EISA-Score: Element Interactive Surface Area Score for Protein–Ligand Binding Affinity Prediction

Abstract

Molecular surface representations have been advertised as a great tool to study protein structure and functions, including protein–ligand binding affinity modeling. However, the conventional surface-area-based methods fail to deliver a competitive performance on the energy scoring tasks. The main reason is the lack of crucial physical and chemical interactions encoded in the molecular surface generations. We present novel molecular surface representations embedded in different scales of the element interactive manifolds featuring the dramatically dimensional reduction and accurately physical and biological properties encoders. Those low-dimensional surface-based descriptors are ready to be paired with any advanced machine learning algorithms to explore the essential structure–activity relationships that give rise to the element interactive surface area-based scoring functions (EISA-score). The newly developed EISA-score has outperformed many state-of-the-art models, including various well-established surface-related representations, in standard PDBbind benchmarks.

Ligand binding affinity prediction with fusion of graph neural networks and 3D structure-based complex graph

“…Accurate prediction of protein-ligand binding affinity remains one of the grand challenges of computational chemistry and biology. [1][2][3] With the ever increasing amount of high-resolution experimentally determined protein-ligand structures, 4 the binding affinity prediction methods have switched from physicsbased [5][6][7][8][9][10][11] to empirical scoring functions [12][13][14][15] and knowledgebased, 16,17 and in the last decade to machine learning [18][19][20][21][22][23][24][25][26][27] and deep learning based methods. [28][29][30][31][32][33][34][35][36][37][38] Especially, deep learning is an end-to-end method that is ideally suited to find hidden nonlinear relationships 39 between 3D protein-ligand complex structures and binding affinity.…”

An ensemble‐based approach to estimate confidence of predicted protein–ligand binding affinity values

“…PPS‐ML, developed by Liu et al., employs persistent path‐spectral to generate a multiscale representation of protein‐ligand complexes based on graphs, simplicial complexes, and hypergraphs [28]. EISA‐score predicts protein–ligand binding affinity using molecular surface representations based on scalable element interactive manifolds instead of a single surface representation, combined with GBT [29]. Wee et al.…”

“…PPS-ML, developed by Liu et al, employs persistent pathspectral to generate a multiscale representation of protein-ligand complexes based on graphs, simplicial complexes, and hypergraphs [28]. EISA-score predicts protein-ligand binding affinity using molecular surface representations based on scalable element interactive manifolds instead of a single surface representation, combined with GBT [29]. Wee et al introduced the FPRC-based scoring function, which is a multiscale representation based on nested simplicial complexes at different scales and uses GBT as a data-driven learning algorithm [30].…”

SadNet: a novel multimodal fusion network for protein–ligand binding affinity prediction

“…1 Thus, the protein-ligand affinity prediction task is proposed as a solution to this problem, with the goal of predicting the most suitable ligand candidates by using deep learning to simulate the proteins-ligand binding process and rapidly calculate the binding affinity of each ligand. 2,3 Adequate data is the basis for deep learning methods to be effective and efficient. In the field of protein ligand affinity, ligand information is mainly based on the atomic dimension, such as SMILES 4 (simplified molecular input line entry system) and MOL2 file.…”