AI scientist system streamlines biomedical research with governed workflows

Researchers have developed NVAITC AI Scientist (NAIS), a governed end-to-end agentic research system designed for scientific workflows in institutional biomedical settings. NAIS integrates mechanisms for research planning, data access, workflow orchestration, evidence tracking, reproducibility, and human oversight, ensuring protected data remains within privacy boundaries. The system was validated through a hypertension genome-wide association study (GWAS) using hospital-linked data from over 286,000 individuals, where it planned cohort extraction, orchestrated GWAS execution, and generated publication-ready outputs. NAIS also successfully supported a drug-induced liver injury prediction workflow, demonstrating its capability for scalable AI-assisted biomedical discovery. AI

IMPACT Governed agentic systems could accelerate AI-assisted biomedical discovery while maintaining data privacy and reproducibility.

RANK_REASON Research paper detailing a new AI system for scientific workflows. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• ATP2B1
• CNNM2
• FGF5
• FTO
• genome-wide association study
• GRB14
• Hypertension GWAS
• NVAITC AI Scientist

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →