这就是问题所在:http ://rosalind.info/problems/cons/
def file_read(fname):
with open(fname, "r") as myfile:
global data
data = myfile.readlines()
print(data)
i = 0
while i < len(data):
data[i] = data[i].replace("\n", "")
if ">" in data[i]:
data.remove(data[i])
else:
i += 1
file_read('rosalind_cons.txt')
res = ["".join(el) for el in zip(*data)]
print(res)
a_str = ""
c_str = ""
g_str = ""
t_str = ""
for x in range(0, len(res)):
a_str += (str(res[x].count("A"))) + " "
for x in range(0, len(res)):
c_str += (str(res[x].count("C"))) + " "
for x in range(0, len(res)):
g_str += (str(res[x].count("G"))) + " "
for x in range(0, len(res)):
t_str += (str(res[x].count("T"))) + " "
a_str_nospace = a_str.replace(" ", "")
c_str_nospace = c_str.replace(" ", "")
g_str_nospace = g_str.replace(" ", "")
t_str_nospace = t_str.replace(" ", "")
consensus_string = ""
for x in range(0, len(a_str_nospace)):
if max(a_str_nospace[x], c_str_nospace[x], g_str_nospace[x], t_str_nospace[x]) in a_str_nospace[x]:
consensus_string += "A"
elif max(a_str_nospace[x], c_str_nospace[x], g_str_nospace[x], t_str_nospace[x]) in c_str_nospace[x]:
consensus_string += "C"
elif max(a_str_nospace[x], c_str_nospace[x], g_str_nospace[x], t_str_nospace[x]) in g_str_nospace[x]:
consensus_string += "G"
elif max(a_str_nospace[x], c_str_nospace[x], g_str_nospace[x], t_str_nospace[x]) in t_str_nospace[x]:
consensus_string += "T"
print(consensus_string)
print("A: " + a_str)
print("C: " + c_str)
print("G: " + g_str)
print("T: " + t_str)
我的代码有什么问题?对于示例输出,它可以工作,但对于较大的数据集则不行。我不知道出了什么问题,我认为是文件读取部分不正确(也许?)
编辑:那里有一些打印功能,但我没有将它们复制到答案框中,因此它们对结果无关紧要