SandboxAQ Launches AQPotency for Drug-Target Screening
aiinsider ·
SandboxAQ announced the general availability of AQPotency, a Large Quantitative Model designed to predict drug-target activity and prioritize candidate molecules. The model can rank molecule-target pairs quickly without requiring a solved 3D structure of the target, and it provides confidence information with each prediction. It runs on ordinary computing hardware and costs as little as $1 per 1,000 comparisons, allowing teams to screen large molecule libraries before lab testing. AQPotency can also work in reverse, scanning a molecule against a broad protein panel to identify potential targets. The tool is available through Claude via Model Context Protocol and SandboxAQ's website, with Google Cloud Marketplace availability expected later. According to SandboxAQ, the model has already been used in eight customer programs with experimentally validated results. Customer quotes highlight applications in Parkinson's disease research and work on difficult membrane targets.
aiinsider