{"id":"W4413536148","doi":"10.1038/s41598-025-13972-7","title":"Knowledge graph-aided Bayesian active learning for top-K genetic interaction discovery","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Schwartz/Reisman Emergency Medicine Institute; Vector Institute","funders":"Lawrence Livermore National Laboratory; U.S. Department of Energy","keywords":"Pairwise comparison; Computer science; Computational biology; In silico; Bayesian probability; Epistasis; Drug discovery; Functional genomics; Machine learning; Outlier; Genomics; Graph; Gene; Artificial intelligence; Biology; Genome; Bioinformatics; Genetics; Theoretical computer science","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":[0.003262209,0.00185444,0.002891245,0.002626595,0.001004673,0.001485178,0.004410896,0.002678517,0.003291348],"category_scores_gemma":[0.007907771,0.001023521,0.001732922,0.00210881,0.001555007,0.001890325,0.001976851,0.003466073,0.001141498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001675201,"about_ca_system_score_gemma":0.002449956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008403845,"about_ca_topic_score_gemma":0.01277753,"domain_scores_codex":[0.9987172,0.0006035051,0.00007582673,0.0002353681,0.0002540874,0.000114096],"domain_scores_gemma":[0.9941968,0.004541992,0.0003067629,0.0003388474,0.0004272258,0.0001884197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002048551,0.0001736647,0.00107008,0.0001383155,0.0001389977,0.00006310001,0.00006184798,0.8837832,0.001789447,0.008120451,0.002349391,0.1021068],"study_design_scores_gemma":[0.00001610621,0.00001648288,0.00004516405,0.000003892198,0.000007644641,0.000006645897,0.000004104701,0.9929137,0.0002999323,0.006523561,0.0001585503,0.000004293378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01295914,0.0004355717,0.9835565,0.0003337983,0.00002492727,0.00009406809,0.0002906634,0.001466572,0.0008388188],"genre_scores_gemma":[0.5015055,0.0004393605,0.4914429,0.0007601165,0.0001508511,0.0005804621,0.002514331,0.0003126733,0.002293768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008403845,"threshold_uncertainty_score":0.01725239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0112431606763772,"score_gpt":0.3001371588843926,"score_spread":0.2888939982080154,"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."}}