用Python和C语言实现DNA双序列简单比对

这是DNA双序列比对类型中最简单的一种，要求输入的两条序列长度相同，通过运行代码给出两条序列的比对得分

Python代码如下

import numpy
## Score matrix for nucleotide alignment
NUC44=numpy.array([[5,-4,-4,-4,-2],
                   [-4,5,-4,-4,-2],
                   [-4,-4,5,-4,-2],
                   [-4,-4,-4,5,-2],
                   [-2,-2,-2,-2,-1]])

NBET='ATGCN'
seq1=input("Please input the sequence 1:")
seq2=input("Please input the sequence 2:")
## Define a function for calculating the alignment score of two sequences
def NUCScore(NUC44,NBET,seq1,seq2,gap=-7):
    scr=0
    seq_len=min(len(seq1),len(seq2))
    for i in range(seq_len):
        if (seq1[i] == '-' or seq2[i] == '-') and seq1[i] != seq2[i] :
            scr+=gap
        else:
            nuc1=NBET.index(seq1[i].upper())
            nuc2=NBET.index(seq2[i].upper())
            scr+=NUC44[nuc1,nuc2]
    return scr


print('The aligned sequences are:')
print(seq1)
print(seq2)
score=NUCScore(NUC44,NBET,seq1,seq2,gap=-7)
print('The alignment score for the two sequences are %d.' % score)

C语言代码如下

#include 
#include
int score_array[5][5] = { {5,-4,-4,-4,-2},{-4,5,-4,-4,-2},{-4,-4,5,-4,-2},{-4,-4,-4,5,-2},{-2,-2,-2,-2,-1} };
int main()
{
    int clu_score(char seq1[100], char seq2[100], char normol[5]);
    char normol[] = "ATCGN";
    char seq1[100], seq2[100];
    printf("Please input sequence 1:");
    scanf("%s", seq1);
    printf("Please input sequence 2:");
    scanf("%s", seq2);
    int score;
    score = clu_score(seq1, seq2, normol);
    printf("the score is %d\t", score);
    return 0;
}

int clu_score(char seq1[100], char seq2[100],char normol[5])
{
    int index1, index2,score_total=0;
    int i, j;
    for (i = 0; i < strlen(seq1); i++)
    {
        for (j = 0; j < strlen(normol); j++)
        {
            if (seq1[i] == normol[j])
                index1 = j;
            if (seq2[i] == normol[j])
                index2 = j;
        }
        score_total += score_array[index1][index2];
    }
    return score_total;
}

如果有问题，欢迎大家和我一起讨论！