{"id":"W2023313300","doi":"10.1371/journal.pcbi.1004074","title":"Machine Learning Assisted Design of Highly Active Peptides for Drug Discovery","year":2015,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Computer science; Leverage (statistics); Drug discovery; Heuristics; Machine learning; Artificial intelligence; Biological data; Bioinformatics; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001308059,0.00009889784,0.0001917589,0.00003595475,0.00003798905,0.000008252438,0.000104286,0.0000743159,0.000004754914],"category_scores_gemma":[0.0003829854,0.00008271679,0.0001020255,0.00005985392,0.00007994097,0.000004181266,0.00005485558,0.0000465178,0.00000232405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001438788,"about_ca_system_score_gemma":0.00006551269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001683215,"about_ca_topic_score_gemma":0.000002991519,"domain_scores_codex":[0.9992892,0.0001042368,0.0001864951,0.000229757,0.0000694078,0.0001208792],"domain_scores_gemma":[0.9993485,0.0002202586,0.0001267425,0.00007207607,0.000182425,0.00005005997],"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":[0.0003968022,0.0001756727,0.00316966,0.00001523149,0.000349092,3.213518e-7,0.00003765508,0.02223887,0.9700252,0.0006158758,0.0004258563,0.00254973],"study_design_scores_gemma":[0.001436126,0.0006524379,0.001416617,0.00002153823,0.0001428586,0.000005658178,0.0001094156,0.05379891,0.9287397,0.008590877,0.004735564,0.0003502971],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8054684,0.0004879656,0.1931413,0.0003309715,0.00003656293,0.0001799587,0.0001476119,0.00001388222,0.0001932965],"genre_scores_gemma":[0.9863679,0.00001520872,0.01211505,0.00006681096,0.0000959954,0.00002362003,0.001091011,0.00001050677,0.0002138779],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1810262,"threshold_uncertainty_score":0.3373093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03447533993846412,"score_gpt":0.2673522571288562,"score_spread":0.2328769171903921,"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."}}