High-Throughput Screening (HiTS) Database

The SMDC manages its small-molecule screening and follow-up data using a secure, high-performance MySQL database hosted on a Linux server with redundant storage and nightly backups. Data analysis and visualization are supported through integration with Biovia Pipeline Pilot. The SMDC’s custom-built web application, HiTS, provides authorized users with a password-protected and encrypted interface to query, visualize, and share chemical and biological data from any research location. HiTS integrates seamlessly with existing computational tools to enable efficient data exploration and collaboration. We are currently building HiTS 2.0 so stay tuned for our new rollout! In addition, the SMDC maintains a long-standing data management program using the Collaborative Drug Discovery (CDD) platform to support secure, web-based data sharing across research teams.

Incorporating AI into your research

AI-driven workflows are becoming an essential part of drug discovery, helping researchers save time and cost while exploring chemical space more efficiently. At the SMDC, we are building artificial intelligence and machine learning to allow these tools to support every stage of small-molecule research, from library design and virtual screening to generative molecular design and compound optimization. Our goal is to use data-driven approaches to design virtual libraries of compounds that are easy to synthesize and then predict their potency, selectivity, and safety with machine learning models. Our AI-based design platform also suggests new molecular structures based on desired properties, helping us identify promising candidates faster. By running much of the design–make–test–analyze process in silico before moving to experimental validation, we aim to accelerate the path from idea to discovery. Strong collaboration between our computational and experimental teams, supported by careful data management, ensures these tools work together to enhance and speed up drug discovery.