def join(args, outs, chunk_defs, chunk_outs):
molecules = [chunk_out.molecule_h5 for chunk_out in chunk_outs]
metrics = MoleculeCounter.naive_concatenate_metrics(molecules)
metrics[cr_mol_counter.IS_AGGREGATED_METRIC] = True
MoleculeCounter.concatenate(outs.merged_molecules,
molecules,
metrics=metrics)
# Record, for each gem group, the range of barcode indices it can contain.
outs.gem_group_barcode_ranges = {}
for chunk_def, chunk_out in zip(chunk_defs, chunk_outs):
for gg in chunk_out.new_gem_groups:
outs.gem_group_barcode_ranges[str(gg)] = [
chunk_def.barcode_idx_offset, chunk_def.barcode_idx_end
]
def join(args, outs, chunk_defs, chunk_outs):
summary = cr_utils.merge_jsons_as_dict([
args.extract_reads_summary,
args.attach_bcs_and_umis_summary,
args.mark_duplicates_summary,
])
# Hack for getting reference metadata -
# this used to be computed in prior stages.
# This is needed for storage in the molecule_info HDF5.
tmp_reporter = cr_report.Reporter()
tmp_reporter.store_reference_metadata(args.reference_path,
cr_constants.REFERENCE_TYPE,
cr_constants.REFERENCE_METRIC_PREFIX)
ref_metadata = tmp_reporter.report(cr_constants.DEFAULT_REPORT_TYPE)
summary.update(ref_metadata)
# Load library info from BAM
in_bam = tk_bam.create_bam_infile(args.inputs[0])
library_info = rna_library.get_bam_library_info(in_bam)
metrics = MoleculeCounter.get_metrics_from_summary(summary, library_info,
args.recovered_cells,
args.force_cells)
input_h5_filenames = [chunk_out.output for chunk_out in chunk_outs]
# update with metrics that were computed in the chunks
chunk_metric = cr_mol_counter.USABLE_READS_METRIC
summed_lib_metrics = MoleculeCounter.sum_library_metric(
input_h5_filenames, chunk_metric)
for lib_key, value in summed_lib_metrics.iteritems():
metrics[cr_mol_counter.LIBRARIES_METRIC][lib_key][chunk_metric] = value
MoleculeCounter.concatenate(outs.output,
input_h5_filenames,
metrics=metrics)