{"id":"W2120688086","doi":"10.1093/bioinformatics/btq262","title":"Fast integration of heterogeneous data sources for predicting gene function with limited annotation","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":139,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Overfitting; Computer science; Function (biology); Data mining; Annotation; Construct (python library); Source code; Artificial intelligence; Gene regulatory network; Machine learning; Association (psychology); Artificial neural network; Gene; Biology; Genetics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003522856,0.001625489,0.001370838,0.005477747,0.0009226913,0.001754308,0.002152865,0.001083381,0.001868875],"category_scores_gemma":[0.02058071,0.0009287316,0.001010426,0.006700854,0.0005161527,0.003776909,0.002963156,0.001671784,0.001485162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000835095,"about_ca_system_score_gemma":0.001042988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004545279,"about_ca_topic_score_gemma":0.006695286,"domain_scores_codex":[0.9979532,0.0005021989,0.0001153449,0.0005605851,0.0007941157,0.00007454831],"domain_scores_gemma":[0.9881814,0.006422484,0.0008620023,0.002589163,0.001638442,0.0003065001],"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":[0.00124313,0.0004521507,0.03642985,0.001173468,0.0007872112,0.00112823,0.0004683798,0.2294551,0.04301911,0.01422714,0.02026845,0.6513477],"study_design_scores_gemma":[0.00005474384,0.00006678026,0.006639164,0.00008619464,0.0001704691,0.0002773985,0.0001244009,0.930553,0.01845847,0.03500907,0.008498976,0.00006135739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05476766,0.0009005142,0.9232993,0.0006857569,0.00007925962,0.0001980284,0.005789605,0.01201439,0.002265512],"genre_scores_gemma":[0.3553764,0.0009559357,0.6169391,0.0002141451,0.0001043696,0.0004819661,0.02345223,0.001023785,0.001452124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005477747,"threshold_uncertainty_score":0.01863086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01543798048489488,"score_gpt":0.2300689522546752,"score_spread":0.2146309717697803,"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."}}