{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007716234,0.0001053934,0.0001460054,0.0002024269,0.0005242235,0.0002220633,0.0001607597,0.00007879943,0.00001021046],"category_scores_gemma":[0.0001541215,0.00008392878,0.00004999118,0.0004673664,0.000181712,0.000003921567,0.0005420736,0.0001649487,3.374736e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004612743,"about_ca_system_score_gemma":0.0001642663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005644922,"about_ca_topic_score_gemma":0.0002179031,"domain_scores_codex":[0.9988753,0.0001066513,0.0001688545,0.0003480886,0.000152071,0.0003489854],"domain_scores_gemma":[0.9993486,0.0001176622,0.00003994936,0.000325039,0.0001021758,0.00006661647],"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":[0.00005979331,0.00001466301,0.03339948,0.0002034008,0.0007041492,0.00001416179,0.0003785295,0.0007756677,0.9346788,0.000908406,0.0000439599,0.02881902],"study_design_scores_gemma":[0.003066575,0.0007557381,0.6664238,0.000232252,0.002044643,0.0001898277,0.003139099,0.2177564,0.08005134,0.008940786,0.01580365,0.001595866],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9857605,0.01059339,0.00288317,0.0002031488,0.00006049249,0.0001967795,0.00001711367,0.000003093678,0.0002822735],"genre_scores_gemma":[0.9969823,0.001040275,0.00158932,0.00007426515,0.000184854,0.00000838122,0.00002618644,0.000009800945,0.00008459596],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8546274,"threshold_uncertainty_score":0.4031956,"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."}}