Computational protein design with evolutionary-based and physics-inspired modeling: current and future synergies

Abstract

Computational protein design facilitates discovery of novel proteins with prescribed structure and functionality. Exciting designs were recently reported using novel data-driven methodologies that can be roughly divided into two categories: evolutionary-based and physics-inspired approaches. The former infer characteristic sequence features shared by sets of evolutionary-related proteins, such as conserved or coevolving positions, and recombine them to generate candidates with similar structure and function. The latter estimate key biochemical properties such as structure free energy, conformational entropy or binding affinities using machine learning surrogates, and optimize them to yield improved designs. Here, we review recent progress along both tracks, discuss their strengths and weaknesses, and highlight opportunities for synergistic approaches.

References in corpus (9)

• Identification of direct residue contacts in protein-protein interaction by message passing
• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
• Learning from Protein Structure with Geometric Vector Perceptrons
• Protein sequence design with deep generative models
• Efficient generative modeling of protein sequences using simple autoregressive models
• Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models
• Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
• Equivariant Graph Neural Networks for 3D Macromolecular Structure
• AlphaDesign: A graph protein design method and benchmark on AlphaFoldDB

Cited by in corpus (4)

• Is novelty predictable?
• Interpretable machine learning of amino acid patterns in proteins: a statistical ensemble approach
• Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
• Functional bottlenecks can emerge from non-epistatic underlying traits