def getChr(self, chr):
"""
Return the genes regions on the specified chr.
:param chr: The chromosome name.
:type chr: str
:return: Genes regions on the specified chr.
:rtype: anacore.region.RegionList
"""
if chr not in self.model:
genes = loadModel(self.filepath, "genes", chr)
self.model[chr] = genes
return self.model[chr]
log = logging.getLogger(os.path.basename(__file__))
log.setLevel(logging.INFO)
log.info("Command: " + " ".join(sys.argv))
# Load selected regions
log.info("Load targeted regions.")
selected_regions = getTargets(args.input_aln, args.input_targets)
# Find shallow areas
log.info("Find shallow areas.")
shallow = shallowFromAlignment(args.input_aln, selected_regions, args.depth_mode, args.min_depth, log)
# Annotate shallow areas
if args.input_annotations is not None:
log.info("Load annotations from {}.".format(args.input_annotations))
transcripts = loadModel(args.input_annotations, "transcripts")
log.info("Annotate shallow areas.")
setTranscriptsAnnotByOverlap(shallow, transcripts)
# Retrieved known variants potentialy masked in shallow areas
for curr_input in args.inputs_variants:
log.info("Load variants from {}.".format(curr_input))
variant_regions = variantsRegionFromVCF(
curr_input,
args.known_min_count,
args.known_symbol_field,
args.known_hgvsc_field,
args.known_hgvsp_field,
args.known_count_field
)
log.info("List potentialy masked mutations.")
group_input = parser.add_argument_group('Inputs') # Inputs
group_input.add_argument('-a', '--input-annotations', help='Path to the genomic annotations file (format: GTF). It contains coordinates for transcripts, exon and cds.')
group_input.add_argument('-d', '--input-domains', help="Path to the domains annotations file (format: TSV). It contains InterPro domains extracted from ensembl's biomart (mandatory fields: 'Transcript stable ID version', 'Protein stable ID version', 'Interpro ID', 'Interpro Short Description', 'Interpro Description', 'Interpro start', 'Interpro end').")
group_output = parser.add_argument_group('Outputs') # Outputs
group_output.add_argument('-o', '--output-annotations', required=True, help='Path to the domains annotations file (format: GFF).')
args = parser.parse_args()
# Logger
logging.basicConfig(format='%(asctime)s -- [%(filename)s][pid:%(process)d][%(levelname)s] -- %(message)s')
log = logging.getLogger(os.path.basename(__file__))
log.setLevel(logging.INFO)
log.info("Command: " + " ".join(sys.argv))
# Load annotations
log.info("Load model from {}.".format(args.input_annotations))
tr_by_id = {tr.annot["id"]: tr for tr in loadModel(args.input_annotations, "transcripts")}
# Parse and convert domains data
log.info("Parse and convert domains data from {}.".format(args.input_domains))
domains_by_tr_id = dict()
with HashedSVIO(args.input_domains) as reader:
for record in reader:
if record['Interpro ID'] != "":
record['Interpro start'] = int(record['Interpro start'])
record['Interpro end'] = int(record['Interpro end'])
tr_id = record['Transcript stable ID version'].split(".", 1)[0]
if tr_id not in tr_by_id:
log.warning("The transcript {} is missing in {}.".format(tr_id, args.input_annotations))
else:
domain_id = record['Interpro ID']
# Get genomic coordinates
required=True,
help='Path to the annotated file. (format: VCF).')
args = parser.parse_args()
# Logger
logging.basicConfig(
format=
'%(asctime)s -- [%(filename)s][pid:%(process)d][%(levelname)s] -- %(message)s'
)
log = logging.getLogger(os.path.basename(__file__))
log.setLevel(logging.INFO)
log.info("Command: " + " ".join(sys.argv))
# Load annotations
log.info("Load model from {}.".format(args.input_annotations))
genes = loadModel(args.input_annotations, "genes")
genes_by_chr = splittedByRef(genes)
# Annot variants
log.info("Annot variants in {}.".format(args.input_variants))
with BreakendVCFIO(args.output_variants, "w",
args.annotation_field) as writer:
with BreakendVCFIO(args.input_variants) as reader:
# Header
writer.copyHeader(reader)
writer.ANN_titles = [
"SYMBOL", "Gene", "Feature", "Feature_type", "Protein",
"STRAND", "RNA_ELT_TYPE", "RNA_ELT_POS", "CDS_position",
"Protein_position", "GENE_SHARD", "IN_FRAME"
]
writer.info[args.annotation_field] = HeaderInfoAttr(
def testLoadModelNCBI(self):
ncbi_genes = loadModel(self.tmp_ncbi_in_gtf, "genes")
self.assertEqual(toBracketTree(self.ncbi_expected),
toBracketTree(ncbi_genes))
def testLoadModelEnsembl(self):
ensembl_genes = loadModel(self.tmp_ensembl_in_gtf, "genes")
self.assertEqual(toBracketTree(self.ensembl_expected),
toBracketTree(ensembl_genes))