Python脚本提取fasta文件单序列信息实现

#!/usr/bin/env python
import sys

file_fasta = sys.argv[1]
#获得文件名
file_name = file_fasta.split('.')
name = file_name[0]

def get_info(chr):
    chr = chr.upper()
    count_g = chr.count('G')
    count_c = chr.count('C')
    count_a = chr.count('A')
    count_t = chr.count('T')

gc = (count_g + count_c) / (count_a + count_t + count_c + count_g)
A = (count_a) / (count_a + count_t + count_c + count_g)
T = (count_t) / (count_a + count_t + count_c + count_g)
C = (count_c) / (count_a + count_t + count_c + count_g)
G = (count_g) / (count_a + count_t + count_c + count_g)
gc_con = '{:.2%}'.format(gc)
A_content = '{:.2%}'.format(A)
T_content = '{:.2%}'.format(T)
C_content = '{:.2%}'.format(C)
G_content = '{:.2%}'.format(G)
return (gc_con,A_content,T_content,C_content,G_content)

#进行函数计算
with open(file_fasta,'r') as read_fa:

    for val in read_fa:
        val = val.strip()
        if not val.startswith(">"):
            seq_info = get_info(val)
            len_fasta = len(val)

#结果屏幕展示
print('******\n{0}\nlength:{1}\ngc content :{2}\nA content :{3}\nT content :{4}\nC content :{5}\nG content :{6}\n******'.format(name,len_fasta,seq_info[0],seq_info[1],seq_info[2],seq_info[3],seq_info[4]))

#结果输出文件
file_output = open("{}sum.txt".format(name),'a')
file_output.write('******\n')
file_output.write('{}\n'.format(name))
file_output.write('length:{:d}\n'.format(len_fasta))
file_output.write('gc content :{}\n'.format(seq_info[0]))
file_output.write('A content :{}\n'.format(seq_info[1]))
file_output.write('T content :{}\n'.format(seq_info[2]))
file_output.write('C content :{}\n'.format(seq_info[3]))
file_output.write('G content :{}\n'.format(seq_info[4]))
file_output.write('******')
file_output.close()