VeriSIM Life Formalizes FDA Collaboration to Advance Mechanistic AI for Translational Drug Development
核心洞察
VeriSIM Life (搜索) has entered into a Material Transfer Agreement with the FDA's National Center for Toxicological Research to advance mechanistically grounded AI for drug development.
The BIOiSIM platform combines mechanistic quantitative models with machine learning, achieving nearly 90% accuracy in predicting clinical trial success across validated studies.
The collaboration builds on prior peer-reviewed work, including a 2025 co-authored publication demonstrating BIOiSIM's ability to predict drug-induced liver injury (搜索).
VeriSIM Life (搜索) has formalized a research collaboration with the U.S. Food and Drug Administration's National Center for Toxicological Research (FDA/NCTR), establishing a framework for ongoing scientific collaboration that reinforces the rigor and translational relevance of the company's BIOiSIM platform. The Material Transfer Agreement (MTA), announced June 25, 2026, builds on prior peer-reviewed work, including a 2025 co-authored publication demonstrating BIOiSIM's ability to predict drug-induced liver injury (搜索).
"BIOiSIM was built on the belief that AI should do more than generate predictions. It should explain the biology behind them and provide evidence scientists can trust," said Jo Varshney, DVM/PhD, founder and CEO of VeriSIM Life (搜索). "Our collaboration with FDA/NCTR advances that vision by strengthening the scientific foundation for more predictive, transparent, and human-relevant drug development."
A Hybrid Approach to Translational Prediction
The BIOiSIM platform integrates mechanistic quantitative models and machine learning into a unified translational framework spanning drug discovery, preclinical development, clinical optimization, and regulatory submission support. Unlike pointed single solutions that focus only on chemistry, clinical trials, or patient populations in isolation, BIOiSIM connects these interconnected domains to provide meaningful, real-world predictions about the challenges a molecule will face during development.
"Predictions are made using hybrid AI models, which combine virtual animal-to-human drug simulations with machine learning," Varshney explained. "The system models how a drug behaves and explains the underlying biological and physical reasons for that behavior. The approach blends the cause-and-effect understanding of algorithms that follow scientific principles with those that can recognize patterns when analyzing vast datasets."
The platform has demonstrated nearly 90% accuracy in predicting clinical trial success across validated retrospective and prospective studies—a striking contrast to the industry-wide statistic that only about one in ten drug candidates entering clinical trials ultimately reaches market approval.
The Translational Index: A Credit-Score-Like Assessment
Central to the BIOiSIM platform is a dynamic risk assessment tool that assigns drug candidates a "credit score," which, much like a person's financial health, dynamically changes based on underlying data—including modifications to chemical structure, dosage, or the targeted disease. This Translational Index is designed to assist drug developers in making better decisions early in the high-risk business of medical research.
"The key challenge facing pharma companies individually and collectively ultimately comes down to translatability," said Varshney. "While the volume of predictions has reached an unprecedented scale, the field has shifted its focus from quantity to quality. Sponsors want predictions they can turn into decisions that hold up in the clinic."
Mechanistic simulations generate biologically grounded features that are integrated with hybrid AI and computational models to improve translational prediction robustness and explainability. The platform transparently identifies gaps in available information—whether in the form of data or domain-specific human expertise—so customers can understand both the confidence level and the boundaries of each prediction.
Synthetic Data and Broad Validation
To enhance translation predictions, VeriSIM Life (搜索) creates its own synthetic data through the BIOiSIM platform, generating mathematical representations of human and animal systems to simulate how drugs interact with the body. This approach helps predict efficacy and toxicity in humans even when input data is limited. The platform has been tested across approximately 72 disease areas and thousands of different targets.
Founded in 2017, VeriSIM Life (搜索) spent its first five years rigorously validating BIOiSIM across disease areas, targets, partner programs, and internal drug development efforts. The company now has about 20 active partnerships with pharmaceutical and co-development partners, as well as a pipeline of its own assets. One of those assets, a small molecule for pulmonary arterial hypertension (搜索), is less than a year shy of entering human trials.
Reducing Reliance on Animal Testing
The collaboration with FDA/NCTR is directly tied to the agency's active transition away from animal testing by prioritizing new approach methodologies, including AI, computational modeling, and organ-on-a-chip technology. VeriSIM Life (搜索) is helping several companies reduce or replace the need for traditional six- to nine-month chronic toxicity studies in monkeys using AI-driven digital twins of both animals and humans.
Varshney, a veterinarian by training, emphasized the importance of human-relevant testing approaches. "You don't have to be a veterinarian to appreciate the differences between horses, monkeys, dogs, and humans," she said, adding that this mindset should extend to the translatability of drug testing across different animal models.
The company envisions a future where 3D organoid systems that are structurally, functionally, and genetically closer to actual human tissues generate data that feeds into AI platforms like BIOiSIM, helping the industry move from trial-and-error development toward a more predictive, human-relevant, and knowledge-driven model of drug translation.