Genome_Annotation.py 文件源码

def augustus_prepare_hint(pasa,exonerate):
    '''
    '''
    dfs = []
    for g,t,feature in zip([pasa,exonerate],['E','P'],['exonpart','CDSpart']):
        df = pd.read_csv(g,sep='\t',header=None)
        df[2] = df[2].map(lambda x: feature)
        df[8] = df[8].map(lambda x: x+';grp='+re.search('(?<=ID=).+?(?=;)',x).group(0)+';src='+t)
        dfs.append(df)
    res = pd.concat(dfs)
    res.to_csv('hints.gff',sep='\t',index=False,header=None)