{"id":"W2160004708","doi":"10.1093/bioinformatics/btl259","title":"Distance based algorithms for small biomolecule classification and structural similarity search","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Minkowski distance; Classifier (UML); Nearest neighbor search; Computer science; Similarity (geometry); Artificial intelligence; Pruning; Pattern recognition (psychology); Data mining; Focus (optics); k-nearest neighbors algorithm; Machine learning; Algorithm; Mathematics; Euclidean distance","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001917871,0.001046564,0.0018334,0.003028575,0.0005579989,0.001656331,0.002448495,0.00178749,0.00395726],"category_scores_gemma":[0.009251792,0.0005157597,0.001020491,0.004141043,0.001022683,0.00258161,0.001818535,0.001957636,0.002322858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001340816,"about_ca_system_score_gemma":0.00105983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002241853,"about_ca_topic_score_gemma":0.001570144,"domain_scores_codex":[0.9978289,0.0005329663,0.000227652,0.0003995546,0.0009371897,0.00007362195],"domain_scores_gemma":[0.9963852,0.00219632,0.0003373806,0.0004144674,0.0005847737,0.00008195351],"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":[0.0001433474,0.0001388349,0.0008074821,0.0004762722,0.00009643005,0.00006397161,0.00008923162,0.2778187,0.002993366,0.06365641,0.005998992,0.647717],"study_design_scores_gemma":[0.00003821246,0.00006492322,0.0002948932,0.00004332411,0.00001753018,0.0001088106,0.00002420607,0.9041567,0.00234168,0.08537365,0.007511379,0.0000245829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002923136,0.001202368,0.9939731,0.0001259602,0.00003863496,0.0000777164,0.00008969346,0.0005675346,0.001001913],"genre_scores_gemma":[0.05997569,0.001175482,0.9351928,0.0001275441,0.000106966,0.0004114523,0.0007692461,0.0001658038,0.002075015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00395726,"threshold_uncertainty_score":0.01323837,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05411668737318064,"score_gpt":0.3177180010844267,"score_spread":0.263601313711246,"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."}}