Genome_Annotation.py 文件源码

def get_cds_sequence(rna,c_df,chrom_seq):
    pr_df = c_df[c_df['rna_id'].values==rna]
    strand = list(set(pr_df[6].tolist()))
    if len(strand) == 2:
        assert False, rna+' has both strands'
    # seqeunce merge
    chr_seq = Seq('')
    for start,end in zip(pr_df[3],pr_df[4]):
        if strand == ['-']:
            chr_seq += chrom_seq[start-1:end].reverse_complement()
        else:
            chr_seq += chrom_seq[start-1:end]
    # consider the frame information in 7th column
    frame = int(pr_df[7].tolist()[0])
    rna_seq = chr_seq[frame:]
    return str(rna_seq.translate())