{"id":"W4400140828","doi":"10.1093/bioinformatics/btae237","title":"Predicting protein functions using positive-unlabeled ranking with ontology-based priors","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Prior probability; Benchmark (surveying); Classifier (UML); Ranking (information retrieval); Artificial intelligence; Machine learning; Data mining; Source code; Gene ontology; Function (biology); Ontology; Pattern recognition (psychology); Bayesian probability","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003371523,0.001775481,0.001682004,0.004324429,0.001042357,0.002042976,0.002952232,0.002174607,0.002093424],"category_scores_gemma":[0.01309162,0.0004940143,0.001395419,0.002460825,0.0009447964,0.003587536,0.001986497,0.001880252,0.00239657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001558256,"about_ca_system_score_gemma":0.001715817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005282251,"about_ca_topic_score_gemma":0.01388052,"domain_scores_codex":[0.9969439,0.0008435785,0.0001438835,0.0009123813,0.0009419553,0.0002142674],"domain_scores_gemma":[0.994022,0.002835857,0.0004949927,0.001455625,0.0009391596,0.0002523677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001393436,0.001744165,0.03530864,0.0008947916,0.0003836644,0.0004503644,0.0002997048,0.3219941,0.02719956,0.026413,0.06615528,0.5177633],"study_design_scores_gemma":[0.00003912317,0.0000760882,0.002349627,0.00003150057,0.000034878,0.0001396311,0.00005128241,0.95116,0.005545722,0.03637585,0.004167467,0.00002882075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1536038,0.002170341,0.8059114,0.00132777,0.0001880056,0.0003137536,0.01171566,0.01667091,0.008098375],"genre_scores_gemma":[0.5811549,0.0005322442,0.3771492,0.0006529605,0.0002530995,0.000325858,0.03449809,0.000983884,0.004449745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005282251,"threshold_uncertainty_score":0.01783055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01501881135075159,"score_gpt":0.2557952577102794,"score_spread":0.2407764463595278,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}