{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007238409,0.001007957,0.0007399307,0.001945173,0.0005867142,0.001187375,0.001602502,0.001290602,0.00118358],"category_scores_gemma":[0.02281055,0.0003963694,0.0008477648,0.0017311,0.0008102584,0.001142939,0.0009820242,0.0009673126,0.0004757026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001570859,"about_ca_system_score_gemma":0.001400695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007508609,"about_ca_topic_score_gemma":0.004316567,"domain_scores_codex":[0.9939918,0.0008242645,0.0004166868,0.001468255,0.002991323,0.00030753],"domain_scores_gemma":[0.9761135,0.01340466,0.002523487,0.002091986,0.005604709,0.0002616672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001334274,0.0001976507,0.06630194,0.000555455,0.000233694,0.0008081665,0.000451196,0.7484019,0.04474036,0.01722118,0.002339246,0.117415],"study_design_scores_gemma":[0.00001325122,0.00006709064,0.01151649,0.00003057865,0.00002932187,0.0002786851,0.00004632004,0.952947,0.02961438,0.004049467,0.001365568,0.00004196056],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3538406,0.001134446,0.6384775,0.0003197905,0.0001394535,0.000185531,0.001753723,0.002064444,0.002084461],"genre_scores_gemma":[0.8602769,0.0003869737,0.1298955,0.0001525748,0.00006545003,0.0002499439,0.005824639,0.0003683936,0.002779664],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007508609,"threshold_uncertainty_score":0.03828079,"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."}}