002 生信基础题

001  'GATCCAGATCCCCATAC'， 计算这串数列中两个出现最高的频率。

t = 'GATCCAGATCCCCATAC'
L = [ ]

for i in range(len(t)-1):
    L.append(t[i:i+2])

x = reduce(lambda x,y: x if L.count(x)>L.count(y) else y, L)

# reduce(function, iterable[, initializer])

print x, 'appeared', L.count(x), 'times! It is the most frequent 2-mer.'

　　

方法二:

def PatternCount(Pattern, Text):                   
    count = 0 
    for i in range(len(Text)-len(Pattern)+1):     #Text 内容， Pattern 去字符长度
        if Text[i:i+len(Pattern)]==Pattern:
            count = count +1
    return count

def CountDict(Text, k):
    Count = {} 
    for i in range(len(Text)-k+1):
        Pattern = Text[i:i+k]
        Count[i] = PatternCount(Pattern, Text)   
    return Count

def FrequentWords(Text, k):
    FrequentPatterns = [] 
    Count = CountDict(Text,k)
    m = max(Count.values())
    for i in Count:
        if Count[i] == m:
            FrequentPatterns.append(Text[i:i+k])
    return FrequentPatterns

import sys
print(FrequentWords("GATCCAGATCCCCATAC", 2))

002  Reverse Complement Problem: 
Find the reverse complement of a DNA string. 
        Input: A DNA string Pattern.
        Output: The reverse complement of Pattern.

        Sample Input:

　　AAAACCCGGT

　　Sample Output:

　　ACCGGGTTTT