{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002003149,0.0001684099,0.0001445496,0.00008836018,0.000161533,0.00007702003,0.0001205123,0.0002020112,0.00001095855],"category_scores_gemma":[0.00009715319,0.0001254894,0.0000656138,0.000193627,0.0001776821,0.000009327844,0.00005098119,0.0001610314,0.00001396536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002963569,"about_ca_system_score_gemma":0.00026484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001633811,"about_ca_topic_score_gemma":0.00002272885,"domain_scores_codex":[0.9990707,0.00002884151,0.0002620502,0.0001865269,0.0001652399,0.0002866261],"domain_scores_gemma":[0.9995725,0.0000274235,0.00007323123,0.0001922055,0.00006120366,0.00007340077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001322425,0.0003829239,0.02993441,0.003236671,0.001864574,0.0001898421,0.003988767,0.003117381,0.6015276,0.0008729029,0.005419358,0.3481432],"study_design_scores_gemma":[0.003966751,0.003967706,0.003074978,0.002612118,0.0004992938,0.0005313159,0.003674775,0.7399904,0.1636421,0.0000775431,0.07618549,0.001777546],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8381615,0.000615301,0.1593492,0.0002179699,0.0002045608,0.000302178,0.00003532525,0.0001557627,0.0009582308],"genre_scores_gemma":[0.9144986,0.000005450493,0.08464466,0.0002162432,0.0001542934,0.00002652455,0.0001268778,0.00002455371,0.0003028355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.736873,"threshold_uncertainty_score":0.5117309,"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."}}