{"id":"W4387164781","doi":"10.1126/sciadv.adg1894","title":"HAVOC: Small-scale histomic mapping of cancer biodiversity across large tissue distances using deep neural networks","year":2023,"lang":"en","type":"article","venue":"Science Advances","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Biodiversity; Profiling (computer programming); Scale (ratio); Pipeline (software); Computer science; Generalizability theory; Benchmark (surveying); Biology; Cartography; Geography; Ecology","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":[0.0002935209,0.0001194188,0.0001468379,0.00005518898,0.0004461193,0.00004077242,0.000416467,0.00005116374,0.000006607077],"category_scores_gemma":[0.00005160411,0.0001190018,0.0000503891,0.0005939174,0.0005914457,0.0000232235,0.0003517764,0.00005716941,0.000002665152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005649781,"about_ca_system_score_gemma":0.00009014966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002081792,"about_ca_topic_score_gemma":0.002771291,"domain_scores_codex":[0.9987026,0.00001221546,0.0001689088,0.0004171221,0.00015766,0.0005414199],"domain_scores_gemma":[0.9994097,0.00001856852,0.0001381104,0.0002377066,0.0001091214,0.00008678146],"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":[0.00005882125,0.00004143985,0.153821,0.00005385768,0.00001572639,0.000007460641,0.0007504595,0.1004537,0.7003294,0.00002090496,0.000151014,0.04429625],"study_design_scores_gemma":[0.001741264,0.0003771659,0.07710845,0.0001115915,0.0000652576,0.00001228225,0.006652125,0.09706074,0.6669112,0.0002414361,0.1483364,0.001382084],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9840239,0.007761559,0.00695823,0.00006649766,0.0008687172,0.0001059717,0.0001580243,0.00001603342,0.00004101157],"genre_scores_gemma":[0.9977679,0.001190283,0.0006842285,0.0001165752,0.0001460508,0.000006345665,0.00002616525,0.000006554314,0.0000558438],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1481854,"threshold_uncertainty_score":0.4852754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01708978821671165,"score_gpt":0.3003750123657183,"score_spread":0.2832852241490066,"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."}}