{"id":"W4302363654","doi":"10.1101/2022.10.03.510614","title":"Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Merck Canada; Canada First Research Excellence Fund; Government of Canada; Génome Québec; Compute Canada","keywords":"Interpretability; Computer science; Machine learning; Artificial intelligence; Deep learning; Predictive modelling; Black box; Data mining","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.004796473,0.002021733,0.0009448324,0.000826523,0.0002653983,0.001873653,0.001935344,0.001352834,0.002940617],"category_scores_gemma":[0.01238665,0.0004485473,0.001253587,0.0007004951,0.001036006,0.002945577,0.001302494,0.004812938,0.001006259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001180668,"about_ca_system_score_gemma":0.001292699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003506591,"about_ca_topic_score_gemma":0.004610773,"domain_scores_codex":[0.9985946,0.0007013407,0.00008482035,0.0002938146,0.0002401986,0.00008509705],"domain_scores_gemma":[0.994723,0.003135496,0.0004671229,0.0008636316,0.0006348443,0.000175919],"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":[0.001080563,0.0004464459,0.01372451,0.001077368,0.0008062884,0.0002471288,0.0002218035,0.72109,0.01063777,0.01569399,0.02129217,0.213682],"study_design_scores_gemma":[0.00007272077,0.0002085898,0.00143547,0.0001673498,0.00014403,0.0000664832,0.00003589706,0.9615389,0.005115058,0.02700959,0.004161103,0.00004479052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2622241,0.02242951,0.6605259,0.0235828,0.0009772636,0.0002163811,0.007052856,0.01271693,0.01027417],"genre_scores_gemma":[0.8601519,0.005089603,0.122481,0.002512898,0.0003950034,0.0001577753,0.006161002,0.0004778623,0.002573022],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004796473,"threshold_uncertainty_score":0.02536649,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01654024791648597,"score_gpt":0.261284270054588,"score_spread":0.244744022138102,"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."}}