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 fill_all_containers (load_alignments):
'''
Fills all the containers with correspondent data.
The containers are: data maps, proteins, genes, transcripts, ensembl exons, and all the alignment exons
'''
dc = DirectoryCrawler()
protein_list_raw = FileUtilities.get_protein_list()
# flatten the raw protein list and take every second element, which is a protein id
protein_list = list(chain.from_iterable(protein_list_raw))[0::2]
algorithms = ["blastn", "tblastn", "sw_gene", "sw_exon"]
for protein_id in protein_list:
dc.generate_directory_tree(protein_id)
ens_exon_container = load_protein_configuration_batch(protein_list)
if ens_exon_container:
load_exon_configuration_batch(protein_list, "ensembl")
load_exon_configuration_batch(protein_list, "genewise")
if load_alignments:
load_exon_configuration_batch (protein_list, "blastn")
load_exon_configuration_batch(protein_list, "tblastn")
load_exon_configuration_batch(protein_list, "sw_gene")
load_exon_configuration_batch(protein_list, "sw_exon")
set_frames_to_coding_exons_batch (protein_list)
remove_overlapping_alignments_batch(protein_list, ["blastn", "tblastn"])
annotate_spurious_alignments_batch(protein_list, algorithms)
def populate_exon_table():
dbm = DBManager.Instance()
ec = ExonContainer.Instance()
dmc = DataMapContainer.Instance()
protein_id_list = FileUtilities.get_protein_list()
species_list = FileUtilities.get_default_species_list()
exon_type_list = ["ensembl", "genewise", "blastn", "tblastn", "sw_gene"]
exon_list = []
for ref_protein_id in protein_id_list:
for species in species_list:
for exon_type in exon_type_list:
exon_key = (ref_protein_id[0], species, exon_type)
try:
exons = ec.get(exon_key).get_ordered_exons()
for exon in exons:
if type(exon) is Exon:
if exon.viability:
exon_list.append(exon)
else:
exon_list.append(exon)
except KeyError:
pass
dbm.update_exon_table(exon_list)
dbm.update_alignment_table(exon_list)
def populate_ortholog_table():
dbm = DBManager.Instance()
dmc = DataMapContainer.Instance()
protein_id_list = FileUtilities.get_protein_list()
species_list = FileUtilities.get_default_species_list()
data_map_list = []
for ref_protein_id in protein_id_list:
for species in species_list:
try:
data_map = dmc.get((ref_protein_id[0], species))
data_map_list.append(data_map)
except KeyError, e:
pass
def populate_gene_table():
dbm = DBManager.Instance()
dmc = DataMapContainer.Instance()
protein_id_list = FileUtilities.get_protein_list()
species_list = FileUtilities.get_default_species_list()
data_map_list = []
for ref_protein_id in protein_id_list:
for species in species_list:
try:
data_map = dmc.get((ref_protein_id[0], species))
data_map_list.append(data_map)
except KeyError:
print "PROTEIN_ID %s ERROR" % (ref_protein_id[0])
print data_map_list
dbm.update_gene_table(data_map_list)
def populate_protein_table():
dbm = DBManager.Instance()
pc = ProteinContainer.Instance()
dmc = DataMapContainer.Instance()
protein_id_list = FileUtilities.get_protein_list()
species_list = FileUtilities.get_default_species_list()
protein_list = []
for ref_protein_id in protein_id_list:
for species in species_list:
try:
protein_id = dmc.get((ref_protein_id[0], species))
protein = pc.get(protein_id.protein_id)
protein_list.append(protein)
except KeyError:
print "PROTEIN_ID %s ERROR" % (ref_protein_id[0])
dbm.update_protein_table(protein_list)
def populate_exon_alignment_piece_table():
dbm = DBManager.Instance()
ec = ExonContainer.Instance()
beac = BestExonAlignmentContainer.Instance()
protein_id_list = FileUtilities.get_protein_list()
species_list = FileUtilities.get_default_species_list()
exon_aln_list = []
for (ref_protein_id, exon_num) in protein_id_list:
for species in species_list:
try:
ref_exons = ec.get((ref_protein_id, 'Homo_sapiens', 'ensembl'))
for ref_exon in ref_exons.get_coding_exons():
best_exon_alignment = beac.get(ref_exon.exon_id, species)
if best_exon_alignment and best_exon_alignment.sw_gene_alignment:
for aln_piece in best_exon_alignment.sw_gene_alignment.alignment_pieces:
if aln_piece.type in ('coding', 'insertion'):
exon_aln_list.append([ref_exon.exon_id, species, aln_piece])
except KeyError, e:
print e
