{"id":"W4408510039","doi":"10.1101/gr.279352.124","title":"Closing the gaps, and improving somatic structural variant analysis and benchmarking using CHM13-T2T","year":2025,"lang":"en","type":"article","venue":"Genome Research","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; National Institute of Neurological Disorders and Stroke; Terry Fox Research Institute; Terry Fox Foundation; National Institute on Drug Abuse; Canada Research Chairs","keywords":"Biology; Somatic cell; Computational biology; Benchmark (surveying); Benchmarking; Annotation; Genome; Set (abstract data type); Genetics; Computer science; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01243208,0.001598775,0.001534712,0.00340178,0.001525357,0.002596911,0.003222169,0.001662539,0.002553037],"category_scores_gemma":[0.02448715,0.0006728926,0.002056103,0.00405905,0.0008010738,0.001529343,0.002581112,0.001664436,0.002053202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001546084,"about_ca_system_score_gemma":0.002515606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01014753,"about_ca_topic_score_gemma":0.02195517,"domain_scores_codex":[0.9915516,0.001906339,0.0009702505,0.002071457,0.00280617,0.0006942915],"domain_scores_gemma":[0.9886416,0.003363755,0.0008651749,0.002814392,0.003457543,0.0008575923],"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":[0.004177663,0.0007501496,0.1626375,0.002899777,0.001993031,0.001683352,0.001691207,0.09135476,0.4346022,0.007311226,0.04544781,0.2454515],"study_design_scores_gemma":[0.000430744,0.002024045,0.1483788,0.0005321846,0.0008714651,0.002145931,0.0008769421,0.3144666,0.4369584,0.009312334,0.08333237,0.0006702174],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7284669,0.003457485,0.2060565,0.0015937,0.0007129106,0.0006509766,0.0300328,0.02032036,0.008708434],"genre_scores_gemma":[0.488596,0.0007285256,0.3826361,0.001091579,0.0001374552,0.0007224847,0.1175179,0.006123841,0.002446165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01243208,"threshold_uncertainty_score":0.06574792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0211102179119088,"score_gpt":0.3390166903304708,"score_spread":0.317906472418562,"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."}}