gga_get_data.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import bioblend
import argparse
import os
import subprocess
import logging
import sys
import fnmatch
import time
import json
import re
import stat
import shutil

from bioblend.galaxy.objects import GalaxyInstance
from bioblend import galaxy

import utilities
import speciesData

""" 
gga_get_data.py

Usage: $ python3 gga_get_data.py -i input_example.yml --config config.yml [OPTIONS]

"""


class GetData(speciesData.SpeciesData):
    """
    Child of SpeciesData

    Contains methods and attributes to copy data into the src_data subfolders of an organism

    """

    def goto_species_dir(self):
        """
        Go to the species directory (starting from the main dir)

        :return:
        """

        os.chdir(self.main_dir)
        species_dir = os.path.join(self.main_dir, self.genus_species) + "/"
        try:
            os.chdir(species_dir)
        except OSError:
            logging.critical("Cannot access %s" % species_dir)
            sys.exit(0)
        return 1


    def get_source_data_files_from_path(self):
        """
        Find source data files and copy them into the src_data dir tree

        :return:
        """

        try:
            os.chdir(self.species_dir)
        except OSError:
            logging.critical("Cannot access " + self.species_dir)
            sys.exit(0)

        organism_annotation_dir = os.path.abspath("./src_data/annotation/{0}/OGS{1}".format(self.species_folder_name, self.genome_version))
        organism_genome_dir = os.path.abspath("./src_data/genome/{0}/v{1}".format(self.species_folder_name, self.genome_version))

        datasets_to_get = {"genome_path": self.genome_path,
                           "gff_path": self.gff_path, 
                           "transcripts_path": self.transcripts_path,
                           "proteins_path": self.proteins_path,
                           "interpro_path": self.interpro_path, 
                           "orthofinder_path": self.orthofinder_path, 
                           "blastp_path": self.blastp_path, 
                           "blastx_path": self.blastx_path}

        genome_datasets = ["genome_path"]
        annotation_datasets = ["gff_path", "transcripts_path", "proteins_path", "orthofinder_path", "interpro_path", "blastp_path", "blastx_path"]  
        # Where to store blast results?

        search_excluded_datasets = ["interpro_path", "orthofinder_path", "blastp_path", "blastx_path"]  
        # These datasets will not be searched if missing in the input file

        # Copy dataset in the organism src_data dir tree correct folder
        for k, v in datasets_to_get.items():
            if k in genome_datasets:
                logging.info("Copying {0} into {1}".format(v, organism_genome_dir))
                try:
                    shutil.copyfile(os.path.abspath(v), os.path.join(organism_genome_dir, os.path.basename(v)))
                except Exception as exc:
                    logging.warning("Could not copy {1} ({2})".format(v, exc))
            elif k in  annotation_datasets:
                logging.info("Copying {0} into {1}".format(v, organism_annotation_dir))
                try:
                    shutil.copyfile(os.path.abspath(v), os.path.join(organism_annotation_dir, os.path.basename(v)))
                except Exception as exc:
                    logging.warning("Could not copy {1} ({2})".format(v, exc))
            else:
                pass

        os.chdir(self.main_dir)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Automatic data loading in containers and interaction "
                                                 "with galaxy instances for GGA"
                                                 ", following the protocol @ "
                                                 "http://gitlab.sb-roscoff.fr/abims/e-infra/gga")

    parser.add_argument("input",
                        type=str,
                        help="Input file (yml)")

    parser.add_argument("-v", "--verbose",
                        help="Increase output verbosity",
                        action="store_false")

    parser.add_argument("--config",
                        type=str,
                        help="Config path, default to the 'config' file inside the script repository")

    parser.add_argument("--main-directory",
                        type=str,
                        help="Where the stack containers will be located, defaults to working directory")

    args = parser.parse_args()

    if args.verbose:
        logging.basicConfig(level=logging.DEBUG)
    else:
        logging.basicConfig(level=logging.INFO)
    logging.getLogger("urllib3").setLevel(logging.WARNING)

    # Parsing the config file if provided, using the default config otherwise
    if not args.config:
        args.config = os.path.join(os.path.dirname(os.path.realpath(sys.argv[0])), "config")
    else:
        args.config = os.path.abspath(args.config)

    if not args.main_directory:
        args.main_directory = os.getcwd()
    else:
        args.main_directory = os.path.abspath(args.main_directory)

    sp_dict_list = utilities.parse_input(args.input)

    for sp_dict in sp_dict_list:

        # Creating an instance of get_data_for_current_species object
        get_data_for_current_species = GetData(parameters_dictionary=sp_dict)

        # Starting
        logging.info("gga_load_data.py called for %s" % get_data_for_current_species.full_name)

        # Setting some of the instance attributes
        get_data_for_current_species.main_dir = args.main_directory
        get_data_for_current_species.species_dir = os.path.join(get_data_for_current_species.main_dir,
                                                                 get_data_for_current_species.genus_species +
                                                                 "/")

        # Parse the config yaml file
        get_data_for_current_species.config = utilities.parse_config(args.config)
        
        # Change serexec permissions in repo
        try:
            os.chmod("%s/serexec" % get_data_for_current_species.script_dir, 0o0777)
        except PermissionError:
            logging.critical("Cannot access %s, exiting" % get_data_for_current_species.script_dir)

        # Load config file
        get_data_for_current_species.config = utilities.parse_config(args.config)

        # Retrieve datasets
        logging.info("Finding and copying datasets for %s" % get_data_for_current_species.full_name)
        get_data_for_current_species.get_source_data_files_from_path()
        logging.info("Sucessfully copied datasets for %s" % get_data_for_current_species.full_name)
        
        # Format fasta headers (proteins)
        # logging.info("Formatting fasta files headers %s " % get_data_for_current_species.full_name)
        # get_data_for_current_species.batch_modify_fasta_headers()
        # logging.info("Successfully formatted files headers %s " % get_data_for_current_species.full_name)

        logging.info("Data successfully loaded and imported for %s" % get_data_for_current_species.full_name)