{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01076428,0.002189776,0.001954464,0.002494041,0.001452165,0.002319614,0.003039063,0.001654021,0.00810098],"category_scores_gemma":[0.04885643,0.001334738,0.001807549,0.002603091,0.0007625017,0.00354872,0.00350253,0.002639859,0.008283638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268316,"about_ca_system_score_gemma":0.001999387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004807349,"about_ca_topic_score_gemma":0.005167474,"domain_scores_codex":[0.9928232,0.002365981,0.0007436702,0.001724123,0.001931298,0.0004117198],"domain_scores_gemma":[0.9700613,0.00982157,0.001931966,0.009626286,0.008084626,0.0004741904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00147119,0.00022089,0.02146325,0.002321389,0.0004906633,0.001046409,0.001329242,0.164425,0.2352232,0.01393304,0.08656899,0.4715067],"study_design_scores_gemma":[0.0001828444,0.0004829264,0.009511195,0.0003853511,0.0003557443,0.00122322,0.0003697207,0.4945064,0.3839231,0.009308298,0.09947323,0.0002778768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0863956,0.001406764,0.8300637,0.0007814904,0.0005627399,0.000232957,0.009150884,0.06550537,0.005900457],"genre_scores_gemma":[0.1371033,0.0007238865,0.8299888,0.000399834,0.0001530646,0.0002137865,0.0175982,0.01031998,0.003499103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01076428,"threshold_uncertainty_score":0.05692768,"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."}}