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

被引:47
|
作者
Allesoe, Rosa Lundbye [1 ,2 ,3 ]
Lundgaard, Agnete Troen [1 ,2 ]
Medina, Ricardo Hernandez [1 ]
Aguayo-Orozco, Alejandro [1 ,2 ]
Johansen, Joachim [1 ,2 ]
Nissen, Jakob Nybo [1 ]
Brorsson, Caroline [1 ,2 ]
Mazzoni, Gianluca [1 ,2 ]
Niu, Lili [1 ]
Biel, Jorge Hernansanz [1 ,2 ]
Brasas, Valentas [1 ]
Webel, Henry [1 ]
Benros, Michael Eriksen [3 ,4 ]
Pedersen, Anders Gorm [2 ]
Chmura, Piotr Jaroslaw [1 ,2 ]
Jacobsen, Ulrik Plesner [1 ,2 ]
Mari, Andrea [5 ]
Koivula, Robert [6 ]
Mahajan, Anubha [6 ]
Vinuela, Ana [7 ,8 ]
Tajes, Juan Fernandez [6 ]
Sharma, Sapna [9 ,10 ,11 ]
Haid, Mark [12 ]
Hong, Mun-Gwan [13 ]
Musholt, Petra B. [14 ]
De Masi, Federico [1 ,2 ]
Vogt, Josef [15 ]
Pedersen, Helle Krogh [2 ,15 ]
Gudmundsdottir, Valborg [1 ,2 ]
Jones, Angus [16 ]
Kennedy, Gwen [17 ]
Bell, Jimmy [18 ]
Thomas, E. Louise [18 ]
Frost, Gary [19 ]
Thomsen, Henrik [20 ]
Hansen, Elizaveta [20 ]
Hansen, Tue Haldor [15 ]
Vestergaard, Henrik [15 ]
Muilwijk, Mirthe [21 ]
Blom, Marieke T. [22 ]
Hart, Leen M. T. [21 ,23 ,24 ]
Pattou, Francois [25 ]
Raverdy, Violeta [25 ]
Brage, Soren [26 ]
Kokkola, Tarja [27 ]
Heggie, Alison [28 ]
McEvoy, Donna [29 ]
Mourby, Miranda [30 ]
Kaye, Jane [30 ]
Hattersley, Andrew [16 ]
机构
[1] Univ Copenhagen, Novo Nordisk Fdn Ctr Prot Res, Fac Hlth & Med Sci, Copenhagen, Denmark
[2] Tech Univ Denmark, Dept Hlth Technol, Lyngby, Denmark
[3] Copenhagen Univ Hosp, Copenhagen Res Ctr Mental Hlth, Mental Hlth Ctr Copenhagen, Copenhagen, Denmark
[4] Univ Copenhagen, Fac Hlth & Med Sci, Dept Immunol & Microbiol, Copenhagen, Denmark
[5] CNR, Inst Neurosci, Padua, Italy
[6] Univ Oxford, Wellcome Ctr Human Genet, Oxford, England
[7] Univ Geneva, Dept Genet Med & Dev, Med Sch, Geneva, Switzerland
[8] Newcastle Univ, Fac Med Sci, Biosci Inst, Newcastle Upon Tyne, Tyne & Wear, England
[9] Helmholtz Zentrum Munchen, Res Unit Mol Epidemiol, German Res Ctr Environm Hlth, Neuherberg, Bavaria, Germany
[10] Helmholtz Zentrum Munchen, Inst Epidemiol, German Res Ctr Environm Hlth, Neuherberg, Bavaria, Germany
[11] Tech Univ Munich, Chair Food Chem & Mol & Sensory Sci, Freising Weihenstephan, Germany
[12] Helmholtz Zentrum Muenchen, German Res Ctr Environm Hlth, Metabol & Prote Core, Neuherberg, Germany
[13] KTH Royal Inst Technol, Sch Engn Sci Chem Biotechnol & Hlth, Sci Life Lab, Affin Prote, Solna, Sweden
[14] Sanofi Aventis Deutschland, Res & Dev Global Dev Translat Med & Clin Pharmaco, Frankfurt, Germany
[15] Univ Copenhagen, Novo Nordisk Fdn Ctr Basic Metab Res, Fac Hlth & Med Sci, Copenhagen, Denmark
[16] Univ Exeter Med Sch, Exeter, Devon, England
[17] Univ Dundee, Sch Med, Immunoassay Biomarker Core Lab, Dundee, Scotland
[18] Univ Westminster, Res Ctr Optimal Hlth, Dept Life Sci, London, England
[19] Imperial Coll London, Fac Med, Sect Nutr Res, London, England
[20] Copenhagen Univ Hosp Herlev Gentofte, Dept Radiol, Herlev, Denmark
[21] Vrije Univ Amsterdam, Amsterdam Publ Hlth Res Inst, Dept Epidemiol & Data Sci, Amsterdam UMC, Amsterdam, Netherlands
[22] Vrije Univ Amsterdam, Amsterdam Publ Hlth Res Inst, Dept Gen Practice, Amsterdam UMC, Amsterdam, Netherlands
[23] Leiden Univ Med Ctr, Dept Biomed Data Sci, Sect Mol Epidemiol, Leiden, Netherlands
[24] Leiden Univ Med Ctr, Dept Cell & Chem Biol, Leiden, Netherlands
[25] Univ Lille, Lille Pasteur Inst, EGID, CHU Lille,Inserm, Lille, France
[26] Univ Cambridge, MRC Epidemiol Unit, Sch Clin Med, Cambridge, England
[27] Univ Eastern Finland, Dept Med, Kuopio, Finland
[28] Newcastle Univ, Inst Cellular Med, Newcastle Upon Tyne, Tyne & Wear, England
[29] Royal Victoria Infirm, Diabet Res Network, Newcastle Upon Tyne, Tyne & Wear, England
[30] Univ Oxford, Fac Law, Ctr Hlth Law & Emerging Technol HeLEX, Oxford, England
[31] Lund Univ, Lund Univ Diabet Ctr, Dept Clin Sci, Malmo, Sweden
[32] Newcastle Univ, Fac Med Sci, Translat & Clin Res Inst, Newcastle Upon Tyne, Tyne & Wear, England
[33] Univ Dundee, Sch Med, Div Populat Hlth & Genom, Dundee, Scotland
[34] Lund Univ, Lund Univ Diabet Ctr, Dept Clin Sci, Genet & Mol Epidemiol Unit,CRC,SUS, Malmo, Sweden
[35] Eli Lilly Reg Operat, Vienna, Austria
[36] Harvard TH Chan Sch Publ Hlth, Boston, MA USA
[37] Univ Oxford, Radcliffe Dept Med, OCDEM, Oxford, England
[38] German Res Ctr Environm Hlth, Inst Expt Genet, Helmholtz Zentrum Munchen, Neuherberg, Germany
[39] Natl Univ Singapore, Yong Loo Lin Sch Med, Dept Biochem, Singapore, Singapore
[40] Univ Ljubljana, Fac Med, Inst Biochem, Ljubljana, Slovenia
[41] Univ Oxford, Oxford Ctr Diabet Endocrinol & Metab, Oxford, England
[42] Genentech Inc, San Francisco, CA 94080 USA
关键词
METFORMIN TREATMENT; MULTI-OMICS; METAANALYSIS; CHOLESTEROL;
D O I
10.1038/s41587-022-01520-x
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
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.
引用
收藏
页码:399 / +
页数:17
相关论文
共 50 条
  • [21] Machine learning and deep learning predictive models for type 2 diabetes: a systematic review
    Fregoso-Aparicio, Luis
    Noguez, Julieta
    Montesinos, Luis
    Garcia-Garcia, Jose A.
    DIABETOLOGY & METABOLIC SYNDROME, 2021, 13 (01):
  • [22] Machine learning and deep learning predictive models for type 2 diabetes: a systematic review
    Luis Fregoso-Aparicio
    Julieta Noguez
    Luis Montesinos
    José A. García-García
    Diabetology & Metabolic Syndrome, 13
  • [23] DeepProg: an ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data
    Olivier B. Poirion
    Zheng Jing
    Kumardeep Chaudhary
    Sijia Huang
    Lana X. Garmire
    Genome Medicine, 13
  • [24] DeepProg: an ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data
    Poirion, Olivier B.
    Jing, Zheng
    Chaudhary, Kumardeep
    Huang, Sijia
    Garmire, Lana X.
    GENOME MEDICINE, 2021, 13 (01)
  • [25] In-vivo and in-vitro models of type 2 diabetes in pharmaceutical drug discovery
    Reed, MJ
    Scribner, KA
    DIABETES OBESITY & METABOLISM, 1999, 1 (02): : 75 - 86
  • [26] A Deep-Learning Based Algorithm for the Management of Hyperglycemia in Type 1 Diabetes Therapy
    Pellizzari, Elisa
    Prendin, Francesco
    Cappon, Giacomo
    Sparacino, Giovanni
    Facchinetti, Andrea
    2023 IEEE 19TH INTERNATIONAL CONFERENCE ON BODY SENSOR NETWORKS, BSN, 2023,
  • [27] Deep-learning prediction of cardiovascular outcomes from routine retinal images in individuals with type 2 diabetes
    Syed, Mohammad Ghouse
    Trucco, Emanuele
    Mookiah, Muthu R. K.
    Lang, Chim C.
    McCrimmon, Rory J.
    Palmer, Colin N. A.
    Pearson, Ewan R.
    Doney, Alex S. F.
    Mordi, Ify R.
    CARDIOVASCULAR DIABETOLOGY, 2025, 24 (01)
  • [28] Thoughts on the progression of type 2 diabetes drug discovery
    Bhatt, Harikrashna B.
    EXPERT OPINION ON DRUG DISCOVERY, 2015, 10 (02) : 107 - 110
  • [29] Adapting Deep Learning QSPR Models to Specific Drug Discovery Projects
    Fluetsch, Andrin
    Di Lascio, Elena
    Gerebtzoff, Gregori
    Rodriguez-Perez, Raquel
    MOLECULAR PHARMACEUTICS, 2024, 21 (04) : 1817 - 1826
  • [30] Discovery of type 2 diabetes mellitus with correlation and optimization driven hybrid deep learning approach
    Middha, Karuna
    Mittal, Apeksha
    COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING, 2024, 27 (13) : 1931 - 1943