def set_sister_species_sentence(dm: WBDataManager,
conf_parser: GenedescConfigParser,
sister_sp_fullname, sister_df: WBDataManager,
species, organism, gene_desc: GeneDescription,
gene: Gene):
best_ortholog = dm.get_best_orthologs_for_gene(
gene_desc.gene_id,
orth_species_full_name=[sister_sp_fullname],
sister_species_data_fetcher=sister_df,
ecode_priority_list=[
"EXP", "IDA", "IPI", "IMP", "IGI", "IEP", "HTP", "HDA", "HMP",
"HGI", "HEP"
])[0][0]
if not best_ortholog[0].startswith("WB:"):
best_ortholog[0] = "WB:" + best_ortholog[0]
sister_sentences_generator = OntologySentenceGenerator(
gene_id=best_ortholog[0],
module=Module.GO,
data_manager=sister_df,
config=conf_parser,
humans=sister_sp_fullname == "H**o sapiens",
limit_to_group="EXPERIMENTAL")
sister_sp_module_sentences = sister_sentences_generator.get_module_sentences(
aspect='P',
qualifier="involved_in",
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
if sister_sp_module_sentences.contains_sentences():
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.SISTER_SP,
description="in " +
species[species[organism]["main_sister_species"]]["name"] + ", " +
best_ortholog[1] + " " +
sister_sp_module_sentences.get_description())
def test_get_common_ancestors(self):
self.load_go_ontology()
generator = OntologySentenceGenerator(gene_id="WB:WBGene00000912", module=Module.GO,
data_manager=self.df, config=self.conf_parser)
node_ids = generator.terms_groups[('P', '')]["EXPERIMENTAL"]
common_ancestors = get_all_common_ancestors(node_ids, generator.ontology)
self.assertTrue(len(common_ancestors) > 0, "Common ancestors not found")
associations = [association for subj_associations in self.df.go_associations.associations_by_subj.values() for
association in subj_associations]
associations.append(DataManager.create_annotation_record(source_line="", gene_id="WB:WBGene00003931",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="GO:0043055", qualifiers="", aspect="P",
ecode="EXP", references="", prvdr="WB", date=""))
associations.append(DataManager.create_annotation_record(source_line="", gene_id="WB:WBGene00003931",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="GO:0061065", qualifiers="", aspect="P",
ecode="EXP", references="", prvdr="WB", date=""))
associations.append(DataManager.create_annotation_record(source_line="", gene_id="WB:WBGene00003931",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="GO:0043054", qualifiers="", aspect="P",
ecode="EXP", references="", prvdr="WB", date=""))
associations.append(DataManager.create_annotation_record(source_line="", gene_id="WB:WBGene00003931",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="GO:0043053", qualifiers="", aspect="P",
ecode="EXP", references="", prvdr="WB", date=""))
self.df.go_associations = AssociationSetFactory().create_from_assocs(assocs=associations,
ontology=self.df.go_ontology)
self.conf_parser.config["go_sentences_options"]["exclude_terms"].append("GO:0040024")
generator = OntologySentenceGenerator(gene_id="WB:WBGene00003931", module=Module.GO,
data_manager=self.df, config=self.conf_parser)
node_ids = generator.terms_groups[('P', '')]["EXPERIMENTAL"]
common_ancestors = get_all_common_ancestors(node_ids, generator.ontology)
self.assertTrue("GO:0040024" not in common_ancestors, "Common ancestors contain blacklisted term")
def test_expression_the_cell_renaming_to_widely(self):
self.df.load_ontology_from_file(
ontology_type=DataType.EXPR,
ontology_url=self.df.expression_ontology_url,
ontology_cache_path=self.df.expression_ontology_cache_path,
config=self.conf_parser)
self.df.load_associations_from_file(
associations_type=DataType.EXPR,
associations_url=self.df.expression_associations_url,
associations_cache_path=self.df.expression_associations_cache_path,
config=self.conf_parser)
gene_desc = GeneDescription(gene_id="WB:WBGene00007352",
gene_name="cdc-48.1",
add_gene_name=False)
expr_sentence_generator = OntologySentenceGenerator(
gene_id=gene_desc.gene_id,
module=Module.EXPRESSION,
data_manager=self.df,
config=self.conf_parser)
expression_module_sentences = expr_sentence_generator.get_module_sentences(
config=self.conf_parser,
aspect='A',
qualifier="Verified",
merge_groups_with_same_prefix=True,
keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=expression_module_sentences,
module=Module.EXPRESSION)
self.assertTrue("is expressed widely" in gene_desc.description)
def set_information_poor_sentence(orth_fullnames: List[str], selected_orthologs, ensembl_hgnc_ids_map,
conf_parser: GenedescConfigParser, human_df_agr: DataManager,
gene_desc: GeneDescription, dm: WBDataManager, gene: Gene):
if len(orth_fullnames) == 1 and orth_fullnames[0] == "H**o sapiens":
best_orth = get_best_human_ortholog_for_info_poor(selected_orthologs, ensembl_hgnc_ids_map,
conf_parser.get_annotations_priority(module=Module.GO),
human_df_agr, config=conf_parser)
if best_orth:
if not best_orth.startswith("RGD:"):
best_orth = "RGD:" + best_orth
human_go_sent_generator = OntologySentenceGenerator(gene_id=best_orth, module=Module.GO,
data_manager=human_df_agr, config=conf_parser,
humans=False, limit_to_group="EXPERIMENTAL")
human_func_module_sentences = human_go_sent_generator.get_module_sentences(
config=conf_parser, aspect='F', merge_groups_with_same_prefix=True, keep_only_best_group=True)
human_func_sent = human_func_module_sentences.get_description()
if human_func_sent:
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.INFO_POOR_HUMAN_FUNCTION, description="human " +
human_df_agr.go_associations.subject_label_map[
best_orth] + " " + human_func_sent)
protein_domains = dm.protein_domains[gene_desc.gene_id[3:]]
if protein_domains:
dom_word = "domain"
if len(protein_domains) > 1:
dom_word = "domains"
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.PROTEIN_DOMAIN,
description="is predicted to encode a protein with the following " + dom_word + ": " +
concatenate_words_with_oxford_comma([ptdom[1] if ptdom[1] != "" else ptdom[0] for
ptdom in protein_domains]))
def set_tissue_expression_sentence(dm, gene, conf_parser, gene_desc):
expr_sentence_generator = OntologySentenceGenerator(gene_id=gene.id, module=Module.EXPRESSION, data_manager=dm,
config=conf_parser)
expression_module_sentences = expr_sentence_generator.get_module_sentences(
config=conf_parser, aspect='A', qualifier="Verified", merge_groups_with_same_prefix=True,
keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(module_sentences=expression_module_sentences,
module=Module.EXPRESSION)
gene_desc.set_initial_stats(module=Module.EXPRESSION, sentence_generator=expr_sentence_generator)
def set_expression_module(df: DataManager, conf_parser: GenedescConfigParser, gene_desc: GeneDescription, gene: Gene):
expr_sentence_generator = OntologySentenceGenerator(gene_id=gene.id, module=Module.EXPRESSION, data_manager=df,
config=conf_parser)
expression_module_sentences = expr_sentence_generator.get_module_sentences(
aspect='A', qualifier="Verified", merge_groups_with_same_prefix=True, keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(module_sentences=expression_module_sentences,
module=Module.EXPRESSION)
gene_desc.set_or_update_initial_stats(module=Module.EXPRESSION, sent_generator=expr_sentence_generator,
module_sentences=expression_module_sentences)
def set_disease_module(df: DataManager, conf_parser: GenedescConfigParser, gene_desc: GeneDescription, gene: Gene,
human: bool = False):
do_sentence_exp_generator = OntologySentenceGenerator(gene_id=gene.id,
module=Module.DO_EXPERIMENTAL, data_manager=df,
config=conf_parser, limit_to_group="EXPERIMENTAL",
humans=human)
disease_exp_module_sentences = do_sentence_exp_generator.get_module_sentences(
aspect='D', merge_groups_with_same_prefix=True, keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(module=Module.DO_EXPERIMENTAL,
module_sentences=disease_exp_module_sentences)
do_sentence_bio_generator = OntologySentenceGenerator(gene_id=gene.id, module=Module.DO_BIOMARKER,
data_manager=df, config=conf_parser,
limit_to_group="BIOMARKER", humans=human)
disease_bio_module_sentences = do_sentence_bio_generator.get_module_sentences(
aspect='D', merge_groups_with_same_prefix=True, keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(module=Module.DO_BIOMARKER,
module_sentences=disease_bio_module_sentences)
do_via_orth_sentence_generator = OntologySentenceGenerator(
gene_id=gene.id, module=Module.DO_ORTHOLOGY, data_manager=df, config=conf_parser, humans=human)
disease_via_orth_module_sentences = do_via_orth_sentence_generator.get_module_sentences(
aspect='D', merge_groups_with_same_prefix=True, keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(module=Module.DO_ORTHOLOGY,
module_sentences=disease_via_orth_module_sentences)
gene_desc.set_or_update_initial_stats(module=Module.DO_EXPERIMENTAL, sent_generator=do_sentence_exp_generator,
module_sentences=disease_exp_module_sentences)
gene_desc.set_or_update_initial_stats(module=Module.DO_BIOMARKER, sent_generator=do_sentence_bio_generator,
module_sentences=disease_bio_module_sentences)
gene_desc.set_or_update_initial_stats(module=Module.DO_ORTHOLOGY, sent_generator=do_via_orth_sentence_generator,
module_sentences=disease_via_orth_module_sentences)
def test_set_or_extend_module_description_and_final_stats(self):
gene_desc = GeneDescription(gene_id="FB:FBgn0027655", gene_name="Test gene", add_gene_name=False)
go_sent_generator = OntologySentenceGenerator(gene_id="FB:FBgn0027655", module=Module.GO,
data_manager=self.df, config=self.conf_parser)
sentences = go_sent_generator.get_module_sentences(config=self.conf_parser, aspect='P',
qualifier='', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(module=Module.GO_PROCESS, module_sentences=sentences)
self.assertTrue(gene_desc.description, "Is involved in several processes, including axo-dendritic transport, "
"establishment of mitotic spindle orientation, and positive regulation "
"of extent of heterochromatin assembly")
gene_desc = GeneDescription(gene_id="FB:FBgn0027655", gene_name="Test gene", add_gene_name=True)
gene_desc.set_or_extend_module_description_and_final_stats(module=Module.GO_PROCESS, module_sentences=sentences)
self.assertTrue(gene_desc.description, "Test gene is involved in several processes, including axo-dendritic "
"transport, establishment of mitotic spindle orientation, and positive "
"regulation of extent of heterochromatin assembly")
def set_expression_cluster_sentence(dm: WBDataManager,
conf_parser: GenedescConfigParser,
gene_desc: GeneDescription, gene: Gene,
api_manager: APIManager):
expr_sentence_generator = OntologySentenceGenerator(
gene_id=gene.id,
module=Module.EXPRESSION,
data_manager=dm,
config=conf_parser)
ec_gene_id = gene_desc.gene_id[3:]
ec_anatomy_studies = dm.get_expression_cluster_feature(
gene_id=ec_gene_id,
expression_cluster_type=ExpressionClusterType.ANATOMY,
feature=ExpressionClusterFeature.STUDIES)
ec_anatomy_terms = dm.get_expression_cluster_feature(
gene_id=ec_gene_id,
feature=ExpressionClusterFeature.TERMS,
expression_cluster_type=ExpressionClusterType.ANATOMY)
if dm.expression_ontology is not None:
expression_enriched_module_sentences = expr_sentence_generator.get_module_sentences(
aspect='A',
qualifier="Enriched",
merge_groups_with_same_prefix=True,
keep_only_best_group=False)
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.EXPRESSION_CLUSTER_ANATOMY,
description=expression_enriched_module_sentences.get_description(),
additional_postfix_terms_list=ec_anatomy_studies,
additional_postfix_final_word="studies",
use_single_form=True)
elif ec_anatomy_terms:
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.EXPRESSION_CLUSTER_ANATOMY,
description="is enriched in " +
concatenate_words_with_oxford_comma(
ec_anatomy_terms,
separator=conf_parser.get_terms_delimiter()) + " based on",
additional_postfix_terms_list=ec_anatomy_studies,
additional_postfix_final_word="studies",
use_single_form=True)
ec_molreg_terms = dm.get_expression_cluster_feature(
gene_id=ec_gene_id,
expression_cluster_type=ExpressionClusterType.MOLREG,
feature=ExpressionClusterFeature.TERMS)
ec_molreg_studies = dm.get_expression_cluster_feature(
gene_id=ec_gene_id,
feature=ExpressionClusterFeature.STUDIES,
expression_cluster_type=ExpressionClusterType.MOLREG)
ec_genereg_terms = dm.get_expression_cluster_feature(
gene_id=ec_gene_id,
expression_cluster_type=ExpressionClusterType.GENEREG,
feature=ExpressionClusterFeature.TERMS)
ec_genereg_studies = dm.get_expression_cluster_feature(
gene_id=ec_gene_id,
feature=ExpressionClusterFeature.STUDIES,
expression_cluster_type=ExpressionClusterType.GENEREG)
if ec_genereg_terms:
several_word = ""
if len(ec_genereg_terms) > 3:
t_p = [
t_p for t_p in sorted(
[[term, api_manager.get_textpresso_popularity(term)]
for term in ec_genereg_terms],
key=lambda x: (x[1], x[0][1]),
reverse=True)
]
ec_genereg_terms = [term for term, popularity in t_p[0:3]]
several_word = "several genes including "
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.EXPRESSION_CLUSTER_GENE,
description="is affected by " + several_word +
concatenate_words_with_oxford_comma(
ec_genereg_terms,
separator=conf_parser.get_terms_delimiter()) + " based on",
additional_postfix_terms_list=ec_genereg_studies,
additional_postfix_final_word="studies",
use_single_form=True)
if ec_molreg_terms:
several_word = ""
if len(ec_molreg_terms) > 3:
several_word = num2words(
len(ec_molreg_terms)) + " chemicals including "
gene_desc.set_or_extend_module_description_and_final_stats(
module=Module.EXPRESSION_CLUSTER_MOLECULE,
description="is affected by " + several_word +
concatenate_words_with_oxford_comma(
ec_molreg_terms[0:3],
separator=conf_parser.get_terms_delimiter()) + " based on",
additional_postfix_terms_list=ec_molreg_studies,
additional_postfix_final_word="studies",
use_single_form=True)
def test_set_covering_with_ontology(self):
self.load_do_ontology()
self.conf_parser.config["do_via_orth_sentences_options"]["trimming_algorithm"] = "ic"
self.conf_parser.config["do_via_orth_sentences_options"]["max_num_terms"] = 5
associations = [DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:0080028", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:0080056", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:14789", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:0080026", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:14415", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:0080045", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:3371", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:8886", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:674", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:5614", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:11830", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:8398", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:2256", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:5327", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date=""),
DataManager.create_annotation_record(source_line="", gene_id="MGI:88452",
gene_symbol="", gene_type="gene", taxon_id="",
object_id="DOID:1123", qualifiers="", aspect="D",
ecode="ISS", references="", prvdr="WB", date="")]
self.df.do_associations = AssociationSetFactory().create_from_assocs(assocs=associations,
ontology=self.df.do_ontology)
generator = OntologySentenceGenerator(gene_id="MGI:88452", module=Module.DO_ORTHOLOGY,
data_manager=self.df, config=self.conf_parser)
sentences = generator.get_module_sentences(
config=self.conf_parser, aspect='D', qualifier='', merge_groups_with_same_prefix=True,
keep_only_best_group=True, high_priority_term_ids=["DOID:0080028", "DOID:0080056", "DOID:14789",
"DOID:0080026", "DOID:14415", "DOID:0080045"])
print(sentences.get_description())
def set_gene_ontology_module(dm: DataManager, conf_parser: GenedescConfigParser, gene_desc: GeneDescription,
gene: Gene):
go_sent_generator_exp = OntologySentenceGenerator(gene_id=gene.id, module=Module.GO, data_manager=dm,
config=conf_parser, limit_to_group="EXPERIMENTAL")
go_sent_generator = OntologySentenceGenerator(gene_id=gene.id, module=Module.GO, data_manager=dm,
config=conf_parser)
# Generate sentences with experimental annotations only
func_module_sentences_contributes_to = go_sent_generator_exp.get_module_sentences(
aspect='F', qualifier='contributes_to', merge_groups_with_same_prefix=True, keep_only_best_group=True)
func_module_sentences_noq = go_sent_generator_exp.get_module_sentences(
aspect='F', qualifier='', merge_groups_with_same_prefix=True, keep_only_best_group=True)
func_module_sentences_enables = go_sent_generator_exp.get_module_sentences(
aspect='F', qualifier='enables', merge_groups_with_same_prefix=True, keep_only_best_group=True)
# If experimental sentences are all empty, generate sentences with all annotations
if not func_module_sentences_contributes_to.contains_sentences() and \
not func_module_sentences_noq.contains_sentences() and \
not func_module_sentences_enables.contains_sentences():
func_module_sentences_contributes_to = go_sent_generator.get_module_sentences(
aspect='F', qualifier='contributes_to', merge_groups_with_same_prefix=True, keep_only_best_group=True)
func_module_sentences_noq = go_sent_generator.get_module_sentences(
aspect='F', qualifier='', merge_groups_with_same_prefix=True, keep_only_best_group=True)
func_module_sentences_enables = go_sent_generator.get_module_sentences(
aspect='F', qualifier='enables', merge_groups_with_same_prefix=True, keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(module_sentences=func_module_sentences_noq,
module=Module.GO_FUNCTION)
gene_desc.set_or_extend_module_description_and_final_stats(module_sentences=func_module_sentences_enables,
module=Module.GO_FUNCTION)
gene_desc.set_or_extend_module_description_and_final_stats(module_sentences=func_module_sentences_contributes_to,
module=Module.GO_FUNCTION)
proc_module_sentences_noq = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='', merge_groups_with_same_prefix=True, keep_only_best_group=True)
proc_module_sentences_inv = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='involved_in', merge_groups_with_same_prefix=True, keep_only_best_group=True)
proc_module_sentences_acts_pos = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_positive_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_neg = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_negative_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_with_pos = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_or_within_positive_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_with_neg = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_or_within_negative_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_with = go_sent_generator_exp.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_or_within', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
if not proc_module_sentences_noq.contains_sentences() and \
not proc_module_sentences_inv.contains_sentences() and \
not proc_module_sentences_acts_pos.contains_sentences() and \
not proc_module_sentences_acts_neg.contains_sentences() and \
not proc_module_sentences_acts_with_pos.contains_sentences() and \
not proc_module_sentences_acts_with_neg.contains_sentences() and \
not proc_module_sentences_acts_with.contains_sentences():
proc_module_sentences_noq = go_sent_generator.get_module_sentences(
aspect='P', qualifier='', merge_groups_with_same_prefix=True, keep_only_best_group=True)
proc_module_sentences_inv = go_sent_generator.get_module_sentences(
aspect='P', qualifier='involved_in', merge_groups_with_same_prefix=True, keep_only_best_group=True)
proc_module_sentences_acts_pos = go_sent_generator.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_positive_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_neg = go_sent_generator.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_negative_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_with_pos = go_sent_generator.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_or_within_positive_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_with_neg = go_sent_generator.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_or_within_negative_effect', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
proc_module_sentences_acts_with = go_sent_generator.get_module_sentences(
aspect='P', qualifier='acts_upstream_of_or_within', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_noq, module=Module.GO_PROCESS)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_inv, module=Module.GO_PROCESS)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_acts_pos, module=Module.GO_PROCESS)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_acts_neg, module=Module.GO_PROCESS)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_acts_with_pos, module=Module.GO_PROCESS)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_acts_with_neg, module=Module.GO_PROCESS)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences_acts_with, module=Module.GO_PROCESS)
comp_module_sentence_colocalizes_with = go_sent_generator_exp.get_module_sentences(
aspect='C', qualifier='colocalizes_with', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
comp_module_sentences_noq = go_sent_generator_exp.get_module_sentences(
aspect='C', qualifier='', merge_groups_with_same_prefix=True, keep_only_best_group=True)
comp_module_sentences_located = go_sent_generator_exp.get_module_sentences(
aspect='C', qualifier='located_in', merge_groups_with_same_prefix=True, keep_only_best_group=True)
comp_module_sentences_part = go_sent_generator_exp.get_module_sentences(
aspect='C', qualifier='part_of', merge_groups_with_same_prefix=True, keep_only_best_group=True)
comp_module_sentences_active = go_sent_generator_exp.get_module_sentences(
aspect='C', qualifier='is_active_in', merge_groups_with_same_prefix=True, keep_only_best_group=True)
if not comp_module_sentence_colocalizes_with.contains_sentences() and \
not comp_module_sentences_noq.contains_sentences() and \
not comp_module_sentences_located.contains_sentences() and \
not comp_module_sentences_part.contains_sentences() and \
not comp_module_sentences_active.contains_sentences():
comp_module_sentence_colocalizes_with = go_sent_generator.get_module_sentences(
aspect='C', qualifier='colocalizes_with', merge_groups_with_same_prefix=True,
keep_only_best_group=True)
comp_module_sentences_noq = go_sent_generator.get_module_sentences(
aspect='C', qualifier='', merge_groups_with_same_prefix=True, keep_only_best_group=True)
comp_module_sentences_located = go_sent_generator.get_module_sentences(
aspect='C', qualifier='located_in', merge_groups_with_same_prefix=True, keep_only_best_group=True)
comp_module_sentences_part = go_sent_generator.get_module_sentences(
aspect='C', qualifier='part_of', merge_groups_with_same_prefix=True, keep_only_best_group=True)
comp_module_sentences_active = go_sent_generator.get_module_sentences(
aspect='C', qualifier='is_active_in', merge_groups_with_same_prefix=True, keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=comp_module_sentences_noq, module=Module.GO_COMPONENT)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=comp_module_sentences_located, module=Module.GO_COMPONENT)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=comp_module_sentences_part, module=Module.GO_COMPONENT)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=comp_module_sentences_active, module=Module.GO_COMPONENT)
gene_desc.set_or_extend_module_description_and_final_stats(module_sentences=comp_module_sentence_colocalizes_with,
module=Module.GO_COMPONENT)
gene_desc.set_or_update_initial_stats(module=Module.GO_FUNCTION, sent_generator=go_sent_generator,
module_sentences=func_module_sentences_contributes_to)
gene_desc.set_or_update_initial_stats(module=Module.GO_FUNCTION, sent_generator=go_sent_generator,
module_sentences=func_module_sentences_noq)
gene_desc.set_or_update_initial_stats(module=Module.GO_FUNCTION, sent_generator=go_sent_generator,
module_sentences=func_module_sentences_enables)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_noq)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_inv)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_acts_pos)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_acts_neg)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_acts_with_pos)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_acts_with_neg)
gene_desc.set_or_update_initial_stats(module=Module.GO_PROCESS, sent_generator=go_sent_generator,
module_sentences=proc_module_sentences_acts_with)
gene_desc.set_or_update_initial_stats(module=Module.GO_COMPONENT, sent_generator=go_sent_generator,
module_sentences=comp_module_sentence_colocalizes_with)
gene_desc.set_or_update_initial_stats(module=Module.GO_COMPONENT, sent_generator=go_sent_generator,
module_sentences=comp_module_sentences_noq)
gene_desc.set_or_update_initial_stats(module=Module.GO_COMPONENT, sent_generator=go_sent_generator,
module_sentences=comp_module_sentences_located)
gene_desc.set_or_update_initial_stats(module=Module.GO_COMPONENT, sent_generator=go_sent_generator,
module_sentences=comp_module_sentences_part)
gene_desc.set_or_update_initial_stats(module=Module.GO_COMPONENT, sent_generator=go_sent_generator,
module_sentences=comp_module_sentences_active)
def set_gene_ontology_module(dm: DataManager,
conf_parser: GenedescConfigParser,
gene_desc: GeneDescription, gene: Gene):
go_sent_generator_exp = OntologySentenceGenerator(
gene_id=gene.id,
module=Module.GO,
data_manager=dm,
config=conf_parser,
limit_to_group="EXPERIMENTAL")
go_sent_generator = OntologySentenceGenerator(gene_id=gene.id,
module=Module.GO,
data_manager=dm,
config=conf_parser)
contributes_to_module_sentences = go_sent_generator.get_module_sentences(
config=conf_parser,
aspect='F',
qualifier='contributes_to',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
if contributes_to_module_sentences.contains_sentences():
func_module_sentences = go_sent_generator_exp.get_module_sentences(
config=conf_parser,
aspect='F',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=func_module_sentences, module=Module.GO_FUNCTION)
else:
func_module_sentences = go_sent_generator.get_module_sentences(
config=conf_parser,
aspect='F',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=func_module_sentences, module=Module.GO_FUNCTION)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=contributes_to_module_sentences,
module=Module.GO_FUNCTION)
proc_module_sentences = go_sent_generator.get_module_sentences(
config=conf_parser,
aspect='P',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=proc_module_sentences, module=Module.GO_PROCESS)
colocalizes_with_module_sentences = go_sent_generator.get_module_sentences(
config=conf_parser,
aspect='C',
qualifier='colocalizes_with',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
if colocalizes_with_module_sentences.contains_sentences():
comp_module_sentences = go_sent_generator_exp.get_module_sentences(
config=conf_parser,
aspect='C',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=comp_module_sentences, module=Module.GO_COMPONENT)
else:
comp_module_sentences = go_sent_generator.get_module_sentences(
config=conf_parser,
aspect='C',
merge_groups_with_same_prefix=True,
keep_only_best_group=True)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=comp_module_sentences, module=Module.GO_COMPONENT)
gene_desc.set_or_extend_module_description_and_final_stats(
module_sentences=colocalizes_with_module_sentences,
module=Module.GO_COMPONENT)
gene_desc.set_initial_stats(
module=Module.GO_FUNCTION,
sentence_generator=go_sent_generator,
sentence_generator_exp_only=go_sent_generator_exp)
gene_desc.set_initial_stats(
module=Module.GO_PROCESS,
sentence_generator=go_sent_generator,
sentence_generator_exp_only=go_sent_generator_exp)
gene_desc.set_initial_stats(
module=Module.GO_COMPONENT,
sentence_generator=go_sent_generator,
sentence_generator_exp_only=go_sent_generator_exp)