{"id":"W2955502047","doi":"10.1093/bioinformatics/btz318","title":"MOLI: multi-omics late integration with deep neural networks for drug response prediction","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":407,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Canada Foundation for Innovation","keywords":"Drug response; Computer science; Representation (politics); Machine learning; Artificial intelligence; Omics; Precision oncology; Artificial neural network; Computational biology; Data mining; Drug; Precision medicine; Bioinformatics; Biology","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":[0.0004239053,0.0002296258,0.0001855258,0.00005905475,0.00010894,0.000083616,0.0001946819,0.000215278,0.000006223783],"category_scores_gemma":[0.00003240709,0.0001841976,0.00009772956,0.00009727219,0.00005132613,0.00003084774,0.00007199503,0.0001453325,0.00001658748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003298366,"about_ca_system_score_gemma":0.00004892464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003085306,"about_ca_topic_score_gemma":0.00002500099,"domain_scores_codex":[0.9988811,0.00002865478,0.0004646225,0.000164358,0.0001195929,0.0003416747],"domain_scores_gemma":[0.9990695,0.00003484503,0.000245416,0.0004106174,0.0001424213,0.00009717936],"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":[0.01671185,0.0003683862,0.007036805,0.0006482315,0.0006918294,0.000002775903,0.005703407,0.767199,0.02502389,0.0009686112,0.0151301,0.1605152],"study_design_scores_gemma":[0.001643322,0.0005111439,0.0008021471,0.00002031669,0.00002900249,0.00001531426,0.0003915458,0.9891064,0.001637598,0.0000181123,0.005573541,0.0002516243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3964393,0.0001188036,0.6015738,0.00008652623,0.0004526041,0.0009474637,0.00007340361,0.00003742781,0.000270769],"genre_scores_gemma":[0.9383566,0.00007482649,0.0582154,0.0007188065,0.0002183907,0.00006399735,0.00115367,0.00004426564,0.001154087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5433583,"threshold_uncertainty_score":0.7511362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007039244457505459,"score_gpt":0.2143085593870241,"score_spread":0.2072693149295187,"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."}}