Skip to main content
B

Boltz

Boltz offers an AI‑driven platform for computational drug discovery that accelerates biomolecular modeling and design of both small molecules and proteins. Its suite of agents—Boltz‑1 for all‑atom co‑folding, Boltz‑2 for ultra‑fast affinity prediction with FEP‑level accuracy, and BoltzGen for universal protein binder design—enables rapid, large‑scale screening and iterative refinement using experimental data, all within a distributed computing environment.

London, United KingdomFounded 2019195K+ followers
Updated 2 months ago

Funding

Funding not disclosed

Funding rounds are not available yet.

Founders

Founder details are not available yet.

Product

Problem

Traditional computational drug discovery relies on slow, resource-intensive simulations and limited chemical space exploration, making it difficult for scientists to rapidly identify and optimize therapeutic candidates.

Solution

Boltz provides an AI-driven platform that accelerates biomolecular modeling and design across small molecules and proteins. Its suite of agents—Boltz-1 for all‑atom co‑folding, Boltz-2 for ultra‑fast affinity prediction, and BoltzGen for universal binder design—enables rapid screening of vast chemical spaces and iterative refinement using experimental feedback. The platform distributes large‑scale computations across a scalable infrastructure, delivering results in hours rather than months while maintaining accuracy comparable to high‑cost free‑energy perturbation methods. Users can define and refine biological targets with AI assistance, run distributed design campaigns, and continuously improve predictions through data integration, all within a single unified environment.

Target Audience

Primary users are computational chemists, molecular biologists, and drug discovery teams in pharmaceutical and biotech companies seeking accelerated AI‑powered design of small molecules and proteins.

Features

  • Boltz-1 open‑source all‑atom co‑folding model with over 1 million downloads
  • Boltz-2 affinity prediction model delivering FEP‑level accuracy 1,000× faster
  • BoltzGen universal binder design engine capable of generating protein binders for arbitrary targets
  • AI‑assisted target definition and iterative refinement workflow that incorporates experimental data
  • Distributed computing framework for large‑scale screening across heterogeneous infrastructure
  • Integrated small‑molecule and protein design agents within a single platform
This profile is AI-generated and may contain inaccuracies.