#!/usr/bin/env python
from __future__ import print_function
import sys
from parsers import parse_fa
import collections
import numpy as np
def print_seq(contig_header, seq, linelen=60):
print(contig_header)
i = 0
while i < len(seq):
print(seq[i:i + linelen])
i += linelen
if __name__ == "__main__":
if len(sys.argv) != 2:
print("usage: {} file.fa".format(sys.argv[0]), file=sys.stderr)
exit(1)
for label, seq in parse_fa(sys.argv[1]):
c = collections.Counter(seq)
unmasked = np.sum(c[x] for x in "ACGT")
if unmasked == 121:
print_seq(label, seq)
from __future__ import print_function
import sys
import matplotlib
matplotlib.use('Agg') # don't try to use $DISPLAY
import matplotlib.pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
import parsers
if __name__ == "__main__":
if len(sys.argv) != 2:
print("usage: {} in.{{fa,fq}}".format(sys.argv[0]), file=sys.stderr)
dist = []
for seq in parsers.parse_fa(sys.argv[1]):
label = seq[0]
extra = label.split(" ")[1]
for ef in extra.split(";"):
k, v = ef.split("=")
if k == "DIST":
dist.append(int(v))
pdf = PdfPages("plot_dist_hist.pdf")
fig_w, fig_h = plt.figaspect(9.0 / 16.0)
fig1 = plt.figure(figsize=(fig_w, fig_h))
ax1 = fig1.add_subplot(111)
ax1.hist(dist, bins=range(0, max(dist) + 1))
ax1.set_xlabel("Edit Distance")
ax1.set_ylabel("Frequency")
s.append("C")
else:
s.append("T")
continue
return "".join(s)
if __name__ == "__main__":
if len(sys.argv) != 2:
print("usage: {} file.fastq[.gz]".format(sys.argv[0]), file=sys.stderr)
exit(1)
filename = sys.argv[1]
for lineno, line in enumerate(parsers.parse_fa(filename), 1):
if len(line) == 3:
# fastq, output single sequence
label, seq, qual = line
bs_seq = bstreat(seq)
print("{}\n{}\n+\n{}".format(label, bs_seq, qual))
elif len(line) == 2:
# fasta, output two sequences
label, seq = line
lfields = label.split()
sname = lfields[0]
if len(lfields) > 1:
comment = " " + " ".join(lfields[1:])
else:
#!/usr/bin/env python
from __future__ import print_function
import sys
import parsers
import collections
if __name__ == "__main__":
if len(sys.argv) != 2:
print(len(sys.argv), sys.argv)
print("usage: {} in.fq".format(sys.argv[0]), file=sys.stderr)
exit(1)
quals = collections.Counter()
for l, s, q in parsers.parse_fa(sys.argv[1]):
quals.update(q)
for k in sorted(quals.keys(), key=ord):
v = quals[k]
print("``{}''".format(k), ord(k), v)
help="reads longer than this are ignored")
parser.add_argument("in_fa", help="in.{fa,fq}")
parser.add_argument("out_pdf",
default="plot_fraglen_hist.pdf",
help="out.pdf")
return parser.parse_args()
if __name__ == "__main__":
args = parse_args()
lengths = np.zeros(args.max_len)
lmin = 1e6
lmax = 0
for line in parsers.parse_fa(args.in_fa):
length = len(line[1])
if length > args.max_len:
continue
lengths[length] += 1
if length < lmin:
lmin = length
elif length > lmax:
lmax = length
pdf = PdfPages(args.out_pdf)
#fig_w, fig_h = plt.figaspect(9.0/16.0)
#fig_w, fig_h = plt.figaspect(3.0/4.0)
fig_w = fig_h = 307.28987 / 72.27
yield last
else:
exclude = False
last = [chrom, pos, ref, alt, dp]
if not exclude:
yield last
if __name__ == "__main__":
if len(sys.argv) != 3:
print("usage: {} in.fa in.vcf".format(sys.argv[0]), file=sys.stderr)
exit(1)
fp = parse_fa(sys.argv[1])
snpdict = {}
for label, seq in fp:
chrom, extent = label[1:].split(":")
start, end = map(int, extent.split("-"))
pos = start + (end - start) / 2
if windowmasker(seq) > 0:
continue
snpdict[(chrom, pos)] = seq
plen = 60
print("chrom",
"pos",
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
import sys
import random
from parsers import parse_fa
sequences = []
for line in parse_fa("/dev/stdin"):
assert (len(line) == 2)
_, seq = line
sequences.append(seq)
random.shuffle(sequences)
def print_fa(label, seq, linelen=60):
print(">{}".format(label))
while len(seq) > 0:
print(seq[:linelen])
seq = seq[linelen:]
for n, seq in enumerate(sequences, 1):