def parse_index_file(index_fn, format='fasta'):
# Map FASTQ sequences to their barcodes
s2b = {} # maps sequences to barcodes
# Case 1: index file is FASTA format
if format=='fasta':
for [s,b] in util.iter_fst(index_fn):
# note: I'm pretty sure this won't work for downstream, because you need
# to remove the first character from sequence ID
s2b[s] = b
# Case 2: index file is tab-delimited
elif format=='tab':
for line in open(index_fn):
[s,b] = line.rstrip().split()
s2b[s] = b
# Case 3: index file is FASTQ format
elif format=='fastq':
for [s,b,_,_] in util.iter_fsq(index_fn):
# If sequence ID has :Y:0: thing at the end (standard Illumina format), remove it
# For this kind of fastq line: @SL-MAJ:AY3TB170104:AY3TB:1:1101:10000:7854 :N:0:
s = s.rsplit(' ', 1)[0]
s2b[s[1:]] = b
return s2b
def parse_index_file(index_fn, format='fasta'):
# Map FASTQ sequences to their barcodes
s2b = {} # maps sequences to barcodes
# Case 1: index file is FASTA format
if format == 'fasta':
for [s, b] in util.iter_fst(index_fn):
# note: I'm pretty sure this won't work for downstream, because you need
# to remove the first character from sequence ID
s2b[s] = b
# Case 2: index file is tab-delimited
elif format == 'tab':
for line in open(index_fn):
[s, b] = line.rstrip().split()
s2b[s] = b
# Case 3: index file is FASTQ format
elif format == 'fastq':
for [s, b, _, _] in util.iter_fsq(index_fn):
# If sequence ID has :Y:0: thing at the end (standard Illumina format), remove it
# For this kind of fastq line: @SL-MAJ:AY3TB170104:AY3TB:1:1101:10000:7854 :N:0:
s = s.rsplit(' ', 1)[0]
s2b[s[1:]] = b
return s2b
parser.add_argument('--fastq', help='FASTQ file', required=True)
parser.add_argument('--blast', help='BLAST file', required=True)
parser.add_argument('--sample', help='Sample name', required=True)
parser.add_argument('--prefix', help='OTU prefix', default='bacteria')
parser.add_argument('--out', help='Output prefix (counts)')
args = parser.parse_args()
# ---------------
# Initialize data
# ---------------
print('Initializing data')
# 1. Read FASTQ sequences into dictionary
seqs = {}
for record in util.iter_fsq(args.fastq):
sid = record[0][1:]
seq = record[1]
seqs[sid] = seq
# 2. Map: microbial contigs to GCF IDs
contig2gcf = {}
for line in open('/home/unix/csmillie/aviv/db/refseq/meta/contig2gcf.txt'):
contig, gcf = re.sub('"', '', line).rstrip().split('\t')
contig2gcf[contig] = gcf
# 3. Map: GCF IDs to taxonomy
gcf2sp = {}
gcf2gn = {}
for line in open('/home/unix/csmillie/aviv/db/refseq/meta/gcf.taxonomy_table.txt'):
parser.add_argument('--prefix', help='Prefix to add', type=str, default='')
parser.add_argument('--prefix_sep',
help='Prefix separator',
type=str,
default='.')
parser.add_argument('--debug',
help='Debug mode',
action='store_true',
default=False)
args = parser.parse_args()
# get iterator
if args.fst:
iter_seq = util.iter_fst(args.fst)
elif args.fsq:
iter_seq = util.iter_fsq(args.fsq)
elif args.FST:
iter_seq = util.iter_fst(sys.stdin)
elif args.FSQ:
iter_seq = util.iter_fsq(sys.stdin)
else:
quit('error: must specify fst, fsq, FST, or FSQ')
# initialize variables
keep = {}
remove = {}
# load IDs/coordinates to keep
if args.keep:
for line in open(args.keep):
line = line.rstrip().split('\t')
#!/usr/bin/env python
import util
q = util.iter_fsq()
for record in q:
print '>%s\n%s' %(record[0][1:], record[1])
line = line.rstrip().split()
folder = line[0]
sample = line[1]
info[sample] = folder
# Extract info
[sample, site] = args.sid.split('.')
folder = info[sample]
site = sites[site]
# Get sequence IDs
seqs = {}
orgs = 'archaea bacteria fungi protozoa viral'.split()
for org in orgs:
fn = './%s/%s_%s_bowtie2_contam.fastq' % (org, args.sid, org)
for record in util.iter_fsq(fn):
if len(record) > 0:
seqs[record[0][1:]] = record
print 'Found %d sequences' % (len(seqs))
# Parse BAM file
out = open(args.out, 'w')
fn = '/home/unix/csmillie/Gut_Human/data/%s/%s/outs/possorted_genome_bam.bam' % (
folder, site)
if not os.path.exists(fn):
print 'BAM file not found'
for line in os.popen('samtools view -f 4 %s' % (fn)):
read = line.split()[0]
if read in seqs:
cell = ''
import argparse
import util
# parse args
parser = argparse.ArgumentParser()
parser.add_argument('-f', help='FASTA file')
parser.add_argument('-q', help='FASTQ file')
parser.add_argument('-s', help='Subset ids')
args = parser.parse_args()
# load subset
subset = [line.rstrip() for line in open(args.s)]
# get iterator
iter_seq = ''
if args.f:
iter_seq = util.iter_fst(args.f)
if args.q:
iter_seq = util.iter_fsq(args.q)
# subset file
for record in iter_seq:
sid = record[0][1:].split(';')[0]
if sid in subset:
print '\n'.join(record)