comparison data_manager/data_manager_snpsift_dbnsfp.py @ 7:fe8a9ab8daf9 draft

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

6:e57f0b0bc73b

#!/usr/bin/env python

import gzip
import json
import optparse
import os

dbNSFP_file_pat = '(dbNSFP(.*)_variant|dbscSNV(.*)).chr(.*)'
tokenize = re.compile(r'(\d+)|(\D+)').findall
dbNSFP_name_pat = r'dbNSFP(v|_light)?(\d*).*?'


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


def get_nsfp_genome_version(name):
    genome_version = 'hg19'
    dbNSFP_name_pat = r'(dbscSNV|dbNSFP(v|_light)?)(\d*).*?'
    m = re.match(dbNSFP_name_pat, name)
    if m:

    return genome_version


def get_annotations(gzip_path):
    annotations = None
    fh = None
    try:
        fh = gzip.open(gzip_path, 'r')
        buf = fh.read(10000)
        lines = buf.splitlines()
        headers = lines[0].split('\t')
        annotations = ','.join([x.strip() for x in headers[4:]])
    except Exception as e:
        stop_err('Error Reading annotations %s : %s' % (gzip_path, e))
    finally:
        if fh:
            fh.close()
    return annotations


def tabix_file(input_fname, output_fname):
    print >> sys.stdout, "tabix_file: %s -> %s" % (input_fname, output_fname)
    ctabix.tabix_compress(input_fname, output_fname, force=True)
    # Column indices are 0-based.
    ctabix.tabix_index(output_fname, seq_col=0, start_col=1, end_col=1)

                    pos = int(line.split('\t')[1])
                    if lastpos and pos < lastpos:
                        tfh.close()
                        tempfiles.append(file + "_%d" % len(tempfiles))
                        tfh = open(tempfiles[-1], 'w')
                        print >> sys.stderr, "%s [%d] pos: %d < %d" % (file, i, pos, lastpos)
                    lastpos = pos
                tfh.write(line)
            tfh.close()
            if len(tempfiles) == 1:
                with open(tempfiles[0], 'r') as tfh:

    parser.add_option('-H', '--snpsiftdbnsfp', dest='snpsiftdbnsfp', action='store', type="string", default=None, help='A history snpsiftdbnsfp dataset')
    parser.add_option('-T', '--dbnsfp_tabular', dest='dbnsfp_tabular', action='store', type="string", default=None, help='A history dbnsfp_tabular dataset')
    (options, args) = parser.parse_args()

    filename = args[0]
    params = json.loads(open(filename).read())
    target_directory = params['output_data'][0]['extra_files_path']
    if not os.path.exists(target_directory):
        os.mkdir(target_directory)
    data_manager_dict = {}
    genome_version = options.dbkey if options.dbkey else 'unknown'

        shutil.copy(options.snpsiftdbnsfp, target_directory)
        shutil.copy(idxpath, target_directory)
        bzip_path = os.path.join(target_directory, bgzip_name)
        db_name = re.sub('(.txt)?.gz$', '', bgzip_name)
    else:
        stop_err('Either --softgenetics or --dbnsfp_tabular required')
    if dbnsfp_tsv:
        bgzip_name = '%s.txt.gz' % db_name
        bzip_path = os.path.join(target_directory, bgzip_name)
        tabix_file(dbnsfp_tsv, bzip_path)
    annotations = get_annotations(bzip_path)

    data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
    data_manager_dict['data_tables'][data_table] = data_manager_dict['data_tables'].get(data_table, [])
    data_manager_dict['data_tables'][data_table].append(data_table_entry)

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


if __name__ == "__main__":
    main()

7:fe8a9ab8daf9

#!/usr/bin/env python
from __future__ import print_function

import gzip
import json
import optparse
import os

dbNSFP_file_pat = '(dbNSFP(.*)_variant|dbscSNV(.*)).chr(.*)'
tokenize = re.compile(r'(\d+)|(\D+)').findall
dbNSFP_name_pat = r'dbNSFP(v|_light)?(\d*).*?'


def get_nsfp_genome_version(name):
    genome_version = 'hg19'
    dbNSFP_name_pat = r'(dbscSNV|dbNSFP(v|_light)?)(\d*).*?'
    m = re.match(dbNSFP_name_pat, name)
    if m:

    return genome_version


def get_annotations(gzip_path):
    annotations = None
    try:
        with gzip.open(gzip_path, 'r') as fh:
            buf = fh.read(10000)
        lines = buf.splitlines()
        headers = lines[0].split('\t')
        annotations = ','.join([x.strip() for x in headers[4:]])
    except Exception as e:
        sys.exit('Error Reading annotations %s : %s' % (gzip_path, e))
    return annotations


def tabix_file(input_fname, output_fname):
    print("tabix_file: %s -> %s" % (input_fname, output_fname))
    ctabix.tabix_compress(input_fname, output_fname, force=True)
    # Column indices are 0-based.
    ctabix.tabix_index(output_fname, seq_col=0, start_col=1, end_col=1)

                    pos = int(line.split('\t')[1])
                    if lastpos and pos < lastpos:
                        tfh.close()
                        tempfiles.append(file + "_%d" % len(tempfiles))
                        tfh = open(tempfiles[-1], 'w')
                        print("%s [%d] pos: %d < %d" % (file, i, pos, lastpos), file=sys.stderr)
                    lastpos = pos
                tfh.write(line)
            tfh.close()
            if len(tempfiles) == 1:
                with open(tempfiles[0], 'r') as tfh:

    parser.add_option('-H', '--snpsiftdbnsfp', dest='snpsiftdbnsfp', action='store', type="string", default=None, help='A history snpsiftdbnsfp dataset')
    parser.add_option('-T', '--dbnsfp_tabular', dest='dbnsfp_tabular', action='store', type="string", default=None, help='A history dbnsfp_tabular dataset')
    (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']
    if not os.path.exists(target_directory):
        os.mkdir(target_directory)
    data_manager_dict = {}
    genome_version = options.dbkey if options.dbkey else 'unknown'

        shutil.copy(options.snpsiftdbnsfp, target_directory)
        shutil.copy(idxpath, target_directory)
        bzip_path = os.path.join(target_directory, bgzip_name)
        db_name = re.sub('(.txt)?.gz$', '', bgzip_name)
    else:
        sys.exit('Either --softgenetics or --dbnsfp_tabular required')
    if dbnsfp_tsv:
        bgzip_name = '%s.txt.gz' % db_name
        bzip_path = os.path.join(target_directory, bgzip_name)
        tabix_file(dbnsfp_tsv, bzip_path)
    annotations = get_annotations(bzip_path)

    data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
    data_manager_dict['data_tables'][data_table] = data_manager_dict['data_tables'].get(data_table, [])
    data_manager_dict['data_tables'][data_table].append(data_table_entry)

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


if __name__ == "__main__":
    main()