Articolo in rivista, 2023, ENG, 10.1038/s41587-022-01520-x

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

Allesøe, Rosa Lundbye; Lundgaard, Agnete Troen; Hernández Medina, Ricardo; Aguayo-Orozco, Alejandro; Johansen, Joachim; Nissen, Jakob Nybo; Brorsson, Caroline; Mazzoni, Gianluca; Niu, Lili; Biel, Jorge Hernansanz; Brasas, Valentas; Webel, Henry; Benros, Michael Eriksen; Pedersen, Anders Gorm; Chmura, Piotr Jaroslaw; Jacobsen, Ulrik Plesner; Mari, Andrea; Koivula, Robert; Mahajan, Anubha; Vinuela, Ana; Tajes, Juan Fernandez; Sharma, Sapna; Haid, Mark; Hong, Mun Gwan; Musholt, Petra B.; De Masi, Federico; Vogt, Josef; Pedersen, Helle Krogh; Gudmundsdottir, Valborg; Jones, Angus; Kennedy, Gwen; Bell, Jimmy; Thomas, E. Louise; Frost, Gary; Thomsen, Henrik; Hansen, Elizaveta; Hansen, Tue Haldor; Vestergaard, Henrik; Muilwijk, Mirthe; Blom, Marieke T.; 't Hart, Leen M.; Pattou, Francois; Raverdy, Violeta; Brage, Soren; Kokkola, Tarja; Heggie, Alison; McEvoy, Donna; Mourby, Miranda; Kaye, Jane; Hattersley, Andrew; McDonald, Timothy; Ridderstråle, Martin; Walker, Mark; Forgie, Ian; Giordano, Giuseppe N.; Pavo, Imre; Ruetten, Hartmut; Pedersen, Oluf; Hansen, Torben; Dermitzakis, Emmanouil; Franks, Paul W.; Schwenk, Jochen M.; Adamski, Jerzy; McCarthy, Mark I.; Pearson, Ewan; Banasik, Karina; Rasmussen, Simon; Brunak, Søren; Froguel, Philippe; Thomas, Cecilia Engel; Haussler, Ragna; Beulens, Joline; Rutters, Femke; Nijpels, Giel; van Oort, Sabine; Groeneveld, Lenka; Elders, Petra; Giorgino, Toni; Rodriquez, Marianne; Nice, Rachel; Perry, Mandy; Bianzano, Susanna; Graefe-Mody, Ulrike; Hennige, Anita; Grempler, Rolf; Baum, Patrick; Stærfeldt, Hans Henrik; Shah, Nisha; Teare, Harriet; Ehrhardt, Beate; Tillner, Joachim; Dings, Christiane; Lehr, Thorsten; Scherer, Nina; Sihinevich, Iryna; Cabrelli, Louise; Loftus, Heather; Bizzotto, Roberto; Tura, Andrea; Dekkers, Koen

Oxford Social Sciences Division; University of Dundee School of Medicine; Institutionen för Kliniska Vetenskaper, Malmö; University of Exeter Medical School; Université de Lille; Itä-Suomen yliopisto; The Wellcome Centre for Human Genetics; Universität des Saarlandes; Harvard T.H. Chan School of Public Health; University of Bath; Università degli Studi di Milano; University of Newcastle upon Tyne, Faculty of Medical Sciences; NUS Yong Loo Lin School of Medicine; Université de Genève Faculté de Médecine; Genentech, Inc; Royal Victoria Infirmary; Helmholtz Center Munich German Research Center for Environmental Health; Univerza v Ljubljani Medicinska Fakulteta; Consiglio Nazionale delle Ricerche; Imperial College Faculty of Medicine; Sanofi-Aventis Deutschland GmbH; Technische Universität München; Servier; Leids Universitair Medisch Centrum; Copenhagen University Hospital; Imperial College London; Copenhagen University Hospital - Herlev and Gentofte; Faculty of Health and Medical Sciences; Boehringer Ingelheim Pharma GmbH & Co. KG; Technical University of Denmark; MRC Epidemiology Unit; Vrije Universiteit Amsterdam; Royal Devon and Exeter NHS Foundation Trust; University of Oxford Medical Sciences Division; The Royal Institute of Technology (KTH); University of Westminster; Eli Lilly Regional Operations

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.

Nature biotechnology (Print) 41 (3), pp. 399–408

Keywords

generative deep-learning models

CNR authors

Tura Andrea, Giorgino Toni, Bizzotto Roberto

CNR institutes

IBF – Istituto di biofisica, IN – Istituto di neuroscienze

ID: 480018

Year: 2023

Type: Articolo in rivista

Creation: 2023-04-06 17:33:21.000

Last update: 2023-10-21 10:07:18.000

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:480018

DOI: 10.1038/s41587-022-01520-x

Scopus: 2-s2.0-85145508974

ISI Web of Science (WOS): 000909067600016