Download and parse all of Reactome with PyBioPAX

download_reactome.py

from pathlib import Path

import pandas as pd

import pybiopax

ALL_PATHWAYS = "https://reactome.org/download/current/ReactomePathways.txt"


def download_reactome(directory):
    directory = Path(directory).resolve()
    directory.mkdir(exist_ok=True)

    reactome_ids = pd.read_csv(ALL_PATHWAYS, sep="\t", usecols=[0], squeeze=True)
    for reactome_id in reactome_ids:
        if not reactome_id.startswith("R-HSA"):
            continue
            
        # Downloads from API and parses into object model
        model = pybiopax.model_from_reactome(reactome_id)

        # Save from object model. Yes, this is a little roundabout
        # from just saving from the API, but it demonstrates parsing
        path = directory.joinpath(reactome_id).with_suffix(".xml")
        pybiopax.model_to_owl_file(model, path)