AlphaFold2-aware protein–DNA binding site prediction using graph transformer

Abstract

Protein–DNA interactions play crucial roles in the biological systems, and identifying protein–DNA binding sites is the first step for mechanistic understanding of various biological activities (such as transcription and repair) and designing novel drugs. How to accurately identify DNA-binding residues from only protein sequence remains a challenging task. Currently, most existing sequence-based methods only consider contextual features of the sequential neighbors, which are limited to capture spatial information. Based on the recent breakthrough in protein structure prediction by AlphaFold2, we propose an accurate predictor, GraphSite, for identifying DNA-binding residues based on the structural models predicted by AlphaFold2. Here, we convert the binding site prediction problem into a graph node classification task and employ a transformer-based variant model to take the protein structural information into account. By leveraging predicted protein structures and graph transformer, GraphSite substantially improves over the latest sequence-based and structure-based methods. The algorithm is further confirmed on the independent test set of 181 proteins, where GraphSite surpasses the state-of-the-art structure-based method by 16.4% in area under the precision-recall curve and 11.2% in Matthews correlation coefficient, respectively. We provide the datasets, the predicted structures and the source codes along with the pre-trained models of GraphSite at https://github.com/biomed-AI/GraphSite. The GraphSite web server is freely available at https://biomed.nscc-gz.cn/apps/GraphSite.

How good are AlphaFold models for docking-based virtual screening?

“…Even the PDBsum database, which contains experimentally determined structures, has incorporated AF predictions (Laskowski and Thornton, 2022). Furthermore, developments implementing AF model predictions are emerging at a fast pace (Akdel et al, 2021;Jones and Thornton, 2022), including coupling AlphaFold with cryogenic electron microscopy maps for structure determination (Gupta et al, 2021), molecular replacement (McCoy et al, 2022Pereira et al, 2021), NMR structural refinements (Fowler and Williamson, 2022), prediction of protein-DNA binding sites (Yuan et al, 2022), protein design (Jendrusch et al, 2021;Moffat et al, 2021), and the prediction of protein-protein interactions (Bryant et al, 2022), among others.…”

RGN: Residue-Based Graph Attention and Convolutional Network for Protein–Protein Interaction Site Prediction

“…Recently, with the unbelievable accuracy of AlphaFold2 in protein structure prediction tasks, more protein structure information is expected to be obtained, which is very helpful for protein-related problems. For example, GraphSite is proposed to identify DNA-binding residues based on the structural models predicted by AlphaFold2. The next work should resolve previously unbreakable problems due to unobtainable structures.…”

Mass Spectrometry for Assessing Protein–Nucleic Acid Interactions

“…The contributions of these two readout mechanisms vary across DNA-binding protein families. Based on the current knowledge about the mechanisms of protein–DNA interactions, many computational methods have been developed to predict protein–DNA binding sites through sequence- or structure-based prediction. − …”