Collaboration pairs tissue and blood samples from disease-specific populations with patient outcomes data to power Network Bio’s foundation models for diagnostics and drug discovery

PALO ALTO, Calif.: #AI--Network Bio, which is building a patient world model of human disease that learns how disease develops and responds to treatment across patients, from tissue, blood and clinical data, today announced a strategic collaboration with Duke University.

The company will partner with Duke investigators to perform molecular profiling in biospecimens from Duke’s biobanks and pair the molecular data with de-identified clinical records, as permitted under research protocols. The resulting datasets will help train models designed to detect disease earlier, match patients to the right therapies and find new drug targets.

Most AI in biology is trained on cell lines, animal models or public datasets that lack an important variable: what happened to the patient. Academic biobanks hold tissue and blood linked to diagnosis, treatment and outcome over many years. Under the collaboration Network Bio and Duke will select disease specific cohorts from Duke’s biobanks. Network Bio will generate molecular profiling data from those biospecimens and pair it with de-identified clinical outcomes. The resulting datasets will support research into disease biology and the development of AI models for early detection and therapeutic discovery. The generated molecular data will be shared back with Duke biobanks to fuel academic research.

The collaboration combines Duke University's extensive biobanking infrastructure and clinical research expertise with Network Bio's approach to generating and integrating large-scale biological datasets. Together, the organizations aim to address a key challenge in using AI to understand human disease: the availability of tissue and blood data connected to clinically meaningful information about human disease.

“Academic medical centers hold vast records of human disease: molecular data contributed by research participants, linked to their clinical outcomes,” said Asad Ali Ahmad, Co-Founder and Chief Executive Officer of Network Bio. “We are thrilled to expand our network of academic medical center biobank partners along with the University of Pennsylvania, Massachusetts General Brigham and the University of Colorado Anschutz.”

Through the collaboration, the organizations will identify disease-specific research cohorts from Duke University's biobanks and support molecular sequencing of tissue and blood biospecimens. The collaboration also establishes a framework for the responsible use of these datasets in research and commercial applications, including data licensing and AI model development, subject to the terms of the agreement and applicable data privacy and security requirements.

“Molecular data generated from cutting-edge technology together with clinical information and AI modeling has great potential for helping us better understand how diseases develop and respond to treatment,” said Svati H. Shah, M.D., Associate Dean for Translational Research at Duke University School of Medicine and Director of the Duke Center for Precision Health. “This collaboration provides an opportunity to study biospecimens alongside linked clinical information, which supports deeper research that could speed discovery, while maintaining our responsibility to steward these resources carefully.”

“Biobanked tissue and blood collections, paired with years of clinical follow up, can help us train on how disease actually develops and responds to treatment in people. For our pharma and diagnostics partners, that means testing targets, biomarkers and patient selection against real human outcomes before a program ever reaches the clinic,” said Raphael Potter, Co-Founder and Chief Business Officer of Network Bio.

The collaboration reflects a growing emphasis across the life sciences industry on developing large-scale, multimodal datasets that combine molecular and clinical information to improve the predictive capabilities of AI and machine learning models. By generating genomic datasets grounded in human disease biology, Network Bio aims to support a more data-driven approach to therapeutic discovery, development and early disease detection.

About Network Bio

Network Bio is a biotechnology company building a patient world model of human disease that learns how disease develops and responds to treatment across patients, from tissue, blood and clinical data. Through collaborations with leading U.S. academic medical centers, the company turns biobanked tissue and blood linked to patient outcomes into models designed to generalize across diseases. Applications include precision diagnostics, biomarker discovery and drug development. Network Bio is based in Palo Alto. For more information, visit www.network.bio.

Fonte: Business Wire

Collaboration pairs tissue and blood samples from disease-specific populations with patient outcomes data to power Network Bio’s foundation models for diagnostics and drug discovery

PALO ALTO, Calif.: #AI--Network Bio, which is building a patient world model of human disease that learns how disease develops and responds to treatment across patients, from tissue, blood and clinical data, today announced a strategic collaboration with Duke University.

The company will partner with Duke investigators to perform molecular profiling in biospecimens from Duke’s biobanks and pair the molecular data with de-identified clinical records, as permitted under research protocols. The resulting datasets will help train models designed to detect disease earlier, match patients to the right therapies and find new drug targets.

Most AI in biology is trained on cell lines, animal models or public datasets that lack an important variable: what happened to the patient. Academic biobanks hold tissue and blood linked to diagnosis, treatment and outcome over many years. Under the collaboration Network Bio and Duke will select disease specific cohorts from Duke’s biobanks. Network Bio will generate molecular profiling data from those biospecimens and pair it with de-identified clinical outcomes. The resulting datasets will support research into disease biology and the development of AI models for early detection and therapeutic discovery. The generated molecular data will be shared back with Duke biobanks to fuel academic research.

The collaboration combines Duke University's extensive biobanking infrastructure and clinical research expertise with Network Bio's approach to generating and integrating large-scale biological datasets. Together, the organizations aim to address a key challenge in using AI to understand human disease: the availability of tissue and blood data connected to clinically meaningful information about human disease.

“Academic medical centers hold vast records of human disease: molecular data contributed by research participants, linked to their clinical outcomes,” said Asad Ali Ahmad, Co-Founder and Chief Executive Officer of Network Bio. “We are thrilled to expand our network of academic medical center biobank partners along with the University of Pennsylvania, Massachusetts General Brigham and the University of Colorado Anschutz.”

Through the collaboration, the organizations will identify disease-specific research cohorts from Duke University's biobanks and support molecular sequencing of tissue and blood biospecimens. The collaboration also establishes a framework for the responsible use of these datasets in research and commercial applications, including data licensing and AI model development, subject to the terms of the agreement and applicable data privacy and security requirements.

“Molecular data generated from cutting-edge technology together with clinical information and AI modeling has great potential for helping us better understand how diseases develop and respond to treatment,” said Svati H. Shah, M.D., Associate Dean for Translational Research at Duke University School of Medicine and Director of the Duke Center for Precision Health. “This collaboration provides an opportunity to study biospecimens alongside linked clinical information, which supports deeper research that could speed discovery, while maintaining our responsibility to steward these resources carefully.”

“Biobanked tissue and blood collections, paired with years of clinical follow up, can help us train on how disease actually develops and responds to treatment in people. For our pharma and diagnostics partners, that means testing targets, biomarkers and patient selection against real human outcomes before a program ever reaches the clinic,” said Raphael Potter, Co-Founder and Chief Business Officer of Network Bio.

The collaboration reflects a growing emphasis across the life sciences industry on developing large-scale, multimodal datasets that combine molecular and clinical information to improve the predictive capabilities of AI and machine learning models. By generating genomic datasets grounded in human disease biology, Network Bio aims to support a more data-driven approach to therapeutic discovery, development and early disease detection.

About Network Bio

Network Bio is a biotechnology company building a patient world model of human disease that learns how disease develops and responds to treatment across patients, from tissue, blood and clinical data. Through collaborations with leading U.S. academic medical centers, the company turns biobanked tissue and blood linked to patient outcomes into models designed to generalize across diseases. Applications include precision diagnostics, biomarker discovery and drug development. Network Bio is based in Palo Alto. For more information, visit www.network.bio.

Fonte: Business Wire