{"id":"W3005694381","doi":"10.1088/2632-2153/ab891b","title":"Predicting drug properties with parameter-free machine learning: pareto-optimal embedded modeling (POEM)","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Overfitting; Machine learning; Hyperparameter; Benchmark (surveying); Computer science; Artificial intelligence; Context (archaeology); Parametric model; Generalization; Pareto principle; Parametric statistics; Algorithm; Mathematical optimization; Mathematics; Statistics; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001477745,0.000320589,0.0003751359,0.0005205443,0.001045615,0.0004570993,0.002113985,0.00009652491,0.000005397429],"category_scores_gemma":[0.004898499,0.0002520699,0.00003899545,0.00285265,0.0008014944,0.001038773,0.001982607,0.001335188,0.00000899379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005845843,"about_ca_system_score_gemma":0.0003207987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001262069,"about_ca_topic_score_gemma":0.00002141911,"domain_scores_codex":[0.9967105,0.0002150075,0.0003661863,0.001174276,0.0008554248,0.0006785783],"domain_scores_gemma":[0.9984915,0.0002548817,0.0002041258,0.0005116447,0.0003296295,0.0002082303],"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":[0.00005117112,0.00004260474,0.04910716,0.0000470358,0.00002810113,0.00004643121,0.00352902,0.8999804,0.003476354,0.006741259,0.00001333302,0.03693713],"study_design_scores_gemma":[0.0005105454,0.0005199396,0.0001226188,0.00004540231,0.00001240247,0.0001075652,0.000417908,0.9937868,0.001907461,0.001749606,0.0004928648,0.0003269536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6692575,0.0005058685,0.3183548,0.01040158,0.00006986504,0.0001925205,0.000001490618,0.001017257,0.000199185],"genre_scores_gemma":[0.8997347,0.00002167627,0.09980833,0.0002800517,0.00004334728,0.00002541736,0.000002635283,0.00002282746,0.00006101104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2304772,"threshold_uncertainty_score":0.9999931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02126592853793483,"score_gpt":0.2468580884938343,"score_spread":0.2255921599558994,"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."}}