n_cpus)
# indices = '-x {}'.format(hisat2_index)
#
# command = [path_to_executable, threads, indices, reads, output_name]
# call_code = ' '.join(command)
# print(call_code)
# process = subprocess.Popen([call_code], shell=True,
# stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
# while True:
# output = process.stdout.readline()
# if output == '' and process.poll() is not None:
# break
# if output:
# print output.strip()
# rc = process.poll()
# print("Done aligning {}".format(sample_base))
#
#
# def star_second_pass(sample_base):
# print("Starting aligning {}".format(sample_base))
# if not os.path.exists('BAM_files'):
# os.mkdir('BAM_files')
#
# path_to_executable = STAR
# run_mode = '--runMode genomeGenerate'
# genome_dir = '--genomeDir {}'.format(genome_directory)
# ref_genome = '--genomeFastaFiles {}'.format(reference_genome)
# options = '--sjdbFileChrStartEnd {}/BAM_files --sjdbOverhang 75 --runThreadN {}'.format(output_directory, n_cpus)
#
# output_name = '-S ./BAM_files/{}.sam'.format(sample_base)
# threads = '-p {}'.format(n_cpus)
# indices = '-x {}'.format(hisat2_index)
#
# command = [path_to_executable, threads, indices, reads, output_name]
# call_code = ' '.join(command)
# print(call_code)
# process = subprocess.Popen([call_code], shell=True,
# stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
# while True:
# output = process.stdout.readline()
# if output == '' and process.poll() is not None:
# break
# if output:
# print output.strip()
# rc = process.poll()
# print("Done aligning {}".format(sample_base))
def bwa_alignment(sample_base):
# global_output = ''
print("Starting alignment for {}".format(sample_base))
if not os.path.exists('BWA_BAM_files'):
os.mkdir('BWA_BAM_files')
path_to_executable = '{} mem'.format(bwa)
first_pair_reads = "{}/{}-trimmed_1.{}".format(fasta_directory, sample_base, sample_suffix)
second_pair_reads = "{}/{}-trimmed_2.{}".format(fasta_directory, sample_base, sample_suffix)
important_options = '-T 15 -M -t {}'.format(n_cpus)
path_to_reference = reference_genome
export_to_file = '> ./BWA_BAM_files/{}.sam'.format(sample_base)
command = [path_to_executable, important_options, path_to_reference, first_pair_reads, second_pair_reads,
export_to_file]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
# if output:
# # global_output += output
# print output.strip()
rc = process.poll()
print("Done aligning {}".format(sample_base))
# with open('{}.sam'.format(sample_base)) as f:
# f.write(global_output)
# Conversion from SAM to BAM and sorting
def sam_to_bam(sample_base):
print("Start sam to bam conversion {}".format(sample_base))
path_to_executable = '{} view'.format(samtools)
path_to_samples = '-S -b ./BAM_files/{}.sam'.format(sample_base)
output_filename = '-o ./BAM_files/{}.bam'.format(sample_base)
threads = '--threads {}'.format(n_cpus)
command = [path_to_executable, path_to_samples, threads, output_filename]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done sam to bam conversion {}".format(sample_base))
# os.remove('./BAM_files/{}.sam'.format(sample_base))
def bam_sort(sample_base):
print("Start sorting {}".format(sample_base))
path_to_executable = '{} sort'.format(samtools)
path_to_samples = './BAM_files/{}.bam'.format(sample_base)
output_filename = '-o ./BAM_files/{}.sorted.bam'.format(sample_base)
threads = '--threads {}'.format(n_cpus)
command = [path_to_executable, threads, output_filename, path_to_samples]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done sorting {}".format(sample_base))
os.remove('./BAM_files/{}.bam'.format(sample_base))
def bwa_read_group(sample_base):
print("Starting read group addition for {}".format(sample_base))
path_to_executable = 'java -jar {}'.format(picard)
picard_program = "AddOrReplaceReadGroups"
input_files = 'I=./BWA_BAM_files/{}.sorted.bam'.format(sample_base)
output_files = 'O=./BWA_BAM_files/{}.rg.sorted.bam'.format(sample_base)
necessary_parameters = "RGID={} RGLB={} RGPL=ILLUMINA RGPU=ILLUMINA RGSM={}".format(sample_base, sample_base,
sample_base)
command = [path_to_executable, picard_program, input_files, output_files, necessary_parameters]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done adding read group {}".format(sample_base))
# os.remove('./BWA_BAM_files/{}.sam'.format(sample_base))
def mark_dup(sample_base):
print("Starting mark dup for {}".format(sample_base))
path_to_executable = "java -jar {}".format(picard)
picard_program = 'MarkDuplicates'
input_files = 'I=./BWA_BAM_files/{}.rg.sorted.bam'.format(sample_base)
output_file = 'O=./BWA_BAM_files/{}.dedeuped.bam'
options = 'CREATE_INDEX=true VALIDATION_STRINGENCY=SILENT M=ouput.{}.metrics'.format(entity_searched)
command = [path_to_executable, picard_program, input_files, output_file, options]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done with mark dup for {}".format(sample_base))
def gatk_splitntrim(sample_base):
print("Starting split for {}".format(sample_base))
path_to_executable = "java -jar {}".format(gatk)
gatk_program = '-T SplitNCigarReads'
path_to_reference = "-R {}".format(reference_genome)
input_files = '-I ./BWA_BAM_files/{}.sorted.bam'.format(sample_base)
output_file = '-o ./BWA_BAM_files/{}.split.bam'.format(sample_base)
important_options = '-rf ReassignOneMappingQuality -RMQF 255 -RMQT 60 -U ALLOW_N_CIGAR_READS'
command = [path_to_executable, gatk_program, path_to_reference, input_files, output_file, important_options]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done split for {}".format(sample_base))
def variant_calling(sample_base):
print("Starting variant calling for {}".format(sample_base))
path_to_executable = "java -jar {}".format(gatk)
gatk_program = '-T HaplotypeCaller'
path_to_reference = "-R {}".format(reference_genome)
input_files = '-I ./BWA_BAM_files/{}.split.bam'.format(sample_base)
options = '-dontUseSoftClippedBases -stand_all_conf {}'.format(confidence_threshold)
output_file = './BWA_BAM_files/{}.{}.vcf'.format(sample_base, entity_searched)
command = [path_to_executable, gatk_program, path_to_reference, input_files, output_file, important_options]
call_code = ' '.join(command)
print(call_code)
process = subprocess.Popen([call_code], shell=True,
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print output.strip()
rc = process.poll()
print("Done split for {}".format(sample_base))