Baylor College of Medicine Leads $21M AI-Driven Cardiac Drug Safety Initiative to Reduce Clinical Trial Failures
核心洞察
Baylor College of Medicine will lead cardiac innovation for DATAMAP, a $21 million ARPA-H (搜索) funded project developing AI-driven models to predict drug-induced cardiotoxicity (搜索) and hepatotoxicity (搜索).
The initiative aims to create FDA-qualified in silico organ toxicity models that integrate artificial intelligence with physiology-based mathematical modeling to predict human drug toxicity for small molecules.
Baylor's team will develop state-of-the-art human heart (搜索) slice culture systems using multi-electrode array technology and optical strain analysis to generate critical validation data.
Baylor College of Medicine has been selected to lead cardiac innovation for a groundbreaking $21 million artificial intelligence-driven drug safety project that aims to revolutionize preclinical toxicity assessment and reduce clinical trial failures. The initiative, known as DATAMAP (Digital Acceleration of Toxicity Assessment with Mechanistic and AI-driven Predictions), represents one of the first Advanced Research Projects Agency for Health (ARPA-H (搜索)) contracts awarded to Baylor.
Dr. Tamer Mohamed, associate professor in the Michael E. DeBakey Department of Surgery and director of cardiac regeneration, will serve as principal investigator for Baylor and co-investigator for the national project team. The project is led by Inductive Bio (搜索), an AI drug discovery partner that helps biopharma teams design and optimize higher quality drugs, through ARPA-H (搜索)'s Computational ADME-Tox and Physiology Analysis for Safer Therapeutics (CATALYST) program.
Addressing Critical Clinical Trial Failures
The project's primary goal is to develop validated, FDA-qualified in silico organ toxicity models that integrate artificial intelligence with physiology-based mathematical modeling. These models will predict human drug toxicity for small molecules, with a specific focus on the liver (搜索) and heart (搜索)—organs most often implicated in clinical trial failure due to toxicity.
"Members of Baylor's Department of Surgery will be able to contribute their unique expertise in cardiac tissue modeling. We will lead the development and optimization of state-of-the-art human heart (搜索) slice culture systems to assess drug-induced cardiotoxicity (搜索)," Mohamed said. "By combining advanced cardiac tissue engineering with AI-driven analytics, we aim to set a new standard for predicting drug safety and reducing the risk of adverse cardiac events in clinical trials."
Innovative Cardiac Tissue Modeling Approach
Mohamed's team at Baylor will refine protocols for preparing and maintaining human cardiac slices, integrating multi-electrode array (MEA) technology and optical strain/contractility analysis to capture real-time, high-resolution functional data. This innovative approach will generate critical data for building and validating the DATAMAP cardiac toxicity prediction models.
The advanced cardiac tissue engineering methodology represents a significant advancement in preclinical drug safety assessment, potentially reducing reliance on animal testing while improving the accuracy of toxicity predictions before human trials begin.
Multi-Institutional Collaboration
For DATAMAP, Inductive Bio (搜索) has assembled a multidisciplinary team that includes leaders in AI, drug development, organoid and tissue modeling, and regulatory science from major institutions including Amgen, Cincinnati Children's Hospital Medical Center, and Torch Bio (搜索), alongside Baylor's cardiac expertise.
"This achievement reflects Baylor's commitment to advancing biomedical innovation and patient safety," said Dr. Todd K. Rosengart, professor and DeBakey-Bard Chair of the Michael E. DeBakey Department of Surgery. "We are proud of Dr. Mohamed and his team's leadership in this national effort."
Transforming Drug Development Pipeline
CATALYST aims to revolutionize preclinical drug safety prediction by developing human-based models that accurately estimate toxicity and safety profiles for drug candidates. ARPA-H (搜索)'s investment in DATAMAP will enable the team to build a secure, scalable data repository, generate high-quality multi-system data, and develop advanced AI models to improve the accuracy of preclinical safety assessments.
The project addresses a critical bottleneck in pharmaceutical development, where unexpected toxicity discoveries in clinical trials can result in significant financial losses and delays in bringing potentially life-saving therapies to patients. By providing more accurate preclinical predictions, DATAMAP could accelerate the development of safer therapeutics while reducing the costs associated with late-stage clinical trial failures.