{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007670115,0.0001048421,0.0001498695,0.0002721234,0.000124688,0.00009023654,0.0003896194,0.00006255788,0.000002546823],"category_scores_gemma":[0.0008561523,0.000104221,0.00008205653,0.0007455119,0.00003480808,0.0007161581,0.0001972898,0.0001074164,0.00002769007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004425714,"about_ca_system_score_gemma":0.00006023799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000457571,"about_ca_topic_score_gemma":9.905871e-7,"domain_scores_codex":[0.998825,0.00006589122,0.0004346882,0.0001253775,0.0003535025,0.0001955521],"domain_scores_gemma":[0.9980398,0.00123006,0.0002595809,0.0002395966,0.0001828061,0.0000480872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000187021,0.0000747201,0.001465995,0.0004519866,0.00005352975,8.993383e-7,0.006858533,0.2196272,0.00006051734,0.6222925,0.001287075,0.1478084],"study_design_scores_gemma":[0.0002817018,0.00006818972,0.009364202,0.00007365661,0.000006900722,0.000001688224,0.0002687384,0.9339213,0.0004303326,0.05494234,0.0005543322,0.00008658024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02803499,0.00002134454,0.970399,0.0001977186,0.0005528842,0.0002631754,0.00002667741,0.0002877483,0.0002164863],"genre_scores_gemma":[0.2298096,0.00002270532,0.7698258,0.00005599545,0.00004199435,0.00004213824,0.0001091403,0.00001050456,0.0000820739],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7142942,"threshold_uncertainty_score":0.4250008,"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."}}