{"id":"W1561182462","doi":"10.1109/csb.2003.1227408","title":"GenericBioMatch: A novel generic pattern match algorithm for biological sequences","year":2004,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Algorithm; Probabilistic logic; Java; Overhead (engineering); Probabilistic analysis of algorithms; DNA sequencing; Software; Biological data; Genomics; Theoretical computer science; Bioinformatics; DNA; Artificial intelligence; Biology; Genetics; Programming language; Genome","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":[0.001672371,0.00143861,0.00126766,0.003453814,0.001067044,0.002008026,0.004092943,0.002467504,0.01199047],"category_scores_gemma":[0.005570937,0.0008085288,0.001738414,0.004598857,0.0009295784,0.004304781,0.00365101,0.001554575,0.006968387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007134557,"about_ca_system_score_gemma":0.001417423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001327258,"about_ca_topic_score_gemma":0.00216925,"domain_scores_codex":[0.99808,0.0002011375,0.0002046,0.0004945702,0.0008763888,0.0001432055],"domain_scores_gemma":[0.9986244,0.0003915387,0.0001790977,0.0004335977,0.0002893705,0.00008194264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006151274,0.0001949394,0.002786402,0.0008242811,0.0001961485,0.0004082379,0.0002777041,0.01914755,0.03321463,0.02309465,0.04904788,0.8701924],"study_design_scores_gemma":[0.0003507002,0.0003403495,0.002168909,0.0001480548,0.0001235752,0.002815887,0.0002387847,0.5803228,0.09712995,0.1209861,0.1952027,0.0001721981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004371387,0.0003122451,0.9752824,0.0000996736,0.00007082478,0.0001146554,0.000998766,0.01723699,0.001513031],"genre_scores_gemma":[0.0228176,0.0002525798,0.9681957,0.0001880872,0.00004164673,0.0002399266,0.004095165,0.001605032,0.002564269],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01199047,"threshold_uncertainty_score":0.04011208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05855086822525702,"score_gpt":0.2744726149219179,"score_spread":0.2159217466966609,"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."}}