def main ():
referenced_species = "Homo_sapiens"
# 'ENSP00000253108', 'Ailuropoda_melanoleuca', 'ensembl'
protein_list_raw = FileUtilities.get_protein_list()
protein_list = []
for protein_tuple in protein_list_raw:
protein_list.append(protein_tuple[0])
fill_all_containers(False)
if(len(sys.argv) < 1):
print "Usage: {0} <blastn | tblastn | SW_gene | SW_exon | all> \n".format(sys.argv[0])
exit
mode = sys.argv[1]
populate_referenced_species_databases(protein_list, referenced_species)
if (mode == "blastn"):
populate_blastn_alignments(protein_list)
elif (mode == "tblastn"):
populate_tblastn_alignments(protein_list)
elif (mode == "SW_gene"):
populate_SW_gene_alignments(protein_list)
elif (mode == "SW_exon"):
populate_SW_exon_alignments(protein_list)
elif (mode == "all"):
populate_blastn_alignments(protein_list)
populate_tblastn_alignments(protein_list)
populate_SW_gene_alignments(protein_list)
populate_SW_exon_alignments(protein_list)
else:
print "Usage: {0} <blastn | tblastn | SW_gene | SW_exon | all> \n".format(sys.argv[0])
exit
def create_msa_alignments ():
dc = DirectoryCrawler()
pc = ProteinContainer.Instance()
dmc = DataMapContainer.Instance()
acg = AlignmentCommandGenerator()
fill_all_containers(False)
for (prot_id, exon_num) in get_protein_list():
if not check_status_file(prot_id):
continue
ref_prot_rec = pc.get(prot_id).get_sequence_record()
exoloc_proteins = []
ensembl_proteins = []
exoloc_proteins.append(ref_prot_rec)
ensembl_proteins.append(ref_prot_rec)
assembled_dir = dc.get_assembled_protein_path(prot_id)
for fasta in sorted(os.listdir(assembled_dir)):
if fasta == "Homo_sapiens.fa":
continue
abs_fasta = "%s/%s" % (assembled_dir, fasta)
prot_rec = load_fasta_single_record(abs_fasta, IUPAC.protein)
exoloc_proteins.append(prot_rec)
species_list = get_species_list(prot_id, None)
for species in species_list:
if species == "Homo_sapiens":
continue
data_map = dmc.get((prot_id, species))
prot_rec = pc.get(data_map.protein_id).get_sequence_record()
prot_rec.id = species
ensembl_proteins.append(prot_rec)
msa_exoloc_path = "%s/msa_exoloc.fa" % dc.get_mafft_path(prot_id)
msa_ensembl_path = "%s/msa_ensembl.fa" % dc.get_mafft_path(prot_id)
write_seq_records_to_file(msa_exoloc_path, exoloc_proteins)
write_seq_records_to_file(msa_ensembl_path, ensembl_proteins)
cmd = acg.generate_mafft_command(msa_exoloc_path, "%s/msa_exoloc.afa" % dc.get_mafft_path(prot_id))
print cmd
os.system(cmd)
cmd = acg.generate_mafft_command(msa_ensembl_path, "%s/msa_ensembl.afa" % dc.get_mafft_path(prot_id))
print cmd
os.system(cmd)
def create_species_msa_alignments ():
dc = DirectoryCrawler()
pc = ProteinContainer.Instance()
dmc = DataMapContainer.Instance()
acg = AlignmentCommandGenerator()
fill_all_containers(False)
for (prot_id, exon_num) in get_protein_list():
if not check_status_file(prot_id):
continue
ref_prot_rec = pc.get(prot_id).get_sequence_record()
ref_prot_rec.id = "Homo_sapiens"
assembled_dir = dc.get_assembled_protein_path(prot_id)
species_list = get_species_list(prot_id, None)
for species in species_list:
protein_recs = []
protein_recs.append(ref_prot_rec)
if species == "Homo_sapiens":
continue
data_map = dmc.get((prot_id, species))
prot_rec = pc.get(data_map.protein_id).get_sequence_record()
prot_rec.id = species
protein_recs.append(prot_rec)
if "%s.fa" % species in os.listdir(assembled_dir):
exoloc_protein_rec = load_fasta_single_record("%s/%s.fa" % (assembled_dir, species), IUPAC.protein)
protein_recs.append(exoloc_protein_rec)
msa_species_path = "%s/%s.fa" % (dc.get_mafft_path(prot_id), species)
if len(protein_recs) == 1:
continue
write_seq_records_to_file(msa_species_path, protein_recs)
cmd = acg.generate_mafft_command(msa_species_path, "%s/%s.afa" % (dc.get_mafft_path(prot_id), species))
print cmd
os.system(cmd)
os.remove(msa_species_path)
def main ():
fill_all_containers(False)
generate_SW_exon_alignments2("ENSP00000341765")
for ref_exon in self.ref_exons.get_coding_exons():
bea = self.best_exons[ref_exon.exon_id]
if not bea:
whole_protein_cdna += "N" * len(ref_exon.sequence)
elif bea.status in ["both", "ensembl"]:
whole_protein_cdna += bea.ensembl_alignment.get_cDNA(len(whole_protein_cdna))
else:
whole_protein_cdna += bea.sw_gene_alignment.create_cDNA()
return whole_protein_cdna.translate()
if __name__ == '__main__':
fill_all_containers(True)
bpp = BestProteinProduct("ENSP00000341765", "Ailuropoda_melanoleuca", "Homo_sapiens")
bpp.decide_on_best_exon_alignments()
bpp.patch_interexon_AAS()
print bpp.export_spec_protein_translation()
be = bpp.best_exons
print
def main():
fill_all_containers(True)
ec = ExonContainer.Instance()
# translate_alignment_exons()
create_statistics(get_protein_list())
def main ():
#ERROR FILE:::
err_f = open('/home/marioot/err_status_monday.txt', 'w')
fill_all_containers(True)
protein_tuples = get_protein_list()
ec = ExonContainer.Instance()
beac = BestExonAlignmentContainer.Instance()
dc = DirectoryCrawler()
for (protein_id, exon_num) in protein_tuples:
if int(exon_num) > 15:
print "too big"
continue
species_list = get_species_list(protein_id, None)
try:
ref_exons = ec.get((protein_id, "Homo_sapiens", "ensembl"))
except KeyError:
print "ERROR: No protein %s" % protein_id
continue
for species in species_list:
try:
print "\nBest_exon_al: %s, %s" % (protein_id, species)
err_f.write("%s, %s" % (protein_id, species))
bpp = BestProteinProduct (protein_id, species, "Homo_sapiens")
bpp.load_alignments()
bpp.decide_on_best_exons()
#bpp.patch_interexon_AAS()
for ref_exon in ref_exons.get_coding_exons():
best_exon_alignment = bpp.best_exons[ref_exon.exon_id]
if best_exon_alignment:
beac.add(ref_exon.exon_id, species, best_exon_alignment)
print "%d. Exon status: %s (%s)" % (ref_exon.ordinal, best_exon_alignment.status, ref_exon.exon_id)
if best_exon_alignment.sw_gene_alignment:
print ref_exon.sequence[ref_exon.frame:].translate()
best_exon_alignment.sw_gene_alignment.create_cDNA()
print "\tAdded %2d alignment pieces" % (len(best_exon_alignment.sw_gene_alignment.alignment_pieces))
for al_piece in best_exon_alignment.sw_gene_alignment.alignment_pieces:
print "\t\t%s:" % (al_piece.type),
if al_piece.type in ["coding", "insertion"]:
print "PROT: %d-%d, GENOME: %d-%d, %s" % (al_piece.ref_protein_start,
al_piece.ref_protein_stop,
al_piece.genomic_start,
al_piece.genomic_stop,
al_piece.sequence_id)
print "\t\t\tHUMAN:", al_piece.ref_protein_seq
print "\t\t\tSPEC :", al_piece.spec_protein_seq
else:
print
whole_prot = bpp.get_spec_protein_translation()
whole_prot_rec = SeqRecord(whole_prot, id = species, description = "assembled_protein")
file_name = "%s/%s.fa" % (dc.get_assembled_protein_path(protein_id), species)
SeqIO.write(whole_prot_rec, file_name, "fasta")
print beac.get("ENSE00002199725", species)
except Exception, e:
print '{0} {1} \n'.format(protein_id, species)
err_f.write('{0} {1} \n'.format(protein_id, species))