Partnering to Advance Biomedicine
We’ve trained a multimodal foundation model to drive the future of clinical trials and patient care.
The Standard Model is a multimodal foundation model that integrates any biomedical measurement at any scale, from the molecular to the whole-patient level, into a universal representation of a human patient.
Built by experts in tech and biopharma
Biomedical organizations have incredibly valuable data. It’s also incredibly siloed. Today, continuity is missing, and data are scattered across departments, time, and modalities, limiting insights and leaving opportunities untapped.
Our foundation model is trained on diverse data across silos, generating insights that are impossible to attain within one organization. Our cross-disciplinary team is transforming the way biomedical data are used for patient care, clinical trials, and more.
Our foundation model brings together the world’s most valuable biomedical data across sources, scales, and formats to create a dynamic and universal representation of human patients. Importantly, we predict future patient state—not just future words in a sentence.
Biological signals exist in a complex hierarchy, from genomic variants to anatomical scans. Yet current AI treats these as isolated silos. We bridge this gap so organizations can optimize clinical trials and care decisions with precision.
We’ve trained a multimodal foundation model to drive the future of clinical trials and patient care.
We partner with academic researchers to provide AI expertise and access to the Standard Model. Researchers make critical discoveries, publish papers, and present their findings. Collaborators use the Standard Model to build applications that:
As standards of care evolve, the cost and complexity of clinical trials has risen. The margin for success is narrowing. Leaders in AI and clinical development use the Standard Model to build applications that:
“Tech and biotech have been on a collision course for a long time. Now we’re at the convergence. Our team comes from both worlds, combining AI, biomedical data, and biopharma expertise. We’re building the Standard Model for biology — not just a foundation model, but a foundation for the future of medicine, enabling others to design, test, and deliver next-generation care to more people.”
We’re building a multimodal foundation model training on a plurality of the world’s biomedical data.
Distinguishing the rare “driver” mutations that fuel cancer progression from the vast background of “passenger” mutations in the non-coding genome is a fundamental challenge in cancer biology.
Electronic Health Records (EHRs) contain rich temporal dynamics that conventional encoding approaches fail to adequately capture.