{"id":"W4413398908","doi":"10.1038/s43856-025-01067-3","title":"Leveraging sequences missing from the human genome to diagnose cancer","year":2025,"lang":"en","type":"article","venue":"Communications Medicine","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Penn State Hershey Cancer Institute; Penn State College of Medicine; Center of Excellence in Regulatory Science and Innovation; University of California, San Francisco; U.S. Food and Drug Administration; Four Diamonds; National Human Genome Research Institute; Wellcome Trust; University of Pennsylvania; Elsa U. Pardee Foundation; Wellcome; Pennsylvania State University; U.S. Department of Health and Human Services","keywords":"Computational biology; Genome; Cancer; Biology; Lung cancer; Enhancer; Gene; DNA sequencing; Genetics; Medicine; Oncology; Gene expression","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":[0.001200867,0.0006325796,0.0005437661,0.001297852,0.0001954565,0.0005092759,0.0004038887,0.0007319584,0.0008578295],"category_scores_gemma":[0.004033891,0.0002032792,0.000457787,0.0005673717,0.000340611,0.0006134154,0.0003970128,0.0006740129,0.0005137892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004351243,"about_ca_system_score_gemma":0.0006403457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001615357,"about_ca_topic_score_gemma":0.002225856,"domain_scores_codex":[0.9995549,0.00009457504,0.00002291551,0.0001816349,0.0001137422,0.00003213562],"domain_scores_gemma":[0.9973592,0.001871237,0.0003066924,0.000159687,0.00023698,0.00006613298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001463344,0.0003644649,0.2880077,0.001005852,0.0005249301,0.0006183508,0.0002341895,0.1710932,0.1665566,0.002776544,0.002899596,0.3644551],"study_design_scores_gemma":[0.00004825194,0.0005757889,0.0552722,0.0001857903,0.0003516421,0.001411011,0.0001108747,0.7823404,0.1375438,0.01247645,0.009616817,0.00006702703],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6026787,0.006170242,0.3824354,0.001160475,0.0001371246,0.00009601008,0.002566777,0.001881938,0.002873353],"genre_scores_gemma":[0.9149299,0.001237782,0.08033914,0.0002967809,0.00005630111,0.00004926304,0.002253708,0.00005845462,0.0007786977],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001615357,"threshold_uncertainty_score":0.006350875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04464979582240002,"score_gpt":0.3599219172991764,"score_spread":0.3152721214767764,"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."}}