SandboxAQ will make its Large Quantitative Models (LQMs) available through Google Cloud Marketplace, starting with AQCat for materials and catalyst discovery, followed by AQPotency for drug discovery. Researchers can access the models through conversational AI tools they already use, without specialized code or infrastructure.
"Bringing our LQMs to Google Cloud's Marketplace will put the rigor of first-principles science directly into the hands of every researcher, in the tools they already use," Jack D. Hidary, CEO of SandboxAQ, said. "Pairing the reasoning of a frontier model such as Gemini with the quantitative precision of our LQMs is a powerful combination."
What the models do
The LQMs are built on real-world lab data and scientific equations, not just statistical patterns. AQCat, expected in the third quarter, calculates adsorption energy - a measure of how strongly molecules bind to a catalyst surface. That metric helps R&D teams screen materials and catalyst candidates earlier, before committing more resources to modeling and lab work.
AQPotency, also slated for Q3, targets computational drug discovery. It lets researchers assess large numbers of possible binders - molecules that attach to a biological target, like a disease-related protein - and prioritize those most likely to be useful in drug development.
"Bringing SandboxAQ's Large Quantitative Models to GCP Marketplace is one of the ways we are empowering healthcare researchers to accelerate drug discovery and solve one of the most critical gaps in healthcare today," Brian Goldstein, vice president of strategic AI and ISV at Google Cloud, said.
The larger trend
The Google Cloud Marketplace listing follows SandboxAQ's June launch of AQState, a GPCR virtual screening solution accelerated by NVIDIA BioNeMo Agent Toolkit. GPCRs, or G protein-coupled receptors, are a major drug target family. A 2025 review in Nature Reviews Drug Discovery found 516 approved drugs target GPCRs, making up 36% of approved drugs. AQState predicts whether a molecule binds to a receptor and whether it is likely to activate or block it, helping researchers distinguish agonists, antagonists and inverse agonists earlier in drug discovery programs.
SandboxAQ first partnered with Google Cloud in January 2025 with the intention of using the marketplace for its go-to-market. The announcement reflects a growing trend in AI for Science & Research, as large AI and cloud companies push deeper into healthcare and life sciences workflows. Google Cloud has previously introduced MedLM for health industry use cases and released open foundation models for health app developers.
Why this matters for science and research professionals
Researchers in materials science and drug discovery can now access quantitative models that combine first-principles physics with AI reasoning, directly inside their existing chat-based tools. This lowers the barrier to entry for advanced computational screening, allowing teams to test more hypotheses earlier in the R&D pipeline without standing up specialized infrastructure. The integration with Google Cloud Marketplace also signals a shift toward making these models available through familiar enterprise channels, which could speed up adoption across research organizations.
Your membership also unlocks:
