def prepare_data_for_target_alignment(self,
query_fasta,
target_fasta,
correspondence_file,
out_dir,
correspondence_query_column=0,
correspondence_target_column=1):
query_dict = self.parse_seq_file(query_fasta, "parse")
target_dict = self.parse_seq_file(target_fasta, "parse")
self.safe_mkdir(out_dir)
correspondence_dict = SynDict(filename=correspondence_file,
allow_repeats_of_key=True,
key_index=correspondence_query_column,
value_index=correspondence_target_column)
for query_id in correspondence_dict:
query_outfile = "%s/%s.query.fasta" % (out_dir, query_id)
target_outfile = "%s/%s.target.fasta" % (out_dir, query_id)
SeqIO.write(self.record_by_id_generator(query_dict, [query_id]),
query_outfile,
format="fasta")
SeqIO.write(self.record_by_id_generator(
target_dict, correspondence_dict[query_id]),
target_outfile,
format="fasta")
queries_with_targets_set = set(correspondence_dict.keys())
queries_set = set(query_dict.keys())
return queries_with_targets_set, queries_set - queries_with_targets_set
pass
fam_soft_fd = open(
"%s%s/%s_with_outer_edges.graph" %
(args.output_dir, family_name, family_name), "w")
"""
with open(args.hclust_input, "r") as in_fd:
for line in in_fd:
edge_nodes = line.split("\t")[:2]
if check_edge_soft(edge_nodes, family_genes_ids):
fam_soft_fd.write(line)
"""
for edge in graph_list:
if check_edge_soft(edge[:-1], family_genes_ids):
fam_soft_fd.write("\t".join(edge) + "\n")
fam_soft_fd.close()
fam_strict_fd = open(
"%s%s/%s.graph" % (args.output_dir, family_name, family_name), "w")
with open(
"%s%s/%s_with_outer_edges.graph" %
(args.output_dir, family_name, family_name), "r") as in_fd:
for line in in_fd:
edge_nodes = line.split("\t")[:2]
if check_edge_strict(edge_nodes, family_genes_ids):
fam_strict_fd.write(line)
fam_strict_fd.close()
pool = Pool(args.threads)
pool.map(extract_fam_graph, families_dict.keys())