{"id":"W1971987634","doi":"10.1093/bioinformatics/bts219","title":"SEQuel: improving the accuracy of genome assemblies","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; University of California, San Diego; National Institutes of Health; National Science Foundation","keywords":"Contig; De Bruijn graph; Sequence assembly; De Bruijn sequence; Indel; Hybrid genome assembly; Substitution (logic); Computer science; Genome; Reference genome; Computational biology; Error detection and correction; Algorithm; Graph; Biology; Genetics; Theoretical computer science; Gene; Mathematics; Combinatorics; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002302099,0.00009712323,0.00009677803,0.00001899471,0.00008261952,0.00001411808,0.0001874468,0.00005606607,0.000004650874],"category_scores_gemma":[0.0001217525,0.00006440775,0.00006413547,0.00005002088,0.00007094316,0.000002543008,0.0001930493,0.00003980015,0.00001015287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005518394,"about_ca_system_score_gemma":0.00003493367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007192659,"about_ca_topic_score_gemma":0.000002180341,"domain_scores_codex":[0.9993997,0.00001301278,0.0002382762,0.00005085565,0.00008428525,0.0002138868],"domain_scores_gemma":[0.9994195,0.00002734739,0.0001604937,0.0002935776,0.00005849958,0.00004063531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000184877,0.00004648648,0.01157275,0.0001295711,0.0001436853,7.862256e-8,0.002362885,0.00009989002,0.9738049,0.0008109384,0.00105251,0.009957837],"study_design_scores_gemma":[0.001003979,0.0005319206,0.1695611,0.00002198933,0.0001659032,0.00005840007,0.007556065,0.001474752,0.5068873,0.0001713184,0.3116921,0.0008750913],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.991591,0.002786458,0.001342481,0.0000545265,0.0002002471,0.0001687149,0.00002779479,0.000003290436,0.003825467],"genre_scores_gemma":[0.9953571,0.0003133484,0.003837814,0.0001804445,0.000188139,0.000008412433,0.00001566277,0.000008920547,0.00009014598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4669175,"threshold_uncertainty_score":0.2626472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01970266929459968,"score_gpt":0.2481336059417708,"score_spread":0.2284309366471711,"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."}}