{"id":"W2610497813","doi":"10.71781/26408","title":"Molecular protein function prediction using sequence similarity-based and similarity-free approaches","year":2007,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Deutsche Forschungsgemeinschaft; Canadian Institute for Advanced Research","keywords":"Similarity (geometry); Sequence (biology); Computational biology; Function (biology); Structural similarity; Computer science; Data mining; Artificial intelligence; Biological system; Mathematics; Biology; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0002990926,0.0003889388,0.0002459525,0.000227485,0.00217185,0.00005811319,0.0002967886,0.0007946853,0.000005254442],"category_scores_gemma":[0.0001326546,0.0004624663,0.0001627917,0.0001672253,0.0001768417,0.00003071297,0.0001496682,0.0004965664,0.000001819322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008271257,"about_ca_system_score_gemma":0.0009024882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001210934,"about_ca_topic_score_gemma":0.0007329374,"domain_scores_codex":[0.9982007,0.0001038018,0.0003472535,0.0005365408,0.000489579,0.0003221718],"domain_scores_gemma":[0.9987183,0.00001500934,0.0003703543,0.000521238,0.0001939895,0.0001810801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003291009,0.0002675615,0.0118221,0.001348148,0.0006370277,0.0004366968,0.002526067,0.04984301,0.9212176,0.004494062,0.0003081996,0.003808527],"study_design_scores_gemma":[0.006690438,0.00172918,0.03532565,0.001258431,0.001947441,0.001284383,0.01253926,0.2301724,0.6472389,0.001387987,0.05686395,0.003561899],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700531,0.003368173,0.01590664,0.00006546537,0.0003540271,0.0006358652,0.0001137206,0.00007912781,0.009423839],"genre_scores_gemma":[0.9797623,0.00005517093,0.01129001,0.0001728787,0.0002110614,0.00002927711,0.004019899,0.0000614264,0.004397953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2739787,"threshold_uncertainty_score":0.9997827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01194725616241279,"score_gpt":0.2026500644435807,"score_spread":0.190702808281168,"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."}}