SandboxAQ brings its drug discovery models to Claude — no PhD in computing required

Drug discovery is notoriously expensive and time-consuming, with most candidate molecules failing to reach viability. While AI startups have aimed to streamline this process, SandboxAQ believes the primary bottleneck isn't the AI models themselves, but rather the complexity of their interfaces. Most existing AI tools require users to possess significant technical sophistication.

To address this, SandboxAQ has partnered with Anthropic to embed its scientific AI models directly into Claude. This integration provides powerful drug discovery and materials science capabilities through a user-friendly conversational interface, eliminating the need for specialized computing infrastructure.

SandboxAQ, an Alphabet spinout founded five years ago, is chaired by former Google CEO Eric Schmidt and has raised over $950 million. The company specializes in large quantitative models (LQMs) that are "physics-grounded." Unlike models based on text patterns, LQMs perform quantum chemistry calculations and simulate molecular dynamics and microkinetics, offering crucial insights into how molecules behave before laboratory testing.

These LQMs are trained on real-world lab data and scientific equations, designed for the $50+ trillion quantitative economy encompassing biopharma, financial services, energy, and advanced materials. This approach distinguishes SandboxAQ from companies focusing solely on model development, as it prioritizes accessibility and broader application of AI in scientific research.