Critical Assessment of Methods for Predicting the 3D Structure of Proteins and Protein Complexes

Advances in a scientific discipline are often measured by small, incremental steps. In this review, we report on two intertwined disciplines in the protein structure prediction field, modeling of single chains and modeling of complexes, that have over decades emulated this pattern, as monitored by the community-wide blind prediction experiments CASP and CAPRI. However, over the past few years, dramatic advances were observed for the accurate prediction of single protein chains, driven by a surge of deep learning methodologies entering the prediction field. We review the main scientific developments that enabled these recent breakthroughs and feature the important role of blind prediction experiments in building up and nurturing the structure prediction field. We discuss how the new wave of artificial intelligence-based methods is impacting the fields of computational and experimental structural biology and highlight areas in which deep learning methods are likely to lead to future developments, provided that major challenges are overcome.

Automated summary

This article discusses two intertwined disciplines in the protein structure prediction field: single chain modeling and complex modeling. The scientific developments in this field have been measured by small incremental steps, as observed through community-wide blind prediction experiments. However, recent dramatic advances in accurately predicting single protein chains have been made with the emergence of deep learning methodologies. The article reviews these breakthroughs and highlights the important role of blind prediction experiments in nurturing the structure prediction field. It also discusses how the new wave of artificial intelligence-based methods is impacting computational and experimental structural biology, and identifies future developments that deep learning methods are likely to lead to, provided that major challenges are overcome.