platoseedplatoseed
Generative AI for protein design
Diffuse is building generative AI for protein design. Our mission is to build AI systems that engineer new and useful proteins with unprecedented control and accuracy. Our team has been behind breakthroughs in AI protein design for the past 7 years, including the first experimental validation of AI-generated proteins and diffusion models for protein structure and sequence.
Diffuse Bio provides generative AI tools for protein design, enabling rapid creation and optimization of protein binders with high control and accuracy. Their platform emphasizes fast in-lab results translated to laptop-scale workflows for protein therapeutics development.
Diffuse Bio offers AI-driven design tools for proteins, including the ability to design novel protein binders in minutes on a laptop, and to perform end-to-end design workflows using DiffuseSandbox and RamaX Opt for accelerated affinity maturation and thermostability assessment. The platform highlights modules for design, optimization, and scaled-up binder development, with public case studies and research publications supporting its capabilities.
Who it’s for: Biotech and pharmaceutical researchers, protein engineers, and organizations pursuing protein therapeutics and binder optimization.
mentions of case studies, research publications, and product launches indicate active R&D and external communications; no explicit funding or hiring data provided.
I’m a bioengineer / computer scientist who’s worked on problems at the intersection of machine learning and biology. For the past several years, I’ve been working on re-envisioning the computational protein design toolkit with AI. Some highlights are the first crystal structures of AI-designed proteins and diffusion models for protein structure generation.
At Diffuse, we build new therapeutics, vaccines, and enzymes with AI!
Diffuse Bio develops AI-driven computational design tools for proteins, vaccines, and enzymes, enabling de novo structure generation, loop and sequence redesign, and binder design. In this launch, they announce beta testing for their first-generation protein design software and scaling up to tackle protein engineering tasks via AI methods.
From the original launch (Mar 2023) — may be outdated.
Creating new protein-based drugs at scale
We're training the next generation of protein foundation models.
