def processBamFiles(genome):
if "main" in inspect.stack()[1][3]:
filename = INPUT_DIR + genome + ".bam"
else:
filename = OUTPUT_DIR + genome + ".bam"
command1 = "samtools sort " + filename + " " + genome + ".sorted"
command2 = "samtools index " + genome + ".sorted.bam"
command3 = (
"samtools mpileup -uD -f ref_files/TB_H37Rv_sequence_validated.fa "
+ genome
+ ".sorted.bam > "
+ OUTPUT_DIR
+ "mpileup/"
+ genome
+ "_mpileup"
)
command4 = (
"bcftools call -mv -Ov -Vindels "
+ OUTPUT_DIR
+ "mpileup/"
+ genome
+ "_mpileup > "
+ OUTPUT_DIR
+ "vcf/"
+ genome
+ "_unfiltered.vcf"
)
command5 = (
"vcfutils.pl varFilter -d10 -Q20 "
+ OUTPUT_DIR
+ "vcf/"
+ genome
+ "_unfiltered.vcf > "
+ OUTPUT_DIR
+ "vcf/"
+ genome
+ ".vcf"
)
command6 = "mv " + genome + ".sorted.bam* " + OUTPUT_DIR
os.system(command1)
os.system(command2)
os.system(command3)
os.system(command4)
os.system(command5)
os.system(command6)
getAnnotations(genome)
def main():
if len(sys.argv) < 2:
sys.stderr.write('USAGE: python processGenomes.py <Genome List>\n')
sys.exit(1)
in_file = sys.argv[1]
genome_list = {}
files = os.listdir(INPUT_DIR)
with open(in_file, 'r') as infile:
for line in infile.readlines():
genome = line.strip()
exists = False
for name in files:
if genome in name and not exists:
ext = name.split('.')[1].strip()
if ext in EXT_DICT.keys():
genome_list[genome] = EXT_DICT[ext]
exists = True
if not exists:
sys.stderr.write('No corresponding input file found for genome ' + genome + '!\n')
count = 0
outfile = open('Mutation-analysis.log', 'w')
for genome in genome_list.keys():
step = genome_list[genome]
if step == 1:
mapFastqFiles(genome)
elif step == 2:
processSamFiles(genome)
elif step == 3:
processBamFiles(genome)
elif step == 4:
getAnnotations(genome)
count = count + 1
if count % 100 == 0:
write_data = 'Processed ' + str(count) + ' genomes ...'
print write_data
outfile.write(write_data + '\n')
outfile.close()