{"id":"W4375864930","doi":"10.1515/ijb-2021-0091","title":"Error analysis of the PacBio sequencing CCS reads","year":2023,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Nanopore sequencing; Computer science; Hybrid genome assembly; Word error rate; Probabilistic logic; Sequence assembly; DNA sequencing; Process (computing); k-mer; Error detection and correction; Binomial distribution; Algorithm; Computational biology; Shotgun sequencing; Data mining; Biology; Mathematics; Statistics; Artificial intelligence; Genetics; DNA","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":[0.0003443974,0.00006354549,0.0001172317,0.00008424145,0.00004720621,0.00001420656,0.0004964757,0.00003192609,0.000006304969],"category_scores_gemma":[0.0002543865,0.00003616191,0.0001401894,0.0002203068,0.0000978135,5.798673e-7,0.0001570547,0.00006683644,0.000001513994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000199913,"about_ca_system_score_gemma":0.00009089436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002435948,"about_ca_topic_score_gemma":0.00005566102,"domain_scores_codex":[0.9992635,0.00004082262,0.0002888163,0.00006486756,0.0002615248,0.00008046969],"domain_scores_gemma":[0.9990644,0.00007701266,0.0003266192,0.0001543632,0.0003593883,0.00001821843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00009988674,0.00002824592,0.01799131,0.000005903963,0.005923603,0.00001400071,0.000680688,0.008545506,0.9521201,0.00187755,0.01036902,0.002344161],"study_design_scores_gemma":[0.001465871,0.0006300653,0.5234643,0.00008856678,0.003707452,0.0001884932,0.004048004,0.00867216,0.4015997,0.007423462,0.04821278,0.000499133],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966092,0.0002113954,0.0009341303,0.0011095,0.0006343796,0.00003466233,0.0002705272,7.965444e-7,0.0001954362],"genre_scores_gemma":[0.9984306,0.0004373711,0.0005213816,0.0002141668,0.0001714997,5.872965e-7,0.0000188237,0.000006002243,0.0001996461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5505204,"threshold_uncertainty_score":0.147464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02603351602590837,"score_gpt":0.2946539920646603,"score_spread":0.2686204760387519,"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."}}