SandboxAQ has integrated its Large Quantitative Models (LQMs) with Anthropic's Claude, making advanced drug discovery and materials science accessible through natural language prompts instead of requiring specialized coding expertise. The integration, announced in May 2026, removes a critical barrier between researchers' scientific questions and computational answers, potentially accelerating discovery across pharmaceuticals, catalysts, and energy materials.

What Are Large Quantitative Models and Why Do They Matter?

Large Quantitative Models are AI systems trained on real-world laboratory data and scientific equations, designed specifically for the quantitative economy, a sector worth more than $50 trillion spanning biopharma, financial services, energy, and advanced materials. Unlike general-purpose language models, LQMs are built from the ground up using physics-grounded training data generated through high-fidelity simulations, including quantum chemistry calculations, molecular dynamics, and microkinetics. This means they understand the actual chemistry and physics governing drug interactions and material properties, not just statistical patterns in text.

Until now, accessing these models required specialized scientists capable of writing complex code and setting up sophisticated computational infrastructure. The Claude integration changes that equation entirely. Researchers can now ask questions in plain English and receive answers grounded in frontier physics and chemistry, without writing a single line of code.

How Does the Claude Integration Work for Drug Discovery?

The integration leverages Claude as a natural language interface to SandboxAQ's quantitative models through Anthropic's Model Context Protocol (MCP), a technical framework that connects large language models to specialized tools. Currently available is AQCat Adsorption Spin, a model that calculates adsorption energy, a measure of how strongly molecules bind to a catalyst surface. This is the most critical first step in catalyst discovery, allowing researchers to rapidly identify and prioritize the most promising candidates before committing costly modeling and laboratory resources to full-scale evaluation.

The impact is substantial. Catalysts underpin more than 90% of all commercially produced chemical products, and the ability to screen candidates at unprecedented speed and accuracy has direct implications across green hydrogen, sustainable aviation fuel, fertilizer production, plastics recycling, and more.

What Drug Discovery Models Are Coming Soon?

SandboxAQ's roadmap includes a suite of pharmaceutical-focused models that will soon be accessible through the same conversational interface. These models represent a significant expansion of the platform's capabilities for drug development teams:

• AQPotency: Allows researchers to identify and prioritize the most promising drug candidates computationally, screening thousands of options at a fraction of the time and cost of traditional methods.
• AQCell: Enables simulation of how living cells respond to drug candidates across thousands of compounds, predicting whether a drug activates the right biological pathway and flagging potential liver toxicity.
• Physics-Grounded Infrastructure: All drug discovery models are built on the same physics-grounded infrastructure that powers AQCat Adsorption Spin, meaning any researcher can run workflows that previously required weeks of computational setup in just hours.

According to Nadia Harhen, General Manager of AI Simulation at SandboxAQ, this democratization of access is transformative. "As we bring these capabilities to Claude, users in pharma and biotech will be able to run workflows that previously required weeks of computational setup in hours," Harhen stated. "Our drug discovery models are built on the same physics-grounded infrastructure that powers AQCat Adsorption Spin today. This means any researcher, regardless of their technical background, can find a faster path from scientific question to answer".

"Now, researchers can access frontier physics-based models directly inside the AI tools they already use, with no additional infrastructure, code or barriers. Our LQMs bring the rigor of first-principles quantum chemistry to a conversational interface, and that changes how fast a user can move from question to answer across chemistry, materials science, and drug development," said Jack D. Hidary, CEO of SandboxAQ.

Jack D. Hidary, CEO of SandboxAQ

How to Access SandboxAQ's Models Through Claude

• Waitlist Registration: Users interested in accessing SandboxAQ's LQMs through Claude can join the waitlist at the company's registration page to gain early access to the integrated platform.
• No Technical Setup Required: Unlike traditional computational chemistry workflows, researchers need no additional infrastructure, specialized software installations, or coding knowledge to begin using the models.
• Immediate Practical Application: Researchers can immediately begin screening drug candidates, calculating molecular binding properties, and simulating cellular responses using natural language queries within Claude.
• Broader Model Rollout: Additional drug discovery models and integrations are coming soon, expanding the range of research questions that can be addressed through the conversational interface.

Why Are Industry Leaders Excited About This Shift?

The integration has garnered support from prominent figures in computational chemistry and pharmaceutical research. Partha P. Mukherjee, Professor and Director of the Center for Advances in Resilient Energy Storage at Purdue University, emphasized the significance of removing barriers between intuition and computation. "SandboxAQ's integration with Claude removes one of the key barriers between a researcher's scientific intuition and rigorous physics-grounded computation, accelerating discovery across energy materials and beyond," Mukherjee noted.

"Bringing quantitative AI into the tools pharma teams already use is the kind of shift that can fundamentally accelerate the pace of drug discovery," said Robin Röhm, CEO and Co-Founder of Apheris.

Robin Röhm, CEO and Co-Founder of Apheris

The broader significance lies in democratizing access to computational power that was previously available only to large pharmaceutical companies with dedicated computational chemistry teams. By embedding these models into Claude, a widely used AI assistant, SandboxAQ is making frontier computational science accessible to biotech startups, academic research groups, and smaller pharmaceutical companies that lack the infrastructure and expertise to build these tools independently.

SandboxAQ's LQMs have already demonstrated real-world impact, with active programs underway at major pharmaceutical companies and demonstrated advances in battery chemistry, catalysts, and alloys. Several frontier models, including AQAffinity and AQCat, were developed in collaboration with NVIDIA, a leading artificial intelligence and computing company. The company's platform also powers AI-native cybersecurity, medical research, and navigation systems, with financial services and risk modeling modules launching soon.

This integration represents a significant shift in how computational science is conducted. Rather than requiring researchers to learn specialized programming languages and maintain expensive computational infrastructure, the future of drug discovery and materials science increasingly involves asking questions in natural language and receiving answers grounded in rigorous physics and chemistry. For pharmaceutical research teams, that shift could mean months of accelerated timelines and significantly reduced computational costs.