A systems-level dissection of aging and longevity mechanisms powered by an evidence-routed AI knowledge graph
Abstract
Aging is a complex biological process influenced by numerous molecular and cellular factors. A systems-level understanding of these mechanisms is essential for identifying key regulatory processes and prioritizing effective interventions. Here, we present a comprehensive dissection of aging and longevity mechanisms powered by an evidence-routed AI-based knowledge graph, HALDxAI. We integrated 445,435 aging- and longevity-related PubMed records with 19 curated biomedical databases to construct a unified Aging Knowledge Graph (Aging-KG). The pipeline combined LLM extraction from two selected abstract subsets with machine learning and deep learning extraction at corpus scale. HALDxAI uses a multi-agent retrieval system that links graph relations and generated answers to sentence-level evidence. In an expert review of 300 database relations, all cited PMIDs resolved, 97.3% of the displayed evidence was attributable to the cited record, and 65.3% of the relation claims were fully supported by that evidence. Network analyses of the Aging-KG identified TP53, mTOR, and SIRT1 as highly ranked bridge candidates between aging and longevity seed sets. These rankings describe graph topology and do not establish regulatory function or causality. In addition, an inflammaging-focused case study demonstrates the capacity of HALDxAI to decompose modular structures and position anti-aging interventions. Overall, HALDxAI reduces knowledge fragmentation and provides a scalable platform for evidence retrieval, network analysis, and hypothesis generation in aging and longevity research.
Related
- Convergent evolution of longevity reveals divergent genomic mechanisms in small and large mammals
- Repurposing Regulatory Rodent Toxicology Safety Archives to Identify Candidate Hormetic Longevity Agents Highlights Emergent Mitochondrial Mechanisms.
- Microbiota-derived metabolite signatures in Alzheimer’s disease across the cognitive aging continuum: a human-focused systematic review and evidence-weighted knowledge graph
- Women's health and female fertility: current evidence and knowledge gaps in the Asia–Pacific region
- What are the pathways for knowledge production during the diversification of cropping systems through the introduction of minor species?
BibTeX
@article{zhang2026systemslevel,
title = {{A systems-level dissection of aging and longevity mechanisms powered by an evidence-routed AI knowledge graph}},
author = {Shilong Zhang and Luyao Xie and Xiaoying Zheng and Enyan Liu and Yifan Chen and Yi Shen and Haoyu Chao and Sida Li and Yueming Hu and Dušan Ušjak and Cong Feng and Ming Chen},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-72859-3},
url = {https://www.nature.com/articles/s41598-026-72859-3},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A systems-level dissection of aging and longevity mechanisms powered by an evidence-routed AI knowledge graph
AU - Shilong Zhang
AU - Luyao Xie
AU - Xiaoying Zheng
AU - Enyan Liu
AU - Yifan Chen
AU - Yi Shen
AU - Haoyu Chao
AU - Sida Li
AU - Yueming Hu
AU - Dušan Ušjak
AU - Cong Feng
AU - Ming Chen
PY - 2026
DA - 2026/10/06
JO - Scientific Reports
DO - 10.1038/s41598-026-72859-3
UR - https://www.nature.com/articles/s41598-026-72859-3
AB - Aging is a complex biological process influenced by numerous molecular and cellular factors. A systems-level understanding of these mechanisms is essential for identifying key regulatory processes and prioritizing effective interventions. Here, we present a comprehensive dissection of aging and longevity mechanisms powered by an evidence-routed AI-based knowledge graph, HALDxAI. We integrated 445,435 aging- and longevity-related PubMed records with 19 curated biomedical databases to construct a unified Aging Knowledge Graph (Aging-KG). The pipeline combined LLM extraction from two selected abstract subsets with machine learning and deep learning extraction at corpus scale. HALDxAI uses a multi-agent retrieval system that links graph relations and generated answers to sentence-level evidence. In an expert review of 300 database relations, all cited PMIDs resolved, 97.3% of the displayed evidence was attributable to the cited record, and 65.3% of the relation claims were fully supported by that evidence. Network analyses of the Aging-KG identified TP53, mTOR, and SIRT1 as highly ranked bridge candidates between aging and longevity seed sets. These rankings describe graph topology and do not establish regulatory function or causality. In addition, an inflammaging-focused case study demonstrates the capacity of HALDxAI to decompose modular structures and position anti-aging interventions. Overall, HALDxAI reduces knowledge fragmentation and provides a scalable platform for evidence retrieval, network analysis, and hypothesis generation in aging and longevity research.
SN - 2045-2322
ER -