Network Bio has launched with $50 million in financing to build disease-specific artificial intelligence models trained on large-scale human tissue, blood, molecular and clinical datasets, as the biotechnology company seeks to apply AI to diagnostics, biomarker discovery and drug development. Investors include Section 32, Thiel Bio, Founders Fund, Breyer Capital, Blue Venture Fund, JSL Health Capital and other life sciences and AI-focused funds.
The financing will support expansion of Network Bio’s life sciences platform, which is designed to train AI models using multimodal biological information connected to longitudinal patient outcomes.
A central component of the company’s strategy is a research network connecting biobanks at major U.S. academic medical centers.
Network Bio is collaborating with institutions including Mass General Brigham, the University of Pennsylvania and the University of Colorado Anschutz.
The company applies common sample-selection criteria, quality standards and data harmonization across participating sites to create datasets that can be used to train biological AI systems.
Those datasets combine information derived from patient tissue and blood samples with molecular data and longitudinal clinical outcomes.
Network Bio said the multi-institutional model enables it to generate datasets at a scale that would be difficult to create using a single academic biobank.
Following harmonization and analysis, generated data are returned to commercial partners and collaborating academic institutions, where they can also support basic science and biomedical research.
Network Bio is developing its platform around two foundational components.
The first is a biological research network that sources, connects and structures tissue, blood and longitudinal clinical information from academic medical centers.
The second is what the company describes as a bio-native AI architecture developed specifically for multimodal biological data.
The architecture is intended to identify biological patterns while accounting for technical confounders and producing interpretable representations that can potentially transfer across diseases and data types.
Network Bio has published research related to its technology in scientific journals including Nature Machine Intelligence.
The platform has demonstrated potential across multiple disease areas, with published results involving respiratory disease and additional studies involving ovarian and bone disease.
Network Bio said these efforts demonstrate the potential for models to transfer biological learning across diseases, including situations involving limited or previously unseen datasets.
The company has also secured an early commercial relationship through a strategic collaboration valued at more than $30 million with an unnamed Fortune 100 company that Network Bio described as a top-10 healthcare company.
The collaboration is focused on developing next-generation AI models and applying Network Bio’s multimodal platform to real-world clinical applications.
Network Bio ultimately wants its models to learn broader biological principles rather than requiring completely separate AI systems to be developed for every individual disease.
The company refers to this longer-term concept as “General Medical Intelligence,” in which the platform becomes more capable as it processes additional biological questions and datasets.
Network Bio’s existing data network spans areas including immunology, metabolic disease, cardiovascular disease and autoimmune conditions.
The company sees applications for its platform across personalized medicine, biomarker identification, diagnostics and pharmaceutical development.
KEY QUOTES:
“Every patient leaves a barcode of their disease in their tissue, and until now no one has been able to read those barcodes at scale. Working with the biobanks of some of the country’s leading academic medical centers, we built the network that makes reading them possible. We then built an AI platform that is already finding signals in conditions it was never trained on. This is the future of medicine.”
Asad Ali Ahmad, Ph.D., CEO And Co-Founder Of Network Bio
“No single academic medical center can capture the full complexity of human disease. By bringing together biobanks from leading institutions with industry partners, Network Bio is creating a research resource that reflects diverse patient populations and supports discoveries that can translate into real-world clinical practice.”
Kimberly Muller, Chief Innovation Officer At CU Anschutz Innovations
“Medicine is approaching an inflection point where AI can fundamentally change how biomedical discovery is done. What differentiates Network Bio is the combination of the network of academic medical center biobanks with an AI architecture built for medicine. Rather than building models one disease at a time, the company is building General Medical Intelligence that becomes more capable with every new biological question it answers.”
Mike Pellini, M.D., Managing Partner At Section 32 And Chairman Of Network Bio’s Board Of Directors
“We built Network Bio based on the belief that AI and data hold the keys to advancing the human condition. We have been focused tirelessly on the dual mandate of gaining access to the tissue datasets which explain disease and building the AI systems capable of interpreting the complex results.”
Hani Goodarzi, Ph.D., And Raphael Potter, Co-Founders Of Network Bio
“Clinical care is the largest biological experiment ever conducted, and we have no system for learning from it at scale. Network Bio pairs deep molecular and clinical phenotyping with tissue and longitudinal outcomes at leading US academic medical centers. The platform enables fundamental mechanistic understanding of human health and disease, compounding at every layer of the stack: data, intelligence, diagnostics, therapeutics.”
Morgan Cheatham, M.D., Partner At Breyer Capital
