{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004222885,0.0001081622,0.000201092,0.0003476167,0.0001453408,0.0001473304,0.001268155,0.00007997188,0.00001314059],"category_scores_gemma":[0.00100565,0.00009396571,0.00003974358,0.0009402558,0.0001169825,0.001517217,0.0009149321,0.0003021783,0.00005546541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006237069,"about_ca_system_score_gemma":0.0001499201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007902312,"about_ca_topic_score_gemma":0.001196388,"domain_scores_codex":[0.9969581,0.0007885911,0.0002946061,0.0004190402,0.0009867575,0.0005528397],"domain_scores_gemma":[0.9972355,0.001467492,0.00006749698,0.0008567285,0.0002436507,0.000129111],"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":[0.0002040761,0.001706215,0.2449107,0.0005814377,0.00002014857,0.00006649952,0.007884931,0.0009411201,0.08396784,0.2013288,0.002565667,0.4558226],"study_design_scores_gemma":[0.001333479,0.0004774115,0.1247853,0.0002963798,0.000001437222,0.000004486242,0.0001879616,0.7506335,0.08692282,0.03229843,0.002734106,0.0003246908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.600436,0.0001258148,0.3976209,0.0006519362,0.00007668709,0.0003315761,0.00001657465,0.00007001316,0.0006705067],"genre_scores_gemma":[0.9787078,0.00004803079,0.02107706,0.00001806452,0.0000451994,0.0000288495,0.00002465492,0.000008974695,0.0000413804],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7496924,"threshold_uncertainty_score":0.3831811,"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."}}