DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
Abstract
We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.
Related
- Genomic foundation models do not yet boost common variant discovery beyond standard functional annotations
- Discovery of Bioresorbable Polymer Suture Coatings for Controlled Tissue Regeneration with Multimodal Foundation Models
- Federated Causal Discovery in Medicine: Trends, Opportunities, and Challenges
- Causal discovery identifies pathways linking physical activity to dementia risk in the UK BioBank
- RAPTORGraph: graph-based pathway modeling for causal discovery in single-cell perturbations
BibTeX
@misc{li2026doatlas2,
title = {{DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery}},
author = {Yulong Li and Rong Xia and Yuxuan Zhang and Jianxu Chen and Xiwei Liu and Haochen Xue and Maosheng Li and Yuhang Liu and Yibo Yuan and Yutong Xie and Chong Li and Jionglong Su and Hagai Rossman and Eran Segal and Imran Razzak},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.35107},
eprint = {2609.35107},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.35107},
}
RIS
TY - UNPB
TI - DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
AU - Yulong Li
AU - Rong Xia
AU - Yuxuan Zhang
AU - Jianxu Chen
AU - Xiwei Liu
AU - Haochen Xue
AU - Maosheng Li
AU - Yuhang Liu
AU - Yibo Yuan
AU - Yutong Xie
AU - Chong Li
AU - Jionglong Su
AU - Hagai Rossman
AU - Eran Segal
AU - Imran Razzak
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2609.35107
UR - https://arxiv.org/abs/2609.35107
AB - We introduce DoAtlas-2, a foundation for self-evolving causal biomedical discovery that organizes knowledge around causal mechanisms and advances through external evidence from human populations. DoAtlas-2 integrates 771 research resources covering more than 720,000 participants in 48 countries, from longitudinal clinical phenotypes, medical imaging, and continuous physiological signals to eight molecular layers, together with an evidence network of approximately 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. DoAtlas-2 autonomously formulates research questions from evidence gaps and unresolved mechanisms, prespecifies their causal designs, and generates validated analyses. Supporting, challenging, and unresolved results continuously revise mechanistic interpretations, the causal evidence state, and the discovery frontier, so that DoAtlas-2 self-evolves within a closed loop of hypothesis generation, empirical testing, and renewed discovery. DoAtlas-2 has systematically evaluated 2,031 research questions. In the Human Phenotype Project (HPP), it formulated 4,014 candidate pathway questions across vascular, early-glycemic, and hepatic-metabolic systems, and screening of the first 1,079 yielded statistical support for 756. Representative studies identify blood pressure as a convergence node linking adiposity, hepatic, and lipid phenotypes to vascular outcomes, and show that an adiposity-inflammation-blood-pressure pathway is largely attenuated by joint adjustment for body mass index (BMI) and smoking. The discovered vascular network constitutes a completely interpretable predictive foundation, admitting exact attribution of every prediction and closed-form mediation effects. DoAtlas-2 thereby unifies causal mechanism discovery, population-evidence testing, and interpretable prediction within one continuously evolving foundation.
ER -