{"id":"W2027014759","doi":"10.2174/138620706775541846","title":"Improving Synthetic Efficiency Using the Computational Prediction of Biological Activity","year":2006,"lang":"en","type":"article","venue":"Combinatorial Chemistry & High Throughput Screening","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"Test set; Quantitative structure–activity relationship; Computer science; Cluster analysis; Set (abstract data type); Extrapolation; Training set; Rank (graph theory); Data mining; Principal component analysis; Data set; Artificial intelligence; Machine learning; Mathematics; Statistics","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":[0.001012702,0.0002561938,0.0003149213,0.00004332473,0.0004317133,0.0001450696,0.0009616512,0.0001492583,0.00001126384],"category_scores_gemma":[0.0002641026,0.0002123954,0.0001638344,0.0006410936,0.0002822656,0.0004913544,0.0005802999,0.0003125955,0.000001269351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001382283,"about_ca_system_score_gemma":0.0001946621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003276368,"about_ca_topic_score_gemma":2.894049e-7,"domain_scores_codex":[0.9975407,0.0002865304,0.0004861249,0.0006132015,0.0007194485,0.0003539581],"domain_scores_gemma":[0.9977534,0.0009820441,0.0004277643,0.0005266958,0.00025265,0.00005746351],"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":[0.00007537189,0.0004361948,0.001102653,0.00008495271,0.00005214709,0.000009929967,0.0001329055,0.7356157,0.1340348,0.1234541,0.00005635055,0.004944747],"study_design_scores_gemma":[0.0007964445,0.00006137883,0.005880422,0.00005299672,0.00002428421,0.00003858736,0.00002058915,0.8380302,0.08964265,0.06515925,0.00004638291,0.0002468229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.449563,0.0000490773,0.5493266,0.00008903954,0.0006023301,0.0001115279,0.00001143863,0.0000959102,0.0001510891],"genre_scores_gemma":[0.936263,8.874105e-7,0.06319714,0.00001198911,0.0004770712,0.000008871933,0.00001917122,0.00001380471,0.000008099229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4867,"threshold_uncertainty_score":0.8661235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03064209666482123,"score_gpt":0.2736427033309345,"score_spread":0.2430006066661133,"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."}}