Getting personal with epigenetics: towards individual-specific epigenomic imputation with machine learning

TY - JOUR

T1 - Getting personal with epigenetics

T2 - towards individual-specific epigenomic imputation with machine learning

AU - Hawkins-Hooker, Alex

AU - Visonà, Giovanni

AU - Narendra, Tanmayee

AU - Rojas-Carulla, Mateo

AU - Schölkopf, Bernhard

AU - Schweikert, Gabriele

N1 - Funding Information: This project has received funding from the Academy of Medical Sciences, UK (Springboard Fellowship SBF004/1060) and from UK Research and Innovation (Future Leader Fellowship MR/T022620/1) for author GS. It has also been supported by the European Union’s Framework Programme for Research and Innovation Horizon 2020 (2014- 2020) under the Marie Skłodowska-Curie Grant Agreement No. 813533- MSCA-ITN-2018 (for author GV) and by the German Federal Ministry of Education and Research (BMBF): Tübingen AI Center, FKZ: 01IS18039B, and by the Machine Learning Cluster of Excellence, EXC number 2064/1- Project number 390727645 (for author BS). AHH was in part supported by the EPSRC Grant EP/S021566/1. The computing infrastructure was partly provided by the BMBF-funded de.NBI Cloud within the German Network for Bioinformatics Infrastructure (de.NBI) (031A532B, 031A533A, 031A533B, 031A534A, 031A535A, 031A537A, 031A537B, 031A537C, 031A537D, 031A538A). The authors thank the International Max Planck Research School for Intelligent Systems (IMPRS-IS) for supporting Tanmayee Narendra. GS would like to thank Dr Hartmut Schweikert for constructive criticism and advice. Copyright: © 2023. Springer Nature Limited.

PY - 2023/8/7

Y1 - 2023/8/7

N2 - Epigenetic modifications are dynamic mechanisms involved in the regulation of gene expression. Unlike the DNA sequence, epigenetic patterns vary not only between individuals, but also between different cell types within an individual. Environmental factors, somatic mutations and ageing contribute to epigenetic changes that may constitute early hallmarks or causal factors of disease. Epigenetic modifications are reversible and thus promising therapeutic targets for precision medicine. However, mapping efforts to determine an individual's cell-type-specific epigenome are constrained by experimental costs and tissue accessibility. To address these challenges, we developed eDICE, an attention-based deep learning model that is trained to impute missing epigenomic tracks by conditioning on observed tracks. Using a recently published set of epigenomes from four individual donors, we show that transfer learning across individuals allows eDICE to successfully predict individual-specific epigenetic variation even in tissues that are unmapped in a given donor. These results highlight the potential of machine learning-based imputation methods to advance personalized epigenomics.

AB - Epigenetic modifications are dynamic mechanisms involved in the regulation of gene expression. Unlike the DNA sequence, epigenetic patterns vary not only between individuals, but also between different cell types within an individual. Environmental factors, somatic mutations and ageing contribute to epigenetic changes that may constitute early hallmarks or causal factors of disease. Epigenetic modifications are reversible and thus promising therapeutic targets for precision medicine. However, mapping efforts to determine an individual's cell-type-specific epigenome are constrained by experimental costs and tissue accessibility. To address these challenges, we developed eDICE, an attention-based deep learning model that is trained to impute missing epigenomic tracks by conditioning on observed tracks. Using a recently published set of epigenomes from four individual donors, we show that transfer learning across individuals allows eDICE to successfully predict individual-specific epigenetic variation even in tissues that are unmapped in a given donor. These results highlight the potential of machine learning-based imputation methods to advance personalized epigenomics.

KW - Humans

KW - Epigenomics/methods

KW - Epigenesis, Genetic

KW - Machine Learning

KW - Epigenome

KW - Precision Medicine/methods

KW - DNA Methylation/genetics

UR - https://www.scopus.com/pages/publications/85166785764

U2 - 10.1038/s41467-023-40211-2

DO - 10.1038/s41467-023-40211-2

M3 - Article

C2 - 37550323

SN - 2041-1723

VL - 14

JO - Nature Communications

JF - Nature Communications

M1 - 4750

ER -