SVSBI: Sequence-based virtual screening of biomolecular interactions

TL;DR

This paper introduces SVSBI, a sequence-based virtual screening model utilizing NLP techniques and deep embedding strategies to predict biomolecular interactions without relying on 3D structures, improving accuracy in drug discovery.

Contribution

The paper presents a novel sequence-based virtual screening approach that bypasses the need for 3D structural data, leveraging NLP and deep learning for biomolecular interaction prediction.

Findings

SVS achieves state-of-the-art performance on multiple datasets.

SVS outperforms traditional docking-based methods.

The model is effective across various interaction types and species.

Abstract

Virtual screening (VS) is an essential technique for understanding biomolecular interactions, particularly, drug design and discovery. The best-performing VS models depend vitally on three-dimensional (3D) structures, which are not available in general but can be obtained from molecular docking. However, current docking accuracy is relatively low, rendering unreliable VS models. We introduce sequence-based virtual screening (SVS) as a new generation of VS models for modeling biomolecular interactions. The SVS model utilizes advanced natural language processing (NLP) algorithms and optimizes deep $K$-embedding strategies to encode biomolecular interactions without invoking 3D structure-based docking. We demonstrate the state-of-art performance of SVS for four regression datasets involving protein-ligand binding, protein-protein, protein-nucleic acid binding, and ligand inhibition of protein-protein interactions and five classification datasets for the protein-protein interactions in five biological species. SVS has the potential to dramatically change the current practice in drug discovery and protein engineering.