{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00228757,0.001511996,0.001750136,0.007108702,0.00182512,0.003255718,0.003143581,0.001540591,0.01388434],"category_scores_gemma":[0.009245951,0.001180166,0.001486507,0.007644536,0.000942898,0.006970549,0.004433132,0.001708645,0.007864751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001680435,"about_ca_system_score_gemma":0.002758733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003466302,"about_ca_topic_score_gemma":0.004945604,"domain_scores_codex":[0.9980336,0.000261658,0.0002629661,0.0006536056,0.0006091807,0.0001790689],"domain_scores_gemma":[0.9969311,0.0008616473,0.0003281097,0.001140329,0.0005407315,0.0001980498],"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":[0.002060927,0.0002419047,0.008193855,0.001682697,0.0003639311,0.0005611856,0.0008286829,0.0101127,0.04807037,0.0659872,0.143319,0.7185774],"study_design_scores_gemma":[0.0004845278,0.0004528808,0.0053921,0.0003917159,0.0003596171,0.00214509,0.0005444182,0.2828824,0.08756409,0.1809408,0.4384617,0.0003808372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02734531,0.004326907,0.8181106,0.001041555,0.000574892,0.0005875892,0.03108958,0.09839302,0.0185306],"genre_scores_gemma":[0.06022719,0.001071302,0.8838493,0.0004816308,0.000152034,0.0006004547,0.04260216,0.005031294,0.005984667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01388434,"threshold_uncertainty_score":0.04644775,"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."}}