PuSH - Publication Server of Helmholtz Zentrum München

Allesøe, R.L.* ; Lundgaard, A.T.* ; Hernández Medina, R.* ; Aguayo-Orozco, A.* ; Johansen, J.D.* ; Nissen, J.N.* ; Brorsson, C.* ; Mazzoni, G.* ; Niu, L.* ; Biel, J.H.* ; Brasas, V.* ; Webel, H.* ; Benros, M.E.* ; Pedersen, A.G.* ; Chmura, P.J.* ; Jacobsen, U.P.* ; Mari, A.* ; Koivula, R.W.* ; Mahajan, A.* ; Viñuela, A.* ; Tajes, J.F.* ; Sharma, S. ; Haid, M. ; Hong, M.G.* ; Musholt, P.B.* ; De Masi, F.* ; Vogt, J.* ; Pedersen, H.K.* ; Gudmundsdottir, V.* ; Jones, A.* ; Kennedy, G.* ; Bell, J.* ; Thomas, E.L.* ; Frost, G.* ; Thomsen, H.* ; Hansen, E.* ; Hansen, T.H.* ; Vestergaard, H.* ; Muilwijk, M.* ; Blom, M.T.* ; 't Hart, L.M.* ; Pattou, F.* ; Raverdy, V.* ; Brage, S.* ; Kokkola, T.* ; Heggie, A.* ; McEvoy, D.* ; Mourby, M.* ; Kaye, J.* ; Hattersley, A.* ; McDonald, T.A.* ; Ridderstråle, M.* ; Walker, M.* ; Forgie, I.* ; Giordano, G.N.* ; Pavo, I.* ; Ruetten, H.* ; Pedersen, O.* ; Hansen, T.* ; Dermitzakis, E.* ; Franks, P.W.* ; Schwenk, J.M.* ; Adamski, J. ; McCarthy, M.I.* ; Pearson, E.* ; Banasik, K.* ; Rasmussen, S.* ; Brunak, S.* ; IMI DIRECT Consortium (Thorand, B. ; Fritsche, A. ; Artati, A. ; Prehn, C. ; Grallert, H. ; Adam, J.)

Discovery of drug-omics associations in type 2 diabetes with generative deep-learning models.

Nat. Biotechnol. 41, 399-408 (2023)
Postprint Research data DOI PMC
Open Access Gold (Paid Option)
Creative Commons Lizenzvertrag
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.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords Metformin Treatment; Multi-omics; Metaanalysis; Cholesterol
ISSN (print) / ISBN 1087-0156
e-ISSN 1546-1696
Journal Nature Biotechnology
Quellenangaben Volume: 41, Issue: 3, Pages: 399-408 Article Number: , Supplement: ,
Publisher Nature Publishing Group
Publishing Place New York, NY
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Institute of Epidemiology II (EPI2)
CF Metabolomics & Proteomics (CF-MPC)
Institute of Experimental Genetics (IEG)
Institute of Diabetes Research and Metabolic Diseases (IDM)
Grants Innovative Medicines Initiative
Novo Nordisk Fonden
Seventh Framework Programme