大豆SNP位点信息查找V2.1版本

import time
import csv
import time

start  = time.time()

f = open("GM18.txt" , "r")
txt = f.read()
txt = txt.strip(">Gm18")
txt = txt.replace("\n","").replace("\r","")        #更改了此处的删除换行符！
txt = txt.strip("")


pie5 = list()
with open("5pie.list", 'r') as fin:
    for f in fin:
        pie5.append(f.replace("\n","").replace("\t",""))

pie3 = list()
with open("3pie.list", 'r') as fin:
    for f in fin:
        pie3.append(f.replace("\n","").replace("\t",""))

pie_all = list()
for i in range(len(pie3)):
    pie_all.append([pie5[i], pie3[i]])
print(pie_all[:5])

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

def main():
    pie_result = list()
    for i in pie_all:
        pie5_pos = indexstr(txt,i[0])
        sequence1 = ""
        sequence2 = ""

        for number in pie5_pos:
            if len(i[0]) == 44:
                sequence1 = txt[number - 302 : number-2]
                sequence2 = txt[number + 44 : number + 344]
            elif len(i[0]) == 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))

        pie3_pos = indexstr(txt,i[1])
        sequence3 = ''
        for number in pie3_pos:
            if len(i[1]) == 44:
                sequence3 = txt[number + 44 : number + 344]
            elif len(i[1]) == 50:
                sequence3 = 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))
        pie_result.append([pie5_pos, pie3_pos, sequence1, sequence2, sequence3])

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

        
    with open('csv.csv', 'w') as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(['5_pos', '3_pos', '5_front', '5_end', '3_end'])
        for result in pie_result:
            writer.writerow([result[0], result[1], result[2], result[3], result[4]])

if __name__ == '__main__':
    main()

   

代码背景介绍：
查找SNP位点的5‘端的前300基因序列和后300基因序列以及3’端后300基因序列，并保存到csv文件中。