Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- subsequences = {}
- def read_file():
- sequence = ""
- file = open("file/sequence.fasta","r")
- file.readline()
- for line in file.readlines():
- sequence += line[:-1]
- return sequence
- def set_subsequence(sequence):
- if sequence in subsequences:
- subsequences[sequence] += 1
- else:
- subsequences[sequence] = 1
- def count_subsequences(sequence,size):
- limit = len(sequence) - size + 1
- for i in range(0,limit,37):
- subsequence = sequence[i:i+size]
- set_subsequence(subsequence)
- if __name__ == '__main__':
- sequence = read_file()
- count_subsequences(sequence,37)
- print(len(subsequences))
- for sub, count in subsequences.items():
- print("{} => {}".format(sub,count))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement