Research Article

Computational and Systems Biology

Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock

Google Research, United States
Buck Institute for Research on Aging, United States
Google Health, United States
Department of Biophysics, Post Graduate Institute of Medical Education and Research, India
Department of Ophthalmology, Zuckerberg San Francisco General Hospital and Trauma Center, United States
Department of Ophthalmology, University of California, San Francisco, United States

Mar 28, 2023

Open access
Copyright information

Abstract
Editor's evaluation
Introduction
Results
Discussion
Materials and methods
Data availability
References
Article and author information
Metrics

Abstract

Biological age, distinct from an individual’s chronological age, has been studied extensively through predictive aging clocks. However, these clocks have limited accuracy in short time-scales. Here we trained deep learning models on fundus images from the EyePACS dataset to predict individuals’ chronological age. Our retinal aging clocking, ‘eyeAge’, predicted chronological age more accurately than other aging clocks (mean absolute error of 2.86 and 3.30 years on quality-filtered data from EyePACS and UK Biobank, respectively). Additionally, eyeAge was independent of blood marker-based measures of biological age, maintaining an all-cause mortality hazard ratio of 1.026 even when adjusted for phenotypic age. The individual-specific nature of eyeAge was reinforced via multiple GWAS hits in the UK Biobank cohort. The top GWAS locus was further validated via knockdown of the fly homolog, Alk, which slowed age-related decline in vision in flies. This study demonstrates the potential utility of a retinal aging clock for studying aging and age-related diseases and quantitatively measuring aging on very short time-scales, opening avenues for quick and actionable evaluation of gero-protective therapeutics.

Editor's evaluation

This paper is an important contribution to the biological aging field using eye image data to create an aging clock of the retina in data from eyePACS with validation in the UK Biobank. The authors provide compelling evidence that the clock correlates with chronological and phenotypic age, predicting mortality independently of chronological age and showing longitudinal evidence. The work identifies novel genetic loci with a top site located in the ALKAL2 region, which is functionally validated in a Drosophila model.

https://doi.org/10.7554/eLife.82364.sa0

Introduction

Aging causes molecular and physiological changes throughout all tissues of the body, enhancing the risk of several diseases (López-Otín et al., 2013). Identifying specific markers of aging is a critical area of research, as each individual ages uniquely depending on both genetic and environmental factors (Ahadi et al., 2020). While a variety of aging clocks have recently been developed to track the aging process, including phenotypic age (Liu et al., 2018; a combination of chronological age and nine biomarkers predictive of mortality) and epigenetic clocks derived from DNA methylation (Horvath and Raj, 2018), many require a blood draw and multiplex assay of many analytes.

A growing body of evidence suggests that the microvasculature in the retina might be a reliable indicator of the overall health of the body’s circulatory system and the brain. Changes in the eyes accompany aging and many age-related diseases such as age-related macular degeneration (AMD) (Luu and Palczewski, 2018), diabetic retinopathy (Namperumalsamy et al., 2009), and neurodegenerative disorders like Parkinson’s (Luu and Palczewski, 2018; Archibald et al., 2009) and Alzheimer’s (Frost et al., 2013). Eyes are also ideal windows for early detection of systemic diseases by ophthalmologists, including AIDS (Sun et al., 2009; Cunningham and Margolis, 1998), chronic hypertension (Wong and McIntosh, 2005), and tumors (Kreusel et al., 2002). This broad utility is perhaps unsurprising, as any subtle changes in the vascular system first appear in the smallest blood vessels, and retinal capillaries are amongst the smallest in the body.

The subtle changes induced in these small vessels often go undetected by even the most sophisticated instruments, necessitating the use of better approaches involving deep learning. Fundus imaging has proven to be a powerful and non-invasive means for identifying specific markers of eye-related health. Deep-learning was initially employed to predict diabetic retinopathy from retinal images at accuracies matching, or even exceeding, experts (Gulshan et al., 2016). Since then, retinal images have been employed to identify at least 39 fundus diseases including glaucoma, diabetic retinopathy, age-related macular degeneration (Wong and McIntosh, 2005; Cen et al., 2021), cardiovascular risk (Poplin et al., 2018), chronic kidney disease (Sabanayagam et al., 2020), and, most recently, in predicting age (Zhu et al., 2023). Given its non-invasive, low-cost nature, retinal imaging provides an intriguing opportunity for longitudinal patient analysis to assess the rate of aging.

Here, we use deep learning models to predict chronological age from fundus retinal images, hereafter ‘eyeAge’, and use the deviation of this value from chronological age, hereafter ‘eyeAgeAccel’, for mortality and association analyses. We train this model on the well-studied EyePACS dataset and apply it on both the EyePACS and UK Biobank cohorts. Together, our results suggest that the trajectory of an individual’s biological age can be predicted in timelines under a year and that statistically significant genome-wide associations are possible. Enrichment analysis of top GWAS hits as well as experimental validation of the Drosophila homolog of ALKAL2, a gene in the top GWAS locus, indicates genetic markers of visual decline with age and demonstrates the potential predictive power of a retinal aging clock in assessing biological age.

Results

Prediction of age from fundus images

Figure 1 summarizes the analysis workflow for the study. Using the EyePACS dataset, we trained a fundus image model on 217,289 examples from 100,692 patients and tuned it on 54,292 images from 25,238 patients. These models were employed for longitudinal analysis of repeat patients and also applied on the UK Biobank dataset (119,532 images) which had a notably distinct demographic distribution (Table 1). For both studies, most visits generated two images, one image each for the left and right eye, the EyePACs dataset had more repeat visits by patients making the ratio of total images to total patients slightly larger (Table 1). In both analyses, we took the average of the predictions between the left and right eye from a single visit to infer age (See Materials and methods).

Figure 1

Download asset Open asset

Schematic of analysis pipeline.

EyePACS images were split into train and tune sets based on the patient. The model was then trained with the final model step being selected via the tune set. Prediction results on the EyePACS tune set were used for longitudinal analysis of aging. After filtering for image quality, inference was performed with the same model on the UK Biobank dataset and filtering for image quality, and the resulting eyeAgeAccel was used for GWAS analysis. Enrichment analysis was performed on the GWAS hits with a homolog of the top gene (*ALKAL2*) validated experimentally in *Drosophila*.

Table 1

Characteristics of patients in the development and validation sets (before filtering).

	Development set (EyePACS)		Test set (UK Biobank)
	Train	Tune	Test set (UK Biobank)
Patients	100,692	25,238	64,019
Images	217,289	54,292	119,532
Ethnicity	Black: 11908 [7%] Asia Pacific Islander: 11842 [7%] White: 22539 [13%] Hispanic: 125595 [71%] Native American: 1791 [1%] Other: 3809 [2%]	Black: 3040 [7%] Asia Pacific Islander: 2923 [7%] White: 5657 [13%] Hispanic: 31521 [71%] Native American: 426 [1%] Other: 918 [2%]	Black: 1540 [1%] Asia Pacific Islander: 4183 [4%] White: 107967 [91%] Hispanic: 0 [0%] Native_american: 0 [0%] Other: 5015 [4%]
Self- reported Sex	Female: 127075 [59%] Male: 90128 [41%]	Female: 31743 [58%] Male: 22531 [42%]	Female: 65739 [55%] Male: 53793 [45%]
Age	median = 55.13 mean = 54.21 std = 11.50	median = 55.19 mean = 54.20 std = 11.46	median = 57.94 mean = 56.85 std = 8.18

The model showed a strong correlation between chronological age and predicted age (eyeAge) in both the EyePACS (0.95) and UK Biobank (0.87) datasets (Figure 2—figure supplement 1). Using mean absolute error (MAE) to assess the fidelity of the aging clock showed that the model performed favorably on both datasets (2.86 and 3.30, respectively, after quality filtering) relative to previous studies (Zhu et al., 2023; Galkin et al., 2021; McEwen et al., 2020; Horvath, 2013). Next, we evaluated the efficacy of our predictions in one to two year time scales using longitudinal data. Using the EyePACS Tune dataset, we restricted ourselves to data from patients with exactly two visits (1719 subjects) and examined the models’ ability to order the two visits over multiple time scales. Note that no longitudinal information about patients was specifically used to train or tune the model to predict chronological age. While the observed and predicted age differences between the two visits (M=0.033, SD = 2.34, Figure 2—figure supplement 2) had low correlation (pearson ⍴=0.17, p-value = 1.4e-12), Figure 2A shows that the model correctly ordered 71% of visits within a year with an MAE less than 2 years. In both metrics, the fidelity decreased in older groups and with smaller age gaps.

Figure 2 with 3 supplements see all

Download asset Open asset

Longitudinal analysis of patients with exactly two visits in the EyePACS cohort.

(A) Changes of PPR (positive prediction ratio: the ratio of data whose eyeAge increased between subsequent visits) and MAE (mean absolute error) calculated on the same individual in relationship to chronological age at the first visit (left) and time between longitudinal visits (right). (B) Scatter plots representing correlation between eyeAge Gap (difference between predicted age and chronological age) of two consecutive visits from an individual (Same) or two consecutive visits from two different individuals (Random). (C) Correlation of eyeAge and chronological age between left and right and two consecutive visits of the same individual. (D) Scatter plots representing the correlation of left and right eyeAge Gap from the same or two random individuals.

Figure 2—source data 1 MAE and positive prediction ratio for time-matched and random individuals based on age at visit 1.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig2-data1-v2.zip
Download elife-82364-fig2-data1-v2.zip
Figure 2—source data 2 MAE and positive prediction ratio for time-matched and random individuals based on months between visits.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig2-data2-v2.zip
Download elife-82364-fig2-data2-v2.zip
Figure 2—source data 3 Age gap for random and time-matched individuals at visit 1 and 2.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig2-data3-v2.zip
Download elife-82364-fig2-data3-v2.zip
Figure 2—source data 4 Chronological and predicted age for left and right eye.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig2-data4-v2.zip
Download elife-82364-fig2-data4-v2.zip
Figure 2—source data 5 Age gap for random and time-matched individuals for left and right eyes.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig2-data5-v2.zip
Download elife-82364-fig2-data5-v2.zip
Figure 2—source data 6 Scatter plot of eyeAge with chronological age.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig2-data6-v2.zip
Download elife-82364-fig2-data6-v2.zip

To understand if this effect was simply a result of the noise of our innate age prediction, we performed an age-matched control experiment. We compared correlations between data points of one individual to data from a random pair of age-matched individuals (see Materials and methods). Comparisons were performed between each eye and timepoint. For all comparisons, the robust correlation observed within an individual’s data was lost in data between time-matched individuals (Figure 2B and D). Additionally, the positive predictive ratio and MAE exhibited reduced performance, 55% and 3.6 years (Figure 2—figure supplement 3), suggesting a reproducible, individual-specific eyeAge component. To further explore this individual-specific component, Figure 2C compares eyeAge and chronological age within an individual between eyes and timepoints, showing strong correlation in each quadrant.

Testing the model in UK Biobank cohort

We next applied our EyePACS-trained eyeAge model to the UK Biobank dataset. The UK Biobank cohort included retinal fundus images from 64,019 patients as well as extensive clinical labs and genomic data. These clinical markers enabled comparison of eyeAge with phenoAge, a clinical blood marker-based aging clock (Liu et al., 2018). The observed 0.87 correlation between eyeAge and chronological age in the UK Biobank cohort was consistent with (and slightly higher than) the observed correlation of phenoAge and chronological age (0.82) (Figure 3A and B). Notably, the correlation between phenoAge and eyeAge was substantially lower (0.72; Figure 3—figure supplement 1) and, in fact, roughly equivalent to the product of their respective correlations with chronological age, suggesting that they were largely independent. To explore this further, we computed the residuals from linear models that independently regressed chronological age on phenoAge and eyeAge, as described previously (Liu et al., 2018), yielding phenoAge acceleration (phenoAgeAccel) and eyeAge acceleration (eyeAgeAccel), and observed little correlation between the two age acceleration measures (Figure 3C). We then performed Cox proportional hazards regression analysis to assess mortality risk (Cox, 1972). The hazard ratio for eyeAge was statistically significant when adjusting for (self-reported) sex (1.09, CI=[1.08, 1.10], p-value = 1.6e-53), sex and age (1.04, CI=[1.02, 1.06], p-value = 1.8e-4), and sex, age, and phenoAge (1.03, CI=[1.01, 1.05], p-value = 2.8e-3) (Figure 3D). Stratifying the hazard ratio analysis showed a slight increase in the hazard ratio for women compared to men (1.035 vs 1.026), however the confidence intervals overlapped heavily (Supplementary file 1). Hazard ratio results adjusted for visual acuity are presented in (Figure 3—figure supplement 2 and Supplementary file 2).

Figure 3 with 2 supplements see all

Download asset Open asset

Relationships between eyeAge, phenoAge, and chronological age in the UK Biobank cohort.

(A) Correlation between eyeAge and chronological age (Pearson ⍴=0.86). (B) Correlation between phenoAge and chronological age (Pearson ⍴=0.82). (C) Correlation between eyeAgeAcceleration and phenoAgeAcceleration (Pearson ⍴=0.12). (D) Forest plot of all-cause mortality hazard ratios (diamonds) and confidence intervals (lines) for the UK Biobank dataset. Purple lines are adjusted only for sex; orange lines are adjusted for sex and age; blue lines are adjusted for sex, age, and phenoAge.

Figure 3—source data 1 Age, eyeAge, phenoAge, eyeAge Acceleration and phenoAge Acceleration values for each individual.: https://cdn.elifesciences.org/articles/82364/elife-82364-fig3-data1-v2.zip
Download elife-82364-fig3-data1-v2.zip

We also investigated the relationship between eyeAge and multiple additional measures of morbidity and disability available in the UK Biobank. We performed Cox proportional hazards regression on six additional chronic disease outcomes when adjusting for age and sex: chronic obstructive pulmonary disease (COPD), myocardial infarction, asthma, stroke, Parkinsonism, and dementia. Nominally significant associations between eyeAge and both COPD (p-value = 0.0048) and myocardial infarction (p-value = 0.049) were observed (Supplementary file 3). We performed linear regression on seven morbidity measurements reported at the time of imaging: fluid intelligence, systolic and diastolic blood pressure, the ‘Health score (England)’ index of multiple deprivation, pulse wave arterial stiffness, self-reported overall health rating, and self-reported presence of a longstanding illness. Increased eyeAgeAccel corresponded to significantly increased systolic blood pressure (p-value = 1.025e-7) and decreased levels of deprivation (p-value = 2.26e-5) as measured by the Health score (England) index of multiple deprivation (Supplementary file 4). Interestingly, increased eyeAgeAccel also corresponded with significantly increased performance in fluid intelligence scores (p-value = 5.34e-27).

As visual acuity has long been known to degrade with age (Gittings and Fozard, 1986), we examined the extent to which eyeAge explains the known correlation between chronological age and visual acuity. Although chronological age and eyeAge are highly correlated (Figure 3A), we observed a slightly higher correlation of eyeAge with visual acuity (⍴=0.221) compared to chronological age vs. visual acuity (⍴=0.218). Both measures of age appear relevant for visual acuity decline, as the influence of chronological age remained significant even after regressing out the influence of eyeAge on visual acuity (p-value = 1.6e-13, Supplementary file 5).

GWAS and experimental validation of ALK

Based on the patient-specific eyeAgeAccel effects and its independence from phenoAgeAccel, a GWAS was conducted to identify genetic factors associated with eyeAgeAccel. We subsetted the cohort to individuals of European ancestry, performed genotype quality control, and utilized a single eyeAgeAccel value per individual, resulting in a cohort of 45,444 individuals for GWAS analysis. GWAS was performed using BOLT-LMM (see Materials and methods) with chronological age, sex, genotyping array type, the top five principal components of genetic ancestry, and indicator variables for the six assessment centers used for the imaging as covariates. Full GWAS summary statistics are available in Supplementary file 6.

Genomic inflation was low (1.05; Figure 4—figure supplement 1). The stratified linkage disequilibrium (LD) score regression-based intercept was 1.02 (SEM = 0.01), indicating that polygenicity, rather than population structure, drove the test statistic inflation. The SNP-based heritability was 0.11 (SEM = 0.02), an appreciable fraction of the estimated broad-sense heritability of biological age (27–57% via twin and family studies). The GWAS identified 38 independent suggestive hits (R² ≤0.1, p≤1 × 10⁻⁶) at 28 independent loci, 12 of which reached genome-wide significance (p≤5 × 10⁻⁸) (Figure 4, Supplementary file 7).

Figure 4 with 2 supplements see all

Download asset Open asset

GWAS analyses and experimental validation.

(A) Manhattan plot representing significant genes associated with eyeAgeAcceleration. (B) p-Values for enriched pathways: Macular thickness, ADHD (attention deficit hyperactivity disorder), AMD (age-related macular degeneration), spherical equivalent, and refractive error. (C) Assessment of visual performance of transgenic and control flies with age. p-Value is relative to control (*=p < 0.05). p-Value for ALK RNAi vs. control is 0.009; p-value for UAS-ALK-DN vs. control is 0.006. Error bars show standard deviation between 3 biological replicates. n = 100 flies per replicate.

Many of the hits were associated with eye function and age-related disease (truncated list of candidate hits summarized in Supplementary file 8). The most significant locus spanned 650 kb and included three genes in a highly significant LD block: SH3YL1, ACP1, and ALKAL2 (Figure 4—figure supplement 2). The SH3YL1 gene has recently been implicated as a biomarker for nephropathy in type 2 diabetes (Choi et al., 2021), whereas ALKAL2 enables protein tyrosine kinase activity (Woodling et al., 2020). In other significant gene candidates, we identified variants in the genes OCA2, POC5, and GJA3, which have all been implicated in eye development and function. OCA2 specifically is known to be important for eye pigmentation (Kamaraj and Purohit, 2014), whereas POC5 is linked to AMD (Yan et al., 2018). GJA3 has been implicated in age-related cataract development (Tang et al., 2019). MEF2C has reported roles in numerous age-related conditions, including Alzheimer’s disease (Xue et al., 2021) and muscle wasting in cancer (Judge et al., 2020) and GRM is associated with age-related hearing loss (Liu et al., 2021b). Additional candidates are reported to be involved in cancer prognosis and progression, including TSPAN11 (Liu et al., 2021a), NKX6-1 (Su et al., 2021), and SLC16A1 (Zhang et al., 2021).

Gene enrichment analysis (Xie et al., 2021) identified significant associations (adjusted p<0.05) between our gene candidates and macular thickness and degeneration, as seen in previous human GWAS studies (Buniello et al., 2019) and cataract formation (Elsevier pathway collection; Cheadle et al., 2017) as well as non-eye related diseases such as bone mineralization, tumor suppression, and Amyloid Precursor Protein pathways (Biocarta; Nishimura, 2001). Gene Ontology (GO) term analysis of our gene candidates revealed significant enrichment (adjusted p<0.05) for protein tyrosine kinase activator activity, gap junction channel activity, and wide pore channel activity (Figure 4B).

Sum of single effects regression (Wang et al., 2020) was used to identify putative causal variants for each locus (Supplementary file 9). In the most significant locus (Figure 4—figure supplement 2), we identified the deletion variant rs56350804 as the single variant with a posterior inclusion probability (PIP) above 0.45 (rs56350804 PIP = 0.9998). While rs56350804 is intronic to SH3YL1, expression quantitative trait locus (eQTL) analysis by the Genotype-Tissue Expression consortium identified significant eQTL between rs56350804 and each of SH3YL1, ACP1, and ALKAL2 (GTEx Consortium 2020). In particular, the ALKAL2 gene had its expression modulated by rs56350804 in cervical spinal cord tissue (p=3.0 × 10^–16), and inhibition of the Drosophila homolog of ALKAL2, Alk, has been shown to extend lifespan (Woodling et al., 2020), making it a good candidate for exploring a potential role in visual function.

Previously, D. melanogaster has been used to study the impact of aging interventions on retinal health by using the phototaxis index, a fly’s ability to be attracted toward light (Hodge et al., 2022). We used D. melanogaster to observe visual decline via phototaxis with transgenic ALK inhibition. We crossed the pan-neuronal RU486-inducible Gal4 driver elav-Gal4-GS with UAS-Alk^RNAi flies or UAS-Alk^DN to determine the effects of neuron-specific Alk inhibition. Both transgenic interventions resulted in significantly increased visual performance with age, whereas background controls showed no change in performance with RU486 treatment (Figure 4C). These results support the implication from the GWAS that ALK influences the aging of the visual system.

Discussion

Retinal health has long been an important factor for visual aging, manifested as glaucoma, AMD, and other age-related retinal diseases, but until recently it was not known whether it could be indicative of overall health and aging. In this study, we applied deep learning models for predicting an individual’s age from retinal fundus images and showed that these predictions may be informative for tracking aging patterns longitudinally. While other cellular and blood-related molecular markers of aging have recently been identified, these are at times invasive and, although accurate, take a long time to develop (Horvath, 2013). Other aging clocks from blood (Horvath, 2013; Peters et al., 2015), saliva (Bocklandt et al., 2011), skin (Bocklandt et al., 2011; Fleischer et al., 2018), muscle (Mamoshina et al., 2018), and liver (Wang et al., 2017) showed an MAE deviating 4–8 years from the actual age. More dynamic markers such as proteins and metabolites can track aging in shorter time intervals but are still limited to 2–4 years (Ahadi et al., 2020; Wang et al., 2017; Chen et al., 2012). In contrast, using deep learning models on retina fundus images, we were able to predict changes in aging at a granularity of less than a year. These small time-scales, and relative low-cost of imaging, makes eyeAge promising for longitudinal studies.

Correlation and hazard ratio analyses from our study suggest that eyeAge and phenotypic age are conditionally independent given chronological age. Therefore, eyeAge is a potential biomarker that reflects a layer of biological aging not included in blood markers. This is supported by our GWAS findings; different genes were associated with eyeAgeAccel compared to phenoAgeAccel (Kuo et al., 2021). However, there are limitations with this approach. Similar to other aging clocks (such as DNA-methylome), eyeAge underperforms phenotypic age in mortality prediction. This is likely because the biomarkers used to calculate phenotypic age were explicitly selected based on their ability to predict mortality. New algorithms that incorporate blood markers and retinal clocks have the potential to be better predictors of morbidity and mortality. Additionally, it remains to be seen whether eyeAgeAccel would reflect interventions such as behavioral changes or medication.

Our GWAS identified candidate genes associated with several eye- and age-related functions, such as POC5 (Yan et al., 2018) and GJA3 (Tang et al., 2019). Additional significant candidates had previously identified functions that are not restricted to the eye but are still related to age, e.g. MEF2C being associated with Alzheimer’s disease (Xue et al., 2021) and multiple candidates (TSPAN11, NKX6-1, SLC16A1, RAET1G, SNTG1, ARRDC3, RASSF3, DIRC3, and GCNT3) associated with cancer (Supplementary file 8). These suggest that eyeAge may identify general signatures of aging rather than purely eye-related traits. Pathway analyses similarly were split between eye-related pathways and others that were not eye-specific. While we suspect many of the eye-related pathways to have an aging component, some pathways may be enriched artifactually. For example, though melanin biosynthesis has been associated with protection from photodamage (Hodge et al., 2022), the predicted quality of fundus images has also been shown to be influenced by eye color (Guenther et al., 2020). Notably, an independent group separately identified our top GWAS candidate locus as the most significant locus (Goallec et al., 2021). This combined with previous studies showing ALK to be important for lifespan extension in flies (Woodling et al., 2020) and our own experimental validation confirming improved ocular health in a fly homolog, Alk, is compelling evidence of a true biological signal in the GWAS.

Taken together, our work reinforces the utility of fundus imaging for evaluating overall health and opens up new opportunities for using it to predict longevity. eyeAge has substantial applications in aging and aging-related diseases, from biomarker application to tracking therapeutics. In particular, the retinal aging clock because of its ease of use, low cost, and non-invasive sample collection, has the unique potential to additionally assess lifestyle and environmental factors implicated in aging. Retinal aging clocks can be immensely valuable to future clinical trials of rejuvenation/anti-aging therapies and for personalized medicine to measure improvements in aging over short periods, not only improving actionability but also enabling rapid iteration.

Materials and methods

Key resources table

Reagent type (species) or resource	Designation	Source or reference	Identifiers	Additional information
Strain, w^Dah background (Drosophila melanogaster, females)	w^Dah control strain	Laboratory of Linda Partridge, Woodling et al., 2020		Maintained in Kapahi Lab
Strain, w^Dah background (Drosophila melanogaster, females)	UAS-ALK^RNAi RNAi for ALK	Laboratory of Linda Partridge, Woodling et al., 2020	VDRC GD 11446	Maintained in Kapahi Lab
Strain, w^Dah background (Drosophila melanogaster, females)	UAS-ALK^DN dominant negative ALK overexpression	Laboratory of Linda Partridge, Woodling et al., 2020		Maintained in Kapahi Lab
Strain, w^Dah background (Drosophila melanogaster, females)	elav-GS Ru486 inducible Gal4 driver	Bloomington Drosophila Stock Center, Woodling et al., 2020	BDSC 43642	Maintained in Kapahi Lab
Chemical compound, drug	RU486 (mifepristone)	United States Biological, Osterwalder et al., 2001	282888	For inducting fly GeneSwitch expression system; 200 µM final concentration in food

EyeAge model development

Request a detailed protocol

Model development was done on the EyePACS train dataset (Table 1). A deep learning model with an Inception-v3 architecture (Deng et al., 2009; Szegedy et al., 2015) was trained to take a color fundus photo as input and predict the chronological age (referred to as chronologicalAge below) using L1 loss. Age values were normalized to have zero mean and unit variance before training (and during inference this normalization is reversed to get back to year units). Model training was stopped after 363,200 steps by looking at performance on the EyePACS tune dataset. The hyperparameters of the model were as follows: the initial learning rate was 0.0001, which was warmed up to 0.001 over 40,751 steps; after the warm up phase, the learning rate was decayed by a factor of 0.99 every 13,584 steps; dropout was applied to the prelogits at a rate of 0.2; a weight decay of 4e-5 was used. The model backbone was pre-trained using the ImageNet dataset (Deng et al., 2009). As some of the color fundus images in the UK Biobank dataset were of very low quality, we also trained a separate deep learning model to predict image quality, similar to what was reported in our prior work (Mitani et al., 2020; Varadarajan et al., 2018).

EyeAge model evaluation

Request a detailed protocol

The model described above was applied to images to predict chronological age. The image quality model described above was used to discard low quality images – reducing the initial 85,645 patient (174,049 image) dataset to 66,533 patients (120,362 images). Finally, we restricted the data to the first assessment visit to UK Biobank. This was done to reduce bias associated with image quality differences, as we observed quality differences between images captured in the later follow-up visits. Since these follow-up visits happened several years after the initial assessment, the time to event or censorship is much smaller, and a model could exploit this association. For participants that had images of both eyes passing the quality filter, we averaged the predictions across the two eyes. After these processing steps, we ended up with 55,267 data points total, one per remaining participant. Next, using the predicted eyeAge and the chronologicalAge of the participant at the time of imaging, an ‘eyeAgeAcceleration’ score was calculated for each participant as the residuals of the ordinary least squares regression model ‘chronologicalAge ~eyeAge’ (Liu et al., 2018). In order to compare with another well-known biological marker of age, phenoAge (Liu et al., 2018) was also computed using the values of blood markers available for the participants. PhenoAgeAcceleration was then computed in an analogous manner to eyeAgeAcceleration.

Method on selection of random set

Request a detailed protocol

Figure 2 required identification of matched, random individuals to assess the potential person-specific component of eyeAge predictions. For Figure 2—figure supplement 3, we created matched sets of visit pairs for each patient’s first visit by identifying a randomly matching patient visit that was 0–2 years after a patient’s first visit. To eliminate artifacts due to sampling differences between first and second visits, once we identified a patient’s first visit to match, we constrained its set of potential randomly matched patient visits to only be from second visits. For the longitudinal analysis in 2B (right), individuals were split both by age and by time between visits (using 2 month buckets) and, again, randomly matched. For Figure 2D, the individuals were split evenly in 2-year buckets. Individuals within the same bucket had their left and right predictions compared to one another.

Regression analyses in UK Biobank

Request a detailed protocol

Cox proportional hazards regression was performed using the lifelines package, https://github.com/CamDavidsonPilon/lifelines. Since retinal imaging was performed at the initial visit, individuals with events with an unknown date or date prior to the initial visit were excluded. All UK Biobank algorithmically defined outcomes with at least 4000 events were analyzed: asthma (field 42014), COPD (field 42016), dementia (field 42018), myocardial infarction (field 42000), all-cause Parkinsonism (field 42030), and stroke (field 42006). We note that because eyeAgeAccel is defined as eyeAge - alpha * age - beta for constants alpha and beta identified through regression of age on eyeAge, hazard ratios for eyeAge are identical to those in which eyeAgeAccel is used in the model instead.

Linear regression was performed on morbidity-related measurements taken at the same visit during which retinal imaging occurred, and was implemented using the statsmodels package with the model INT(outcome)~INT(age)+sex + INT(eyeAgeAccel), where INT(...) represents the rank-based inverse normal transformation. Individuals for which any of the outcome, age, or eyeAgeAccel variables were in the top 1% of outlier values were excluded. Measurements analyzed were: Overall health rating (field 2178), Long-standing illness (field 2188), Systolic blood pressure (field 4080), Diastolic blood pressure (field 4079), Pulse wave arterial stiffness index (field 21021), Health score (England) (field 26413), Fluid intelligence score (field 20016).

GWAS

Request a detailed protocol

The eyeAgeAccel value defined above was used as the target for GWAS analysis. GWAS analysis was performed on the fundus-based phenotype as described previously (Alipanahi et al., 2021). Briefly, samples were restricted to individuals of European ancestry to avoid confounding effects due to population structure. European genetic ancestry was defined by computing the medioid of the 15-dimensional space of the top genetic principal components in individuals who self-identified as ‘British’ ancestry and defining all individuals within a distance of 40 from the medioid as ‘European’ (corresponding to the 99th percentile of distances of all individuals who self-identified as British or Irish). Samples were further restricted to those who also passed sample quality control measures computed by UK Biobank, that is those not flagged as outliers for heterozygosity or missingness, possessing a putative sex chromosome aneuploidy, or whose self-reported and genetically inferred sex were discordant.

BOLT-LMM v2.3.4 was used to examine associations between genotype and eyeAgeAcceleration in European individuals in the UK Biobank (n=45,444). All genotyped variants with minor allele frequency >0.001 were used to perform model fitting and heritability estimation. GWAS was performed in genotyped variants and imputed variants on autosomal chromosomes, with imputed variants filtered to exclude those with minor allele frequency (MAF) <0.001, imputation INFO score <0.8, or Hardy-Weinberg equilibrium (HWE) P<1 × 10^–10 in Europeans. In total, 13,297,147 variants passed all quality control measures. Covariates included in the association study were chronological age, sex, genotyping array type, the top five principal components of genetic ancestry, and indicator variables for the six assessment centers used for the imaging.

Genome-wide suggestive (p≤1 × 10⁻⁶) lead SNPs, independent at R² ≤0.1, were identified using the –clump command in PLINK version v1.90b4. The LD reference panel contained 10,000 unrelated UK Biobank subjects of European ancestry (as defined above). To identify distinct non-overlapping loci of association, all variants with R² ≥0.1 with a lead SNP were grouped into a ‘cluster’ with that lead SNP, and subsequently clusters within 250 kilobases of each other were merged, with the lowest p-value lead SNP retained as the locus representative. Putative causal variants were identified using susieR version 0.9.0. At each locus containing at least 10 variants in LD, the susieR::susie_suff_stat function was used to estimate posterior inclusion probabilities for each variant in the locus, using the same LD reference panel as was used to generate loci and with a maximum of L=10 causal variants per locus and 200 iterations of coordinate ascent.

Validation of Alk in fly

Fly husbandry and phenotyping

Request a detailed protocol

For fly crosses, 15 virgin females were crossed with 3 males in bottles containing 1.55% live yeast, cornmeal, sugar, and agar (Wilson et al., 2020). Crosses were dumped 5 days following crossing, and female progeny were sorted into 4 replicate vials of 25 flies each, with food containing 200 μm RU486 to induce activation of the Gal-UAS system (Nicholson et al., 2008). Flies were maintained in 65% relative humidity at 25 °C in a 24 hr light/dark cycle throughout life. Two weeks post-induction, phototaxis was tested as previously described Hodge et al., 2022 by placing flies in a clear, empty 30 cm-long vial horizontally in a dark room. Light was shined on one end and the number of flies in the last 10 cm closest to the light source after 1 min was scored for responsiveness to light signals. This was tested across each of the four vials per group in three biological replicates (total 100 flies per replicate). Strains used were 3xelav-GS (provided from the lab of Geetanjali Chawla) Parkhitko et al., 2020 for RU486-dependent pan-neuronal Gal4, w^Dah control strain, UAS-Alk^RNAi, and UAS-Alk^DN (provided from the lab of Linda Partridge) (Woodling et al., 2020).

Pathway analysis

Request a detailed protocol

All significant (p<1.0 × 10^–6) GWAS candidates were used to assess pathway enrichment via Enrichr (Xie et al., 2021).

Statistical analysis

Request a detailed protocol

For Drosophila phototaxis results, significance (p<0.05) was assessed using unpaired t-test. For Figure 4C, error bars represent SD across at least three biological replicates. Significant differences between experimental groups and controls are indicated by *. *, p<0.05. Statistical analyses were calculated with GraphPad Prism 4.

Data and code availability

Request a detailed protocol

A subset of EyePACS data is freely available online (https://www.kaggle.com/competitions/diabetic-retinopathy-detection/data). To enquire about access to the full EyePACS dataset, researchers should contact Jorge Cuadros (jcuadros@eyepacs.com). The UK Biobank data are available for approved projects (application process detailed at https://www.ukbiobank.ac.uk/enable-your-research/apply-for-access) through the UK Biobank Access Management System (https://www.ukbiobank.ac.uk). We have deposited the derived data fields and model predictions following UK Biobank policy, which will be available through the UK Biobank Access Management System. Full GWAS summary statistics are available in the Supplementary File. To develop the eyeAge model we used the TensorFlow deep learning framework, available at https://www.tensorflow.org. Code and detailed instructions for both model training and prediction of chronological age from fundus images is open-source and freely available as a minor modification (https://gist.github.com/cmclean/a7e01b916f07955b2693112dcd3edb60), (Ahadi, 2023 copy archived at swh:1:rev:ba002c0a6edddd13814ecc9e07ec14249b2375f4) of our previously published repository for fundus model training (https://zenodo.org/record/7154413) (Cosentino et al., 2021).

Data availability

A subset of EyePACS data is freely available online (https://www.kaggle.com/competitions/diabetic-retinopathy-detection/data). To enquire about access to the full EyePACS dataset, researchers should contact Jorge Cuadros (jcuadros@eyepacs.com). Proposals and agreements are assessed internally at EyePACS and may be subject to ethics approvals. The UKB data are available for approved projects (application process detailed at https://www.ukbiobank.ac.uk/enable-your-research/apply-for-access) through the UK Biobank Access Management System (https://www.ukbiobank.ac.uk) . We have deposited the derived data fields and model predictions following UKB policy, which will be available through the UK Biobank Access Management System. Full GWAS summary statistics are available in the Supplementary File. To develop the eyeAge model we used the TensorFlow deep learning framework, available at https://www.tensorflow.org. Code and detailed instructions for both model training and prediction of chronological age from fundus images is open-source and freely available as a minor modification (https://gist.github.com/cmclean/a7e01b916f07955b2693112dcd3edb60, (copy archived at swh:1:rev:ba002c0a6edddd13814ecc9e07ec14249b2375f4)) of our previously published repository for fundus model training (https://zenodo.org/record/7154413).

The following previously published data sets were used

(2021) Zenodo
Code for training fundus models.

https://doi.org/10.5281/zenodo.7154413

References

(2020) Personal aging markers and ageotypes revealed by deep longitudinal profiling
Nature Medicine 26:83–90.

https://doi.org/10.1038/s41591-019-0719-5
- PubMed
- Google Scholar
Software
1. Ahadi S
(2023) Cmclean/eye_age.patch, version swh:1:rev:ba002c0a6edddd13814ecc9e07ec14249b2375f4
Software Heritage.

https://archive.softwareheritage.org/swh:1:dir:64dfbc1c9ab27bbd009f57e14386da3d456b17d2;origin=https://gist.github.com/cmclean/a7e01b916f07955b2693112dcd3edb60;visit=swh:1:snp:0f20edfe3c8236f9baff5a1150078dc1aa2d59ea;anchor=swh:1:rev:ba002c0a6edddd13814ecc9e07ec14249b2375f4
1. Alipanahi B
2. Hormozdiari F
3. Behsaz B
4. Cosentino J
5. McCaw ZR
6. Schorsch E
7. Sculley D
8. Dorfman EH
9. Foster PJ
10. Peng LH
11. Phene S
12. Hammel N
13. Carroll A
14. Khawaja AP
15. McLean CY
(2021) Large-Scale machine-learning-based phenotyping significantly improves genomic discovery for optic nerve head morphology
American Journal of Human Genetics 108:1217–1230.

https://doi.org/10.1016/j.ajhg.2021.05.004
- PubMed
- Google Scholar
(2009) The retina in Parkinson’s disease
Brain 132:1128–1145.

https://doi.org/10.1093/brain/awp068
- PubMed
- Google Scholar
1. Bocklandt S
2. Lin W
3. Sehl ME
4. Sánchez FJ
5. Sinsheimer JS
6. Horvath S
7. Vilain E
(2011) Epigenetic predictor of age
PLOS ONE 6:e14821.

https://doi.org/10.1371/journal.pone.0014821
- PubMed
- Google Scholar
1. Buniello A
2. MacArthur JAL
3. Cerezo M
4. Harris LW
5. Hayhurst J
6. Malangone C
7. McMahon A
8. Morales J
9. Mountjoy E
10. Sollis E
11. Suveges D
12. Vrousgou O
13. Whetzel PL
14. Amode R
15. Guillen JA
16. Riat HS
17. Trevanion SJ
18. Hall P
19. Junkins H
20. Flicek P
21. Burdett T
22. Hindorff LA
23. Cunningham F
24. Parkinson H
(2019) The NHGRI-EBI GWAS catalog of published genome-wide association studies, targeted arrays and summary statistics 2019
Nucleic Acids Research 47:D1005–D1012.

https://doi.org/10.1093/nar/gky1120
- PubMed
- Google Scholar
1. Cen LP
2. Ji J
3. Lin JW
4. Ju ST
5. Lin HJ
6. Li TP
7. Wang Y
8. Yang JF
9. Liu YF
10. Tan S
11. Tan L
12. Li D
13. Wang Y
14. Zheng D
15. Xiong Y
16. Wu H
17. Jiang J
18. Wu Z
19. Huang D
20. Shi T
21. Chen B
22. Yang J
23. Zhang X
24. Luo L
25. Huang C
26. Zhang G
27. Huang Y
28. Ng TK
29. Chen H
30. Chen W
31. Pang CP
32. Zhang M
(2021) Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks
Nature Communications 12:4828.

https://doi.org/10.1038/s41467-021-25138-w
- PubMed
- Google Scholar
(2017) Advanced literature analysis in a big data world
Annals of the New York Academy of Sciences 1387:25–33.

https://doi.org/10.1111/nyas.13270
- PubMed
- Google Scholar
1. Chen R
2. Mias GI
3. Li-Pook-Than J
4. Jiang L
5. Lam HYK
6. Chen R
7. Miriami E
8. Karczewski KJ
9. Hariharan M
10. Dewey FE
11. Cheng Y
12. Clark MJ
13. Im H
14. Habegger L
15. Balasubramanian S
16. O’Huallachain M
17. Dudley JT
18. Hillenmeyer S
19. Haraksingh R
20. Sharon D
21. Euskirchen G
22. Lacroute P
23. Bettinger K
24. Boyle AP
25. Kasowski M
26. Grubert F
27. Seki S
28. Garcia M
29. Whirl-Carrillo M
30. Gallardo M
31. Blasco MA
32. Greenberg PL
33. Snyder P
34. Klein TE
35. Altman RB
36. Butte AJ
37. Ashley EA
38. Gerstein M
39. Nadeau KC
40. Tang H
41. Snyder M
(2012) Personal omics profiling reveals dynamic molecular and medical phenotypes
Cell 148:1293–1307.

https://doi.org/10.1016/j.cell.2012.02.009
- PubMed
- Google Scholar
1. Choi GS
2. Min HS
3. Cha JJ
4. Lee JE
5. Ghee JY
6. Yoo JA
7. Kim KT
8. Kang YS
9. Han SY
10. Bae YS
11. Lee SR
12. Yoo JY
13. Moon SH
14. Lee SJ
15. Cha DR
(2021) SH3YL1 protein as a novel biomarker for diabetic nephropathy in type 2 diabetes mellitus
Nutrition, Metabolism, and Cardiovascular Diseases 31:498–505.

https://doi.org/10.1016/j.numecd.2020.09.024
- PubMed
- Google Scholar
Software
(2021) Code for training fundus models
Zenodo.

https://doi.org/10.5281/zenodo.7154713
1. Cox DR
(1972) Regression models and life-tables
Journal of the Royal Statistical Society 34:187–202.

https://doi.org/10.1111/j.2517-6161.1972.tb00899.x
- Google Scholar
1. Cunningham ET
2. Margolis TP
(1998) Ocular manifestations of HIV infection
The New England Journal of Medicine 339:236–244.

https://doi.org/10.1056/NEJM199807233390406
- PubMed
- Google Scholar
Conference
1. Deng J
2. Dong W
3. Socher R
4. Li L-J
(2009) ImageNet: A large-scale hierarchical image database
2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

https://doi.org/10.1109/CVPR.2009.5206848
- Google Scholar
1. Fleischer JG
2. Schulte R
3. Tsai HH
4. Tyagi S
5. Ibarra A
6. Shokhirev MN
7. Huang L
8. Hetzer MW
9. Navlakha S
(2018) Predicting age from the transcriptome of human dermal fibroblasts
Genome Biology 19:221.

https://doi.org/10.1186/s13059-018-1599-6
- PubMed
- Google Scholar
1. Frost S
2. Kanagasingam Y
3. Sohrabi H
4. Vignarajan J
5. Bourgeat P
6. Salvado O
7. Villemagne V
8. Rowe CC
9. Macaulay SL
10. Szoeke C
11. Ellis KA
12. Ames D
13. Masters CL
14. Rainey-Smith S
15. Martins RN
16. AIBL Research Group
(2013) Retinal vascular biomarkers for early detection and monitoring of alzheimer’s disease
Translational Psychiatry 3:e233.

https://doi.org/10.1038/tp.2012.150
- PubMed
- Google Scholar
(2021) DeepMAge: A methylation aging clock developed with deep learning
Aging and Disease 12:1252–1262.

https://doi.org/10.14336/AD.2020.1202
- PubMed
- Google Scholar
1. Gittings NS
2. Fozard JL
(1986) Age related changes in visual acuity
Experimental Gerontology 21:423–433.

https://doi.org/10.1016/0531-5565(86)90047-1
- PubMed
- Google Scholar
Preprint
1. Goallec AL
2. Diai S
3. Collin S
4. Vincent T
5. Patel CJ
(2021) Identifying the Genetic and Non-Genetic Factors Associated with Accelerated Eye Aging by Using Deep Learning to Predict Age from Fundus and Optical Coherence Tomography Images
medRxiv.

https://doi.org/10.1101/2021.06.24.21259471
- Google Scholar
1. Guenther F
2. Brandl C
3. Winkler TW
4. Wanner V
5. Stark K
6. Kuechenhoff H
7. Heid IM
(2020) Chances and challenges of machine learning-based disease classification in genetic association studies illustrated on age-related macular degeneration
Genetic Epidemiology 44:759–777.

https://doi.org/10.1002/gepi.22336
- PubMed
- Google Scholar
1. Gulshan V
2. Peng L
3. Coram M
4. Stumpe MC
5. Wu D
6. Narayanaswamy A
7. Venugopalan S
8. Widner K
9. Madams T
10. Cuadros J
11. Kim R
12. Raman R
13. Nelson PC
14. Mega JL
15. Webster DR
(2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus Photographs
JAMA 316:2402–2410.

https://doi.org/10.1001/jama.2016.17216
- PubMed
- Google Scholar
1. Hodge BA
2. Meyerhof GT
3. Katewa SD
4. Lian T
5. Lau C
6. Bar S
7. Leung NY
8. Li M
9. Li-Kroeger D
10. Melov S
11. Schilling B
12. Montell C
13. Kapahi P
(2022) Dietary restriction and the transcription factor clock delay eye aging to extend lifespan in Drosophila melanogaster
Nature Communications 13:3156.

https://doi.org/10.1038/s41467-022-30975-4
- PubMed
- Google Scholar
1. Horvath S
(2013) Dna methylation age of human tissues and cell types
Genome Biology 14:R115.

https://doi.org/10.1186/gb-2013-14-10-r115
- PubMed
- Google Scholar
1. Horvath S
2. Raj K
(2018) Dna methylation-based biomarkers and the epigenetic clock theory of ageing
Nature Reviews. Genetics 19:371–384.

https://doi.org/10.1038/s41576-018-0004-3
- PubMed
- Google Scholar
1. Judge SM
2. Deyhle MR
3. Neyroud D
4. Nosacka RL
5. D’Lugos AC
6. Cameron ME
7. Vohra RS
8. Smuder AJ
9. Roberts BM
10. Callaway CS
11. Underwood PW
12. Chrzanowski SM
13. Batra A
14. Murphy ME
15. Heaven JD
16. Walter GA
17. Trevino JG
18. Judge AR
(2020) MEF2c-dependent downregulation of myocilin mediates cancer-induced muscle wasting and associates with cachexia in patients with cancer
Cancer Research 80:1861–1874.

https://doi.org/10.1158/0008-5472.CAN-19-1558
- PubMed
- Google Scholar
1. Kamaraj B
2. Purohit R
(2014) Mutational analysis of oculocutaneous albinism: a compact review
BioMed Research International 2014:905472.

https://doi.org/10.1155/2014/905472
- PubMed
- Google Scholar
(2002) Choroidal metastasis in disseminated lung cancer: frequency and risk factors
American Journal of Ophthalmology 134:445–447.

https://doi.org/10.1016/s0002-9394(02)01580-5
- PubMed
- Google Scholar
1. Kuo CL
2. Pilling LC
3. Liu Z
4. Atkins JL
5. Levine ME
(2021) Genetic associations for two biological age measures point to distinct aging phenotypes
Aging Cell 20:e13376.

https://doi.org/10.1111/acel.13376
- PubMed
- Google Scholar
1. Liu Z
2. Kuo PL
3. Horvath S
4. Crimmins E
5. Ferrucci L
6. Levine M
(2018) A new aging measure captures morbidity and mortality risk across diverse subpopulations from NHANES IV: A cohort study
PLOS Medicine 15:e1002718.

https://doi.org/10.1371/journal.pmed.1002718
- PubMed
- Google Scholar
1. Liu J
2. Jiang C
3. Xu C
4. Wang D
5. Shen Y
6. Liu Y
7. Gu L
(2021a) Identification and development of a novel invasion-related gene signature for prognosis prediction in colon adenocarcinoma
Cancer Cell International 21:101.

https://doi.org/10.1186/s12935-021-01795-1
- PubMed
- Google Scholar
(2021b) A combined genome-wide association and molecular study of age-related hearing loss in H. sapiens
BMC Medicine 19:302.

https://doi.org/10.1186/s12916-021-02169-0
- PubMed
- Google Scholar
(2013) The hallmarks of aging
Cell 153:1194–1217.

https://doi.org/10.1016/j.cell.2013.05.039
- PubMed
- Google Scholar
1. Luu J
2. Palczewski K
(2018) Human aging and disease: lessons from age-related macular degeneration
PNAS 115:2866–2872.

https://doi.org/10.1073/pnas.1721033115
- PubMed
- Google Scholar
(2018) Machine learning on human muscle transcriptomic data for biomarker discovery and tissue-specific drug target identification
Frontiers in Genetics 9:242.

https://doi.org/10.3389/fgene.2018.00242
- PubMed
- Google Scholar
1. McEwen LM
2. O’Donnell KJ
3. McGill MG
4. Edgar RD
5. Jones MJ
6. MacIsaac JL
7. Lin DTS
8. Ramadori K
9. Morin A
10. Gladish N
11. Garg E
12. Unternaehrer E
13. Pokhvisneva I
14. Karnani N
15. Kee MZL
16. Klengel T
17. Adler NE
18. Barr RG
19. Letourneau N
20. Giesbrecht GF
21. Reynolds JN
22. Czamara D
23. Armstrong JM
24. Essex MJ
25. de Weerth C
26. Beijers R
27. Tollenaar MS
28. Bradley B
29. Jovanovic T
30. Ressler KJ
31. Steiner M
32. Entringer S
33. Wadhwa PD
34. Buss C
35. Bush NR
36. Binder EB
37. Boyce WT
38. Meaney MJ
39. Horvath S
40. Kobor MS
(2020) The pedbe clock accurately estimates DNA methylation age in pediatric buccal cells
PNAS 117:23329–23335.

https://doi.org/10.1073/pnas.1820843116
- PubMed
- Google Scholar
1. Mitani A
2. Huang A
3. Venugopalan S
4. Corrado GS
5. Peng L
6. Webster DR
7. Hammel N
8. Liu Y
9. Varadarajan AV
(2020) Author correction: detection of anaemia from retinal fundus images via deep learning
Nature Biomedical Engineering 4:242.

https://doi.org/10.1038/s41551-020-0530-0
- PubMed
- Google Scholar
1. Namperumalsamy P
2. Kim R
3. Vignesh TP
4. Nithya N
5. Royes J
6. Gijo T
7. Thulasiraj RD
8. Vijayakumar V
(2009) Prevalence and risk factors for diabetic retinopathy: a population-based assessment from theni district, South India
Postgraduate Medical Journal 85:643–648.

https://doi.org/10.1136/bjo.2008.147934
- PubMed
- Google Scholar
(2008) Spatial and temporal control of gene expression in Drosophila using the inducible GeneSwitch GAL4 system. I. screen for larval nervous system drivers
Genetics 178:215–234.

https://doi.org/10.1534/genetics.107.081968
- PubMed
- Google Scholar
1. Nishimura D
(2001) BioCarta
Biotech Software & Internet Report 2:117–120.

https://doi.org/10.1089/152791601750294344
- Google Scholar
(2001) A conditional tissue-specific transgene expression system using inducible GAL4
PNAS 98:12596–12601.

https://doi.org/10.1073/pnas.221303298
- PubMed
- Google Scholar
1. Parkhitko AA
2. Ramesh D
3. Wang L
4. Leshchiner D
5. Filine E
6. Binari R
7. Olsen AL
8. Asara JM
9. Cracan V
10. Rabinowitz JD
11. Brockmann A
12. Perrimon N
(2020) Downregulation of the tyrosine degradation pathway extends Drosophila lifespan
eLife 9:e58053.

https://doi.org/10.7554/eLife.58053
- PubMed
- Google Scholar
1. Peters MJ
2. Joehanes R
3. Pilling LC
4. Schurmann C
5. Conneely KN
6. Powell J
7. Reinmaa E
8. Sutphin GL
9. Zhernakova A
10. Schramm K
11. Wilson YA
12. Kobes S
13. Tukiainen T
14. Ramos YF
15. Göring HHH
16. Fornage M
17. Liu Y
18. Gharib SA
19. Stranger BE
20. De Jager PL
21. Aviv A
22. Levy D
23. Murabito JM
24. Munson PJ
25. Huan T
26. Hofman A
27. Uitterlinden AG
28. Rivadeneira F
29. van Rooij J
30. Stolk L
31. Broer L
32. Verbiest M
33. Jhamai M
34. Arp P
35. Metspalu A
36. Tserel L
37. Milani L
38. Samani NJ
39. Peterson P
40. Kasela S
41. Codd V
42. Peters A
43. Ward-Caviness CK
44. Herder C
45. Waldenberger M
46. Roden M
47. Singmann P
48. Zeilinger S
49. Illig T
50. Homuth G
51. Grabe HJ
52. Völzke H
53. Steil L
54. Kocher T
55. Murray A
56. Melzer D
57. Yaghootkar H
58. Bandinelli S
59. Moses EK
60. Kent JW
61. Curran JE
62. Johnson MP
63. Williams-Blangero S
64. Westra HJ
65. McRae AF
66. Smith JA
67. Kardia SLR
68. Hovatta I
69. Perola M
70. Ripatti S
71. Salomaa V
72. Henders AK
73. Martin NG
74. Smith AK
75. Mehta D
76. Binder EB
77. Nylocks KM
78. Kennedy EM
79. Klengel T
80. Ding J
81. Suchy-Dicey AM
82. Enquobahrie DA
83. Brody J
84. Rotter JI
85. Chen YDI
86. Houwing-Duistermaat J
87. Kloppenburg M
88. Slagboom PE
89. Helmer Q
90. den Hollander W
91. Bean S
92. Raj T
93. Bakhshi N
94. Wang QP
95. Oyston LJ
96. Psaty BM
97. Tracy RP
98. Montgomery GW
99. Turner ST
100. Blangero J
101. Meulenbelt I
102. Ressler KJ
103. Yang J
104. Franke L
105. Kettunen J
106. Visscher PM
107. Neely GG
108. Korstanje R
109. Hanson RL
110. Prokisch H
111. Ferrucci L
112. Esko T
113. Teumer A
114. van Meurs JBJ
115. Johnson AD
116. NABEC/UKBEC Consortium
(2015) The transcriptional landscape of age in human peripheral blood
Nature Communications 6:8570.

https://doi.org/10.1038/ncomms9570
- PubMed
- Google Scholar
1. Poplin R
2. Varadarajan AV
3. Blumer K
4. Liu Y
5. McConnell MV
6. Corrado GS
7. Peng L
8. Webster DR
(2018) Prediction of cardiovascular risk factors from retinal fundus Photographs via deep learning
Nature Biomedical Engineering 2:158–164.

https://doi.org/10.1038/s41551-018-0195-0
- PubMed
- Google Scholar
1. Sabanayagam C
2. Xu D
3. Ting DSW
4. Nusinovici S
5. Banu R
6. Hamzah H
7. Lim C
8. Tham Y-C
9. Cheung CY
10. Tai ES
11. Wang YX
12. Jonas JB
13. Cheng C-Y
14. Lee ML
15. Hsu W
16. Wong TY
(2020) A deep learning algorithm to detect chronic kidney disease from retinal Photographs in community-based populations
The Lancet Digital Health 2:e295–e302.

https://doi.org/10.1016/S2589-7500(20)30063-7
- PubMed
- Google Scholar
1. Su PH
2. Huang RL
3. Lai HC
4. Chen LY
5. Weng YC
6. Wang CC
7. Wu CC
(2021) NKX6-1 mediates cancer stem-like properties and regulates sonic hedgehog signaling in leiomyosarcoma
Journal of Biomedical Science 28:32.

https://doi.org/10.1186/s12929-021-00726-6
- PubMed
- Google Scholar
1. Sun C
2. Wang JJ
3. Mackey DA
4. Wong TY
(2009) Retinal vascular caliber: systemic, environmental, and genetic associations
Survey of Ophthalmology 54:74–95.

https://doi.org/10.1016/j.survophthal.2008.10.003
- PubMed
- Google Scholar
Conference
1. Szegedy C
2. Vanhoucke V
3. Ioffe S
4. Shlens J
5. Wojna Z
(2015) Rethinking the Inception Architecture for Computer Vision
2016 IEEE Conference on Computer Vision and Pattern Recognition.

https://doi.org/10.1109/CVPR.2016.308
- Google Scholar
1. Tang XJ
2. Shentu XC
3. Tang YL
4. Ping XY
5. Yu XN
(2019) The impact of snps on susceptibility to age-related cataract
International Journal of Ophthalmology 12:1008–1011.

https://doi.org/10.18240/ijo.2019.06.21
- Google Scholar
1. Varadarajan AV
2. Poplin R
3. Blumer K
4. Angermueller C
5. Ledsam J
6. Chopra R
7. Keane PA
8. Corrado GS
9. Peng L
10. Webster DR
(2018) Deep learning for predicting refractive error from retinal fundus images
Investigative Ophthalmology & Visual Science 59:2861–2868.

https://doi.org/10.1167/iovs.18-23887
- PubMed
- Google Scholar
1. Wang T
2. Tsui B
3. Kreisberg JF
4. Robertson NA
5. Gross AM
6. Yu MK
7. Carter H
8. Brown-Borg HM
9. Adams PD
10. Ideker T
(2017) Epigenetic aging signatures in mice livers are slowed by dwarfism, calorie restriction and rapamycin treatment
Genome Biology 18:57.

https://doi.org/10.1186/s13059-017-1186-2
- PubMed
- Google Scholar
(2020) A simple new approach to variable selection in regression, with application to genetic fine mapping
Journal of the Royal Statistical Society Series B 82:1273–1300.

https://doi.org/10.1111/rssb.12388
- Google Scholar
1. Wilson KA
2. Beck JN
3. Nelson CS
4. Hilsabeck TA
5. Promislow D
6. Brem RB
7. Kapahi P
(2020) Gwas for lifespan and decline in climbing ability in flies upon dietary restriction reveal decima as a mediator of insulin-like peptide production
Current Biology 30:2749–2760.

https://doi.org/10.1016/j.cub.2020.05.020
- PubMed
- Google Scholar
1. Wong TY
2. McIntosh R
(2005) Systemic associations of retinal microvascular signs: a review of recent population-based studies
Ophthalmic & Physiological Optics 25:195–204.

https://doi.org/10.1111/j.1475-1313.2005.00288.x
- PubMed
- Google Scholar
1. Woodling NS
2. Aleyakpo B
3. Dyson MC
4. Minkley LJ
5. Rajasingam A
6. Dobson AJ
7. Leung KHC
8. Pomposova S
9. Fuentealba M
10. Alic N
11. Partridge L
(2020) The neuronal receptor tyrosine kinase ALK is a target for longevity
Aging Cell 19:e13137.

https://doi.org/10.1111/acel.13137
- PubMed
- Google Scholar
(2021) Gene set knowledge discovery with enrichr
Current Protocols 1:e90.

https://doi.org/10.1002/cpz1.90
- PubMed
- Google Scholar
1. Xue F
2. Tian J
3. Yu C
4. Du H
5. Guo L
(2021) Type I interferon response-related microglial MEF2C deregulation at the onset of alzheimer’s pathology in 5×FAD mice
Neurobiology of Disease 152:105272.

https://doi.org/10.1016/j.nbd.2021.105272
- PubMed
- Google Scholar
1. Yan Q
2. Ding Y
3. Liu Y
4. Sun T
5. Fritsche LG
6. Clemons T
7. Ratnapriya R
8. Klein ML
9. Cook RJ
10. Liu Y
11. Fan R
12. Wei L
13. Abecasis GR
14. Swaroop A
15. Chew EY
16. AREDS2 Research Group
17. Weeks DE
18. Chen W
(2018) Genome-Wide analysis of disease progression in age-related macular degeneration
Human Molecular Genetics 27:929–940.

https://doi.org/10.1093/hmg/ddy002
- PubMed
- Google Scholar
1. Zhang L
2. Song ZS
3. Wang ZS
4. Guo YL
5. Xu CG
6. Shen H
(2021) High expression of SLC16A1 as a biomarker to predict poor prognosis of urological cancers
Frontiers in Oncology 11:706883.

https://doi.org/10.3389/fonc.2021.706883
- PubMed
- Google Scholar
1. Zhu Z
2. Shi D
3. Guankai P
4. Tan Z
5. Shang X
6. Hu W
7. Liao H
8. Zhang X
9. Huang Y
10. Yu H
11. Meng W
12. Wang W
13. Ge Z
14. Yang X
15. He M
(2023) Retinal age gap as a predictive biomarker for mortality risk
The British Journal of Ophthalmology 107:547–554.

https://doi.org/10.1136/bjophthalmol-2021-319807
- PubMed
- Google Scholar

Article and author information

Author details

Sara Ahadi

Google Research, Mountain View, United States

Contribution
Conceptualization, Data curation, Formal analysis, Supervision, Investigation, Visualization, Methodology, Writing – original draft, Project administration, Writing – review and editing

For correspondence
saraahadi@gmail.com

Competing interests
is not currently affiliated with Google Research, however work for this manuscript was conducted while affiliated with Google Research. The author has no other competing interests to declare

"This ORCID iD identifies the author of this article:" 0000-0002-7849-2135
Kenneth A Wilson

Buck Institute for Research on Aging, Novato, United States

Contribution
Formal analysis, Validation, Visualization, Writing – original draft, Writing – review and editing, Investigation

Contributed equally with
Boris Babenko and Cory Y McLean

Competing interests
No competing interests declared

"This ORCID iD identifies the author of this article:" 0000-0003-3227-9977
Boris Babenko

Google Health, Palo Alto, United States

Contribution
Data curation, Software, Formal analysis, Visualization, Methodology, Writing – original draft, Writing – review and editing

Contributed equally with
Kenneth A Wilson and Cory Y McLean

Competing interests
is affiliated with Google Health. The author has no other competing interests to declare
Cory Y McLean

Google Health, Cambridge, United States

Contribution
Data curation, Software, Formal analysis, Visualization, Methodology, Writing – original draft, Writing – review and editing

Contributed equally with
Kenneth A Wilson and Boris Babenko

For correspondence
cym@google.com

Competing interests
is affiliated with Google Health. The author has no other competing interests to declare

"This ORCID iD identifies the author of this article:" 0000-0001-9928-8216
Drew Bryant

Google Research, Mountain View, United States

Contribution
Formal analysis

Competing interests
is affiliated with Google Research. The author has no other competing interests to declare
Orion Pritchard

Google Research, Mountain View, United States

Contribution
Formal analysis

Competing interests
is affiliated with Google Research. The author has no other competing interests to declare
Ajay Kumar

Department of Biophysics, Post Graduate Institute of Medical Education and Research, Chandigarh, India

Contribution
Writing – original draft

Competing interests
No competing interests declared
Enrique M Carrera

Buck Institute for Research on Aging, Novato, United States

Contribution
Validation

Competing interests
No competing interests declared
Ricardo Lamy

Department of Ophthalmology, Zuckerberg San Francisco General Hospital and Trauma Center, San Francisco, United States

Contribution
Interpretation of results

Competing interests
No competing interests declared
Jay M Stewart

Department of Ophthalmology, University of California, San Francisco, San Francisco, United States

Contribution
Interpretation of results

Competing interests
No competing interests declared
Avinash Varadarajan

Google Health, Palo Alto, United States

Contribution
Conceptualization, Resources, Data curation, Software, Formal analysis

Competing interests
is affiliated with Google Health. The author has no other competing interests to declare
Marc Berndl

Google Research, Mountain View, United States

Contribution
Conceptualization, Formal analysis, Supervision, Visualization, Methodology

Competing interests
is affiliated with Google Research. The author has no other competing interests to declare
Pankaj Kapahi

Buck Institute for Research on Aging, Novato, United States

Contribution
Conceptualization, Supervision, Funding acquisition, Validation, Methodology, Writing – original draft, Writing – review and editing

Contributed equally with
Ali Bashir

For correspondence
Pkapahi@buckinstitute.org

Competing interests
Reviewing editor, eLife

"This ORCID iD identifies the author of this article:" 0000-0002-5629-4947
Ali Bashir

Google Research, Mountain View, United States

Contribution
Conceptualization, Data curation, Formal analysis, Supervision, Investigation, Visualization, Methodology, Writing – original draft, Writing – review and editing

Contributed equally with
Pankaj Kapahi

Competing interests
is not currently affiliated with Google Research, however work for this manuscript was conducted while affiliated with Google Research. The author has no other competing interests to declare

Funding

NIH (T32AG000266-23)

Kenneth A Wilson

NIH (R01AG038688)

Pankaj Kapahi

NIH (AG045835)

Pankaj Kapahi

Larry L. Hillblom Foundation

Pankaj Kapahi

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Acknowledgements

This research has been conducted with the UK Biobank resource application 17643. We thank Jorge Cuadros from EyePACS for data access and helpful conversations. KAW is supported by NIH T32AG000266-23. We thank the Bloomington Drosophila Stock Center for providing flies used in this study. This work is funded by grants awarded to PK from the Reta Haynes Foundation, American Federation of Aging Research, NIH grants R01 R01AG038688 and AG045835 and the Larry L Hillblom Foundation.

Ethics

The UK Biobank study was reviewed and approved by the North West Multi-Centre Research Ethics Committee. For the EyePACS study, ethics review and IRB exemption was obtained using Quorum Review IRB (Seattle, WA).

Copyright

This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use and redistribution provided that the original author and source are credited.