{"id":"W4360980788","doi":"10.1007/s42979-023-01690-8","title":"On the Multiple Pattern String Matching in DNA Databases","year":2023,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University of Winnipeg","funders":"School of Natural Sciences, Mathematics, and Engineering, California State University, Bakersfield","keywords":"Substring; String searching algorithm; Pattern matching; Suffix tree; Search engine indexing; Computer science; String (physics); Character (mathematics); Transformation (genetics); Tree (set theory); Set (abstract data type); Matching (statistics); Combinatorics; Algorithm; Mathematics; Artificial intelligence; Data structure; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001214583,0.0001373667,0.0001137425,0.0003088024,0.0004729539,0.0005034845,0.002930783,0.0000162388,0.00000582008],"category_scores_gemma":[0.00006411265,0.00009131939,0.00003000886,0.002078801,0.000127842,0.001251369,0.002845407,0.0001959182,0.0001941391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004337152,"about_ca_system_score_gemma":0.00008573983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001872913,"about_ca_topic_score_gemma":0.00003392373,"domain_scores_codex":[0.9978965,0.00006374807,0.0001990885,0.0006814507,0.0006617047,0.0004975216],"domain_scores_gemma":[0.9980829,0.0005997919,0.00006262286,0.001127746,0.00003765888,0.00008929572],"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":[0.000004854836,0.0001452191,0.005434042,0.00002187367,0.000005519392,0.0002246185,0.00290854,0.02201541,0.003584465,0.0970525,0.005705226,0.8628978],"study_design_scores_gemma":[0.0001498744,0.00002861085,0.02546621,0.0001061972,3.548849e-7,0.000006221283,0.00002025877,0.9689204,0.001413442,0.003198334,0.0005402289,0.0001498664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2618206,0.000006775863,0.7362119,0.0008113405,0.0007759974,0.0001119002,0.000006943364,0.0001903857,0.00006414053],"genre_scores_gemma":[0.9751778,0.000006028444,0.02390385,0.0007758182,0.0001000048,0.00001085189,0.000004784751,0.000006009937,0.00001484286],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.946905,"threshold_uncertainty_score":0.5446172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04220773460392502,"score_gpt":0.2763246664326198,"score_spread":0.2341169318286948,"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."}}