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

IMI DIRECT Consortium, Rosa Lundbye Allesøe, Agnete Troen Lundgaard, Ricardo Hernández Medina, Alejandro Aguayo-Orozco, Joachim Johansen, Jakob Nybo Nissen, Caroline Brorsson, Gianluca Mazzoni, Lili Niu, Jorge Hernansanz Biel, Valentas Brasas, Henry Webel, Michael Eriksen Benros, Anders Gorm Pedersen, Piotr Jaroslaw Chmura, Ulrik Plesner Jacobsen, Andrea Mari, Robert Koivula, Anubha MahajanAna Vinuela, Juan Fernandez Tajes, Sapna Sharma, Mark Haid, Mun-Gwan Hong, Petra B Musholt, Federico De Masi, Josef Vogt, Helle Krogh Pedersen, Valborg Gudmundsdottir, Angus Jones, Gwen Kennedy, Jimmy Bell, E Louise Thomas, Gary Frost, Henrik Thomsen, Elizaveta Hansen, Tue Haldor Hansen, Henrik Vestergaard, Mirthe Muilwijk, Marieke T Blom, Leen M 't Hart, Francois Pattou, Violeta Raverdy, Soren Brage, Tarja Kokkola, Alison Heggie, Donna McEvoy, Miranda Mourby, Ian Forgie, Ewan Pearson, Simon Rasmussen (Lead / Corresponding author), Soren Brunak (Lead / Corresponding author)

Research output: Contribution to journalArticlepeer-review

1 Downloads (Pure)

Abstract

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.

Original languageEnglish
Number of pages17
JournalNature Biotechnology
Early online date2 Jan 2023
DOIs
Publication statusE-pub ahead of print - 2 Jan 2023

Keywords

  • Data integration
  • Machine learning
  • Systems biology
  • Type 2 diabetes

Fingerprint

Dive into the research topics of 'Discovery of drug-omics associations in type 2 diabetes with generative deep-learning models'. Together they form a unique fingerprint.

Cite this