Large Quantitative Models

SandboxAQ generates proprietary data using physics-based methods, and trains Large Quantitative Models (LQMs) on that data, leading to new insights in areas, such as life sciences, energy, chemicals, and financial services. While Large Language Models (LLMs) have recently captured widespread attention, the next wave of AI — LQMs — promises an even greater impact. 

Biopharma

  • Accelerate drug discovery with faster, more accurate predictions for lead generation and hitting targets. 
  • Generative AI-based output of new drugs optimized for multiple objectives including synthesizability.
  • Causal reasoning over multi-omics and literature-omics data to model biology and address scientific hypotheses directly.

New Materials

  • Develop new materials for cars, planes and construction. 
  • Deliver increased efficiency, affordability, and sustainability.
  • Create new compounds, including innovative battery chemistries.

AQBioSim – Accelerating drug discovery from molecule to medicine

Our AQBioSim technology stack allows us to accurately predict the behavior of molecules, to generate new molecular structures with desired properties, and to combine these predictions into biologically-relevant insights. It includes AQ-FEP, the fastest available free energy perturbation solution, able to deliver unprecedented accuracy in affinity prediction even to the hit finding stage of drug discovery with no need for congeneric reference data. 

LQM models trained on our physics-based technology go on to produce entirely new molecules from scratch with desired sets of properties. By combining our molecular simulation insights with biological pathway analysis inferred from literature, simulated, and omics data streams, we are able to connect the biological to the molecular scale, making predictions about target identification, toxicity, and qualitative disease mode of action (MOA). 
AQBioSim - Accelerating drug discovery from molecule to medicine

AQChemSim Large Quantitative Models for Chemicals & Materials

Designing and manufacturing new materials and chemicals has traditionally been slow, expensive, and challenging. AI can revolutionize discovery by creating novel molecules in seconds, but it relies on high-quality data, which is scarce. SandboxAQ addresses this through Large Quantitative Models, generating its own training data in silico and guiding AI with physics. This improves speed and accuracy, bringing products to market faster while reducing cost.

The AQ Difference

SandboxAQ has built a global team with some of the world’s foremost experts in AQ, including physicists, biologists, computational and medicinal chemists.  We are working with global enterprises and government organizations to deliver practical solutions to the market today. Our expertise and deep ties with quantum leaders in academia, industry and the government make SandboxAQ uniquely qualified to develop unmatched AI simulation applications.

Our Scientific Advisory Board

Current and former attributions

  • Dr. Steven Deitcher, CEO, Bespoke Biotherapeutics
  • Dr. Nikhil Gupta, Professor of Mechanical Engineering, New York University
  • Dr. Samir N Khleif, Immunologist, Oncologist, Drug Discovery, NIH, Georgetown, Georgiamune
  • Dr. Geoff Ling, CEO, OnDemand Pharmaceuticals, Professor of Neurology, Johns Hopkins, DARPA Biotech
  • Dr. Chris Marianetti, Professor of Materials Science, Applied Physics, and Applied Mathematics, Columbia University
  • Dr. Dane Morgan, Professor of Materials Science and Engineering, University of Wisconsin
  • Dr. Adrian Roitberg, Professor of Chemistry, University of Florida
  • Dr. Mark Smith, PhD - Head of Medicinal Chemistry, Stanford, Sarafan ChEM-H, Roche
  • ‍Dr. Patricia Weber, PhD - SBDD expert
  • Dr. Eva Zurek, Professor of Chemistry, University of Buffalo

Resources