def translate_alignment_exons_for_protein(protein_id, exon_number):
'''
Translates all the proteins for which there is SW to gene alignment
'''
algorithm = "sw_gene"
# instantiate all the utilities
logger = Logger.Instance()
dc = DirectoryCrawler()
translation_logger = logger.get_logger("translator")
# instantiate all the containters
eec = EnsemblExonContainer.Instance()
ec = ExonContainer.Instance()
pc = ProteinContainer.Instance()
failed_species = []
assembled_protein_path = dc.get_assembled_protein_path(protein_id)
# for all the species for which it is required to generate translated protein
for species in get_species_list(protein_id, assembled_protein_path):
# get all you need for the processing
assembled_protein_fasta = "%s/%s.fa" % (dc.get_assembled_protein_path(protein_id), species)
exon_key = (protein_id, species, algorithm)
target_prot = pc.get(protein_id)
target_prot_seq = target_prot.get_sequence_record().seq
try:
exons = ec.get(exon_key)
except KeyError:
translation_logger.error("%s,%s,%s" % (protein_id, species, "No exons available"))
failed_species.append(species)
continue
exons_for_transcription = []
# THIS PART WILL NOT EXIST IN THE NEAR FUTURE
last_translated_exon = False
for al_exon in exons.get_ordered_exons():
ref_exon = eec.get(al_exon.ref_exon_id)
trans_exon = Exon_translation(ref_exon, al_exon)
# if we've already bumped into exon with UTR on its end, all the other exons are not viable
if last_translated_exon:
trans_exon.viability = False
if trans_exon.viability:
(trans_exon, last_translated_exon) = chop_off_start_utr(al_exon.ref_exon_id, trans_exon, target_prot_seq, exon_number)
trans_exon = chop_off_end_utr (al_exon.ref_exon_id, trans_exon, target_prot_seq, exon_number, protein_id)
exons_for_transcription.append(trans_exon)
# up to here - this will get trashed
assemble_and_store_protein (protein_id, species, exons_for_transcription, target_prot_seq, assembled_protein_fasta)
create_protein_alignment (protein_id, species)
write_failed_species_to_status(failed_species, assembled_protein_path)
return failed_species
def set_failed_SW_exon_targets(self, protein_id, failed_species_list):
path = self.crawler.get_SW_exon_path(protein_id)
write_failed_species_to_status(failed_species_list, path)