{"id":"W2101649702","doi":"10.1109/tcbb.2008.99","title":"Finding the Nearest Neighbors in Biological Databases Using Less Distance Computations","year":2008,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"University of Science and Technology of China; University of Alberta","keywords":"Nearest neighbor search; Computer science; Pruning; Speedup; Computation; Similarity (geometry); k-nearest neighbors algorithm; Tree (set theory); Pairwise comparison; Sequence (biology); Preprocessor; k-d tree; Data mining; Sequence database; Algorithm; Artificial intelligence; Mathematics; Image (mathematics); Gene; Combinatorics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001479672,0.0006898045,0.001515602,0.003272293,0.00110343,0.001735433,0.00178484,0.001058717,0.002527754],"category_scores_gemma":[0.01055351,0.0005776852,0.0006927843,0.003971821,0.0006084771,0.004738066,0.001659038,0.0007395219,0.001680667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006963753,"about_ca_system_score_gemma":0.001382902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005796591,"about_ca_topic_score_gemma":0.00885406,"domain_scores_codex":[0.9976054,0.000559699,0.000230882,0.0004740216,0.001020593,0.000109404],"domain_scores_gemma":[0.9960065,0.001918935,0.0003520832,0.001121187,0.0004935748,0.0001076936],"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":[0.001216007,0.0004180497,0.007002912,0.0004581928,0.0001859774,0.0003247333,0.0006013435,0.1392228,0.02919924,0.01728764,0.006822194,0.7972608],"study_design_scores_gemma":[0.0002325236,0.000235556,0.003076272,0.0000475264,0.00007869133,0.0007372502,0.0003832077,0.9364331,0.02064535,0.02890459,0.009174645,0.00005123141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2363401,0.002847683,0.7510056,0.0006072445,0.0001641538,0.0001844539,0.0007045728,0.004383573,0.003762458],"genre_scores_gemma":[0.2676027,0.0008023288,0.727045,0.0001087893,0.00005890709,0.0001724803,0.001646965,0.0001359758,0.002426901],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005796591,"threshold_uncertainty_score":0.01152569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.109771359574609,"score_gpt":0.3209844104495188,"score_spread":0.2112130508749098,"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."}}