{"id":"W2921591500","doi":"10.1093/bioinformatics/btz158","title":"Dr.VAE: improving drug response prediction via modeling of drug perturbation effects","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; SickKids Foundation; Vector Institute; University of Toronto","funders":"University of Toronto; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Hospital for Sick Children; Cancer Research Society","keywords":"Computer science; Autoencoder; Drug; Machine learning; Artificial intelligence; Deep learning; Medicine; Pharmacology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001522477,0.0001517421,0.0001992751,0.0002399185,0.00007550712,0.0001031703,0.0004845095,0.00005284327,0.000003247786],"category_scores_gemma":[0.0002863837,0.0001430403,0.00008845467,0.000382863,0.00001964316,0.001701779,0.0002606993,0.0001329368,0.00005795208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001097208,"about_ca_system_score_gemma":0.0001771978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001758837,"about_ca_topic_score_gemma":7.100758e-7,"domain_scores_codex":[0.998334,0.0001996419,0.0005596761,0.0001795747,0.0005189566,0.0002081628],"domain_scores_gemma":[0.9981757,0.0008038211,0.0002770844,0.0004992768,0.000177984,0.00006616656],"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":[0.0001601478,0.00007606474,0.000364734,0.0008428493,0.00003416765,0.000001227501,0.0140693,0.9183321,0.003421476,0.007610423,0.0003082676,0.05477924],"study_design_scores_gemma":[0.0003944094,0.00006105052,0.0007802718,0.00007861719,0.000008607251,0.000007004454,0.0001187939,0.9927262,0.002766967,0.002863463,0.00005453849,0.0001400467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3363092,0.00003494196,0.6621971,0.0001273036,0.0005582317,0.0002858842,0.000004119509,0.00009763246,0.0003855587],"genre_scores_gemma":[0.7695482,0.000003067026,0.2300407,0.0000996454,0.00003321446,0.000008615629,0.00001082813,0.000009617685,0.000246118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.433239,"threshold_uncertainty_score":0.5833015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0097157888356798,"score_gpt":0.2451470891509636,"score_spread":0.2354313003152838,"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."}}