{"id":"W4205330988","doi":"10.1089/cmb.2021.0290","title":"MONI: A Pangenomic Index for Finding Maximal Exact Matches","year":2022,"lang":"en","type":"article","venue":"Journal of Computational Biology","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute","keywords":"Parsing; Computer science; Index (typography); Trie; Prefix; Matching (statistics); Pattern matching; Algorithm; Sequence (biology); Tree (set theory); Theoretical computer science; Mathematics; Data structure; Artificial intelligence; Combinatorics; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002728638,0.00008583799,0.0001620964,0.00007505392,0.0001530109,0.000007970131,0.0001722317,0.00004184416,0.00002134159],"category_scores_gemma":[0.00003297276,0.00008059421,0.0001156951,0.00004027074,0.00004217674,6.578352e-7,0.0001260484,0.00008159991,7.625384e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002739405,"about_ca_system_score_gemma":0.0001254818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000027784,"about_ca_topic_score_gemma":0.000001535473,"domain_scores_codex":[0.99933,0.00005769556,0.0002775431,0.0001248533,0.00006996346,0.0001399394],"domain_scores_gemma":[0.9994621,0.00007047633,0.0002582169,0.00005756468,0.0001165929,0.00003500482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001363909,0.0002078304,0.09036966,0.00002354625,0.0008787185,0.000008896614,0.0002838831,0.2105164,0.6780713,0.001764284,0.00558836,0.0109232],"study_design_scores_gemma":[0.009073903,0.01369172,0.3221289,0.00001630732,0.000210603,0.001793607,0.002000483,0.004742431,0.01834266,0.1302861,0.4965356,0.001177731],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9845384,0.001549769,0.01298414,0.0003159387,0.0003616952,0.00009631785,0.00008621658,9.197191e-7,0.00006655473],"genre_scores_gemma":[0.9942918,0.00004203095,0.004939253,0.0002761429,0.0003292895,0.00001526328,0.0000468256,0.00001071061,0.00004871823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6597286,"threshold_uncertainty_score":0.3286537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02062048482590375,"score_gpt":0.2744811594893764,"score_spread":0.2538606746634727,"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."}}