def extract_GO_terms_from_emapper_annotation_file(emapper_annotation_file,
output_file):
GO_terms_dict = SynDict(filename=emapper_annotation_file,
key_index=0,
value_index=5,
split_values=True,
values_separator=",",
comments_prefix="#",
separator="\t")
GO_terms_dict.header = "#protein_id\tGO_terms"
GO_terms_dict.write(output_file, header=True, splited_values=True)
return GO_terms_dict
def extract_predicted_gene_names_from_emapper_annotation_file(
emapper_annotation_file, output_file):
extract_predicted_gene_names_dict = SynDict(
filename=emapper_annotation_file,
key_index=0,
value_index=4,
split_values=True,
values_separator=",",
comments_prefix="#",
separator="\t")
extract_predicted_gene_names_dict.header = "#protein_id\tpredicted_gene_name"
extract_predicted_gene_names_dict.write(output_file,
header=True,
splited_values=True)
return extract_predicted_gene_names_dict
def count_miRNA_reads(self, alignment_file, gff_file, output_prefix, annotation_file_type="GTF",
min_read_fraction_overlap=1.0, feature_type_to_use=None, attribute_type_to_use=None,
sample_name=None, stranded=1):
no_multimapped_read_counts = "%s.no_multimapped_reads.count" % output_prefix
with_multimapped_read_counts = "%s.with_multimapped_reads.count" % output_prefix
all_adjusted_read_counts = "%s.all_adjusted_reads.count" % output_prefix
self.count(alignment_file, gff_file, no_multimapped_read_counts, annotation_file_type=annotation_file_type,
min_read_fraction_overlap=min_read_fraction_overlap, feature_type_to_use=feature_type_to_use,
attribute_type_to_use=attribute_type_to_use, stranded=stranded)
self.count(alignment_file, gff_file, with_multimapped_read_counts, count_multimapped_reads=True,
annotation_file_type=annotation_file_type,
min_read_fraction_overlap=min_read_fraction_overlap, feature_type_to_use=feature_type_to_use,
attribute_type_to_use=attribute_type_to_use, stranded=stranded)
no_multimapped_read_count_dict = SynDict(filename=no_multimapped_read_counts, comments_prefix="#",
key_index=0, value_index=6, expression=int, header=True)
with_multimapped_read_count_dict = SynDict(filename=with_multimapped_read_counts, comments_prefix="#",
key_index=0, value_index=6, expression=int, header=True)
similar_feature_number_dict = SynDict(filename=with_multimapped_read_counts, comments_prefix="#", header=True,
key_index=0, value_index=1, expression=lambda s: len(s.split(";")))
sample_nameeee = sample_name if sample_name else similar_feature_number_dict.header.split()[6]
all_adjusted_read_count_dict = SynDict()
all_adjusted_read_count_dict.header = ".\t%s" % sample_nameeee
#print no_multimapped_read_count_dict
#print with_multimapped_read_count_dict
#print similar_feature_number_dict
for feature_id in no_multimapped_read_count_dict:
all_adjusted_read_count_dict[feature_id] = int(ceil(float(no_multimapped_read_count_dict[feature_id]) + \
(float(with_multimapped_read_count_dict[feature_id]) - float(no_multimapped_read_count_dict[feature_id])) / float(similar_feature_number_dict[feature_id])))
all_adjusted_read_count_dict.write(all_adjusted_read_counts, header=True)