{"id":"W3181070182","doi":"10.1007/s00204-021-03113-0","title":"Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning","year":2021,"lang":"en","type":"article","venue":"Archives of Toxicology","topic":"Carcinogens and Genotoxicity Assessment","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; University of Cambridge; National Institutes of Health; Girton College, University of Cambridge; Health Canada; National Institute of General Medical Sciences; Medical Research Council; Directorate for Biological Sciences","keywords":"Micronucleus test; Micronucleus; Artificial intelligence; Flow cytometry; Deep learning; Computer science; Pattern recognition (psychology); Biology; Medicine; Genetics; Internal medicine; Toxicity","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001333104,0.00007289767,0.0001412898,0.00006874635,0.00003753112,0.000005769566,0.00008839513,0.00004874067,0.000006571696],"category_scores_gemma":[0.0001193574,0.00006772789,0.00005614563,0.00009844233,0.0001504727,0.000003028296,0.0002654564,0.00009803921,1.27252e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001047568,"about_ca_system_score_gemma":0.00006675805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000891356,"about_ca_topic_score_gemma":0.00004885501,"domain_scores_codex":[0.9992199,0.0002410897,0.0001878535,0.000176435,0.00004644829,0.000128295],"domain_scores_gemma":[0.9996358,0.00004677388,0.0001064211,0.0001588804,0.00003026826,0.00002183481],"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":[0.00003685674,0.00004985195,0.02100657,0.00002876472,0.00002664749,0.00000355402,0.000222525,0.0004198714,0.9629254,0.0000142684,0.000002730225,0.01526298],"study_design_scores_gemma":[0.0003264919,0.00004547884,0.05288225,0.00001671494,0.00001334888,0.00002259592,0.0003331992,0.01365994,0.932364,0.00005075415,0.0002214086,0.00006382206],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913076,0.0009317327,0.007302696,0.0001138531,0.00006951025,0.00006594943,0.00001270405,0.000002169405,0.0001937617],"genre_scores_gemma":[0.990214,0.00005521173,0.00957613,0.00009175391,0.00002182537,0.000002245993,0.00001198182,0.000007806908,0.00001903504],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03187569,"threshold_uncertainty_score":0.2761863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005506279197920746,"score_gpt":0.245925247521598,"score_spread":0.2404189683236773,"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."}}