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 get_cluster_names(clusters_dict, out_file=None, white_list_ids=None):
cluster_names = IdSet()
for species in clusters_dict:
species_clusters = IdSet(clusters_dict[species].keys())
cluster_names |= species_clusters
if out_file:
cluster_names.write(out_file)
return cluster_names & IdSet(
white_list_ids) if white_list_ids else cluster_names
def intersect_ids_from_files(files_with_ids_from_group_a,
files_with_ids_from_group_b,
result_file=None,
mode="common"):
a = IdSet()
b = IdSet()
if mode == "common":
expression = lambda a, b: a & b
elif mode == "only_a":
expression = lambda a, b: a - b
elif mode == "only_b":
expression = lambda a, b: b - a
elif mode == "not_common":
expression = lambda a, b: a ^ b
elif mode == "combine":
expression = lambda a, b: a | b
#print(files_with_ids_from_group_a)
for filename in [files_with_ids_from_group_a] if isinstance(
files_with_ids_from_group_a,
str) else files_with_ids_from_group_a:
id_set = IdSet()
id_set.read(filename, comments_prefix="#")
a = a | id_set
for filename in [files_with_ids_from_group_b] if isinstance(
files_with_ids_from_group_b,
str) else files_with_ids_from_group_b:
id_set = IdSet()
id_set.read(filename, comments_prefix="#")
b = b | id_set
result_fd = open(result_file, "w") if result_file else sys.stdout
if mode != "count":
final_set = IdSet(expression(a, b))
final_set.write(result_fd)
else:
result_fd.write(
"Group_A\t%i\nGroup_B\t%i\nCommon\t%i\nOnly_group_A\t%i\nOnly_group_B\t%i\nNot_common\t%i\nAll\t%i\n"
% (len(a), len(b), len(a & b), len(a - b), len(b - a),
len(a ^ b), len(a | b)))
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)