Deep biomarkers of human aging: Application of deep neural networks to biomarker development

Abstract

One of the major impediments in human aging research is the absence of a comprehensive and actionable set of biomarkers that may be targeted and measured to track the effectiveness of therapeutic interventions. In this study, we designed a modular ensemble of 21 deep neural networks (DNNs) of varying depth, structure and optimization to predict human chronological age using a basic blood test. To train the DNNs, we used over 60,000 samples from common blood biochemistry and cell count tests from routine health exams performed by a single laboratory and linked to chronological age and sex. The best performing DNN in the ensemble demonstrated 81.5 % epsilon-accuracy r = 0.90 with R2 = 0.80 and MAE = 6.07 years in predicting chronological age within a 10 year frame, while the entire ensemble achieved 83.5% epsilon-accuracy r = 0.91 with R2 = 0.82 and MAE = 5.55 years. The ensemble also identified the 5 most important markers for predicting human chronological age: albumin, glucose, alkaline phosphatase, urea and erythrocytes. To allow for public testing and evaluate real-life performance of the predictor, we developed an online system available at http://www.aging.ai. The ensemble approach may facilitate integration of multi-modal data linked to chronological age and sex that may lead to simple, minimally invasive, and affordable methods of tracking integrated biomarkers of aging in humans and performing cross-species feature importance analysis.

Ageing, neurodegeneration and brain rejuvenation

“…(The epidemiology of longevity is reviewed comprehensively elsewhere 23 .) Further insights into the links between ageing and neurodegeneration are being generated from genetic studies that explore not only longevity and exceptional lifespan but also the genetics of disease-free ageing 24,25 and the integration of genetics with other omics approaches 26 .…”

Classification for Longevity Potential: The Use of Novel Biomarkers

“…The difficulty in the comparison of each of these studies is that different study cohorts have been used and that different parameters have been determined to be included in analyses. Previously, albumin has been determined as an important predictor of biological age and residual lifespan (37, 38), which should encourage cohorts to measure metabolomics platforms that include albumin levels. Ultimately, transcriptomics, proteomics, and metabolomics measures should be harmonized for human cohorts and then added to the models for biological age and physiological dysregulation and investigate generalizability over multiple studies.…”

An omic approach to spinal cord injury mechanisms

“…Due to the complexity of coordinated signalling and communication between cells wherein most events do not function in isolation, a systems level analysis based on transcriptomic, proteomic, and connectomic mechanisms is needed 15 . An omic analysis can be described as follow: macromic where big-data analytics reveal neural tract adaptation in response to injury and regeneration and system wide motor-sensory adaptation; mesomic where the connectome of newly formed synapses are mapped as structure-function models, revealing new circuitry between the regenerating axon and grafted substrates in the lesion site; micromic where the molecular identity of regenerating neurons and permissive substrates are established through the utilization of transcriptomic and proteomic network analysis.…”