大豆SNP位点查找V2.0

大豆SNP位点查找V2.0

from time import perf_counter
import csv
import time


start  = perf_counter()

f = open("GM18.txt" , "r")
txt = f.read()
#print(txt[:1000])
txt = txt.strip(">Gm18")
txt = txt.replace("\n","").replace("\r","")        #更改了此处的删除换行符！
# txt = txt.strip(r"\n")
# txt = txt.strip(r"\r")
txt = txt.strip("")      #注意这个地方有错误就是开头的第一个字符串是1，光标位置是0。

#print(txt[:1000])
aimseq = input("请输入你想查找的DNA序列文件（回车结束）：")
def indexstr(str1,str2):
    '''查找指定字符串str1包含指定子字符串str2的全部位置，
    以列表形式返回'''
    lenth2=len(str2)
    lenth1=len(str1)
    indexstr2=[]
    i=0
    while str2 in str1[i:]:
        indextmp = str1.index(str2, i, lenth1)
        indexstr2.append(indextmp)
        i = (indextmp + lenth2)
    return indexstr2



if __name__ == '__main__':
    print(indexstr(txt,aimseq))
    pos = indexstr(txt,aimseq)
#     def getseq():
    num = len(aimseq)
    for number in pos:
        if num == 45:
            sequence1 = txt[number - 300 : number]
            sequence2 = txt[number + 45 : number + 345]
        elif num == 50:
            sequence1 = txt[number - 300 : number]
            sequence2 = txt[number + 50 : number + 350]
        print("由以上条件我们可以得知前300个碱基为 {} ，后300个碱基为 {} ".format(sequence1,sequence2))

    print("此次查找花费的时间是：{:.5f} 秒".format(perf_counter() - start))

        
    c= open ("SNP相关数据.csv","w+")
    writer=csv.writer(c)
    datalist = []
    datalist.append(aimseq)
    time.sleep(0.1)
    datalist.append(sequence1)
    time.sleep(0.1)
    datalist.append(sequence2)
    time.sleep(0.1)
    for numbers in pos:
        datalist.append(numbers)
    time.sleep(0.1)
    writer.writerow(["SNP","前300个碱基","后300个碱基","所在位置"])
    writer.writerow(datalist)
    c.close()