HDU - 1560 DNA sequence (IDA*) (day_11_E)

DNA sequence

Time Limit: 15000/5000 MS (Java/Others) Memory Limit: 32768/32768 K (Java/Others)
Total Submission(s): 4652 Accepted Submission(s): 2228

Problem Description
The twenty-first century is a biology-technology developing century. We know that a gene is made of DNA. The nucleotide bases from which DNA is built are A(adenine), C(cytosine), G(guanine), and T(thymine). Finding the longest common subsequence between DNA/Protein sequences is one of the basic problems in modern computational molecular biology. But this problem is a little different. Given several DNA sequences, you are asked to make a shortest sequence from them so that each of the given sequence is the subsequence of it.

For example, given “ACGT”,“ATGC”,“CGTT” and “CAGT”, you can make a sequence in the following way. It is the shortest but may be not the only one.

Input
The first line is the test case number t. Then t test cases follow. In each case, the first line is an integer n ( 1<=n<=8 ) represents number of the DNA sequences. The following k lines contain the k sequences, one per line. Assuming that the length of any sequence is between 1 and 5.

Output
For each test case, print a line containing the length of the shortest sequence that can be made from these sequences.

Sample Input
1
4
ACGT
ATGC
CGTT
CAGT

Sample Output
8

题目分析：

这题用了IDA*算法，大体思路是，先定一个有可能的最短长度depth，然后先深搜到depth这么长，搜完没有答案的话就增加depth的长度，直到能搜到。而在dfs中判断当前状态在当前的depth下有没有可能找到符合题意的答案，从而剪枝。详细的请看这篇博客。

代码实现：

#include<iostream>
#include<cstdio>
#include<algorithm>
#include<cstring>
#include<string>
#include<vector>
#include<stack>
#include<cstdlib>
#include<cmath>
#include<map>
#include<queue>
//#include <bits/stdc++.h>
using namespace std;

const int INF = 0x3f3f3f3f;
#define LL long long
#define pf          printf
#define sf(n)       scanf("%d", &n)
#define sff(a,b)    scanf("%d %d", &a, &b)
#define sfff(a,b,c) scanf("%d %d %d", &a, &b, &c)
#define ms(i,j) memset(i,j,sizeof(i))


char a[10][6],d[4]= {'A','G','C','T'};
int len[10],now[10],depth,maxl,ans,n,T;
void dfs(int l,int nlen[])
{
    if(l>depth)
        return;
    int left=0,t=0;					//left表示最少还需要增加多少个字符来满足题意
    for(int i=0; i<n; i++)
    {
        t=len[i]-nlen[i];
        left=max(left,t);
    }
    if(left==0)
    {
        ans=l;
        return;
    }
    if(l+left>depth)				//剪枝
        return;
    for(int i=0; i<4; i++)
    {
        int pos[10]= {0};			//pos[i]表示第i个字符串已匹配的字符数
        int flag=0;					//flag标记当前增加的字符能否使得离目标更
        for(int j=0; j<n; j++)		//近，如果不能就不用再继续往下搜了。
        {
            if(d[i]==a[j][nlen[j]])
            {
                pos[j]=nlen[j]+1;
                flag=1;
            }
            else
                pos[j]=nlen[j];
        }
        if(flag)
        	dfs(l+1,pos);
    }
}
int main()
{
    sf(T);
    while(T--)
    {
        sf(n);
        maxl=0;
        ans=-1;
        ms(now,0);
        for(int i=0; i<n; i++)
        {
            scanf("%s",a[i]);
            len[i]=strlen(a[i]);
            maxl=max(maxl,len[i]);
        }
        depth=maxl;
        while(1)						
        {
            dfs(0,now);				
            if(ans!=-1)
                break;
            depth++;						//迭代加深
        }
        pf("%d\n",ans);
    }
}