comparison data_manager/data_manager_snpEff_download.py @ 10:c6fbc5421697 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_snpeff commit 02d2967f77e3fa5a18aea63dc84aa9ab418dc165"

9:08d7998c3afb

import re
import subprocess
import sys


def stop_err(msg):
    sys.stderr.write(msg)
    sys.exit(1)


def fetch_databases(genome_list=None):
    snpDBs = dict()
    databases_path = 'databases.out'
    databases_output = open(databases_path, 'w')
    args = ['snpEff', 'databases']
    return_code = subprocess.call(args=args, shell=False, stdout=databases_output.fileno())
    if return_code:
        sys.exit(return_code)
    databases_output.close()
    try:
        fh = open(databases_path, 'r')
        for i, line in enumerate(fh):
            fields = line.split('\t')
            if len(fields) >= 2:
                genome_version = fields[0].strip()
                if genome_list and genome_version not in genome_list:
                    continue
                if genome_version.startswith("Genome") or genome_version.startswith("-"):
                    continue
                description = fields[1].strip()
                snpDBs[genome_version] = description
    except Exception as e:
        stop_err('Error parsing %s %s\n' % (databases_path, str(e)))
    else:
        fh.close()
    return snpDBs


def getOrganismNames(genomes, organisms):
    genome_list = genomes.split(',')

def getSnpeffVersion():
    snpeff_version = 'SnpEff ?.?'
    stderr_path = 'snpeff.err'
    stderr_fh = open(stderr_path, 'w')
    args = ['snpEff', '-h']
    return_code = subprocess.call(args=args, shell=False, stderr=stderr_fh.fileno())
    if return_code != 255:
        sys.exit(return_code)
    stderr_fh.close()
    fh = open(stderr_path, 'r')
    for line in fh:
        m = re.match(r'^[Ss]npEff version (SnpEff)\s*(\d+\.\d+).*$', line)
        if m:
            snpeff_version = m.groups()[0] + m.groups()[1]
            break
    fh.close()
    return snpeff_version


# Download human database 'hg19'
# java -jar snpEff.jar download -v hg19

    regulation_pattern = 'regulation_(.+).bin'
    genome_path = os.path.join(data_dir, genome_version)
    snpeff_version = getSnpeffVersion()
    key = snpeff_version + '_' + genome_version
    if os.path.isdir(genome_path):
        for root, dirs, files in os.walk(genome_path):
            for fname in files:
                if fname.startswith('snpEffectPredictor'):
                    # if snpEffectPredictor.bin download succeeded
                    name = genome_version + (' : ' + organism if organism else '')
                    data_table_entry = dict(key=key, version=snpeff_version, value=genome_version, name=name, path=data_dir)

    parser.add_option('-o', '--organism', dest='organism', action='store', type="string", default=None, help='organism name')
    (options, args) = parser.parse_args()

    filename = args[0]

    params = json.loads(open(filename).read())
    target_directory = params['output_data'][0]['extra_files_path']
    os.mkdir(target_directory)
    data_manager_dict = {}

    # Create SnpEff Reference Data
    for genome_version, organism in zip(options.genome_version.split(','), getOrganismNames(options.genome_version, options.organism).split(',')):
        download_database(data_manager_dict, target_directory, genome_version, organism)

    # save info to json file
    open(filename, 'w').write(json.dumps(data_manager_dict, sort_keys=True))


if __name__ == "__main__":
    main()

10:c6fbc5421697

import re
import subprocess
import sys


def fetch_databases(genome_list=None):
    snpDBs = dict()
    databases_path = 'databases.out'
    args = ['snpEff', 'databases']
    with open(databases_path, 'w') as databases_output:
        return_code = subprocess.call(args=args, shell=False, stdout=databases_output.fileno())
    if return_code:
        sys.exit(return_code)
    try:
        with open(databases_path, 'r') as fh:
            for line in fh:
                fields = line.split('\t')
                if len(fields) >= 2:
                    genome_version = fields[0].strip()
                    if genome_list and genome_version not in genome_list:
                        continue
                    if genome_version.startswith("Genome") or genome_version.startswith("-"):
                        continue
                    description = fields[1].strip()
                    snpDBs[genome_version] = description
    except Exception as e:
        sys.exit('Error parsing %s %s\n' % (databases_path, str(e)))
    return snpDBs


def getOrganismNames(genomes, organisms):
    genome_list = genomes.split(',')

def getSnpeffVersion():
    snpeff_version = 'SnpEff ?.?'
    stderr_path = 'snpeff.err'
    args = ['snpEff', '-h']
    with open(stderr_path, 'w') as stderr_fh:
        return_code = subprocess.call(args=args, shell=False, stderr=stderr_fh.fileno())
    if return_code != 255:
        sys.exit(return_code)
    with open(stderr_path) as fh:
        for line in fh:
            m = re.match(r'^[Ss]npEff version (SnpEff)\s*(\d+\.\d+).*$', line)
            if m:
                snpeff_version = m.groups()[0] + m.groups()[1]
                break
    return snpeff_version


# Download human database 'hg19'
# java -jar snpEff.jar download -v hg19

    regulation_pattern = 'regulation_(.+).bin'
    genome_path = os.path.join(data_dir, genome_version)
    snpeff_version = getSnpeffVersion()
    key = snpeff_version + '_' + genome_version
    if os.path.isdir(genome_path):
        for _, _, files in os.walk(genome_path):
            for fname in files:
                if fname.startswith('snpEffectPredictor'):
                    # if snpEffectPredictor.bin download succeeded
                    name = genome_version + (' : ' + organism if organism else '')
                    data_table_entry = dict(key=key, version=snpeff_version, value=genome_version, name=name, path=data_dir)

    parser.add_option('-o', '--organism', dest='organism', action='store', type="string", default=None, help='organism name')
    (options, args) = parser.parse_args()

    filename = args[0]

    with open(filename) as fh:
        params = json.load(fh)
    target_directory = params['output_data'][0]['extra_files_path']
    os.mkdir(target_directory)
    data_manager_dict = {}

    # Create SnpEff Reference Data
    for genome_version, organism in zip(options.genome_version.split(','), getOrganismNames(options.genome_version, options.organism).split(',')):
        download_database(data_manager_dict, target_directory, genome_version, organism)

    # save info to json file
    with open(filename, 'w'):
        json.dump(data_manager_dict, fh, sort_keys=True)


if __name__ == "__main__":
    main()