Adapting Blood DNA Methylation Aging Clocks for Use in Saliva Samples With Cell-type Deconvolution

Abstract

DeepMAge is a deep-learning DNA methylation aging clock that measures the organismal pace of aging with the information from human epigenetic profiles. In blood samples, DeepMAge can predict chronological age within a 2.8 years error margin, but in saliva samples, its performance is drastically reduced since aging clocks are restricted by the training set domain. However, saliva is an attractive fluid for genomic studies due to its availability, compared to other tissues, including blood. In this article, we display how cell type deconvolution and elastic net can be used to expand the domain of deep aging clocks to other tissues. Using our approach, DeepMAge's error in saliva samples was reduced from 20.9 to 4.7 years with no retraining.

Keywords: DNA methylation; aging; aging clock; biogerontology; cell-type deconvolution; deep learning; domain adaptation; epigenetics.

FIGURE 1

Publicly available studies of DNAm in saliva samples have high inter- and intra-study cell composition variability. (A) Average cell composition of saliva samples in the studies used, estimated with EpiDISH DNAm deconvolution. N = Total number of samples in a study. (B) Immune cell distributions within the studies used. Boxes correspond to the IQR, whiskers protrude no further than 1.5×IQR. Boxes are colored according to their inclusion in the training or verification set.

FIGURE 2

Cell-type adjustment (“total age-transformed”) significantly improves the performance of DeepMAge (originally developed for blood samples) in the domain of saliva samples. (A) Training set, unadjusted: R ² = 0.73. (B) Training set, adjusted: R ² = 0.95. (C) Verification set, unadjusted: R ² = 0.63. (D) Verification set, adjusted: R ² = 0.92. R ² = coefficient of determination. Predictions for the training set were obtained with leave-one-study-out cross-validation.

FIGURE 3

The reported adjustment significantly increases the accuracy of age prediction in all studies, despite their different cell-type composition (Figure 1). (A) Prior to the adjustment DeepMAge _Blood predicts chronological age in saliva samples with a MAE of 26.36 years in the training set and 20.86 years in the verification set (Table 1). Numbers above boxes stand for the number of samples in each study. (B) After the “total age-transformed” adjustment DeepMAge’s error in saliva samples drops to a MAE of 4.57 years in the training set and 4.74 years in the verification set, despite the variable cell type composition of the samples across studies (Figure 1A). Boxes correspond to the interquartile region (IQR), whiskers protrude no further than 1.5×IQR. Boxes are colored according to their inclusion in the training or verification set.

FIGURE 4

The “total age-transformed” adjustment increases the age prediction accuracy in individual samples by up to 50 years in saliva samples. The absolute increase in accuracy is smaller in samples with higher immune cell count. Very few (5%) samples are predicted less accurately (left to the red vertical line) after the adjustment. Black line is the ordinary least squares regression, its R ² is 0.72 and Pearson’s r is −0.85.