def count_transcripts(cargs):
args, contig = cargs
if args.alleles is not None:
allele_resolver = alleleTools.AlleleResolver(
args.alleles, lazyLoad=(not args.loadAllelesToMem))
else:
allele_resolver = None
contig_mapping = None
if args.contigmapping == 'danio':
contig_mapping = {
'1': 'CM002885.2',
'2': 'CM002886.2',
'3': 'CM002887.2',
'4': 'CM002888.2',
'5': 'CM002889.2',
'6': 'CM002890.2',
'7': 'CM002891.2',
'8': 'CM002892.2',
'9': 'CM002893.2',
'10': 'CM002894.2',
'11': 'CM002895.2',
'12': 'CM002896.2',
'13': 'CM002897.2',
'14': 'CM002898.2',
'15': 'CM002899.2',
'16': 'CM002900.2',
'17': 'CM002901.2',
'18': 'CM002902.2',
'19': 'CM002903.2',
'20': 'CM002904.2',
'21': 'CM002905.2',
'22': 'CM002906.2',
'23': 'CM002907.2',
'24': 'CM002908.2',
'25': 'CM002909.2',
}
# Load features
contig_mapping = None
#conversion_table = get_gene_id_to_gene_name_conversion_table(args.gtfexon)
features = singlecellmultiomics.features.FeatureContainer()
if contig_mapping is not None:
features.remapKeys = contig_mapping
features.loadGTF(
args.gtfexon,
select_feature_type=['exon'],
identifierFields=(
'exon_id',
'transcript_id'),
store_all=True,
head=args.hf,
contig=contig)
features.loadGTF(
args.gtfintron,
select_feature_type=['intron'],
identifierFields=['transcript_id'],
store_all=True,
head=args.hf,
contig=contig)
# What is used for assignment of molecules?
if args.method == 'nla':
moleculeClass = singlecellmultiomics.molecule.AnnotatedNLAIIIMolecule
fragmentClass = singlecellmultiomics.fragment.NLAIIIFragment
pooling_method = 1 # all data from the same cell can be dealt with separately
stranded = None # data is not stranded
elif args.method == 'vasa' or args.method == 'cs':
moleculeClass = singlecellmultiomics.molecule.VASA
fragmentClass = singlecellmultiomics.fragment.SingleEndTranscript
pooling_method = 1
stranded = 1 # data is stranded, mapping to other strand
else:
raise ValueError("Supply a valid method")
# COUNT:
exon_counts_per_cell = collections.defaultdict(
collections.Counter) # cell->gene->umiCount
intron_counts_per_cell = collections.defaultdict(
collections.Counter) # cell->gene->umiCount
junction_counts_per_cell = collections.defaultdict(
collections.Counter) # cell->gene->umiCount
gene_counts_per_cell = collections.defaultdict(
collections.Counter) # cell->gene->umiCount
gene_set = set()
sample_set = set()
annotated_molecules = 0
read_molecules = 0
if args.producebam:
bam_path_produced = f'{args.o}/output_bam_{contig}.unsorted.bam'
with pysam.AlignmentFile(args.alignmentfiles[0]) as alignments:
output_bam = pysam.AlignmentFile(
bam_path_produced, "wb", header=alignments.header)
ref = None
if args.ref is not None:
ref = pysamiterators.iterators.CachedFasta(pysam.FastaFile(args.ref))
for alignmentfile_path in args.alignmentfiles:
i = 0
with pysam.AlignmentFile(alignmentfile_path) as alignments:
molecule_iterator = MoleculeIterator(
alignments=alignments,
check_eject_every=5000,
moleculeClass=moleculeClass,
molecule_class_args={
'features': features,
'stranded': stranded,
'min_max_mapping_quality': args.minmq,
'reference': ref,
'allele_resolver': allele_resolver
},
fragmentClass=fragmentClass,
fragment_class_args={
'umi_hamming_distance': args.umi_hamming_distance,
'R1_primer_length': 4,
'R2_primer_length': 6},
perform_qflag=True,
# when the reads have not been tagged yet, this flag is very
# much required
pooling_method=pooling_method,
contig=contig
)
for i, molecule in enumerate(molecule_iterator):
if not molecule.is_valid():
if args.producebam:
molecule.write_tags()
molecule.write_pysam(output_bam)
continue
molecule.annotate(args.annotmethod)
molecule.set_intron_exon_features()
if args.producebam:
molecule.write_tags()
molecule.write_pysam(output_bam)
allele = None
if allele_resolver is not None:
allele = molecule.allele
if allele is None:
allele = 'noAllele'
# Obtain total count introns/exons reduce it so the sum of the
# count will be 1:
# len(molecule.introns.union( molecule.exons).difference(molecule.junctions))+len(molecule.junctions)
total_count_for_molecule = len(molecule.genes)
if total_count_for_molecule == 0:
continue # we didn't find any gene counts
# Distibute count over amount of gene hits:
count_to_add = 1 / total_count_for_molecule
for gene in molecule.genes:
if allele is not None:
gene = f'{allele}_{gene}'
gene_counts_per_cell[molecule.sample][gene] += count_to_add
gene_set.add(gene)
sample_set.add(molecule.get_sample())
# Obtain introns/exons/splice junction information:
for intron in molecule.introns:
gene = intron
if allele is not None:
gene = f'{allele}_{intron}'
intron_counts_per_cell[molecule.sample][gene] += count_to_add
gene_set.add(gene)
for exon in molecule.exons:
gene = exon
if allele is not None:
gene = f'{allele}_{exon}'
exon_counts_per_cell[molecule.sample][gene] += count_to_add
gene_set.add(gene)
for junction in molecule.junctions:
gene = junction
if allele is not None:
gene = f'{allele}_{junction}'
junction_counts_per_cell[molecule.sample][gene] += count_to_add
gene_set.add(gene)
annotated_molecules += 1
if args.head and (i + 1) > args.head:
print(
f"-head was supplied, {i} molecules discovered, stopping")
break
read_molecules += i
if args.producebam:
output_bam.close()
final_bam_path = bam_path_produced.replace('.unsorted', '')
sort_and_index(bam_path_produced, final_bam_path, remove_unsorted=True)
return (
gene_set,
sample_set,
gene_counts_per_cell,
junction_counts_per_cell,
exon_counts_per_cell,
intron_counts_per_cell,
annotated_molecules,
read_molecules,
contig
)
try:
for i, molecule in enumerate(
singlecellmultiomics.molecule.MoleculeIterator(
alignments=alignments,
moleculeClass=moleculeClass,
yield_invalid=(output is not None),
fragmentClass=fragmentClass,
fragment_class_args={'umi_hamming_distance': 1},
molecule_class_args=molecule_class_args,
contig=args.contig)):
if args.head and (i - 1) >= args.head:
break
if not molecule.is_valid(set_rejection_reasons=True):
if output is not None:
molecule.write_pysam(output)
continue
# Skip sample if not selected
if samples is not None and molecule.sample not in samples:
molecule.set_rejection_reason('sample_not_selected')
if output is not None:
molecule.write_pysam(output)
continue
for (chromosome,
location), call in molecule.methylation_call_dict.items():
if call['context'] == '.': # Only print calls concerning C's
continue
statistics['Input']['molecules'] += 1
statistics['Input']['fragments'] += len(molecule)
# Set (chromosome) unique identifier
molecule.set_meta('mi', f'NLA_{i}')
if args.transcriptome:
molecule.set_intron_exon_features()
if samples is not None and molecule.sample not in samples:
molecule.set_rejection_reason('sample_not_selected')
if output is not None:
molecule.write_pysam(output)
continue
if args.transcriptome:
if not molecule.is_valid():
if molecule.is_multimapped(
) or molecule.get_max_mapping_qual() < args.min_mq:
molecule.set_meta('RF', 'rejected_molecule_mq')
molecule.write_tags()
molecule.write_pysam(output)
statistics['Filtering']['low mapping quality'] += 1
statistics['Filtering']['rejected'] += 1
continue
rejected_reads.append(molecule[0].reads)
continue
statistics['Filtering'][f'valid {args.method} molecule'] += 1
if len(molecule.junctions):
molecule.set_meta('RF', 'transcript_junction')
molecule.set_meta('dt', 'RNA')