{"id":"W2166017353","doi":"10.1177/1087057105281048","title":"Screening for Dihydrofolate Reductase Inhibitors Using MOLPRINT 2D, a Fast Fragment-Based Method Employing the Naïve Bayesian Classifier: Limitations of the Descriptor and the Importance of Balanced Chemistry in Training and Test Sets","year":2005,"lang":"en","type":"article","venue":"SLAS DISCOVERY","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"McMaster University; Bill and Melinda Gates Foundation","keywords":"Dihydrofolate reductase; Cheminformatics; Test set; Computer science; Training set; Fragment (logic); Artificial intelligence; Naive Bayes classifier; Classifier (UML); Computational biology; Fold (higher-order function); Pattern recognition (psychology); Similarity (geometry); Chemistry; Machine learning; Support vector machine; Bioinformatics; Algorithm; Biochemistry; Biology; Enzyme","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":[],"consensus_categories":[],"category_scores_codex":[0.001660174,0.000196927,0.0003084758,0.00006451917,0.0002554379,0.0001515508,0.0004673654,0.00005555435,9.688408e-7],"category_scores_gemma":[0.001293508,0.0001228933,0.0001335016,0.0004576959,0.0003408629,0.0005597633,0.0002764538,0.000218392,2.915897e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006304176,"about_ca_system_score_gemma":0.0002568455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003776633,"about_ca_topic_score_gemma":0.00004666056,"domain_scores_codex":[0.9981733,0.0003129901,0.0005553313,0.0003931292,0.0003022947,0.0002629745],"domain_scores_gemma":[0.9941082,0.004914471,0.0004344286,0.0004328561,0.00006423326,0.00004578584],"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":[0.0003873773,0.0003937962,0.05498888,0.000422767,0.0002836835,0.000006068206,0.02496053,0.5507175,0.2299882,0.05477431,0.00006684876,0.08301007],"study_design_scores_gemma":[0.001225444,0.00002109844,0.00777705,0.0002844939,0.00003479091,0.00001081562,0.001646979,0.9452183,0.03806739,0.005532026,0.00001708137,0.0001645125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5817222,0.0001727397,0.4160086,0.001594147,0.00005474826,0.0003719803,0.00003312528,0.000009654948,0.00003282765],"genre_scores_gemma":[0.8105505,0.000006607701,0.1891723,0.0001630445,0.00003592343,0.00004734453,0.000002599122,0.00001378178,0.000007958036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3945008,"threshold_uncertainty_score":0.5011442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06512662934812148,"score_gpt":0.3137792726821431,"score_spread":0.2486526433340216,"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."}}