Skip to content
Open access

A Hybrid Ligand- and Structure-Based Drug Design Invoked through Square Attention in Protein–Ligand Transformer

Oct 2026 · ACS Omega · Vol 11, pp. 68439 - 68452 · 0 citations · 63 references
Medicine

TL;DR

PLTransformer, a novel attention mechanism with Softmax normalization exerting on both directions of protein residues and ligand atoms in a more equivalent manner, shows competitive affinity predictive performance over a representative baseline while also providing the ability to identify binding pockets and important ligand scaffolds and protein substructures without employing three-dimensional structures of PL complexes.

Abstract

Computer-aided molecular design based on evaluation of protein–ligand (PL) binding affinity is important for accelerating drug discovery. A deep-learning model for natural language processing (NLP) involving an attention mechanism (i.e., Transformer) is expected to improve the PL-affinity evaluation along with clarifying amino acid residues and ligand atoms that are responsible for molecular interactions. However, the original attention (i.e., a scaled dot-product with row-wise Softmax normalization) is an adapted method for relationships between homogeneous inputs (e.g., two sentences in the translation tasks) and thus is not suitable to analyze heterogeneity found in input data such as proteins (102–103 residues) and ligands (101–102 atoms). In fact, due to the significant difference between the numbers of protein residues and ligand atoms, gaps in the scale of attention weights emerge after the normalization, which thus affects model performance. Herein, we report PLTransformer, which involves our novel attention mechanism with Softmax normalization exerting on both directions of protein residues and ligand atoms in a more equivalent manner, for correcting the imbalance by a tandem of attention blocks with swapped inputs. As a result, our PLTransformer shows competitive affinity predictive performance over a representative baseline while also providing the ability to identify binding pockets, including allosteric sites, and important ligand scaffolds and protein substructures without employing three-dimensional (3D) structures of PL complexes (i.e., a ligand-based drug design (LBDD) framework). Thus, the possible PL (residue–ligand atom) contacts provided by PLTransformer can assist us to select plausible PL binding modes obtained by docking simulations, promoting the identification of the appropriate binding mode such as to maximize the performance of PLTransformer (i.e., structure-based drug design (SBDD) framework).

Read PDF

Similar papers

Open access Oct 2026

Protein–Protein Interface Residue Prediction by Integrating Protein Language Representations and Structural Graph Attention

Accurate residue-level prediction of protein–protein interaction interfaces is important for elucidating molecular recognition mechanisms and guiding targeted drug design. However, interface residues are relatively sparse and governed by complex spatial dependencies, making their accurate identification challenging. In...

Zhen Hou, Wei He, Wei-Nan Cao et al. · 1 citation
#artificial intelligence Open access Oct 2026

HierDTA: Hierarchical Structure-Aware Representation Learning for Drug–Target Affinity Prediction

Drug–target affinity (DTA) prediction plays an important role in computer-aided drug discovery, where reliable computational models can help prioritize compound–protein pairs before experimental validation. A key challenge in DTA prediction is to effectively mine multilevel molecular information from drug structures wh...

Huang-Chao Xu, Bao-Hua Zhang, Qian Liu et al. · 0 citations
Review Oct 2026

AlphaFold-driven structure-based drug discovery: Capabilities, benchmarks and limitations for medicinal chemistry.

This review covers the aspects of SBDD approach, traditional methods of protein structure determination and limitations that have restricted the application of this methodology, and addresses the use of AlphaFold models in major drug discovery processes including target identification, binding site prediction, molecula...

M. Pathak · 0 citations
Open access Nov 2026

Integrated machine learning, molecular docking and ADMET analysis for computational prioritization of S1PR1-targeting drug candidates

Sphingosine-1-phosphate receptor 1 (S1PR1) is a G protein-coupled receptor involved in immune-cell trafficking and has attracted considerable interest as a pharmacological target. The availability of structurally characterized ligand-bound S1PR1 provides an opportunity to combine ligand-based machine learning with stru...

Akshata P. Pauskar, Elamathi Natarajan · 0 citations
Open access Oct 2026

HierL2GDTA: Hierarchical Interaction Modeling with Local and Global Features for Drug–Target Affinity Prediction

Accurate prediction of drug–target binding affinity is essential for drug discovery. However, existing methods face limitations in capturing local and global molecular features and in effectively integrating protein and ligand representations for interaction modeling. Here, we present HierL2GDTA, a sequence-based hiera...

Kai-Li Wang, Yao-Xiang Yin, Yang-Lan Gan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.