Tempus AI, Inc. (NASDAQ: TEM) announced an initiative to build a research platform containing 100,000 whole genome sequences linked to longitudinal clinical information, with a long-term goal of expanding to one million genomes.

According to a company statement, the dataset will pair whole-genome sequencing data with clinical histories, imaging, pathology and patient outcomes, and will be designed specifically for AI model development. Tempus describes the effort as the first de-identified multimodal whole-genome sequencing dataset built around disease populations and patient outcomes.

The new data will be integrated into Tempus' existing de-identified multimodal data environment, accessible through its Tempus Lens platform, which allows researchers to analyze data and build AI models without transferring datasets between systems.

Development is already underway, and an initial dataset is available through the company's Early Adopter Program. General availability is planned for mid-2027, with additional members to be added in waves as the dataset grows.

"A large dataset is only valuable if you can turn it into insight," said Eric Lefkofsky, Founder and CEO of Tempus. "Adding whole genome data linked to longitudinal outcomes makes that platform even more powerful and gives researchers a richer foundation to build AI models, generate new insights and ultimately improve patient care."

Tempus said existing population-scale genome programs are largely drawn from general populations and are not structured to link genomic data with longitudinal disease and treatment outcomes.