DoAtlas-2: A Foundation for Self-Evolving Causal Biomedical Discovery
DoAtlas-2 is a self-evolving causal biomedical foundation linking population evidence, mechanisms, and interpretable prediction.
DoAtlas-2 organizes biomedical knowledge around causal mechanisms and updates itself using external human-population evidence. It integrates 771 research resources covering more than 720,000 participants in 48 countries, eight molecular layers, and about 4.7 million literature-derived records over 93,566 concepts and 149,383 candidate causal relations. The system has evaluated 2,031 research questions; in the Human Phenotype Project it formulated 4,014 pathway questions and found statistical support for 756 of the first 1,079 screened. Reported findings treat blood pressure as a convergence node and show an adiposity-inflammation-blood-pressure pathway largely attenuated after joint adjustment for BMI and smoking.
- Integrates 771 resources and over 720,000 participants across 48 countries.
- Evidence network holds about 4.7 million literature-derived records.
- Evaluated 2,031 questions; 756 of 1,079 HPP screens had statistical support.
- Blood pressure links adiposity, hepatic, and lipid phenotypes to vascular outcomes.
- Vascular network supports exact attribution and closed-form mediation effects.
Full article231 words · extracted from arxiv.org · click to collapse
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.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.35107