Excelra, a leading global Data & Analytics organization, announced the partnership for its Global Online Structure Activity Relationship Database (GOSTAR) with XtalPi Inc., an AI-based pharmaceutical biotechnology company reinventing the industry’s approach to drug research and development with its Intelligent Digital Drug Discovery and Development platform.
Excelra will provide ADMET datasets in the GOSTAR database to XtalPi Inc. as part of the partnership. GOSTAR’s ADMET data will power XtalPi’s predictive models. The data helps XtalPi with high precision and predictability to confidently tackle clinical failures of new chemical entities. The well-annotated, high-quality ADMET datasets of GOSTAR are built with a proprietary QMS-ISO certified curation process powered by NLP and human intelligence.
GOSTAR provides comprehensive information encompassing over 8 million compounds, manually curated from a variety of sources including patents and journal articles. The database contains over 29 million SAR associated data points. The well-structured relational database can be utilized for diverse applications across various stages of drug discovery and development lifecycle and aids in target validation, hit identification, early lead identification, and optimization.
Min Xu, Senior Scientist, Research Manager, XtalPi Inc., said, “In XtalPi Inc., we develop advanced AI-based algorithms to tackle the challenges in the drug design process. The size and quality of datasets are always a big concern for us to build high-accuracy predictive models. That is why we consider GOSTAR as a unique and precious resource. It has millions of data points covering different compounds’ ADMET properties and is also trustful, structured, and updated. We highly recommend GOSTAR to whoever is involved in the innovation of drug design methodologies.”
Norman Azoulay, Product Leader, Excelra, said, “Artificial Intelligence and Machine Learning is bringing a paradigm shift to drug discovery and development. This partnership will help train XtalPi’s models to accurately predict efficacy and safety parameters and to ultimately increase the success rate of drug design.”