Genome_Annotation.py 文件源码

python
阅读 18 收藏 0 点赞 0 评论 0

项目:NGS-Pipeline 作者: LewisLabUCSD 项目源码 文件源码
def fa2embl(fa,embl,gff,path):
    if not os.path.exists(path): os.mkdir(path)
    os.chdir(path)
    df = pd.read_csv(gff,sep='\t',header=None,comment='#',usecols=[0,2])
    df = df[df[2].values=='gene']
    chroms = list(set(df[0].tolist()))
    dic = SeqIO.index(fa,'fasta')
    for s in chroms:
        SeqIO.write(dic[s],open('fa','w'),'fasta')
        sarge.run('grep \'{s}\' {gff} > gff'.format(s=s,gff=gff))
        sarge.run('/home/shangzhong/Installation/EMBOSS-6.6.0/bin/seqret \
        -sequence fa -feature -fformat gff -fopenfile1 gff -osformat2 embl \
        -auto -outseq {s}.embl'.format(s=s))
    fns = glob.glob('*.embl')
    sarge.run('cat {files} > {embl}'.format(files=' '.join(fns),embl=embl))
#     for f in fns:
#         os.remove(f)
# fa2embl('/data/genome/hamster/ncbi_refseq/hamster.fa','hamster.embl','/data/genome/hamster/ncbi_refseq/hamster.gff','/data/shangzhong/Picr_assembly/Annotation/RATT/embl')
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号