Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Mar;41(3):399-408.
doi: 10.1038/s41587-022-01520-x. Epub 2023 Jan 2.

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

Rosa Lundbye Allesøe  1   2   3 Agnete Troen Lundgaard  1   2 Ricardo Hernández Medina  1 Alejandro Aguayo-Orozco  1   2 Joachim Johansen  1   2 Jakob Nybo Nissen  1 Caroline Brorsson  1   2 Gianluca Mazzoni  1   2 Lili Niu  1 Jorge Hernansanz Biel  1   2 Cristina Leal Rodríguez  1 Valentas Brasas  1 Henry Webel  1 Michael Eriksen Benros  3   4 Anders Gorm Pedersen  2 Piotr Jaroslaw Chmura  1   2 Ulrik Plesner Jacobsen  1   2 Andrea Mari  5 Robert Koivula  6 Anubha Mahajan  6 Ana Vinuela  7   8 Juan Fernandez Tajes  6 Sapna Sharma  9   10   11 Mark Haid  12 Mun-Gwan Hong  13 Petra B Musholt  14 Federico De Masi  1   2 Josef Vogt  15 Helle Krogh Pedersen  2   15 Valborg Gudmundsdottir  1   2 Angus Jones  16 Gwen Kennedy  17 Jimmy Bell  18 E Louise Thomas  18 Gary Frost  19 Henrik Thomsen  20 Elizaveta Hansen  20 Tue Haldor Hansen  15 Henrik Vestergaard  15 Mirthe Muilwijk  21 Marieke T Blom  22 Leen M 't Hart  21   23   24 Francois Pattou  25 Violeta Raverdy  25 Soren Brage  26 Tarja Kokkola  27 Alison Heggie  28 Donna McEvoy  29 Miranda Mourby  30 Jane Kaye  30 Andrew Hattersley  16 Timothy McDonald  16 Martin Ridderstråle  31 Mark Walker  32 Ian Forgie  33 Giuseppe N Giordano  34 Imre Pavo  35 Hartmut Ruetten  14 Oluf Pedersen  15 Torben Hansen  15 Emmanouil Dermitzakis  7 Paul W Franks  31   36   37 Jochen M Schwenk  13 Jerzy Adamski  38   39   40 Mark I McCarthy  6   41   42 Ewan Pearson  33 Karina Banasik  1   2 Simon Rasmussen  43 Søren Brunak  44   45 IMI DIRECT Consortium
Collaborators, Affiliations

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

Rosa Lundbye Allesøe et al. Nat Biotechnol. 2023 Mar.

Erratum in

  • Author Correction: Discovery of drug-omics associations in type 2 diabetes with generative deep-learning models.
    Allesøe RL, Lundgaard AT, Hernández Medina R, Aguayo-Orozco A, Johansen J, Nissen JN, Brorsson C, Mazzoni G, Niu L, Biel JH, Leal Rodríguez C, Brasas V, Webel H, Benros ME, Pedersen AG, Chmura PJ, Jacobsen UP, Mari A, Koivula R, Mahajan A, Vinuela A, Tajes JF, Sharma S, Haid M, Hong MG, Musholt PB, De Masi F, Vogt J, Pedersen HK, Gudmundsdottir V, Jones A, Kennedy G, Bell J, Thomas EL, Frost G, Thomsen H, Hansen E, Hansen TH, Vestergaard H, Muilwijk M, Blom MT, 't Hart LM, Pattou F, Raverdy V, Brage S, Kokkola T, Heggie A, McEvoy D, Mourby M, Kaye J, Hattersley A, McDonald T, Ridderstråle M, Walker M, Forgie I, Giordano GN, Pavo I, Ruetten H, Pedersen O, Hansen T, Dermitzakis E, Franks PW, Schwenk JM, Adamski J, McCarthy MI, Pearson E, Banasik K, Rasmussen S, Brunak S; IMI DIRECT Consortium. Allesøe RL, et al. Nat Biotechnol. 2023 Jul;41(7):1026. doi: 10.1038/s41587-023-01805-9. Nat Biotechnol. 2023. PMID: 37130959 Free PMC article. No abstract available.

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.

PubMed Disclaimer

Conflict of interest statement

S. Brunak has ownerships in Intomics A/S, Hoba Therapeutics Aps, Novo Nordisk A/S, Lundbeck A/S, and managing board memberships in Proscion A/S and Intomics A/S. M.I.C. has served on advisory panels for Pfizer, Novo Nordisk, and Zoe Global; has received honoraria from Merck, Pfizer, Novo Nordisk, and Eli Lilly; and has received research funding from Abbvie, Astra Zeneca, Boehringer Ingelheim, Eli Lilly, Janssen, Merck, Novo Nordisk, Pfizer, Roche, Sanofi Aventis, Servier, and Takeda. As of June 2019, M.I.C. is an employee of Genentech and a holder of Roche stock. E.P. has received honoraria from Sanofi and Lilly. The other authors declare no competing interests.

Figures

Fig. 1
Fig. 1. Integrating multi-omics data with a VAE.
a, Principle of integration and analysis approach using MOVE. Individual-level non-omics and multi-omics data were used as input to a VAE. The optimal network hyperparameters were estimated from the summed test set error across all individuals in the test (test likelihood), training reconstruction accuracy, and model stability. Significant drug–omics associations were identified by perturbing drug status from no (0) to yes (1) for all individuals that were not already administered the drug. b, UMAP representation of the latent representation from the 789 people with newly diagnosed T2D. Individuals were colored according to their z-scaled Matsuda index from low (blue), average (yellow), and high (red). c, Overlap in significant drug–omics associations between standard t-test (two-sided, Benjamini–Hochberg FDR < 0.01) on the input data, MOVE t-test (multi-stage Bonferroni-corrected, P adjust < 0.05) and MOVE Bayes approaches (FDR Bayes < 0.05). The different methods of multiple testing correction corresponded to FDR of 0.05 on the ground-truth dataset. The overlap between MOVE t-test and MOVE Bayes was used for further analysis (n = 573). d, The number of significant associations found between drugs and features in the multi-omics datasets using MOVE t-test and MOVE Bayes (purple), t-test (green) or ANOVA (orange). See c for information on the tests. e, Fraction of features in the multi-omics datasets that was found by MOVE to be significantly associated with at least one drug (n = 20). The lower and upper hinges correspond to the first and third quartiles. The upper and lower whiskers extend from the hinge to the highest and lowest values, respectively, but no further than 1.5× interquartile range from the hinge. Data beyond the ends of whiskers are outliers and are plotted individually. Source data
Fig. 2
Fig. 2. Significant associations between drugs, clinical, and multi-omics features.
a, Significant associations between drugs and clinical features. Effects are given as effect size (z-scaled units) from negative (blue) to positive (red). Significant associations identified by both MOVE t-test and MOVE Bayes are indicated using a star. Features (y-axis) and drugs (x-axis) are clustered using hierarchical clustering on the basis of Euclidean distances. b, As in a but showing per individual-level associations of metformin to multi-omics features demonstrating that associations are highly stable across individuals. Features (y-axis) and newly diagnosed T2D individuals (x-axis). Source data
Fig. 3
Fig. 3. Drug associations with metagenomics species and drug–drug similarities.
a, Display of effect sizes (z-scaled units) for (outer to inner) metformin, simvastatin, atorvastatin, omeprazole, lansoprazole, paracetamol, and codeine. Only significant associations to any of the drugs are shown and effect size is visualized as brown (negative), gray (none), and green (positive). Selected omics features are indicated. The Gene Ontologies element represents significantly over-represented Gene Ontology terms using transcriptomics (hypergeometric test, FDR < 0.05) (green). The innermost ring indicates SHAP importance for the individual features in the encoding from input data to the latent representation. b, Effect size (z-scaled units) (x-axis) of the human gut metagenomics species that were significantly associated with metformin (orange) or omeprazole (teal). c, Drug–drug similarities by comparing drug-response profiles across the multi-omics datasets. Cosine similarity indicated from no similarity (blue) to identical profiles (red). d, Average effect (z-score) of drugs for the omics datasets. All 20 drugs are shown, however, only metformin (red), omeprazole (purple), atorvastatin (green), and simvastatin (blue) are indicated. All other drugs are colored gray without a text label. e, Distribution of multi-omics ranks for the different drugs. The ranks are determined as a number between 1–20 (drugs) on the basis of the average effect size from d. The boxes are colored according to number of individuals taking a particular drug from 0 (white) to 323 (purple). There was no correlation between rank scores and number of individuals taking a drug (PCC = 0.14). The lower and upper hinges correspond to the first and third quartiles. The upper and lower whiskers extend from the hinge to the highest and lowest values, respectively, but no further than 1.5× interquartile range from the hinge. Data beyond the ends of whiskers are outliers and are plotted individually. Source data

References

    1. Fares H, DiNicolantonio JJ, O’Keefe JH, Lavie CJ. Amlodipine in hypertension: a first-line agent with efficacy for improving blood pressure and patient outcomes. Open Heart. 2016;3:e000473. doi: 10.1136/openhrt-2016-000473. - DOI - PMC - PubMed
    1. Hu JX, Thomas CE, Brunak S. Network biology concepts in complex disease comorbidities. Nat. Rev. Genet. 2016;17:615–629. doi: 10.1038/nrg.2016.87. - DOI - PubMed
    1. Austin RP. Polypharmacy as a risk factor in the treatment of type 2 diabetes. Diabetes Spectr. 2006;19:13–16. doi: 10.2337/diaspect.19.1.13. - DOI
    1. Zhou W, et al. Longitudinal multi-omics of host–microbe dynamics in prediabetes. Nature. 2019;569:663–671. doi: 10.1038/s41586-019-1236-x. - DOI - PMC - PubMed
    1. Hasin Y, Seldin M, Lusis A. Multi-omics approaches to disease. Genome Biol. 2017;18:83. doi: 10.1186/s13059-017-1215-1. - DOI - PMC - PubMed

Publication types