INNER CODE UNIT · Python

gene_position

BortonWrightonLabs/DRAM · bin/combine_annotations.py:105

        gene_position = split_label[-1]
        start_position, end_position, strandedness = seq.metadata["description"].split(
            "#"
        )[1:4]

        input_fasta_name = Path(gene_faa).stem.split("_called_genes")[0]
        genes_faa_dict[seq.metadata["id"]][FASTA_COLUMN] = input_fasta_name
        genes_faa_dict[seq.metadata["id"]]["scaffold"] = (
            seq.metadata["id"]
            .removeprefix(genes_faa_dict[seq.metadata["id"]][FASTA_COLUMN])
            .removeprefix("_")
            .removesuffix(f"_{gene_position}")
        )
        genes_faa_dict[seq.metadata["id"]]["gene_number"] = int(gene_position)
        genes_faa_dict[seq.metadata["id"]]["start_position"] = int(start_position)
        genes_faa_dict[seq.metadata["id"]]["stop_position"] = int(end_position)
        genes_faa_dict[seq.metadata["id"]]["strandedness"] = int(strandedness)
    return genes_faa_dict

View source record →