chrom_hmm_cnn.py 文件源码

def load_dna_and_chrom_label(args, only_labels=None):
    record_dict = SeqIO.to_dict(SeqIO.parse(args.reference_fasta, "fasta"))
    bed_dict, bed_labels = bed_file_labels_to_dict(args.bed_file)

    train_data = np.zeros(( args.samples, args.window_size, len(args.inputs) ))
    train_labels = np.zeros(( args.samples, len(bed_labels) ))

    idx_offset = (args.window_size/2)

    amiguity_codes = {'K':[0,0,0.5,0.5], 'M':[0.5,0.5,0,0], 'R':[0.5,0,0,0.5], 'Y':[0,0.5,0.5,0], 'S':[0,0.5,0,0.5], 
                      'W':[0.5,0,0.5,0], 'B':[0,0.333,0.333,0.334], 'V':[0.333,0.333,0,0.334],'H':[0.333,0.333,0.334,0],
                      'D':[0.333,0,0.333,0.334], 'X':[0.25,0.25,0.25,0.25], 'N':[0.25,0.25,0.25,0.25]}

    count = 0
    while count < args.samples:
        contig_key, pos = sample_from_bed(bed_dict, contig_key_prefix='chr')
        contig = record_dict[contig_key]
        record = contig[pos-idx_offset: pos+idx_offset]

        cur_label_key = bed_file_label(bed_dict, contig_key, pos)

        if only_labels and not cur_label_key in only_labels:
            continue

        train_labels[count, args.labels[cur_label_key]] = 1

        for i,b in enumerate(record.seq):
            B=b.upper()
            if B in args.inputs.keys():
                train_data[count, i, args.inputs[B]] = 1.0
            elif B in amiguity_codes.keys():
                train_data[count, i, :4] = amiguity_codes[B]
            else:
                print('Error! Unknown code:', b)
                return

        count += 1

    print('Label:', bed_labels.keys(), 'label counts:', np.sum(train_labels, axis=0))
    print('Train data shape:', train_data.shape, ' Training labels shape:', train_labels.shape)

    return (train_data, train_labels)