# NHLBI-AI Stanford Data Science Center

> The NHLBI-AI Stanford Data Science Center advances safe agentic AI, multimodal models, and reproducible research across large-scale biomedical data.

Canonical site: https://nhlbi-ai-dsc.org/
Institution: Stanford University
Funder: National Heart, Lung, and Blood Institute (NHLBI)
Initiative: NHLBI-AI Enabled Precision Medicine Initiative (https://nhlbi-ai.org/)
## Core pages

- [Center overview](https://nhlbi-ai-dsc.org/): Mission, capabilities, services, community, and team.
- [Participate](https://nhlbi-ai-dsc.org/participate/): Official funding calls, center collaboration, and future team opportunities.
- [Work with us](https://nhlbi-ai-dsc.org/work-with-us/): Expressions of interest from postdoctoral-level researchers advancing agentic systems and research software engineers building dependable shared tools.
- [Official NHLBI-AI funding opportunities](https://nhlbi-ai.org/funding-opportunities): Authoritative call status, eligibility, deadlines, and application instructions.

## Center capabilities

- Interoperable, AI-ready research environments. Deliver reproducible environments for BioData Catalyst workspaces and other approved secure computing platforms, with portable containers, complete provenance, and safeguards for AI agents.
- Models that connect data across modalities. Develop and evaluate reusable models that link imaging, physiological signals, clinical phenotypes, genomics, and proteomics across large cohorts.
- Guarded agents for reproducible discovery. Enable agents to plan, run, check, and document multi-step analyses within secure environments, then share validated workflows through a community hub.

## Open-source foundations

- [Heartwood](https://github.com/SchmiedmayerLab/heartwood): An open-source, auditable coding agent for biomedical research environments, with explicit project boundaries, review before execution, and verifiable session history.

## Center team

- Euan A. Ashley, MB ChB, DPhil: Contact Principal Investigator. Center leadership and AI for cardiovascular medicine.
- Matthew T. Wheeler, MD, PhD: Multiple Principal Investigator. Bioinformatics, secure infrastructure, and center operations.
- James Zou, PhD: Multiple Principal Investigator. Reliable agentic AI and biomedical machine learning.
- Bruna Gomes, MD: Co-Investigator. AI for cardiovascular signals and imaging.
- Daniel H. Katz, MD: Co-Investigator. Multi-omic data pipelines and analysis.
- Jure Leskovec, PhD: Co-Investigator. Agentic systems, machine learning, and governance.
- Marco Perez, MD: Co-Investigator. Digital health data and cardiovascular model evaluation.
- Albert “A.J.” Rogers, MD, MBA, FAHA: Co-Investigator. Machine learning for cardiovascular signals.
- Ben Rogers, PhD: Co-Investigator. Secure research computing and privacy.
- Paul Schmiedmayer, PhD: Co-Investigator. Open, interoperable agentic AI and multimodal AI models.
- Holly Tabor, PhD: Co-Investigator. Ethics, safety, and participant engagement.
- Mia Levanto, BS: Program Manager. Center operations and research coordination.

## Working groups

- Agentic AI Workflows: Test agent-assisted workflows and define what must be logged, reviewed, and controlled.
- Foundation Models and Omics: Set benchmarks for multimodal models and standardize analysis pipelines.
- ELSI + Safety: Bring ethics, privacy, safety, and participant perspectives into design and evaluation.

## Researcher services

- Shape the research plan: Match a scientific question with the right NHLBI data resource, access path, computing environment, models, and agentic workflow.
- Build and adapt: Start from maintained environments, containers, pipelines, model templates, and reference implementations.
- Evaluate with confidence: Test models and agents across cohorts with common benchmarks, provenance, human review, and safety checks.
- Share, train, and reuse: Package validated models and workflows with documentation, training, and support for the wider community.

## NHLBI data ecosystem

NHLBI studies and programs generate and curate data. dbGaP governs access to much controlled genomic data. BioData Catalyst brings selected approved datasets, tools, and secure cloud workspaces together for analysis. Terra and Seven Bridges by Velsera provide workspaces within BioData Catalyst.

### Studies and data programs

- [TOPMed](https://www.nhlbi.nih.gov/science/trans-omics-precision-medicine-topmed-program): NHLBI program connecting genomic, omic, imaging, environmental, and clinical data.
- [MESA](https://www.nhlbi.nih.gov/science/multi-ethnic-study-atherosclerosis-mesa): NHLBI cohort and TOPMed parent study with longitudinal cardiovascular data.
- [HeartShare](https://www.nhlbi.nih.gov/news/2022/accelerating-heart-failure-research): NHLBI heart failure program combining phenotypes, images, and multi-omics.
- [AMP Heart Failure](https://www.nhlbi.nih.gov/science/accelerating-medicines-partnership-heart-failure-program-amp-hf): Public-private program using HeartShare and other NHLBI resources to study HFpEF.
- [BioLINCC collections](https://www.nhlbi.nih.gov/science/biologic-specimen-and-data-repository-information-coordinating-center-biolincc): NHLBI repository resources from population studies and clinical trials.

### Access and cloud infrastructure

- [dbGaP](https://www.ncbi.nlm.nih.gov/gap/): NIH system for requesting approved access to controlled genomic data.
- [BioData Catalyst](https://biodatacatalyst.nhlbi.nih.gov/): NHLBI cloud ecosystem for finding, accessing, analyzing, and sharing data and tools.
- [Terra](https://terra.biodatacatalyst.nhlbi.nih.gov/): BioData Catalyst workspace hosted and operated by the Broad Institute.
- [Seven Bridges by Velsera](https://platform.sb.biodatacatalyst.nhlbi.nih.gov/): BioData Catalyst workspace hosted and operated by Velsera.

## Machine-readable records

- [Structured site index](https://nhlbi-ai-dsc.org/site-index.json)
- [XML sitemap](https://nhlbi-ai-dsc.org/sitemap-index.xml)