Python get_data_from_sampleの例

コード例 #1

ファイル: peaks.py プロジェクト: yepl/bcbio-nextgen

def create_peaktable(samples):
    """create a table of peak counts per sample to use with differential peak calling
    """
    data = dd.get_data_from_sample(samples[0])
    peakcounts = []
    out_dir = os.path.join(dd.get_work_dir(data), "consensus")
    out_file = os.path.join(out_dir, "consensus-counts.tsv")
    if dd.get_chip_method(data) == "chip":
        for data in dd.sample_data_iterator(samples):
            peakcounts.append(tz.get_in(("peak_counts"), data))
    elif dd.get_chip_method(data) == "atac":
        for data in dd.sample_data_iterator(samples):
            if bam.is_paired(dd.get_work_bam(data)):
                peakcounts.append(tz.get_in(("peak_counts", "NF"), data))
            else:
                logger.info(f"Creating peak table from full BAM file because "
                            f"{dd.get_work_bam(data)} is single-ended.")
                peakcounts.append(tz.get_in(("peak_counts", "full"), data))
    combined_peaks = count.combine_count_files(peakcounts,
                                               out_file,
                                               ext=".counts")
    new_data = []
    for data in dd.sample_data_iterator(samples):
        data = tz.assoc_in(data, ("peak_counts", "peaktable"), combined_peaks)
        new_data.append(data)
    new_samples = dd.get_samples_from_datalist(new_data)
    return new_samples

コード例 #2

ファイル: peaks.py プロジェクト: Humaasif/bcbio-nextgen

def create_peaktable(samples):
    """create a table of peak counts per sample to use with differential peak calling
    """
    data = dd.get_data_from_sample(samples[0])
    peakcounts = []
    out_dir = os.path.join(dd.get_work_dir(data), "consensus")
    out_file = os.path.join(out_dir, "consensus-counts.tsv")
    if dd.get_chip_method(data) == "chip":
        for data in dd.sample_data_iterator(samples):
            peakcounts.append(tz.get_in(("peak_counts"), data))
    elif dd.get_chip_method(data) == "atac":
        for data in dd.sample_data_iterator(samples):
            peakcounts.append(tz.get_in(("peak_counts", "NF"), data))
    combined_peaks = count.combine_count_files(peakcounts,
                                               out_file,
                                               ext=".counts")
    new_data = []
    for data in dd.sample_data_iterator(samples):
        data = tz.assoc_in(data, ("peak_counts", "peaktable"), combined_peaks)
        new_data.append(data)
    new_samples = dd.get_samples_from_datalist(new_data)
    return new_samples