SandboxAQ Advances AI Research with NVIDIA DGX Collaboration
SandboxAQ has announced a collaboration with NVIDIA to drive faster innovation across industries. The company is leveraging the power of NVIDIA DGX to build advanced AI models that support breakthroughs in biopharma, chemicals, materials, finance, cybersecurity, navigation, and medical imaging.
As a member of the NVIDIA Inception program, SandboxAQ is developing a next-generation Large Quantitative Model (LQM) platform. Built on NVIDIA DGX, this platform is designed to solve complex scientific and business problems with more speed, scale, and precision.
With this collaboration, SandboxAQ is improving customer outcomes across several areas.
First, drug, chemical, and materials development is becoming faster. Using NVIDIA DGX, SandboxAQ can reduce discovery cycles from years to weeks. This is done through simulations that replace slow lab experiments, helping teams test and validate new ideas quickly.
Second, the partnership enables the creation of high-quality scientific datasets. By combining chemical and biological simulations, SandboxAQ can detect interactions that were previously hard to identify. These datasets improve model accuracy and reduce false positives.
Third, a new AI Chemist powered by LQMs and NVIDIA DGX is transforming how discoveries are made. This tool can explore millions of chemical pathways automatically, allowing researchers to find new molecules and optimize compounds more efficiently.
The collaboration builds on earlier success. In 2024, the companies achieved an 80x acceleration in quantum chemistry calculations using CUDA-accelerated DMRG. In 2025, they published research showing orbital optimization on a system with 82 electrons and 82 orbitals—double the size of previous simulations.
This joint effort has broad impact. In healthcare, SandboxAQ helps pharma companies speed up preclinical testing. In materials science, it supports the development of sustainable processes and energy storage. In cybersecurity, it enables better modeling and prediction.
The core advantage lies in SandboxAQ's LQMs. These AI models reflect the laws of science and economics. They provide deterministic and reliable outputs, unlike general-purpose AI models. This makes them ideal for high-stakes environments.
According to Jack Hidary, CEO of SandboxAQ, the collaboration gives customers a clear advantage. 'By building on NVIDIA DGX, we help our customers innovate faster and lead with confidence,' he said.
Alexis Bjorlin, Vice President of NVIDIA DGX Cloud, added, 'SandboxAQ is setting new standards in AI-native science. With NVIDIA DGX, they can deliver performance at scale and solve real-world problems.'
This partnership highlights how advanced AI and high-performance computing are reshaping R&D. With NVIDIA DGX, SandboxAQ is unlocking new levels of discovery and impact across industries.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Tahawul Tech
2 days ago
- Tahawul Tech
drug discovery Archives
The synthetic data, which SandboxAQ is releasing publicly, can be used to train AI models that can predict whether a new drug molecule is likely to stick to the protein researchers are targeting.
Tahawul Tech
2 days ago
- Tahawul Tech
data creation Archives
The synthetic data, which SandboxAQ is releasing publicly, can be used to train AI models that can predict whether a new drug molecule is likely to stick to the protein researchers are targeting.
Tahawul Tech
2 days ago
- Tahawul Tech
SandboxAQ improves drug discovery with data creation
SandboxAQ, an artificial intelligence startup, recently released a wealth of data in hopes it will speed up the discovery of new medical treatments. The goal is to help scientists predict whether a drug will bind to its target in the human body. But while the data is backed up by real-world scientific experiments, it did not come from a lab. Instead, SandboxAQ, which has raised nearly $1 billion in venture capital, generated the data using Nvidia's chips and will feed it back into AI models that it hopes scientists can use to rapidly predict whether a small-molecule pharmaceutical will bind to the protein that researchers are targeting, a key question that must be answered before a drug candidate can move forward. For example, if a drug is meant to inhibit a biological process like the progression of a disease, scientists can use the tool to predict whether the drug molecule is likely to bind to the proteins involved in that process. The approach is an emerging field that combines traditional scientific computing techniques with advancements in AI. In many fields, scientists have long had equations that can precisely predict how atoms combine into molecules. But even for relatively small three-dimensional pharmaceutical molecules, the potential combinations become far too vast to calculate manually, even with today's fastest computers. So SandboxAQ's approach was to use existing experimental data to calculate about 5.2 million new, 'synthetic' three-dimensional molecules – molecules that haven't been observed in the real world, but were calculated with equations based on real-world data. That synthetic data, which SandboxAQ is releasing publicly, can be used to train AI models that can predict whether a new drug molecule is likely to stick to the protein researchers are targeting in a fraction of the time it would take to calculate it manually, while retaining accuracy. SandboxAQ will charge money for its own AI models developed with the data, which it hopes will get results that rival running lab experiments, but virtually. 'This is a long-standing problem in biology that we've all, as an industry, been trying to solve for', said Nadia Harhen, general manager of AI simulation at SandboxAQ. 'All of these computationally generated structures are tagged to a ground-truth experimental data, and so when you pick this data set and you train models, you can actually use the synthetic data in a way that's never been done before'. Source: Reuters Image Credit: Stock Image
