Extract the gene annotation table from the geneshot results HDF5

geneshot_extract_gene_annot.py

#!/usr/bin/env python3

import click
import os
import pandas as pd

# Set up the command line processor
@click.command()
@click.option("--input_fp", help="Provide the path to the geneshot output file containing all gene abundances (*.results.hdf5)")
def geneshot_extract_gene_annot(input_fp):

    assert input_fp is not None, "Must provide path to the geneshot output file containing all gene abundances (*.results.hdf5)"
    assert os.path.exists(input_fp), f"Cannot file file: {input_fp}"

    assert input_fp.endswith(".results.hdf5"), f"Input file must be named *.results.hdf5"

    print(f"Reading {input_fp}")

    # Open the file
    with pd.HDFStore(input_fp, "r") as store:

        # Write out the gene annotation table
        pd.read_hdf(store, "/annot/gene/all").to_csv(input_fp.replace(".results.hdf5", '') + ".gene_annot.csv", index=None)

if __name__ == "__main__":

    geneshot_extract_gene_annot()