{"id":"W3180150214","doi":"10.1101/2021.07.06.451246","title":"MONI: A Pangenomics Index for Finding MEMs","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Israel Institute for Biological Research; National Institutes of Health; National Science Foundation","keywords":"Parsing; Computer science; Index (typography); Prefix; Matching (statistics); Trie; Tree (set theory); Pattern matching; Algorithm; Sequence (biology); Theoretical computer science; Data mining; Artificial intelligence; Data structure; Mathematics; Combinatorics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002397359,0.00142339,0.001595535,0.006502276,0.001503613,0.003104451,0.003084595,0.001457378,0.0106216],"category_scores_gemma":[0.009955689,0.001212389,0.001209821,0.007756344,0.0006071895,0.004399643,0.004053504,0.001611588,0.007794932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555914,"about_ca_system_score_gemma":0.00237095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003188431,"about_ca_topic_score_gemma":0.004995612,"domain_scores_codex":[0.998403,0.0001817434,0.0002257649,0.0005920855,0.000453463,0.0001438726],"domain_scores_gemma":[0.9970307,0.000870963,0.0004053554,0.0008989468,0.0005567204,0.0002373393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003026148,0.0002768062,0.01776255,0.003062386,0.0007113827,0.0007491907,0.0010119,0.008232853,0.0841267,0.03331986,0.2817029,0.5660172],"study_design_scores_gemma":[0.0004682349,0.0004747928,0.01839778,0.0006183673,0.0004640571,0.001423843,0.0005437077,0.2137498,0.1367746,0.0536101,0.5730059,0.000468767],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.04732352,0.008537723,0.5040359,0.001434078,0.001025945,0.0006127461,0.09132419,0.3259599,0.0197461],"genre_scores_gemma":[0.1002981,0.001775105,0.7362925,0.0007759833,0.0002666354,0.0009410782,0.1388007,0.01368576,0.007164004],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.0106216,"threshold_uncertainty_score":0.03553283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01777155173069409,"score_gpt":0.2282378329133029,"score_spread":0.2104662811826088,"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."}}