{"id":"W1963589141","doi":"10.1186/1756-0500-7-466","title":"Suffix tree searcher: exploration of common substrings in large DNA sequence sets","year":2014,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; University of Victoria","keywords":"Substring; Suffix tree; Computer science; Sequence (biology); Generalized suffix tree; Suffix; Tree (set theory); Computational biology; Artificial intelligence; Data mining; Mathematics; Set (abstract data type); Combinatorics; Genetics; Biology; Data structure; Programming language","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":[0.001593925,0.001426678,0.0009461305,0.004005938,0.00103348,0.001927922,0.001642534,0.001033601,0.01580211],"category_scores_gemma":[0.005804981,0.0006167699,0.00116774,0.005053313,0.0005012751,0.002609405,0.00174881,0.0009913873,0.006203532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004373711,"about_ca_system_score_gemma":0.0014922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009920284,"about_ca_topic_score_gemma":0.001725487,"domain_scores_codex":[0.999194,0.0001153488,0.0001026683,0.0002684493,0.000271243,0.00004828993],"domain_scores_gemma":[0.9982712,0.001071268,0.0002023101,0.0001280574,0.000203855,0.0001232553],"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":[0.00237587,0.0005284209,0.03509563,0.005407785,0.0005762574,0.003236407,0.002457199,0.02231727,0.1283296,0.01794556,0.1515864,0.6301436],"study_design_scores_gemma":[0.0006728453,0.0009034854,0.02546577,0.0007760579,0.0004102342,0.005847652,0.001529196,0.5612489,0.1158112,0.06147166,0.2255566,0.0003063153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1111938,0.002167691,0.6490242,0.0007493558,0.0002005758,0.0006325071,0.04839094,0.1781363,0.009504665],"genre_scores_gemma":[0.1112038,0.0009336752,0.8333282,0.0001897861,0.00006641032,0.0006760171,0.04521944,0.005738818,0.002643854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01580211,"threshold_uncertainty_score":0.05286336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2928156735960591,"score_gpt":0.4294086005335125,"score_spread":0.1365929269374535,"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."}}