def test_named_QCMetricRecord_repr(obj_a1, obj_b):
metrics = [obj_a1, obj_b]
record = QCMetricRecord(metrics, name="dis_my_name")
assert (
record.__repr__() ==
"QCMetricRecord([QCMetric('a', OrderedDict([(1, 2)])), QCMetric('b', OrderedDict([(3, 4)]))], name='dis_my_name')"
)
def main(args):
remove_bam_from_end_re = re.compile("\.bam$")
bam_root = remove_bam_from_end_re.sub("", os.path.basename(args.anno_bam))
with tarfile.open(args.rsem_index, "r:gz") as archive:
archive.extractall(".",
members=make_modified_TarInfo(
archive, "rsem_index"))
rsem_call = shlex.split(
RSEM_COMMAND.format(
rnd_seed=args.rnd_seed,
ncpus=args.ncpus,
ramGB=args.ramGB,
fwd_prob=strand_to_fwd_prob(args.read_strand),
paired_end=format_endedness(args.endedness),
anno_bam=args.anno_bam,
bam_root=bam_root,
))
logger.info("Running RSEM command %s", " ".join(rsem_call))
subprocess.call(rsem_call)
gene_quant_fn = str(bam_root) + "_rsem.genes.results"
number_of_genes_detected = calculate_number_of_genes_detected(
gene_quant_fn)
number_of_genes_detected_dict = {
"number_of_genes_detected": number_of_genes_detected
}
qc_record = QCMetricRecord()
number_of_genes_QC = QCMetric("number_of_genes_detected",
number_of_genes_detected_dict)
qc_record.add(number_of_genes_QC)
with open(str(bam_root) + "_number_of_genes_detected.json", "w") as f:
json.dump(qc_record.to_ordered_dict(), f)
def test_QCMetricRecord_repr(obj_a1, obj_b):
metrics = [obj_a1, obj_b]
record = QCMetricRecord(metrics)
assert (
record.__repr__() ==
"QCMetricRecord([QCMetric('a', OrderedDict([(1, 2)])), QCMetric('b', OrderedDict([(3, 4)]))])"
)
def main(args):
quant1 = pd.read_csv(args.quants[0], sep="\t", header=None, skiprows=4)
quant2 = pd.read_csv(args.quants[1], sep="\t", header=None, skiprows=4)
spearman_correlation = quant1[1].corr(quant2[1], method="spearman")
qc_record = QCMetricRecord()
spearman_metric = QCMetric("spearman_correlation",
{"spearman_correlation": spearman_correlation})
qc_record.add(spearman_metric)
with open(args.output_filename, "w") as fp:
json.dump(qc_record.to_ordered_dict(), fp)
def main(args):
qc_record = QCMetricRecord()
logger.info(
"Reading transcript id to gene type mapping from %s",
args.tr_id_to_gene_type_tsv,
)
tr_to_gene_type_map = read_dict_from_tsv(args.tr_id_to_gene_type_tsv)
logger.info("Calculating gene type counts for bam %s", args.input_bam)
gene_type_counts = get_gene_type_counts(tr_to_gene_type_map, args.input_bam)
gene_type_counts = QCMetric("gene_type_count", gene_type_counts)
qc_record.add(gene_type_counts)
logger.info("Writing QC output into %s", args.output_filename)
with open(args.output_filename, "wt") as fp:
json.dump(qc_record.to_ordered_dict(), fp)
def main(args):
abundance = pd.read_csv(args.abundance, sep="\t")
abundance_filtered = filter_startswith_prefix(
remove_genomic_transcripts(abundance), args.idprefix)
gene_counts = calculate_abundances_aggregated_by_gene(
abundance_filtered, args.counts_colname)
number_of_genes_detected = sum(gene_counts >= 1)
number_of_genes_record = QCMetricRecord()
number_of_genes_metric = QCMetric(
"number_of_genes_detected",
{"number_of_genes_detected": number_of_genes_detected},
)
number_of_genes_record.add(number_of_genes_metric)
with open(args.outfile, "w") as fp:
json.dump(number_of_genes_record.to_ordered_dict(), fp)
def main(args):
logger.info("Reading input tsv: %s" % args.quants)
quants_tsv = pd.read_csv(args.quants, sep="\t", header=None, skiprows=4)
# calculate number of mirnas expressed at cpm>2
per_million = quants_tsv[1].sum() / 1000000
quants_tsv["cpm"] = quants_tsv[1] / per_million
cpm_gte2 = sum(quants_tsv["cpm"] >= 2)
star_qc_record = QCMetricRecord()
cpm_metric = QCMetric("expressed_mirnas", {"expressed_mirnas": cpm_gte2})
# get metrics from star log
star_qc = QCMetric("star_qc_metric", args.star_log, parse_starlog)
star_qc_record.add_all([cpm_metric, star_qc])
# calculate number of reads (unique + multimapping)
reads_mapped = int(star_qc.content["Uniquely mapped reads number"]) + int(
star_qc.content["Number of reads mapped to multiple loci"]
)
reads_mapped_qc = QCMetric("aligned_reads", {"aligned_reads": reads_mapped})
star_qc_record.add(reads_mapped_qc)
logger.info("Writing output json %s" % args.output_filename)
with open(args.output_filename, "w") as fp:
json.dump(star_qc_record.to_ordered_dict(), fp)
def main(args):
rep1_abundance = pd.read_csv(args.rep1_abundance, sep="\t")
rep2_abundance = pd.read_csv(args.rep2_abundance, sep="\t")
rep1_filtered = filter_startswith_prefix(
remove_genomic_transcripts(rep1_abundance), args.rep1_idprefix)
rep2_filtered = filter_startswith_prefix(
remove_genomic_transcripts(rep2_abundance), args.rep2_idprefix)
del rep1_abundance
del rep2_abundance
rep1_counts = calculate_abundances_aggregated_by_gene(
rep1_filtered, rep1_filtered.columns[-1])
rep2_counts = calculate_abundances_aggregated_by_gene(
rep2_filtered, rep2_filtered.columns[-1])
del rep1_filtered
del rep2_filtered
aligned_counts = rep1_counts.align(rep2_counts, join="outer", fill_value=0)
spearman = aligned_counts[0].corr(aligned_counts[1], method="spearman")
correlation_qc = QCMetric("replicates_correlation",
{"spearman_correlation": spearman})
spearman_record = QCMetricRecord([correlation_qc])
with open(args.outfile, "w") as fp:
json.dump(spearman_record.to_ordered_dict(), fp)
def qc_record():
return QCMetricRecord()
def test_QCMetricRecord_getname():
named_record = QCMetricRecord(name="dis_my_name")
assert named_record.name == "dis_my_name"
def test_add_all_failure_because_not_unique(obj_a1, obj_a2, obj_b):
record = QCMetricRecord([obj_a1])
with pytest.raises(AssertionError):
record.add_all([obj_b, obj_a2])
assert len(record) == 1
def test_add_all_to_nonempty_success(qc_record, obj_a1, obj_b, obj_c, obj_d):
metrics = [obj_a1, obj_b]
record = QCMetricRecord(metrics)
record.add_all([obj_c, obj_d])
assert len(record) == 4
def test_init_from_list_success(obj_a1, obj_b):
metrics = [obj_a1, obj_b]
record = QCMetricRecord(metrics)
assert record.metrics[0] is obj_a1
assert record.metrics[1] is obj_b
def test_init_from_list_not_unique(obj_a1, obj_a2):
metrics = [obj_a1, obj_a2]
with pytest.raises(AssertionError):
QCMetricRecord(metrics)