comparison data_manager/data_manager_snpEff_download.py @ 5:8952990fcab9

Update to snpEff version 3.4 and add data managers to download snpEff genome reference databases

4:47ddc9f4d0b6

    ## E.g.: Information for 'hg19' is stored in data_dir/hg19/
    ##
    ## Note: Since version 2.1 you can use tilde ('~') as first character to refer to your home directory
    ##---
    #data_dir = ~/snpEff/data/
    data_dir = None
    try:
        fh = open(config)
        for i,line in enumerate(fh):
            if line.strip().startswith('data_dir'):
                (k,v) = line.split('=')
                data_dir = os.path.expanduser(v.strip())
                break
    except Exception, e:
        stop_err( 'Error parsing %s %s\n' % (config,str( e )) )
    else:
        fh.close()
    (snpEff_dir,snpEff_jar) = os.path.split(jar_path)
    args = [ 'java','-jar' ]
    args.append( jar_path )
    args.append( 'download' )
    # args.append( '-c' )
    # args.append( 'config' )
    args.append( '-v' )
    args.append( genome_version )
    proc = subprocess.Popen( args=args, shell=False, cwd=snpEff_dir )
    return_code = proc.wait()
    if return_code:

        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(value=genome_version, name=name)
                    _add_data_table_entry( data_manager_dict, 'snpeff_genomedb', data_table_entry )
                else:
                    m = re.match(regulation_pattern,fname)
                    if m:
                        name = m.groups()[0]

5:8952990fcab9

    ## E.g.: Information for 'hg19' is stored in data_dir/hg19/
    ##
    ## Note: Since version 2.1 you can use tilde ('~') as first character to refer to your home directory
    ##---
    #data_dir = ~/snpEff/data/
    data_dir = target_directory
    (snpEff_dir,snpEff_jar) = os.path.split(jar_path)
    args = [ 'java','-jar' ]
    args.append( jar_path )
    args.append( 'download' )
    args.append( '-c' )
    args.append( config )
    args.append( '-dataDir' )
    args.append( data_dir )
    args.append( '-v' )
    args.append( genome_version )
    proc = subprocess.Popen( args=args, shell=False, cwd=snpEff_dir )
    return_code = proc.wait()
    if return_code:

        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(value=genome_version, name=name, path=data_dir)
                    _add_data_table_entry( data_manager_dict, 'snpeff_genomedb', data_table_entry )
                else:
                    m = re.match(regulation_pattern,fname)
                    if m:
                        name = m.groups()[0]