def uncommon_Kmers():
file = seqlib.read_fasta(arg.file)
count = {}
for name, seq in file:
seq = seq.upper()
for i in range(len(seq) - arg.k + 1):
if seq[i:(i + arg.k)] not in count:
count[seq[i:(i + arg.k)]] = 1
else:
count[seq[i:(i + arg.k)]] += 1
sortedKmers = sorted(count, key=count.__getitem__)
mostKmers = {}
leastKmers = {}
for i in range(arg.n):
leastKmers[sortedKmers[i]] = count[sortedKmers[i]]
mostKmers[sortedKmers[-i - 1]] = count[sortedKmers[-i - 1]]
print(f"The most common kmers are {mostKmers}")
print(f"The least common kmers are {leastKmers}")
parser.add_argument("--file", required=True, type=str, metavar='<path>')
parser.add_argument("--window", required=True, type=int, metavar='<int>')
parser.add_argument("--threshold", required=False, default=1, type=int)
parser.add_argument("--mod", required=False, type=str)
parser.add_argument("--step", required=False, type=int, default=1)
parser.add_argument("--verbose", action="store_true")
arg = parser.parse_args()
def status(s):
if arg.verbose:
sys.stderr.write(s)
sys.stderr.write("\n")
myfasta = seqlib.read_fasta(arg.file)
window = arg.window
for name, seq in myfasta:
seq = seq.upper()
i = 0
while (i < (len(seq) - window + 1)):
selection = seq[i:i + window]
e = seqlib.entropy(selection)
if e < arg.threshold:
status("entering modifications")
status(f"window:{selection} {e}")
status(f"current seq {seq}")
if arg.mod == "lower": selection = selection.lower()
else:
import seqlib
parser = argparse.ArgumentParser(description="Global alignment using SW alg")
parser.add_argument("--s1", required=True, type=str, metavar='<path>')
parser.add_argument("--s2", required=True, type=str, metavar='<path>')
parser.add_argument("--match", required=True, type=int)
parser.add_argument("--mismatch", required=True, type=int)
parser.add_argument("--indel", required=True, type=int)
arg = parser.parse_args()
'''
for debugging, this example is from wikipedia
seqa = "TGTTACGG"
seqb = "GGTTGACTA"
'''
file1 = seqlib.read_fasta(arg.s1)
file2 = seqlib.read_fasta(arg.s2)
seqa = ""
seqb = ""
for name, seq, in file1:
seqa = seqa + seq
for name, seq in file2:
seqb = seqb + seq
#make score and direction matrix
seqa = " " + seqa
seqb = " " + seqb
cols = len(seqa)
rows = len(seqb)
metavar='<int>',
help="only show this many k-mers")
parser.add_argument('--verbose',
action='store_true',
help='print some diagnostic messages to stderr')
arg = parser.parse_args()
if arg.verbose:
sys.stderr.write(f'Reading {arg.fasta}\n')
#counting
seq_count = 0
nt_count = 0
k_count = {}
for name, seq in seqlib.read_fasta(arg.fasta):
seq_count += 1
nt_count += len(seq)
for i in range(len(seq) - arg.k + 1):
kmer = seq[i:i + arg.k]
if kmer not in k_count: k_count[kmer] = 0
k_count[kmer] += 1
if arg.verbose:
sys.stderr.write(f'{seq_count} sequences\n')
sys.stderr.write(f'{nt_count} letters\n')
sys.stderr.write(f'{len(k_count)} kmers\n')
# output
n = 0
for kmer, count in sorted(k_count.items(),