{"id":"W2953326935","doi":"10.1093/bioinformatics/btz400","title":"ntEdit: scalable genome sequence polishing","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; Genome British Columbia; Université Laval; Natural Resources Canada; Ministry of Forests","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Sequence (biology); Scalability; Polishing; Computer science; Whole genome sequencing; Genome; Computational biology; Genetics; Biology; Gene; Materials science; Database; Metallurgy","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":[0.0001199611,0.0001239482,0.0001186127,0.00002916369,0.00006485997,0.00004325801,0.0002112194,0.0000876641,0.0000298256],"category_scores_gemma":[0.00002777182,0.0001133052,0.00004761428,0.00006500528,0.00003901783,0.000002595567,0.000173572,0.00005596206,0.0002330061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001356571,"about_ca_system_score_gemma":0.00005273424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001240767,"about_ca_topic_score_gemma":0.00000435548,"domain_scores_codex":[0.9992921,0.000008005217,0.0002140221,0.0001292782,0.000105119,0.0002514942],"domain_scores_gemma":[0.9994588,0.00000675098,0.00007986811,0.0003293015,0.00006277155,0.00006249236],"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":[0.0000272299,0.00002404134,0.008510365,0.00009963682,0.0000926272,8.286207e-7,0.0004122875,0.0005450562,0.9824949,0.0004580807,0.004768429,0.002566524],"study_design_scores_gemma":[0.0009441041,0.0005663937,0.02250523,0.00003091796,0.00003150561,0.00004847487,0.0009613584,0.003542744,0.04019276,0.000230511,0.9301715,0.0007744279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9795126,0.0004592682,0.0002840223,0.0001011236,0.0005074482,0.0001911278,0.00006849627,0.000008006606,0.01886794],"genre_scores_gemma":[0.9917611,0.0002698132,0.004571779,0.0005932786,0.0002125488,0.000006630373,0.00007330358,0.00001599978,0.002495479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9423021,"threshold_uncertainty_score":0.4620453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01446762705254454,"score_gpt":0.2310440146055117,"score_spread":0.2165763875529672,"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."}}