Boltz PBC Enhances Drug Discovery Models with Excelra’s GOSTAR™
News related to:Boltz PBC · 1 min read
HYDERABAD, India and CAMBRIDGE, Mass., Nov. 10, 2026 /CourierPR/ -- Boltz PBC, an applied AI research lab and public benefit corporation, has partnered with Excelra to enhance its AI drug discovery models. The partnership leverages Excelra's GOSTAR™ database, which provides a curated, ISO 9001-certified view of over 11 million small molecules and their biological properties. This extensive dataset powers Boltz's ADMET (absorption, distribution, metabolism, excretion) models, which act as an early triage layer in the drug discovery process.
Boltz's ADMET models are trained on curated ADME data from GOSTAR™, enabling the company to filter out unfavorable compounds before purchase or synthesis. In a recent technical report, Boltz prospectively tested ten challenging targets, most of which were absent from its affinity training data. The company confirmed binders or active compounds for six of these targets, using only 28 to 96 compounds per target. This approach contrasts sharply with conventional high-throughput screens, which often require thousands to millions of compounds and hit rates below 0.15%.
Gabriele Corso, Co-founder and CEO of Boltz PBC, highlighted the importance of GOSTAR™ in the company's modeling work.
Excelra's CEO, Anandbir Brar, expressed pride in supporting Boltz.
The GOSTAR™ database offers a comprehensive view of small molecules and their biological properties, making it a valuable resource for Boltz's ADMET models. The models have demonstrated the ability to match or exceed the leading open-source ADMET package, particularly in solubility and permeability. This partnership underscores the growing importance of AI in drug discovery, allowing for more efficient and effective screening processes.
Boltz's vision is to make biology programmable and accelerate discovery by keeping frontier capabilities broadly accessible. The company's work with Excelra represents a significant step toward achieving this goal, leveraging advanced AI and extensive data sets to streamline the drug discovery process.