def extract_monocluster_ids(self,
clusters_dict,
white_list_ids=None,
out_file=None):
"""
Extracts clusters with only one sequence in all species.
"""
monocluster_ids = IdSet()
cluster_names = self.get_cluster_names(clusters_dict)
for cluster_name in cluster_names:
for species in clusters_dict:
if white_list_ids:
if cluster_name not in white_list_ids:
break
if cluster_name not in clusters_dict[species]:
break
if len(clusters_dict[species][cluster_name]) > 1:
break
else:
monocluster_ids.add(cluster_name)
if out_file:
monocluster_ids.write(out_file)
return monocluster_ids
def rename_scaffolds_in_gff(self, input_gff, syn_file, output_prefix, verbose=True):
syn_dict = SynDict(filename=syn_file)
skipped_id_list = IdSet()
output_gff = "%s.renamed.gff" % output_prefix
skipped_gff = "%s.skipped.gff" % output_prefix
skipped_id_file = "%s.skipped_scaffolds.ids" % output_prefix
with self.metaopen(input_gff, "r") as in_fd, \
self.metaopen(output_gff, "w") as out_fd, \
self.metaopen(skipped_gff, "w") as skipped_fd:
for line in in_fd:
if line[0] == "#":
out_fd.write(line)
gff_list = line.split("\t")
if gff_list[0] in syn_dict:
gff_list[0] = syn_dict[gff_list[0]]
out_fd.write("\t".join(gff_list))
else:
skipped_fd.write(line)
skipped_id_list.add(gff_list[0])
if verbose:
print("Not renamed scaffolds: %i" % len(skipped_id_list))
skipped_id_list.write(skipped_id_file)
def convert_rm_out_to_gff(input_file, output_file,
annotated_repeat_classes_file,
annotated_repeat_families_file):
repeat_classes_set = IdSet()
repeat_families_set = IdSet()
with open(input_file, "r") as in_fd:
for i in range(0, 3):
in_fd.readline()
with open(output_file, "w") as out_fd:
for line in in_fd:
tmp = line.strip().split()
strand = "+" if tmp[8] == "+" else "-"
repeat_class_family = tmp[10].split("/")
if len(repeat_class_family) == 1:
repeat_class_family.append(".")
repeat_classes_set.add(repeat_class_family[0])
repeat_families_set.add("/".join(repeat_class_family))
parameters = "Class=%s;Family=%s;Matching_repeat=%s;SW_score=%s;Perc_div=%s;Perc_del=%s;Pers_ins=%s" \
% (repeat_class_family[0], repeat_class_family[1],
tmp[9], tmp[0], tmp[1], tmp[2], tmp[3])
out_fd.write(
"%s\tRepeatMasker\trepeat\t%s\t%s\t.\t%s\t.\t%s\n" %
(tmp[4], tmp[5], tmp[6], strand, parameters))
repeat_classes_set.write(annotated_repeat_classes_file)
repeat_families_set.write(annotated_repeat_families_file)
def get_scaffold_ids_from_gff(gff_file, out_file=None):
scaffold_id_set = IdSet()
with open(gff_file, "r") as gff_fd:
for line in gff_fd:
if line[0] == "#":
continue
scaffold_id = line.split("\t")[0]
scaffold_id_set.add(scaffold_id)
if out_file:
scaffold_id_set.write(out_file)
return scaffold_id_set
complicated_families_syn_dict = SynDict()
complicated_families_syn_ids = IdSet()
sl_keys = list(complicated_families_dict.sl_keys())
for sl_key in sl_keys:
sp_set = set()
for species in complicated_families_dict:
if sl_key not in complicated_families_dict[species]:
continue
tmp = complicated_families_dict[species][sl_key].split(";")
for i in range(0, len(tmp)):
if "_" in tmp[i]:
tmp[i] = tmp[i][2:]
tmp[i] = tmp[i].split(",")
for syn_id in tmp[i]:
complicated_families_syn_ids.add(syn_id)
sp_set.add(syn_id)
complicated_families_syn_dict[sl_key] = sp_set
complicated_families_syn_dict.write("complicated_families_connections.t", splited_values=True)
for entry in complicated_families_dict.all_values():
tmp = entry.split(";")
for i in range(0, len(tmp)):
if "_" in tmp[i]:
tmp[i] = tmp[i][2]
tmp[i] = tmp[i].split(",")
for syn_id in tmp[i]:
complicated_families_syn_ids.add(syn_id)
complicated_families_syn_ids.write("complicated_families_check.ids")
nonassembled.write("splited_to_several_families.t", absent_symbol=".")
accordance_dict[species].read(accordance_file, key_index=1, value_index=0)
if args.name_first:
def split_name(pep_name):
gene_list = pep_name.split(args.name_separator)
return gene_list[0], args.name_separator.join(gene_list[1:])
else:
def split_name(pep_name):
gene_list = pep_name.split(args.name_separator)
return gene_list[-1], args.name_separator.join(gene_list[:-1])
families_with_errors = IdSet()
for family in pep_fam_dict:
cds_fam_dict[family] = []
for pep in pep_fam_dict[family]:
species, pep_name = split_name(pep)
if pep_name in accordance_dict[species]:
cds_name = "%s%s%s" % (species, args.name_separator, accordance_dict[species][pep_name]) if args.name_first else \
"%s%s%s" % (accordance_dict[species][pep_name], args.name_separator, species)
cds_fam_dict[family].append(cds_name)
else:
print("%s %s %s doesn't have associated cds in accordance file" % (family, species, pep_name))
families_with_errors.add(family)
for family in families_with_errors:
cds_fam_dict.pop(family, None)
families_with_errors.write(args.fam_error)
cds_fam_dict.write(args.output, splited_values=True)
