{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002704632,0.00103744,0.002343633,0.001716266,0.0005999969,0.001121657,0.001522231,0.001096303,0.003484911],"category_scores_gemma":[0.004596765,0.0006175007,0.0010438,0.00107843,0.0003237678,0.0008414945,0.0008128145,0.0008605406,0.001422102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009506888,"about_ca_system_score_gemma":0.001846139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005030473,"about_ca_topic_score_gemma":0.01083504,"domain_scores_codex":[0.9981262,0.000502728,0.00008461393,0.0002325045,0.0009556206,0.00009836453],"domain_scores_gemma":[0.998394,0.0009066574,0.0001261525,0.0001834451,0.0002870115,0.0001027337],"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":[0.005099171,0.001058393,0.01090762,0.001115237,0.0006370753,0.0002481829,0.00007501378,0.0807231,0.1686772,0.003107805,0.009290121,0.7190612],"study_design_scores_gemma":[0.001233935,0.003095991,0.005477793,0.00005503905,0.0003573733,0.0007069308,0.00005437688,0.8436059,0.1313958,0.003350405,0.01052545,0.0001409797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4026443,0.007564093,0.5449879,0.001547855,0.0002046194,0.00135939,0.01487449,0.01828771,0.008529788],"genre_scores_gemma":[0.4268906,0.001655003,0.5578794,0.0004756701,0.00003962481,0.0004867295,0.009210925,0.0002816735,0.003080363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005030473,"threshold_uncertainty_score":0.01430362,"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."}}