def _combine_qc_samples(samples): """Combine split QC analyses into single samples based on BAM files. """ by_bam = collections.defaultdict(list) for data in [utils.to_single_data(x) for x in samples]: batch = dd.get_batch(data) or dd.get_sample_name(data) if not isinstance(batch, (list, tuple)): batch = [batch] batch = tuple(batch) by_bam[(dd.get_align_bam(data) or dd.get_work_bam(data), batch)].append(data) out = [] for data_group in by_bam.values(): data = data_group[0] alg_qc = [] qc = {} metrics = {} for d in data_group: qc.update(dd.get_summary_qc(d)) metrics.update(dd.get_summary_metrics(d)) alg_qc.extend(dd.get_algorithm_qc(d)) data["config"]["algorithm"]["qc"] = alg_qc data["summary"]["qc"] = qc data["summary"]["metrics"] = metrics out.append([data]) return out
def _combine_qc_samples(samples): """Combine split QC analyses into single samples based on BAM files. """ by_bam = collections.defaultdict(list) for data in [utils.to_single_data(x) for x in samples]: batch = dd.get_batch(data) or dd.get_sample_name(data) if not isinstance(batch, (list, tuple)): batch = [batch] batch = tuple(batch) by_bam[(dd.get_align_bam(data), batch)].append(data) out = [] for data_group in by_bam.values(): data = data_group[0] alg_qc = [] qc = {} metrics = {} for d in data_group: qc.update(dd.get_summary_qc(d)) metrics.update(dd.get_summary_metrics(d)) alg_qc.extend(dd.get_algorithm_qc(d)) data["config"]["algorithm"]["qc"] = alg_qc data["summary"]["qc"] = qc data["summary"]["metrics"] = metrics out.append([data]) return out