{"id":"W4362657842","doi":"10.1093/bioinformatics/btad177","title":"MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":48,"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; Compute Canada; Government of Canada; McGill University","keywords":"Python (programming language); Machine learning; Computer science; Artificial intelligence; Multi-task learning; Deep learning; Drug; Encoder; Drug repositioning; Task (project management); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001622395,0.001834788,0.001360291,0.00081886,0.0002975179,0.0009325218,0.002583012,0.001989412,0.003315259],"category_scores_gemma":[0.003737957,0.0008593357,0.001520184,0.0005831523,0.0005668557,0.001234266,0.001409319,0.002687838,0.001013539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001197332,"about_ca_system_score_gemma":0.002099591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009812407,"about_ca_topic_score_gemma":0.01355563,"domain_scores_codex":[0.9995553,0.0001274048,0.00002695855,0.0001307973,0.00008965904,0.00006990914],"domain_scores_gemma":[0.9992732,0.0004022008,0.00007967871,0.0000534178,0.0001174819,0.00007399746],"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":[0.0003813908,0.0002496322,0.003194179,0.0002272292,0.0002391214,0.0001511376,0.00003544436,0.9057038,0.002476969,0.002650657,0.01193803,0.07275241],"study_design_scores_gemma":[0.00001357763,0.00003246927,0.00009409303,0.000006600209,0.000008365291,0.000007338375,0.000001972394,0.997326,0.0004711112,0.001643474,0.0003893735,0.000005657347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1000401,0.004287696,0.8596884,0.002252457,0.0003192412,0.0002881877,0.009762442,0.02068458,0.002676882],"genre_scores_gemma":[0.6925762,0.001368435,0.2784624,0.00167689,0.0002520522,0.0009093523,0.01702939,0.000671981,0.007053354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009812407,"threshold_uncertainty_score":0.01951063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02296927055731774,"score_gpt":0.2910711524486899,"score_spread":0.2681018818913721,"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."}}