python中 从gff文件提取指定基因信息

 

1、测试数据下载：ftp://ftp.ensemblgenomes.org/pub/plants/release-44/gff3/arabidopsis_thaliana/Arabidopsis_thaliana.TAIR10.44.chromosome.1.gff3.gz

 

 

 

2、

[root@PC1 test2]# ls
Arabidopsis_thaliana.TAIR10.44.chromosome.1.gff3.gz
[root@PC1 test2]# gunzip Arabidopsis_thaliana.TAIR10.44.chromosome.1.gff3.gz
[root@PC1 test2]# ls
Arabidopsis_thaliana.TAIR10.44.chromosome.1.gff3
[root@PC1 test2]# mv Arabidopsis_thaliana.TAIR10.44.chromosome.1.gff3 a.txt    ## 测试数据
[root@PC1 test2]# ls
a.txt

 

 

3、

[root@PC1 test2]# ls
a.txt  test.py
[root@PC1 test2]# cat test.py    ## 提取信息脚本

in_file = open("a.txt", "r")
out_file = open("result.txt", "w")

for i in in_file:
    i = i.strip()
    if i.startswith("#"):
        continue
    else:
        tmp = i.split("\t")
        if int(tmp[0]) == 1 and tmp[2] == "gene" and int(tmp[3]) > 100000 and int(tmp[4]) < 500000:
            gene = tmp[8].split(";")[0].split("=")[1]
            final = tmp[0] + "\t" + tmp[3] + "\t" + tmp[4] + "\t" + gene
            out_file.write(final + "\n")
in_file.close()
out_file.close()
[root@PC1 test2]# python test.py     ## 运行程序
[root@PC1 test2]# ls
a.txt  result.txt  test.py
[root@PC1 test2]# head result.txt     ## 查看结果
1       104440  105330  gene:AT1G01250
1       108946  111699  gene:AT1G01260
1       112263  113947  gene:AT1G01280
1       114202  116407  gene:AT1G01290
1       116784  118845  gene:AT1G01300
1       119381  119997  gene:AT1G01305
1       120154  121130  gene:AT1G01310
1       121067  130577  gene:AT1G01320
1       130736  130858  gene:AT1G01335
1       132270  135924  gene:AT1G01340