source code
# The Computer Language Benchmarks Game
# https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
#
# Naive transliteration from bearophile's program
# contributed by Isaac Gouy
from sys import stdin
def seq_lines():
for line in stdin:
if line.startswith(">THREE"):
break
lines = []
for line in stdin:
if line.startswith(">"):
break
lines.append( line[:-1] )
return lines
def base_counts(bases, seq):
counts = {}
size = len(seq) + 1 - bases
for i in range(size):
nucleo = seq[i: i + bases]
if nucleo in counts:
counts[nucleo] += 1
else:
counts[nucleo] = 1
return counts
def sorted_freq(bases, seq):
keysValues = base_counts(bases, seq).items()
size = len(seq) + 1 - bases
sorted_ = sorted(keysValues, reverse=True, key=lambda kv: kv[1])
return [ (kv[0], 100.0 * kv[1] / size) for kv in sorted_ ]
def specific_count(code, seq):
return base_counts(len(code), seq).get(code,0)
def main():
lines = seq_lines()
seq = "".join([s.upper() for s in lines])
for base in 1,2:
for kv in sorted_freq(base, seq):
print("%s %.3f" % (kv[0], kv[1]))
print()
for code in "GGT", "GGTA", "GGTATT", \
"GGTATTTTAATT", "GGTATTTTAATTTATAGT":
print("%d\t%s" % (specific_count(code, seq), code))
if __name__ == '__main__':
main()
notes, command-line, and program output
NOTES:
64-bit Ubuntu quad core
Python 3.13.0
Fri, 01 Nov 2024 23:58:10 GMT
MAKE:
mv knucleotide.python3-8.python3 knucleotide.py
pyright .
0 errors, 0 warnings, 0 informations
2.99s to complete and log all make actions
COMMAND LINE:
/opt/src/Python-3.13.0/bin/python3 -OO knucleotide.py 0 < knucleotide-input25000000.txt
PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754
AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902
1471758 GGT
446535 GGTA
47336 GGTATT
893 GGTATTTTAATT
893 GGTATTTTAATTTATAGT