{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001853186,0.0001686135,0.0001792567,0.0001663831,0.0008873542,0.00005732787,0.0004933914,0.00008267792,0.000005895702],"category_scores_gemma":[0.00002224015,0.0001133328,0.00004677161,0.000445734,0.0003346352,0.0004934607,0.0000435627,0.0002751852,0.00001021281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003677945,"about_ca_system_score_gemma":0.00009493585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005785175,"about_ca_topic_score_gemma":0.00002297256,"domain_scores_codex":[0.9988827,0.00009782694,0.0003996153,0.0002405141,0.0001432848,0.0002360283],"domain_scores_gemma":[0.9985428,0.0008972956,0.0001209572,0.0003107476,0.00006333882,0.00006487407],"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":[0.0000748212,0.0004803813,0.01068284,0.00004886927,0.00007860349,0.00003513226,0.002836824,0.8115003,0.00007866803,0.03333362,0.000206275,0.1406436],"study_design_scores_gemma":[0.0003903838,0.00007784193,0.009024882,0.00003774005,0.000004442564,0.0001460675,0.000148936,0.9858959,0.00003678351,0.003598348,0.0004617408,0.0001768916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09443151,0.00007231161,0.9044084,0.0003942777,0.0002963384,0.0001548079,0.0001529523,0.00005846944,0.00003094181],"genre_scores_gemma":[0.7253184,0.00009572232,0.2740848,0.0003773755,0.00002545379,0.000008612946,0.00008131302,0.000003551091,0.000004735462],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6308869,"threshold_uncertainty_score":0.6824901,"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."}}