Verseon’s paper, “A Novel Graph Neural Network Approach for Predicting Drug-Target Interactions,” has just been published on IEEE Xplore. This publication follows one of Verseon’s earlier presentations at IEEE FMLDS.
The paper details Verseon’s work extending graph neural network architectures to better capture the topology of knowledge graphs used in drug discovery. In benchmark testing on the widely used ChG-Miner dataset, the approach produced a 41% lower error rate than current state-of-the-art methods.
Accurately predicting how a drug candidate will interact with its intended biological target is a persistent challenge in pharmaceutical development. Improving those predictions can shorten discovery timelines, reduce spending on dead-end candidates that ultimately fail, and improve the safety profile of molecules that advance into clinical testing.
Where to Access the Papers:
To view the paper, go to https://doi.org/10.1109/FMLDS67896.2025.00114.
About Verseon
Verseon International Corporation (www.verseon.com) is a clinical-stage, technology-driven pharmaceutical company transforming the delay, prevention, and treatment of disease. Using its Deep Quantum Modeling + AI platform, Verseon is rolling out a steady stream of life-changing medicines. Each of the company's drug programs features multiple novel candidates with unique therapeutic properties. None of these candidates can be found by other current methods. Verseon's fast-growing pipeline addresses major human diseases in the areas of cardiometabolic disorders and cancers. The company's supporters and advisors include multiple Nobel laureates, former heads of R&D of major pharmaceutical companies, and various key opinion leaders in medicine.