Illuminating protein space with a programmable generative model

By John Ingraham, M. Baranov, Zak Costello, Vincent Frappier, Ahmed Ismail, Shanshan Tie, Wujie Wang, Vincent Xue, Fritz Obermeyer, Andrew Beam and 1 more. 2022

605 citations recorded by the source corpus.

Three billion years of evolution has produced a tremendous diversity of protein molecules^ 1 , but the full potential of proteins is likely to be much greater. Accessing this potential has been challenging for both computation and experiments because the space of possible protein molecules is much larger than the space of those likely to have functions. Here we introduce Chroma, a generative model for proteins and protein complexes that can directly sample novel protein structures and sequences, and that can be conditioned to steer the generative process towards desired properties and functions. To enable this, we introduce a diffusion process that respects the conformational statistics of polymer ensembles, an efficient neural architecture for molecular systems that enables long-range reasoning with sub-quadratic scaling, layers for efficiently synthesizing three-dimensional structures of proteins from predicted inter-residue geometries and a general low-temperature sampling algorithm for diffusion models. Chroma achieves protein design as Bayesian inference under external constraints, which can involve symmetries, substructure, shape, semantics and even natural-language prompts. The experimental characterization of 310 proteins shows that sampling from Chroma results in proteins that are highly expressed, fold and have favourable biophysical properties. The crystal structures of two designed proteins exhibit atomistic agreement with Chroma samples (a backbone root-mean-square deviation of around 1.0 Å). With this unified approach to protein design, we hope to accelerate the programming of protein matter to benefit human health, materials science and synthetic biology. Evolution has produced a range of diverse proteins, and now a generative model called Chroma can expand that set by allowing the user to design new proteins and protein complexes with desired properties and functions.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom (2023, positive): “protein diffusion models are trained unconditionally and incorporate conditional information through forms of guidance (43),(44), we train an explicitly conditional model that learns the distribution of proteins conditioned on biomolecular substructure.”
State-specific protein–ligand complex structure prediction with a multiscale deep generative model (2022, positive): “Several works have demonstrated that deep generative models are capable of producing de novo-designed proteins with experimentally validated functions, including language models for protein sequence design 9,27,28 and diffusion models for protein backbone generation 29–32 .”
SE(3) diffusion model with application to protein backbone generation (2023, methodology): “We compared ourselves with published results from two promising protein backbone diffusion models for protein design: Chroma (Ingraham et al., 2022) and RFdiffusion (Watson et al., 2022).”