{"id":"W4392311499","doi":"10.2131/jts.49.105","title":"DTox: A deep neural network-based <i>in visio</i> lens for large scale toxicogenomics data","year":2024,"lang":"en","type":"article","venue":"The Journal of Toxicological Sciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Aptose Biosciences (Canada)","funders":"Co-creation place formation support program; University of Tokyo; Japan Science and Technology Agency; Okinawa Institute of Science and Technology Graduate University; Ministry of Health, Labour and Welfare","keywords":"Toxicogenomics; Scale (ratio); Artificial neural network; Computer science; Artificial intelligence; Chemistry; Cartography; Geography","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":[0.002714425,0.0001223284,0.0001670974,0.00005711108,0.0002328765,0.00009853981,0.001163761,0.000125125,0.00006609982],"category_scores_gemma":[0.0002385873,0.00006736694,0.0001067161,0.0002931796,0.0002029562,0.00002347628,0.0002149992,0.000139771,0.00000281662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002756908,"about_ca_system_score_gemma":0.0002053954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.303844e-7,"about_ca_topic_score_gemma":0.00009650356,"domain_scores_codex":[0.9985268,0.0001949835,0.0003658315,0.0003036743,0.000254061,0.0003546996],"domain_scores_gemma":[0.9992172,0.0001572033,0.0001652996,0.0003004032,0.00005812301,0.000101783],"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":[0.000214367,0.0001253442,0.0002385014,0.00001072947,0.00001419538,0.000004183088,0.00004664387,0.0119503,0.9651508,0.000411424,0.01550188,0.0063316],"study_design_scores_gemma":[0.00147016,0.003684646,0.006331479,0.0001135317,0.0001072118,0.0001089415,0.0002648806,0.290194,0.06191133,0.001593808,0.6337475,0.0004725206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.960489,0.01046422,0.02132897,0.005865715,0.0008874768,0.0003059993,0.00004119832,0.00001180575,0.0006056166],"genre_scores_gemma":[0.9957889,0.0005255545,0.001905773,0.001052676,0.0005865839,0.000007799591,0.00001331174,0.000007282219,0.0001121014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9032395,"threshold_uncertainty_score":0.2747144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05451882582509644,"score_gpt":0.3230857780567298,"score_spread":0.2685669522316334,"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."}}