Cross-species and tissue imputation of species-level DNA methylation samples across mammalian species

Abstract

DNA methylation data offers valuable insights into various aspects of mammalian biology. The recent introduction and large-scale application of the mammalian methylation array has significantly expanded the availability of such data across conserved sites in many mammalian species. In our study, we consider 13,245 samples profiled on this array encompassing 348 species and 59 tissues from 746 species-tissue combinations. While having some coverage of many different species and tissue types, this data captures only 3.6% of potential species-tissue combinations. To address this gap, we developed CMImpute (Cross-species Methylation Imputation), a method based on a Conditional Variational Autoencoder, to impute DNA methylation for non-profiled species-tissue combinations. In cross-validation, we demonstrate that CMImpute achieves a strong correlation with actual observed values, surpassing several baseline methods. Using CMImpute we imputed methylation data for 19,786 new species-tissue combinations. We believe that both CMImpute and our imputed data resource will be useful for DNA methylation analyses across a wide range of mammalian species.

Cross Tissue DNAm Biomarker Prediction using Transfer Learning

“…While some research has looked at estimating methylation across tissues [13], algorithms that do this without having access to multiple tissue data are still unavailable. While some research has looked at estimating methylation across tissues [13] or predicting species' average methylation across tissues [14], algorithms are not available for individual level prediction yet or without needing access to multiple tissue data. Moreover, simply measuring these tissues and applying current DNAm biomarkers may not yield meaningful insights, a point underscored by researchers who advise caution when using methylation markers from surrogate tissues [15].…”