Insilico Medicine Shanghai Ltd

The aging population worldwide necessitates the development of novel therapeutics that enhance the quality of life by preventing and treating age-related diseases. In this review, we first discuss the advantages of a dual-purpose target identification strategy for aging and age-related diseases, with assessment of the hallmarks of aging as an approach to identify such dual-purpose targets. Resulting from a convergence of aging research with machine learning (ML) and other artificial intelligence (AI) models, aging clocks were initially developed as aging biomarkers, but its value in identifying therapeutic targets is also increasingly recognized. Building on recently published aging clocks, we reestablish a significant proportion of known drug targets by identifying clock-associated genes, highlighting the potential of these clocks for target identification. Lastly, we discuss other applications of aging clocks in drug development such as population stratification and disease and treatment monitoring. With the growing availability of multi-omics data and rapid advancements in ML and AI, we anticipate accelerated progress in aging clock research, paving the way for innovative treatments to meet the healthcare needs of a global aging population.

While aging-related diseases are often used as proxies for the general aging process in research, they largely differ in terms of how integral their development is to organismal aging. Hallmarks of aging offer a convenient conceptual framework to assess the relevance of a disease to the anti-aging narrative. In this review, we propose hallmark decomposition as a method of measuring the potential of a therapy to translate from a disease-specific treatment to a general geroprotector. To help other researchers adopt and improve this methodology, we are releasing a disease scoring system and report the hallmark alignment of 13 aging-related diseases, among which IPF is the disease most aligned with aging.

Idiopathic pulmonary fibrosis (IPF) is a condition predominantly affecting the elderly and leading to a decline in lung function. Our study investigates the aging-related mechanisms in IPF using artificial intelligence (AI) approaches. We developed a pathway-aware proteomic aging clock using UK Biobank data and applied it alongside a specialized version of Precious3GPT (ipf-P3GPT) to demonstrate an AI-driven mode of IPF research. The aging clock shows great performance in cross-validation (R²=0.84) and its utility is validated in an independent dataset to show that severe cases of COVID-19 are associated with an increased aging rate. Computational analysis using ipf-P3GPT revealed distinct but overlapping molecular signatures between aging and IPF, suggesting that IPF represents a dysregulation rather than mere acceleration of normal aging processes. Our findings establish novel connections between aging biology and IPF pathogenesis while demonstrating the potential of AI-guided approaches in therapeutic development for age-related diseases.