gff3格式
基因结构注释文件一般为gff3的格式，一共是9列，依次为基因组序列id，注释来源，类型，起始位置，终止位置，得分，正负链，相位，属性。
基因结构注释文件中，基因包含mRNA，mRNA包含exon, CDS, UTR等信息，同时在注释文件中除基因行外，其他行在第9列会通过Parent指明该行从属的上一级ID，也就是一个基因的gene行、mRNA行、CDS行、exon行都会通过Parent层层关联在一起。
EVM软件整合出的基因结构注释文件一般如下所示，目前有一个需求，就是修改基因名称，修改为类似AT01G000001这种形式
Contig1 EVM gene 6013 6784 . - . ID=evm.TU.Contig1.1;Name=EVM%20prediction%20Contig1.1
Contig1 EVM mRNA 6013 6784 . - . ID=evm.model.Contig1.1;Parent=evm.TU.Contig1.1;Name=EVM%20prediction%20Contig1.1
Contig1 EVM exon 6013 6447 . - . ID=cds.evm.model.Contig1.1;Parent=evm.model.Contig1.1
Contig1 EVM exon 6530 6784 . - . ID=cds.evm.model.Contig1.1;Parent=evm.model.Contig1.1
Contig1 EVM CDS 6013 6447 . - 0 ID=cds.evm.model.Contig1.1;Parent=evm.model.Contig1.1
Contig1 EVM CDS 6530 6784 . - 0 ID=cds.evm.model.Contig1.1;Parent=evm.model.Contig1.1
gffutils包
gffutils是一个用于解析gff3/gtf格式的python包，读取gff3文件非常方便，利用这个包实现对基因结构注释文件重新命名python脚本如下
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re
import sys
import argparse
import logging
import gffutils
from collections import defaultdict
def rename(args):
seqid2name = dict()
for line in open(args.change, 'r'):
tem = line.strip().split()
seqid2name[tem[0]] = tem[1]
db = gffutils.create_db(args.gff,':memory:',force=True,keep_order=True,merge_strategy="create_unique", sort_attribute_values = True)
mRNA_children=("five_prime_UTR","three_prime_UTR","CDS","exon")
idmap={
"CDS" : "cds",
"exon" : "exon",
"five_prime_UTR":"5utrp",
"three_prime_UTR":"3utrp"
}
f_out = open('%s.rename.gff3' % args.prefix, 'w')
seqid = None
for gene in db.features_of_type("gene",order_by=('seqid','start','end')):
if gene.seqid != seqid:
genenum = 0
genenum += args.addnum
seqid = gene.seqid
genename = '{0}G{1:06}'.format(seqid2name[seqid],genenum)
f_out.write('{seqid}\t{source}\t{featuretype}\t{start}\t{end}\t{score}\t{strand}\t{frame}\tID={geneid}\n'.format(seqid=gene.seqid, source=gene.source, featuretype=gene.featuretype, start=gene.start, end=gene.end, score=gene.score, strand=gene.strand, frame=gene.frame, geneid=genename))
for t,mRNA in enumerate(db.children(gene,featuretype="mRNA",order_by=('seqid','start','end'))):
mrna_num = t + 1
mrnaid = '{genename}.mRNA{num}'.format(genename=genename,num=mrna_num)
f_out.write('{seqid}\t{source}\t{featuretype}\t{start}\t{end}\t{score}\t{strand}\t{frame}\tID={mrnaid};Parent={geneid}\n'.format(seqid=mRNA.seqid, source=mRNA.source, featuretype=mRNA.featuretype, start=mRNA.start, end=mRNA.end, score=mRNA.score, strand=mRNA.strand, frame=mRNA.frame, mrnaid=mrnaid, geneid=genename))
numdict = defaultdict(int)
for child in db.children(mRNA,featuretype=mRNA_children,order_by=("start",'end')):
numdict[child.featuretype] += 1
child_id = '{genename}.{childid}{num}'.format(genename=genename,childid=idmap[child.featuretype],num=numdict[child.featuretype])
f_out.write('{seqid}\t{source}\t{featuretype}\t{start}\t{end}\t{score}\t{strand}\t{frame}\tID={child_id};Parent={mrnaid}\n'.format(seqid=child.seqid, source=child.source, featuretype=child.featuretype, start=child.start, end=child.end, score=child.score, strand=child.strand, frame=child.frame, child_id=child_id, mrnaid=mrnaid))
f_out.close()
def main():
logging.basicConfig(
stream=sys.stderr,
level=logging.INFO,
format="[%(levelname)s] %(message)s"
)
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="rename gff3 file")
parser.add_argument('-g', '--gff', required=True, help='gff3 file')
parser.add_argument('-c', '--change', required=True, help='a file, correspondence between sequence name and gene name prefix')
parser.add_argument('-a', '--addnum', type=int,default=1, help='diff in gene number, such as if addnum = 10, xx1G000010, xx1G000020')
parser.add_argument('-p', '--prefix', default='result', help='prefix of output')
args = parser.parse_args()
rename(args)
if __name__ == "__main__":
main()
帮助文档，用法
python rename_gff.py -h
usage: rename_gff.py [-h] -g GFF -c CHANGE [-a ADDNUM] [-p PREFIX]
rename gff3 file
optional arguments:
-h, --help show this help message and exit
-g GFF, --gff GFF gff3 file #输入注释文件
-c CHANGE, --change CHANGE #序列id和更换前缀之间的对应关系文件
a file, correspondence between sequence name and gene
name prefix
-a ADDNUM, --addnum ADDNUM #相邻基因编号差值
diff in gene number, such as if addnum = 10,
xx1G000010, xx1G000020
-p PREFIX, --prefix PREFIX #输出文件前缀
prefix of output
我输入的change.bed文件内容如下
Contig1 AT01
Contig2 AT02
Contig3 AT03
Contig4 AT04
Contig5 AT05
最终得到更换名称后的注释文件
Contig1 EVM gene 6013 6784 . - . ID=AT01G000001
Contig1 EVM mRNA 6013 6784 . - . ID=AT01G000001.mRNA1;Parent=AT01G000001
Contig1 EVM exon 6013 6447 . - . ID=AT01G000001.exon1;Parent=AT01G000001.mRNA1
Contig1 EVM CDS 6013 6447 . - 0 ID=AT01G000001.cds1;Parent=AT01G000001.mRNA1
Contig1 EVM exon 6530 6784 . - . ID=AT01G000001.exon2;Parent=AT01G000001.mRNA1
Contig1 EVM CDS 6530 6784 . - 0 ID=AT01G000001.cds2;Parent=AT01G000001.mRNA1
Contig1 EVM gene 7765 9021 . + . ID=AT01G000002
Contig1 EVM mRNA 7765 9021 . + . ID=AT01G000002.mRNA1;Parent=AT01G000002
Contig1 EVM exon 7765 8006 . + . ID=AT01G000002.exon1;Parent=AT01G000002.mRNA1
Contig1 EVM CDS 7765 8006 . + 0 ID=AT01G000002.cds1;Parent=AT01G000002.mRNA1
参考资料
http://www.chenlianfu.com/?p=1323
http://daler.github.io/gffutils/
