run_utils.py

import datetime
import os
import shutil
import subprocess
import tempfile
import uuid

import logging
from typing import List

import yaml


def set_env_variables():
    if "DiffDock-Pocket-Dir" not in os.environ:
        work_dir = os.path.abspath(os.path.join("../DiffDock-Pocket"))
        if os.path.exists(work_dir):
            os.environ["DiffDock-Pocket-Dir"] = work_dir
        else:
            raise ValueError(f"DiffDock-Pocket-Dir {work_dir} not found")

    if "LOG_LEVEL" not in os.environ:
        os.environ["LOG_LEVEL"] = "INFO"


def configure_logging(level=None):
    if level is None:
        level = getattr(logging, os.environ.get("LOG_LEVEL", "INFO"))

    # Note that this sets the universal logger,
    # which includes other libraries.
    logging.basicConfig(
        level=level,
        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
        handlers=[
            logging.StreamHandler(),  # Outputs logs to stderr by default
            # If you also want to log to a file, uncomment the following line:
            # logging.FileHandler('my_app.log', mode='a', encoding='utf-8')
        ],
    )


def kwargs_to_cli_args(**kwargs) -> List[str]:
    """
    Converts keyword arguments to a CLI argument string.
    Boolean kwargs are added as flags if True, and omitted if False.
    """
    cli_args = []
    for key, value in kwargs.items():
        if isinstance(value, bool):
            if value:
                cli_args.append(f"--{key}")
        else:
            if value is not None:
                cli_args.append(f"--{key}={value}")

    return cli_args


def run_cli_command(
    protein_path: str,
    ligand: str,
    samples_per_complex: int,
    keep_local_structures: bool,
    save_visualisation: bool,
    other_arg_file: str,
    work_dir=None,
):
    if work_dir is None:
        work_dir = os.environ.get(
            "DiffDock-Pocket-Dir", os.path.join(os.environ["HOME"], "DiffDock-Pocket")
        )

    all_arg_dict = {}
    if other_arg_file:
        all_arg_dict = yaml.safe_load(open(other_arg_file, "r"))
        logging.debug(f"YAML dict: {all_arg_dict}")

    ui_args = ["protein_path", "ligand", "samples_per_complex",
               "keep_local_structures", "save_visualisation"]
    for ui_arg in ui_args:
        my_str = f"all_arg_dict['{ui_arg}'] = {ui_arg}"
        exec(my_str)

    command = [
        "python3",
        "inference.py"]

    command += kwargs_to_cli_args(**all_arg_dict)

    with tempfile.TemporaryDirectory() as temp_dir:
        temp_dir_path = temp_dir
        command.append(f"--out_dir={temp_dir_path}")

        # Convert command list to string for printing
        command_str = " ".join(command)
        logging.info(f"Executing command: {command_str}")

        # Running the command
        try:
            result = subprocess.run(
                command,
                cwd=work_dir,
                check=False,
                text=True,
                capture_output=True,
                env=os.environ,
            )
            logging.debug(f"Command output:\n{result.stdout}")
            if result.stderr:
                logging.error(f"Command error:\n{result.stderr}")
        except subprocess.CalledProcessError as e:
            logging.error(f"An error occurred while executing the command: {e}")

        # Zip the output directory
        # Generate a unique filename using a timestamp and a UUID
        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
        uuid_tag = str(uuid.uuid4())[0:8]
        unique_filename = f"diffdock_pocket_output_{timestamp}_{uuid_tag}"
        zip_base_name = os.path.join("tmp", unique_filename)
        full_zip_path = shutil.make_archive(zip_base_name, "zip", temp_dir)

        logging.debug(f"Directory '{temp_dir}' zipped to '{full_zip_path}'")

    return full_zip_path


if __name__ == "__main__":
    # Testing code
    set_env_variables()
    configure_logging()

    work_dir = os.path.abspath("../DiffDock-Pocket")
    os.environ["DiffDock-Pocket-Dir"] = work_dir
    protein_path = os.path.join(work_dir, "example_data", "3dpf_protein.pdb")
    ligand = os.path.join(work_dir, "example_data", "3dpf_ligand.sdf")
    other_arg_file = os.path.join(work_dir, "example_data", "example_args.yml")

    run_cli_command(
        protein_path,
        ligand,
        samples_per_complex=1,
        keep_local_structures=True,
        save_visualisation=True,
        other_arg_file=other_arg_file
    )