{"id":"W4205262153","doi":"10.1089/cmb.2021.0445","title":"Finding Maximal Exact Matches Using the r-Index","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Set (abstract data type); Sequence (biology); Computer science; Data structure; Index (typography); Key (lock); Space (punctuation); Code (set theory); k-mer; Algorithm; Theoretical computer science; Data set; Genome; Programming language; Artificial intelligence; Biology","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":[0.004036806,0.001853267,0.00229519,0.00417702,0.001402945,0.004114288,0.003695605,0.00184343,0.008290975],"category_scores_gemma":[0.02936944,0.001255787,0.002225151,0.00447621,0.001954431,0.007189785,0.005419032,0.00194661,0.01082218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008434364,"about_ca_system_score_gemma":0.002396287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001127586,"about_ca_topic_score_gemma":0.001336396,"domain_scores_codex":[0.9939851,0.001151256,0.0009495436,0.001708184,0.001754019,0.000451784],"domain_scores_gemma":[0.9896031,0.004743941,0.001150444,0.002979225,0.001155085,0.0003682302],"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":[0.003071245,0.0005280008,0.02322812,0.003098116,0.0006174432,0.001245627,0.002187609,0.05188573,0.09461392,0.1490993,0.06959559,0.6008293],"study_design_scores_gemma":[0.0004165999,0.0007326658,0.004963347,0.0003814989,0.0002032287,0.001791524,0.0007313467,0.4674278,0.1463309,0.295347,0.0812365,0.0004375663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03737441,0.0007859806,0.9028548,0.000429236,0.0001324235,0.0002117864,0.006144713,0.04588981,0.006176833],"genre_scores_gemma":[0.1156223,0.0002680137,0.8684711,0.0001561125,0.00006870733,0.0004424792,0.009171057,0.004233392,0.001566813],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008290975,"threshold_uncertainty_score":0.02773607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02605860066026066,"score_gpt":0.2836659147171742,"score_spread":0.2576073140569136,"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."}}