{"id":"W3026218946","doi":"10.1109/tit.2020.2996543","title":"Levenshtein Distance, Sequence Comparison and Biological Database Search","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Levenshtein distance; Edit distance; Nearest neighbor search; Heuristics; Computer science; Metric (unit); Similarity (geometry); Data mining; Smith–Waterman algorithm; Database; Theoretical computer science; Artificial intelligence; Sequence alignment; Biology","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":[0.003443483,0.000801907,0.002095181,0.005300562,0.0008679905,0.003998686,0.002465859,0.002166261,0.003129849],"category_scores_gemma":[0.0146106,0.0004200996,0.0008116223,0.01002275,0.00385721,0.007971514,0.002477349,0.002039287,0.001920384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002240685,"about_ca_system_score_gemma":0.001506453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002495119,"about_ca_topic_score_gemma":0.001531971,"domain_scores_codex":[0.9951873,0.001359054,0.0004820423,0.0008710427,0.001910459,0.0001900204],"domain_scores_gemma":[0.9948682,0.00352213,0.0004436806,0.000362615,0.0006740957,0.0001293163],"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":[0.0001446504,0.00006399905,0.001468648,0.002050488,0.0001402033,0.0003546281,0.0003367045,0.04587206,0.004006873,0.4272676,0.008299133,0.509995],"study_design_scores_gemma":[0.0000195249,0.0001446886,0.001441126,0.0003194208,0.00004432027,0.001116357,0.0002412223,0.1143796,0.005145313,0.795156,0.08189297,0.00009951864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01286812,0.1447018,0.8181243,0.002474359,0.0007296243,0.0001228571,0.0005120327,0.0008611238,0.0196058],"genre_scores_gemma":[0.2236068,0.07989604,0.6824314,0.00107083,0.001661545,0.0003448386,0.001726698,0.0003979028,0.008863887],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005300562,"threshold_uncertainty_score":0.01821107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04782399564894595,"score_gpt":0.2778887731993038,"score_spread":0.2300647775503578,"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."}}