{"id":"W2024539262","doi":"10.1145/1294301.1294307","title":"Novel approaches for small biomolecule classification and structural similarity search","year":2007,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Nearest neighbor search; Classifier (UML); Minkowski distance; Pruning; Similarity (geometry); Artificial intelligence; Data mining; Pattern recognition (psychology); Binary classification; k-nearest neighbors algorithm; Machine learning; Euclidean distance; Support vector machine","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":[0.0008900145,0.0001711771,0.000141149,0.0002180294,0.0003085076,0.000321496,0.00071226,0.00008347724,0.00000312238],"category_scores_gemma":[0.0003088171,0.0001678824,0.00006503037,0.0004702241,0.00009806947,0.0008881051,0.0003516371,0.000151054,0.00000916197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006195376,"about_ca_system_score_gemma":0.00007696875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000173322,"about_ca_topic_score_gemma":0.00004095743,"domain_scores_codex":[0.998477,0.00008784428,0.000316855,0.0005402273,0.0002463705,0.0003317224],"domain_scores_gemma":[0.997981,0.0009589305,0.0000810989,0.0007158204,0.0001556052,0.0001075994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001000659,0.000304454,0.002921921,0.0001122459,0.0001358802,0.000008733562,0.007497697,0.01863693,0.1510108,0.5863374,0.003993504,0.2289404],"study_design_scores_gemma":[0.000956649,0.0001040282,0.05886061,0.00001153726,0.00002136612,0.00003302996,0.0003411157,0.8737705,0.01839096,0.04412705,0.002860351,0.0005228289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1266618,0.00002722453,0.8549194,0.01756341,0.0001716863,0.0004284697,0.00001328012,0.00009278283,0.0001219469],"genre_scores_gemma":[0.4397019,0.000001097605,0.5586464,0.001348676,0.0001452196,0.0000538855,0.00005758329,0.00001242885,0.00003277773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8551335,"threshold_uncertainty_score":0.6846046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2537296575736704,"score_gpt":0.3552435413062274,"score_spread":0.101513883732557,"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."}}