{"id":"W1990064224","doi":"10.1186/1756-0500-2-14","title":"Sequence Searcher: A Java tool to perform regular expression and fuzzy searches of multiple DNA and protein sequences","year":2009,"lang":"en","type":"article","venue":"BMC Research Notes","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Computer science; Sequence (biology); Set (abstract data type); Java; Data mining; Matching (statistics); Fuzzy logic; Feature (linguistics); Limiting; Approximate string matching; Regular expression; Computational biology; Nearest neighbor search; Bioinformatics; Information retrieval; Pattern matching; Artificial intelligence; Biology; Genetics; Programming language; Mathematics","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":[0.002246956,0.0001634562,0.0001991189,0.0001371767,0.0002005724,0.00007784391,0.0002922847,0.0001730154,0.00001982675],"category_scores_gemma":[0.002556082,0.0001338365,0.00004495981,0.0001893901,0.0002954722,0.00001961584,0.000283615,0.0001734715,0.000007486263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001735117,"about_ca_system_score_gemma":0.0001898207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009306578,"about_ca_topic_score_gemma":0.00003386186,"domain_scores_codex":[0.9977659,0.0004190263,0.0002180027,0.00053432,0.0005667412,0.0004960068],"domain_scores_gemma":[0.9988634,0.0001877361,0.00003442465,0.0004446621,0.0002492799,0.0002205119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003157332,0.00003672736,0.002198277,0.000107482,0.000007466886,0.000003718082,0.000182296,0.000004139615,0.972582,0.0002058398,0.0000543129,0.02430198],"study_design_scores_gemma":[0.0003019763,0.001167892,0.003573576,0.0001812432,0.000002232244,0.00000955688,0.0002129296,0.00008815518,0.9909653,0.002502375,0.0008234881,0.0001712909],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967816,0.0009728383,0.0004992927,0.0005113137,0.000009397457,0.0009595916,0.00001800908,0.00000964253,0.000238352],"genre_scores_gemma":[0.98023,0.0002501809,0.01882296,0.00003170794,0.00009770498,0.00008612448,0.000008945062,0.00001596728,0.0004564049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02413069,"threshold_uncertainty_score":0.5457694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1220691926556259,"score_gpt":0.3636630721064739,"score_spread":0.241593879450848,"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."}}