{"id":"W2999694445","doi":"10.1101/2020.01.15.908384","title":"Deep Learning Modelling of Androgen Receptor Responses to Prostate Cancer Therapies","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Prostate Cancer Treatment and Research","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Androgen receptor; Prostate cancer; Leverage (statistics); Mutant; Computational biology; Machine learning; Artificial intelligence; Artificial neural network; Phenotype; Drug; Computer science; Deep learning; Bioinformatics; Biology; Cancer; Medicine; Pharmacology; Genetics; 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":[0.0004667869,0.0005917933,0.0004871185,0.0002966554,0.0001279772,0.0005001077,0.0005247479,0.0009941832,0.001637133],"category_scores_gemma":[0.001202621,0.0002929042,0.0006416138,0.0002869438,0.0003601065,0.0002782303,0.0003054363,0.0007640888,0.0002072285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008918661,"about_ca_system_score_gemma":0.0007078815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01296191,"about_ca_topic_score_gemma":0.008813112,"domain_scores_codex":[0.9998958,0.00003133596,0.00000483189,0.00002585075,0.0000188152,0.00002321277],"domain_scores_gemma":[0.9995974,0.0002789848,0.00003295705,0.00001508717,0.00005662102,0.00001896536],"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":[0.00002398467,0.0000161194,0.000394794,0.00001047215,0.000008558688,0.000009444845,0.000003131801,0.996514,0.0004284306,0.0001320572,0.0001082907,0.002350722],"study_design_scores_gemma":[0.000001383971,0.000006189469,0.00007333279,7.393565e-7,0.00000102073,0.000001042827,6.2022e-7,0.9996543,0.0001351448,0.0001010345,0.0000245688,5.946116e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7987121,0.001167443,0.1899758,0.0008403606,0.0001360604,0.00009082922,0.001405268,0.0007885854,0.00688357],"genre_scores_gemma":[0.9865905,0.000155789,0.01019953,0.00007929042,0.00001156006,0.00006467687,0.0004496852,0.00002177131,0.002427238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01296191,"threshold_uncertainty_score":0.02577293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04366986498323012,"score_gpt":0.2879926492047851,"score_spread":0.244322784221555,"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."}}