{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000973081,0.0007591496,0.001625753,0.002292727,0.0005619989,0.001520207,0.002178154,0.001387024,0.002425392],"category_scores_gemma":[0.002324812,0.0004843497,0.001263856,0.002636962,0.0009136142,0.002064306,0.001396073,0.00134822,0.001372974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041079,"about_ca_system_score_gemma":0.001063423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001547434,"about_ca_topic_score_gemma":0.001788121,"domain_scores_codex":[0.998718,0.0001491555,0.0001090109,0.0002868761,0.0006678045,0.00006914711],"domain_scores_gemma":[0.9990526,0.0003024024,0.0001331543,0.0001890461,0.0002816392,0.00004110203],"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":[0.0001386807,0.0002353808,0.001214688,0.0005388155,0.0001149176,0.0001429185,0.0001200314,0.1285105,0.03283333,0.09315337,0.004377791,0.7386196],"study_design_scores_gemma":[0.00002117802,0.00006833074,0.0004464665,0.00002901313,0.00002249931,0.0001468983,0.00002797952,0.926623,0.008486012,0.05299591,0.01111011,0.00002259455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003774489,0.0006022376,0.9937596,0.00009531013,0.00004454398,0.00005871624,0.00005585181,0.0004177853,0.001191635],"genre_scores_gemma":[0.05684989,0.000765164,0.9381091,0.0001556606,0.000107559,0.0002510637,0.0004422839,0.0001135869,0.00320565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002425392,"threshold_uncertainty_score":0.008113801,"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."}}