TY - JOUR
T1 - Discovery of drug–omics associations in type 2 diabetes with generative deep-learning models
AU - IMI DIRECT Consortium
AU - Allesøe, Rosa Lundbye
AU - Lundgaard, Agnete Troen
AU - Hernández Medina, Ricardo
AU - Aguayo-Orozco, Alejandro
AU - Johansen, Joachim
AU - Nissen, Jakob Nybo
AU - Brorsson, Caroline
AU - Mazzoni, Gianluca
AU - Niu, Lili
AU - Biel, Jorge Hernansanz
AU - Brasas, Valentas
AU - Webel, Henry
AU - Benros, Michael Eriksen
AU - Pedersen, Anders Gorm
AU - Chmura, Piotr Jaroslaw
AU - Jacobsen, Ulrik Plesner
AU - Mari, Andrea
AU - Koivula, Robert
AU - Mahajan, Anubha
AU - Vinuela, Ana
AU - Tajes, Juan Fernandez
AU - Sharma, Sapna
AU - Haid, Mark
AU - Hong, Mun-Gwan
AU - Musholt, Petra B.
AU - de Masi, Federico
AU - Vogt, Josef
AU - Pedersen, Helle Krogh
AU - Gudmundsdottir, Valborg
AU - Jones, Angus
AU - Kennedy, Gwen
AU - Bell, Jimmy
AU - Thomas, E. Louise
AU - Frost, Gary
AU - Thomsen, Henrik
AU - Hansen, Elizaveta
AU - Hansen, Tue Haldor
AU - Vestergaard, Henrik
AU - Muilwijk, Mirthe
AU - Blom, Marieke T.
AU - ‘t Hart, Leen M.
AU - Pattou, Francois
AU - Raverdy, Violeta
AU - Brage, Soren
AU - Kokkola, Tarja
AU - Heggie, Alison
AU - McEvoy, Donna
AU - Mourby, Miranda
AU - Kaye, Jane
AU - Hattersley, Andrew
AU - Beulens, Joline
AU - Rutters, Femke
AU - Nijpels, Giel
AU - van Oort, Sabine
AU - Groeneveld, Lenka
AU - Elders, Petra
AU - Slieker, Roderick
N1 - Funding Information: We are grateful to IMI-DIRECT study participants who volunteered for phenotyping, and clinical and technical staff across involved European study centers who contributed to recruitment and clinical assessment of study participants. The work leading to this publication has received support from the Innovative Medicines Initiative Joint Undertaking under grant agreement 115317 (DIRECT), resources of which are composed of financial contribution from the European Union’s Seventh Framework Programme (FP7/2007-2013) and EFPIA companies’ in kind contribution. Information on the initiatives and activities of the IMI-DIRECT research consortium is available at https://directdiabetes.org . R.L.A., A.T.L, R.H.M., J.J., V.B., H.W., J.N.N., C.B., G.M., L.N., P.J.C., U.P.J, K.B., S.R., and S.B. were supported also by the Novo Nordisk Foundation (grants NNF14CC0001 and NNF17OC0027594). Additionally, R.H.M. was supported by Novo Nordisk Foundation (grant NNF20SA0035590). Figure a was partly created using BioRender.com. Finally, we would like to thank Tugce Karaderi for critical comments on the manuscript. Publisher Copyright: © 2023, The Author(s).
PY - 2023/3
Y1 - 2023/3
N2 - The application of multiple omics technologies in biomedical cohorts has the potential to reveal patient-level disease characteristics and individualized response to treatment. However, the scale and heterogeneous nature of multi-modal data makes integration and inference a non-trivial task. We developed a deep-learning-based framework, multi-omics variational autoencoders (MOVE), to integrate such data and applied it to a cohort of 789 people with newly diagnosed type 2 diabetes with deep multi-omics phenotyping from the DIRECT consortium. Using in silico perturbations, we identified drug–omics associations across the multi-modal datasets for the 20 most prevalent drugs given to people with type 2 diabetes with substantially higher sensitivity than univariate statistical tests. From these, we among others, identified novel associations between metformin and the gut microbiota as well as opposite molecular responses for the two statins, simvastatin and atorvastatin. We used the associations to quantify drug–drug similarities, assess the degree of polypharmacy and conclude that drug effects are distributed across the multi-omics modalities.
AB - The application of multiple omics technologies in biomedical cohorts has the potential to reveal patient-level disease characteristics and individualized response to treatment. However, the scale and heterogeneous nature of multi-modal data makes integration and inference a non-trivial task. We developed a deep-learning-based framework, multi-omics variational autoencoders (MOVE), to integrate such data and applied it to a cohort of 789 people with newly diagnosed type 2 diabetes with deep multi-omics phenotyping from the DIRECT consortium. Using in silico perturbations, we identified drug–omics associations across the multi-modal datasets for the 20 most prevalent drugs given to people with type 2 diabetes with substantially higher sensitivity than univariate statistical tests. From these, we among others, identified novel associations between metformin and the gut microbiota as well as opposite molecular responses for the two statins, simvastatin and atorvastatin. We used the associations to quantify drug–drug similarities, assess the degree of polypharmacy and conclude that drug effects are distributed across the multi-omics modalities.
UR - http://www.scopus.com/inward/record.url?scp=85145508974&partnerID=8YFLogxK
U2 - https://doi.org/10.1038/s41587-022-01520-x
DO - https://doi.org/10.1038/s41587-022-01520-x
M3 - Article
C2 - 36593394
SN - 1087-0156
VL - 41
SP - 399
EP - 408
JO - Nature biotechnology
JF - Nature biotechnology
IS - 3
ER -