Recent Progress of Protein Tertiary Structure Prediction

Abstract

The prediction of three-dimensional (3D) protein structure from amino acid sequences has stood as a significant challenge in computational and structural bioinformatics for decades. Recently, the widespread integration of artificial intelligence (AI) algorithms has substantially expedited advancements in protein structure prediction, yielding numerous significant milestones. In particular, the end-to-end deep learning method AlphaFold2 has facilitated the rise of structure prediction performance to new heights, regularly competitive with experimental structures in the 14th Critical Assessment of Protein Structure Prediction (CASP14). To provide a comprehensive understanding and guide future research in the field of protein structure prediction for researchers, this review describes various methodologies, assessments, and databases in protein structure prediction, including traditionally used protein structure prediction methods, such as template-based modeling (TBM) and template-free modeling (FM) approaches; recently developed deep learning-based methods, such as contact/distance-guided methods, end-to-end folding methods, and protein language model (PLM)-based methods; multi-domain protein structure prediction methods; the CASP experiments and related assessments; and the recently released AlphaFold Protein Structure Database (AlphaFold DB). We discuss their advantages, disadvantages, and application scopes, aiming to provide researchers with insights through which to understand the limitations, contexts, and effective selections of protein structure prediction methods in protein-related fields.

Editorial: Functions, working mechanisms, and regulation of rotary ATPases and Ductin proteins

“…Structural biology of membrane proteins is rapidly catching up thanks to improved experimental approaches (for example, cryo-EM) (e.g., Pinke et al, 2020 ; Gerle et al, 2022 ; Yamamori and Tomii, 2022 ) and structure predictions enhanced with artificial intelligence ( Versini et al, 2023 ; Wuyun et al, 2024 ). Structure models with atomic detail are already available, also for the F o , V o and A o domains.…”

A Reversible Spherical Geometric Conversion of Protein Backbone Structure Coordinate Matrix to Three Independent Vectors of ρ, θ and φ

“…This process is crucial for understanding protein function, interactions, and designing novel therapeutics [1][2][3][4][5][6][7][8]. By definition, accurate prediction of protein structure from its amino acid sequence is a formidable challenge in computational structural biology, with profound implications for understanding biological function and designing novel therapeutics [9][10][11][12]. Over the past decade, numerous computational methods have been developed to tackle this problem, ranging from physics-based simulations to machine learning approaches.…”