{"id":"W2110899240","doi":"10.1186/1758-2946-1-4","title":"A constructive approach for discovering new drug leads: Using a kernel methodology for the inverse-QSAR problem","year":2009,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Quantitative structure–activity relationship; Kernel (algebra); Feature vector; Molecular descriptor; Computer science; Support vector machine; Kernel method; Feature (linguistics); Artificial intelligence; Inverse; Algorithm; Pattern recognition (psychology); Mathematics; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.002116592,0.0001699157,0.000379365,0.0001290382,0.0001408693,0.0001943546,0.0008930204,0.00005665287,7.725192e-7],"category_scores_gemma":[0.0006289441,0.000117774,0.0002744684,0.000257081,0.00006730517,0.00145041,0.000107722,0.0002204252,2.501976e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001360203,"about_ca_system_score_gemma":0.0006010194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002853208,"about_ca_topic_score_gemma":5.304055e-7,"domain_scores_codex":[0.9984393,0.00004063323,0.0008045998,0.0001133937,0.0003269818,0.0002751287],"domain_scores_gemma":[0.9962044,0.002139259,0.0009951064,0.0002271422,0.0003293037,0.0001048132],"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":[0.0002744389,0.00011391,0.00002375837,0.0003630991,0.0003391317,0.000002259389,0.03341384,0.6748015,0.00193805,0.06038781,0.01062374,0.2177185],"study_design_scores_gemma":[0.001093372,0.0001125247,0.00002267201,0.00005545693,0.00007876349,0.0003777436,0.001344412,0.9233211,0.007324283,0.06482232,0.001288004,0.0001592988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005937594,0.000110894,0.9919283,0.0007310699,0.0002992259,0.000477634,0.000004924135,0.0000139875,0.0004963414],"genre_scores_gemma":[0.01063071,0.000008977364,0.9884928,0.0004976506,0.0002944421,0.000005371573,0.000001496254,0.000007966671,0.00006054395],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2485196,"threshold_uncertainty_score":0.4802683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09032694935977614,"score_gpt":0.348785861803831,"score_spread":0.2584589124440548,"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."}}