Ai2 Launches Asta DataVoyager: Data-driven Discovery and Analysis for Science

Audio By Carbonatix

SEATTLE--(BUSINESS WIRE)--Oct 1, 2025--

Ai2 (The Allen Institute for AI) today launched Asta DataVoyager, a powerful data analysis AI agent within the Asta ecosystem. Scientists across disciplines face an abundance of structured data but lack intuitive tools to efficiently transform it into meaningful answers. With Asta DataVoyager, researchers can upload datasets and ask questions in plain language, receiving trustworthy, reproducible outputs that combine statistical rigor with usability.

At a time when most analysis tools require advanced coding skills or fall short on compliance and security, Asta DataVoyager fills the gap by empowering researchers, including those in sensitive domains like medicine, to directly explore their data while maintaining privacy and reproducibility.

“AI can only accelerate science if it is as rigorous and transparent as science itself,” said Ali Farhadi, CEO of Ai2. “With Asta DataVoyager, we are giving researchers a trusted partner that puts powerful analytical tools directly into their hands while preserving standards of accuracy and trust that the scientific community depends on.”

A New Standard for Data-Driven Discovery

Asta DataVoyager is designed to be intuitive for users, regardless of their comfort level working with dataset analysis tooling. Users can upload a dataset in CSV, Excel, JSON, HDF5, TSV, or Parquet format, ask a question, share an optional prompt to establish context, and Asta DataVoyager will output:

• Clear, scientific answers to natural language queries
• Copyable code that fully reproduces the analysis
• Visualizations that make findings immediately interpretable
• A methods section documenting assumptions, reasoning, and statistical tests

Researchers can refine results with follow-up prompts, adding new analysis cells while preserving provenance, much like a Python notebook. This ensures analyses remain transparent, traceable, and shareable across collaborations and publications.

Real-World Impact in Cancer Research

The Cancer AI Alliance (CAIA), which unites four leading cancer centers, is piloting Asta DataVoyager to accelerate research into multiple cancer types. By analyzing de-identified patient records that never leave their home institutions, CAIA researchers can generate cross-institution insights while safeguarding patient privacy.

One ongoing study focuses on lung cancer, comparing treatments and outcomes across centers by analyzing factors such as time to surgery with neoadjuvant chemo-immunotherapy, the impact of adding immunotherapy after definitive radiation, and the relative effectiveness of targeted drugs versus standard platinum chemotherapy. Ai2’s engagement with CAIA is made possible by generous support from Allen Family Philanthropies.

“When I think about the future of where I want it to go, I think about this tool in the hands of clinicians, helping to answer important questions that will ensure the best possible care for cancer patients,” said Jeff Leek, Chief Data Officer at the Fred Hutchinson Cancer Research Center.

Beyond CAIA, clinicians at the Paul G. Allen Research Center at Swedish Cancer Institute are also piloting DataVoyager. With large volumes of structured health data but limited in-house data-science bandwidth, SCI sees the tool as a way to put analytical power directly into the hands of physicians.

Trustworthy Tools for Research

Asta DataVoyager was designed for sensitive, high-stakes scientific environments. Teams retain full control over their data with flexible deployment options: hosted portals, secure on-premises setups, or private cloud infrastructure. Datasets can be deleted at any time, ensuring researchers define their own data handling protocols.

By shortening the path from questions to well-supported answers, Asta DataVoyager supercharges statistical workflows—without sacrificing transparency or reproducibility.

“We wanted to build a system that meets scientists where they are,” said Bodhisattwa Prasad Majumder, Research Scientist at Ai2. “Instead of asking researchers to become programmers, Asta DataVoyager lets them ask questions about their data in their own words and receive answers they can trust, complete with code, visuals, and documentation. Our goal is to shorten the distance between a researcher’s idea and a reproducible scientific result.”

Looking Ahead

Asta DataVoyager is the latest milestone in Ai2’s mission to build an open, principled ecosystem for scientific AI. As researchers test the tool in federated and clinical contexts, Ai2 will continue to expand its capabilities to support new domains and workflows.

Have a scientific use case or sensitive dataset? The Asta team is actively seeking pilot partners. Learn more and sign up for updates at allenai.org/asta.

About Ai2

Ai2 is a Seattle-based nonprofit AI research institute with the mission of building breakthrough AI to solve the world’s biggest problems. Founded in 2014 by the late Paul G. Allen, Ai2 develops foundational AI research and innovative new applications that deliver real-world impact through large-scale open models, open data, robotics, conservation platforms, and more. Ai2 champions true openness through initiatives like OLMo, the world’s first truly open language model framework, Molmo, a family of open state-of-the-art multimodal AI models, and Tulu, the first application of fully open post-training recipes to the largest open-weight models. These solutions empower researchers, engineers, and tech leaders to participate in the creation of state-of-the-art AI and to directly benefit from the many ways it can advance critical fields like medicine, scientific research, climate science, and conservation efforts. For more information, visit allenai.org.

View source version on businesswire.com:https://www.businesswire.com/news/home/20251001569928/en/

[email protected]

KEYWORD: UNITED STATES NORTH AMERICA WASHINGTON

INDUSTRY KEYWORD: DATA MANAGEMENT TECHNOLOGY OTHER SCIENCE SOFTWARE RESEARCH ARTIFICIAL INTELLIGENCE SCIENCE

SOURCE: Ai2

Copyright Business Wire 2025.

PUB: 10/01/2025 09:00 AM/DISC: 10/01/2025 09:02 AM

http://www.businesswire.com/news/home/20251001569928/en