San Francisco, CA - April 3, 2024 – VeriSIM Life, the leading AI-enabled R&D de-risker for breakthrough drug design and development, announced today the availability of AtlasGEN™ Novel Drug Designer. AtlasGEN is the first and only platform that combines generative chemical discovery with biological validation to dramatically compress drug candidate selection and reduce costly experimental research, while increasing the likelihood of clinical success.
Unlike other generative AI drug discovery tools that design compounds based on chemical properties, AtlasGEN also considers biological translation—how well the drugs work in the human body and if they're safe. Integrating biological translation into drug design is critical because novel drug compounds generated by AI are unfeasible for clinical use when the AI is unconstrained by biological parameters. Thousands of prospective compound hits may be identified, resulting in significant experimental validation to determine clinical viability, at great expense to drug developers. Computationally pre-validating novel compound hits based on biological translation greatly reduces experimental burden and increases the likelihood of drug program success.
“At a time when the drug industry has become less effective developing new approved drugs, drug costs have continued to increase while drug shortages negatively impact patients in need of new alternatives,” said Dr. Jo Varshney, CEO and Founder of VeriSIM Life. “The sustainability of our healthcare system requires faster and more effective methods to generate new safe and effective drugs, and I’m excited at the prospect of AtlasGEN contributing to meet this critical challenge.”
AtlasGEN Novel Drug Designer is part of the BIOiSIM® platform, a first-in-class decision engine that enables drug discovery and R&D de-risking. BIOiSIM features Translational Index™, a unique combination of metrics representing a compound’s likely therapeutic effect, akin to a credit score. The Translational Index provides explainability into the platform's artificial intelligence analysis. This not only helps create innovative compounds but also explains why they're predicted to be potent and safe, making its AI-designed drugs more transparent.
AtlasGEN comes at a time when more than 300 million patients lack treatments for unmet diseases, and 10 million will die this year from cancer alone, but current methods of finding new drugs have become less successful. In fact, the number of registered new drug candidates has increased 72%, but the relative proportion of approved drugs from big pharma has fallen from 76% to 25%.
“Generative AI has created much excitement in the industry, for good reason,” said Dr. Jascha Blobel, CBO at Golden Gate Biotech. “But AI by itself cannot design drugs for real patients. I strongly believe the path forward for computational drug design will be built on the integration of generative AI with bio knowledge systems that can govern and guide discovery. AtlasGEN has the true potential to transform the pharmaceutical industry.”
About VeriSIM Life
VeriSIM Life has developed a sophisticated computational platform that leverages advanced AI and ML techniques to improve drug discovery and development by significantly reducing the time and money it takes to bring a drug to market. BIOiSIM® is a first-in-class 'virtual drug development engine' that offers unprecedented value for the drug development industry by narrowing down the number of drug compounds that offer anticipated value for the treatment or cure of specific illnesses or diseases. The platform predicts the likelihood of a candidate’s success in clinical trials early in the preclinical stage, while reducing unnecessary experimentation and better informing key program decisions. For more information, visit www.verisimlife.com.
AtlasGEN Novel Drug Designer efficiently identifies new molecules based on favorable chemical properties and simultaneously evaluates them for clinical safety and effectiveness based on biology using VeriSIM Life’s groundbreaking Translational Index™ technology.
Iterative ranking of target engaging hits by their Translational Index values reduces the time and cost associated with other computational hit discovery approaches, while compressing the hit-to-lead refinement and optimization process by pre-validating hits for translatability. This unique integration dramatically reduces the number of compounds to evaluate in subsequent experimental research.
The ability to generate target engaging compound hits depends largely on the size of the molecular search library. The AtlasGEN search space is supported by more than 1 trillion compounds. Generative AI and deep learning techniques deliver unprecedented discovery capability.
AtlasGEN accurately predicts protein-lygand binding affinity by combining geometric conformer analysis with machine learning based on experimental data 72% more efficiently than molecular docking-based approaches.
.png)
