def remove_UTR_ensembl_exons (protein_id, species, exons):
'''
Removes the untranslated regions from ensembl exons
This is for the purpose of statistics generating
'''
pc = ProteinContainer.Instance()
dmc = DataMapContainer.Instance()
dm_key = (protein_id, species)
try:
dm = dmc.get(dm_key)
except KeyError:
return None
new_exons =[]
for exon in exons:
new_exon = EnsemblExon((exon.ref_protein_id, exon.species), exon.exon_id, exon.start, exon.stop, exon.strand, exon.sequence)
new_exon.set_exon_ordinal(exon.ordinal)
return new_exons
def load_exons (self):
'''
Load the exons from the fasta file and create
the dictionary mapping them by their Ensembl id.
Exons are given appropriate ordinals.
'''
data_map_container = DataMapContainer.Instance()
logger = Logger.Instance()
containers_logger = logger.get_logger('containers')
data_map = data_map_container.get((self.ref_protein_id, self.species))
self.strand = data_map.strand
fasta_path = self.get_exon_file_path()
try:
fasta = open(fasta_path, 'r')
except IOError:
containers_logger.error("%s,%s,%s" % (self.ref_protein_id, self.species, "Loading ensembl exons failed."))
return None
fasta.close()
exon_list = []
seq_records = read_seq_records_from_file(fasta_path, IUPAC.ambiguous_dna)
for seq_record in seq_records:
(start, stop, transcript_id, exon_id, strand) = seq_record.id.split('|')
if (int(strand) == 1):
self.strand = 1
exon = EnsemblExon((self.ref_protein_id, self.species), exon_id, start, stop, strand, seq_record.seq)
else:
self.strand = -1
exon = EnsemblExon((self.ref_protein_id, self.species), exon_id, stop, start, strand, seq_record.seq)
exon_list.append(exon)
fasta.close()
self.exons = dict([(exon.exon_id, exon) for exon in exon_list])
# assign orinals to exons
ordinal = 1
if self.strand == 1:
for exon in sorted (self.exons.values(), key = lambda exon: exon.start ):
exon.set_exon_ordinal(ordinal)
ordinal += 1
else:
for exon in sorted (self.exons.values(), key = lambda exon: exon.start, reverse = True):
exon.set_exon_ordinal(ordinal)
ordinal += 1
return exon_list
