default=sys.stdout, help='File to output.')
parser.add_argument('--first', type=int, \
help='How many sequences to analyse, starting with the first.')
parser.add_argument('--maxlength', type=int, \
help='Maximum sequence length.')
parser.add_argument('--minlength', type=int, \
default=0, help='Minimum sequence length.')
parser.add_argument('--coverage', type=argparse.FileType('r'), \
default=None, help='A CSV file with "read_name, coverage".')
parser.add_argument('--maxcov', type=float, \
help='Maximum coverage for each sequence.')
parser.add_argument('--mincov', type=float, \
default=0, help='Minimum coverage for each sequence.')
args = parser.parse_args()
infile = open(args.infile, 'rb')
seqs = seqlist(infile)
if args.first is not None:
seqs = seqs[:args.first]
if args.maxlength is not None:
seqs = [s for s in seqs if len(s) <= args.maxlength \
and len(s) >= args.minlength]
elif args.minlength > 0:
seqs = [s for s in seqs if len(s) >= args.minlength]
if args.coverage is not None:
n2cov = dict(line.split(',') for line in args.coverage)
def getcov(nme):
return float(n2cov.get(nme.split(' ')[0], 0))
parser.add_argument(
"--megan", type=argparse.FileType("r"), default=None, help='A CSV file from Megan with "read_name, taxon_name".'
)
parser.add_argument(
"--coverage", type=argparse.FileType("r"), default=None, help='A CSV file with "read_name, coverage".'
)
parser.add_argument(
"--assembler",
choices=("idba", "velvet", "none"),
default="none",
help="The assembler used to produce the contigs.",
)
# TODO: loose indexing for gc, bycontig and tetra?
args = parser.parse_args()
infile = open(args.infile, "rb")
seqs = seqlist(infile)
if args.first is not None:
seqs = seqs[: args.first]
if args.type == "bycontig":
if args.coverage is not None:
cov = args.coverage
else:
cov = args.assembler
bycontig(seqs, args.outfile, kmer=args.kmer, megan=args.megan, cov=cov)
elif args.type == "summary":
summary(seqs, args.outfile)
elif args.type == "gc":
gc(seqs, args.outfile)
elif args.type == "tetra":
tetra(seqs, args.outfile)
elif args.type == "tetraz":
import ochre
with open('gc.csv', 'w') as f:
for seq in ochre.seqlist('test.fa'):
f.write(seq.name + ',' + str(seq.gc()))
# VERSUS
import Bio.SeqIO
import Bio.SeqUtils
with open('gc.csv', 'w') as f:
for seq in Bio.SeqIO.parse('test.fa', 'fasta'):
f.write(seq.name + ',' + str(Bio.SeqUtils.GC(seq)))
