On-premises AI drug discovery HPC for NVIDIA BioNeMo

basic information

【Recommended Hardware Configuration Example】 MSI XpertStation WS300 (NVIDIA DGX Station Architecture) ■Processor: NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip ■GPU: NVIDIA Blackwell Ultra GPU ■Memory: Up to 748GB Coherent Memory ■Network: 400GbE compatible ■Form Factor: Tower Workstation 【Expected Software Environment】 - NVIDIA BioNeMo related components - AI inference environment using NVIDIA NIM - Chemoinformatics tools such as RDKit - Molecular generation AI, machine learning, and deep learning models *The required GPU performance, OS, containers, and licensing conditions vary depending on the models and components used. The implementation configuration will be proposed individually.

Price range

Delivery Time

Applications/Examples of results

【Pharmaceuticals and Drug Discovery Research】 Utilized for the exploration of new lead compounds, optimization of candidate molecules, and evaluation of interactions with target proteins. Supports drug discovery research by combining generative AI for molecular structure proposals and computational evaluations. 【Chemistry and Functional Materials Development】 Used for the exploration of candidates such as new organic molecules, additives, and functional materials, as well as property predictions. Aims to enhance the efficiency of material design by combining molecular simulations and AI. 【Universities and Research Institutions】 Supports the development of molecular foundation models, machine learning of compound data, QSAR analysis, and integrated research of generative AI and quantum chemistry calculations. 【On-Premises AI Research Infrastructure】 Can be utilized as a computational infrastructure for managing highly confidential research data in an internal environment, enabling AI model training, inference, fine-tuning, and large-scale molecular generation.