Bioptimus Announces STELA: The World's Largest Clinically Linked Spatial Biology Atlas, alongside key partners 10x Genomics and Broad Clinical Labs
The global initiative aims to profile up to 100,000 patient specimens to scale M-Optimus, the world model of biology, representing a ~20x increase in scale over existing data available in the world today
- The Launch of STELA: Bioptimus is establishing the largest clinically linked multimodal atlas, starting in oncology and immunology tissue, designed to generate harmonized multi-omics patient data.
- A Strategic Partnership with 10x Genomics: Leveraging the Xenium spatial transcriptomics platform as the foundational partner for the launch, the initiative sets a new benchmark for reproducible, AI-ready data generation across leading research institutions worldwide.
- A Strategic Partnership with the Broad Clinical Labs: A multi-year agreement with Broad Clinical Laboratories to support STELA via the generation of spatial biology data at scale.
- Profiling Up to 100,000 Patient Specimens: Representing a ~20-fold increase in scale over existing spatial biology atlases, STELA will integrate spatial technologies, pathology imaging, multi-omics, and longitudinal clinical data across three continents.
PARIS, March 25, 2026 /PRNewswire/ -- Bioptimus, a global AI company building the world's first world model for biology, today announced the launch of its Spatial Tissue Embedding Learning Atlas (STELA), a multinational spatial data generation initiative anchored by a partnership with 10x Genomics, Inc. (Nasdaq: TXG) and Broad Clinical Labs.
While foundation models for language have thrived on vast digital datasets, biology has long lacked the standardized, high-quality data scale required for a similar breakthrough, particularly for clinical data; Bioptimus is closing this gap by building the data infrastructure necessary to power M-Optimus, the first multimodal and multiscale world model of biology. STELA will serve as the data backbone for M-Optimus, generating massive datasets designed to decrypt the complex organization of human tissues. M-Optimus will leverage this massive multimodal repository to map how molecular and cellular interactions drive disease in fields like oncology and inflammation, ultimately allowing researchers to anticipate patient responses to novel therapies, accelerate drug development, and design more effective immunotherapies.
Starting with 10x Genomics'' Xenium spatial transcriptomics and designed to integrate additional spatial and molecular profiling technologies over time, STELA will generate harmonized datasets, integrating: high-resolution spatial transcriptomics, matched histopathology imaging, multi-omics data (e.g., genomics, transcriptomics and proteomics), with longitudinal clinical records. The initiative aims to profile up to 100,000 patient tissue specimens across three continents: the United States, Europe, and Asia, establishing the world's largest clinically linked, spatially profiled, multimodal patient data atlas.
Participating hospitals and research institutions will contribute samples under standardized protocols and, in return, receive access to rich spatial characterization and foundation model capabilities. This collaboration empowers clinicians to turn raw data into actionable insights through more precise diagnostic and therapeutic strategies. By aligning data generation protocols, data processing and storage, and AI model development within a unified framework at a diverse, global scale, STELA establishes foundational infrastructure for the next era of biological AI.
"Today, most patients' diagnostic data is used to inform decisions for only that individual. We envision a world where every patient can contribute insights to better inform the care and treatment outcomes of future patients; just as patients with other diseases, other heritage and even from the past are informing their treatment," said Jean Philippe Vert, PhD, Co-Founder and CEO of Bioptimus. "STELA is the fuel to power M-Optimus, allowing us to map the intricate interactions between cells and tissues, across indications, at unprecedented scales, unlocking a new era of precision medicine."
Industry-Shaping Partnerships
The collaboration between Bioptimus and 10x Genomics aligns advanced spatial biology technologies with large-scale AI foundation model development, bringing together complementary capabilities to reshape how biomedical data is generated and applied. Using the Xenium platform, STELA will generate highly standardized spatial datasets across participating institutions worldwide, enabling the large-scale, reproducible data generation required for large-scale AI model development.
"Many of the most important questions in medicine come down to understanding how cells interact within complex human tissues," said Serge Saxonov, Chief Executive Officer and Co-founder of 10x Genomics. "By enabling spatial profiling at unprecedented scale, STELA will generate foundational datasets that allow researchers to connect the underlying biology with disease outcomes, unlocking new insights that can accelerate and improve therapeutic discovery and development."
Bioptimus will anchor its STELA initiative through a landmark collaboration with the Broad Clinical Laboratories, bridging industrial-scale data generation with frontier AI research. This partnership leverages Broad's high-throughput spatial biology capabilities to process biological samples at scale, creating a massive-scale repository of high-resolution spatial transcriptomics data. Beyond data production, the two organizations will co-develop next-generation, AI-driven quality control metrics and predictive tools designed to optimize assay performance and automate biological insights. By integrating Bioptimus's proprietary AI models with Broad's world leading laboratory workflows, this collaboration ensures that the STELA initiative is built on a foundation of unprecedented technical precision, accelerating the development of transformative AI models for the life sciences.
"To unlock the true clinical potential of spatial biology, we must pair massive-scale data generation with uncompromising data quality," Niall Lennon, Chief Scientific Officer of Broad Clinical Labs added. "By combining our high-throughput laboratory workflows with Bioptimus's advanced AI, we are co-developing next-generation quality control metrics that ensure the highest data integrity. This unprecedented technical precision guarantees that the insights generated by STELA can be confidently translated into actionable clinical diagnostics and precision therapies."
About Bioptimus
Bioptimus is a global AI biotech company pioneering the world's first universal foundation model for biology. By combining cutting-edge AI with massive, multimodal, proprietary data generation, Bioptimus is building a unifying framework that connects all scales of biology, from molecules to patients, delivering interpretable, dynamic, and actionable insights. M-Optimus-1 represents the first World Model of Biology. H-Optimus, the foundation model of human histology has over 1 million downloads, and is an industry-leading model being adopted across research, drug discovery, and clinical pipelines. Bioptimus models are in use by 16 of the top 20 pharmaceutical companies.
For more information about Bioptimus, visit: www.bioptimus.com
Media Contact:
About 10x Genomics
10x Genomics is a life science technology company building products to accelerate the mastery of biology and advance human health. Our integrated research solutions include instruments, consumables and software for single cell and spatial biology, which help academic and translational researchers and biopharmaceutical companies understand biological systems at a resolution and scale that matches the complexity of biology. Our products are behind breakthroughs in oncology, immunology, neuroscience and more, fueling powerful discoveries that are transforming the world's understanding of health and disease. To learn more, visit 10xgenomics.com or connect with us on LinkedIn, X, Facebook, Bluesky or YouTube.
SOURCE Bioptimus
Share this article