{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001623207,0.00008634595,0.000104016,0.00003191486,0.0003859748,0.00002283141,0.0008724831,0.00003943677,0.00004909188],"category_scores_gemma":[0.0002911144,0.00006534793,0.0000269073,0.0001563276,0.0002050116,0.000001531729,0.0004471189,0.00009596269,0.000003378502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004033954,"about_ca_system_score_gemma":0.0001093157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003206577,"about_ca_topic_score_gemma":0.001697464,"domain_scores_codex":[0.9994223,0.00005537994,0.0001756801,0.0001698261,0.00005953005,0.0001173074],"domain_scores_gemma":[0.9982743,0.0001940172,0.00004670018,0.001353864,0.000079635,0.00005144591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001321048,0.00006551604,0.02764519,0.0000105075,0.0001523415,0.000001129546,0.001852875,0.0002623623,0.8763707,0.002449155,0.05338265,0.03779437],"study_design_scores_gemma":[0.0003830515,0.00004549551,0.053596,0.0001874675,0.00007036375,6.555907e-7,0.0006977026,0.00006184804,0.005465794,0.001715506,0.9376443,0.0001318165],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7398974,0.08004018,0.003813952,0.1651172,0.000393263,0.000418845,0.00007329947,0.00002244643,0.01022341],"genre_scores_gemma":[0.9817248,0.006076202,0.0008949891,0.01024782,0.00030476,0.00009422283,0.0002243443,0.000008915315,0.0004239345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8842617,"threshold_uncertainty_score":0.4847407,"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."}}