{"id":"W4316170966","doi":"10.1101/2023.01.11.22283903","title":"HAVOC: Small-scale histomic mapping of biodiversity across entire tumor specimens using deep neural networks","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"Ontario Institute for Cancer Research; Princess Margaret Cancer Foundation","keywords":"Profiling (computer programming); Biodiversity; Computer science; Tumor heterogeneity; Biology; Cartography; Geography; Artificial intelligence; Ecology; Cancer","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":[0.0009289897,0.0006989574,0.0004560419,0.001118729,0.0003543806,0.001255151,0.0009699857,0.0007199648,0.001326939],"category_scores_gemma":[0.001432585,0.0004457072,0.0005540792,0.0005801744,0.0005935873,0.0006743544,0.00158928,0.001043332,0.0003839504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009653176,"about_ca_system_score_gemma":0.0009318938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004507539,"about_ca_topic_score_gemma":0.007073441,"domain_scores_codex":[0.9996415,0.00005743316,0.00001549488,0.0001352328,0.00009986398,0.00005039933],"domain_scores_gemma":[0.9995233,0.0001461683,0.00009780784,0.0001005815,0.00007422004,0.00005797012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006352463,0.0002095977,0.02525233,0.0006816045,0.0005111929,0.0004788923,0.0004306136,0.3502317,0.2380383,0.01532832,0.02117991,0.3470222],"study_design_scores_gemma":[0.00002590896,0.00007263251,0.006562809,0.00003759424,0.00004305682,0.0001546572,0.00009251698,0.9231729,0.04531191,0.01746514,0.007009759,0.00005111905],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2032196,0.001156765,0.776494,0.0009150288,0.0001161974,0.0001077894,0.002948917,0.01179136,0.003250327],"genre_scores_gemma":[0.7228281,0.0005242074,0.2685012,0.0005261713,0.00005468433,0.0002666008,0.003763148,0.0007925697,0.002743223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004507539,"threshold_uncertainty_score":0.008962631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03837972175867832,"score_gpt":0.2590531593422248,"score_spread":0.2206734375835465,"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."}}