NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study

2026-07-13

AI Summary

Current biomedical research lacks governed intelligent systems that simultaneously ensure data privacy, reproducibility, and human oversight. This work proposes the first end-to-end intelligent research system compliant with institutional governance requirements, integrating an agent-based architecture to support a complete closed-loop workflow—from study planning and controlled data access to reproducible execution and human-in-the-loop review. The system successfully executes a real-world genome-wide association study (GWAS) under strict privacy constraints, replicating key genetic loci for hypertension (e.g., FGF5, −log₁₀(p) ≈ 70), and achieves an AUC of 0.842 in drug-induced liver injury prediction—matching expert-level performance. These results demonstrate the system’s effectiveness, scalability, and readiness for deployment in regulated biomedical research environments.

Abstract

Agentic research systems are emerging as a new paradigm for coordinating scientific workflows beyond isolated model inference, code generation, or statistical analysis. However, deployment in institutional biomedical environments requires governed mechanisms for research planning, data access, workflow orchestration, evidence tracking, reproducibility, and human oversight. We present NVAITC AI Scientist (NAIS), a governed end-to-end agentic research system designed to support domain-general scientific workflows while keeping protected data within institutional privacy boundaries. NAIS integrates proposal review, execution planning, governed computational routing, reproducible workflow orchestration, evidence generation, and scientist-in-the-loop oversight. We validate NAIS in a real-world hypertension genome-wide association study (GWAS) using hospital-linked genotype and electronic health record (EHR) data from 286,422 individuals under an aggregate-only data policy. The agent planned cohort extraction, orchestrated GWAS execution, generated quality-control summaries, and drafted publication-oriented outputs. Human-AI review identified phenotype discrepancies and enabled iterative refinement of the hypertension definition. After reconciliation, the agent-orchestrated GWAS reproduced established hypertension loci, including FGF5, ATP2B1, CNNM2, FTO, and GRB14, with the strongest signal at FGF5 reaching $-\log_{10}(p) \sim 70$. As a secondary demonstration, NAIS also supported a drug-induced liver injury prediction workflow, achieving a multimodal graph neural network AUC of 0.842. These results demonstrate that governed agentic research systems can support scalable AI-assisted biomedical discovery while producing outputs comparable to expert-led workflows.

Problem

• agentic research systems
• governed AI
• biomedical data privacy
• reproducible workflows
• human-in-the-loop oversight

Innovation

• agentic research system
• governed AI
• end-to-end scientific workflow
• privacy-preserving GWAS
• human-in-the-loop oversight