{"id":"W4388928478","doi":"10.1093/bioadv/vbad166","title":"Adversarial training improves model interpretability in single-cell RNA-seq analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University Health Network; University of Toronto; Sinai Health System; University of Waterloo","funders":"","keywords":"Interpretability; Robustness (evolution); Machine learning; Computer science; Artificial intelligence; Classifier (UML); Data mining; Biology; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007594518,0.001765064,0.001077563,0.0008227328,0.0007272533,0.00185777,0.001708047,0.001638933,0.003742182],"category_scores_gemma":[0.02562204,0.0006094853,0.001638022,0.0005067999,0.002152226,0.002133806,0.002121814,0.003851682,0.001432575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642873,"about_ca_system_score_gemma":0.001753934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005785941,"about_ca_topic_score_gemma":0.00595714,"domain_scores_codex":[0.9981647,0.0008567994,0.00009107392,0.0004904,0.0002620672,0.0001351001],"domain_scores_gemma":[0.9859439,0.01121852,0.0004792253,0.001466603,0.0005544196,0.0003373639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005723744,0.0001152681,0.007758822,0.000319564,0.0002054945,0.0002221519,0.0002043125,0.920059,0.01213115,0.006642899,0.009621131,0.04214784],"study_design_scores_gemma":[0.00001441274,0.00003106429,0.0005758715,0.00002766064,0.00001487074,0.00002366639,0.00001838639,0.9842095,0.003980874,0.01032033,0.0007680986,0.0000151949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2109013,0.001966981,0.7518146,0.004741183,0.0006101856,0.0001577318,0.003916095,0.0196945,0.006197461],"genre_scores_gemma":[0.7915248,0.0005879335,0.191877,0.002058506,0.0001646523,0.0001919356,0.007098487,0.003042121,0.003454645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007594518,"threshold_uncertainty_score":0.04016411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02329046184857348,"score_gpt":0.2499431431405594,"score_spread":0.2266526812919859,"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."}}