{"id":"W3158945941","doi":"10.1101/2021.05.05.442619","title":"Inter-laboratory automation of the <i>in vitro</i> micronucleus assay using imaging flow cytometry and deep learning","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"DNA Repair Mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Girton College, University of Cambridge; Health Canada; University of Cambridge","keywords":"Micronucleus test; Micronucleus; Flow cytometry; Artificial intelligence; Computer science; Automation; Pattern recognition (psychology); Biology; Engineering; Medicine; Molecular biology; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001998213,0.0008426965,0.0005289277,0.000713315,0.0003390654,0.0007386623,0.0009098654,0.0006036622,0.001654826],"category_scores_gemma":[0.002316941,0.0003417637,0.0004464647,0.0002939311,0.0005228868,0.0005274938,0.001124112,0.0008807619,0.001051642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006476945,"about_ca_system_score_gemma":0.000824675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002483016,"about_ca_topic_score_gemma":0.003397203,"domain_scores_codex":[0.9987628,0.0001964214,0.00008316087,0.0004752402,0.0003653582,0.0001169894],"domain_scores_gemma":[0.9984383,0.0003329003,0.000224185,0.0004010699,0.0005192849,0.00008416051],"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":[0.0004268416,0.000263697,0.01125559,0.0001920148,0.00007883007,0.0001254168,0.0002121091,0.01588658,0.8303819,0.0005499153,0.002149939,0.1384773],"study_design_scores_gemma":[0.00001979693,0.0003976758,0.02354506,0.00003404149,0.00003958414,0.0001926387,0.00007644216,0.1691549,0.8008428,0.0007258034,0.00490388,0.00006738859],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4428162,0.0002182739,0.5388904,0.0003468581,0.0001455712,0.0004224984,0.001284581,0.01261481,0.003260821],"genre_scores_gemma":[0.7617128,0.000159327,0.2333938,0.0002257214,0.00002653351,0.0005063799,0.00132314,0.0004542752,0.002197949],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002483016,"threshold_uncertainty_score":0.01056772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005690653244311673,"score_gpt":0.2067964180627075,"score_spread":0.2011057648183958,"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."}}