相关实验视频

Updated: Jan 17, 2026

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions

Published on: December 1, 2020

热屏:一种基于序列的药物虚拟查方法,使用数据增强和蛋白质语言模型

Geng Chen¹, Jinbiao Liao¹, Yanzhen Yu¹

¹College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, P. R. China.

Journal of chemical information and modeling

|September 16, 2025

概括

HitScreen 增强了仅使用蛋白序列的药物向相互作用预测,实现基于结构的方法性能. 这种深度学习框架通过捕捉空间特征和解决数据偏差来改善虚拟查和药物设计.

科学领域:

计算生物学是一种计算生物学.
药物发现药物发现
生物信息学是一种生物信息学.

背景情况:

基于序列的药物向相互作用 (DTI) 预测对于识别没有3D蛋白质结构的候选药物至关重要.
现有的基于序列的DTI方法在概括和捕捉空间相互作用方面扎,这导致了基于结构的方法的性能差距.

研究的目的:

开发一个强大的深度学习框架,HitScreen,用于虚拟选中的基于序列的DTI预测.
为了弥合基于序列和基于结构的DTI预测方法之间的性能差距.

主要方法:

HitScreen采用一个有条件标签反转策略来缓解数据偏差.
它集成了多个预训练的蛋白质语言模型 (Ankh,ESM-2,ProtT5) 和Uni-Mol用于空间信息编码.
交叉注意力机制捕捉了药物分子和蛋白质序列之间的局部分子间相互作用.

主要成果:

在独立数据集 (DEKOIS2.0,DUD-E) 上,HitScreen的性能与基于最先进的结构的方法相当或超过.
该框架仅使用蛋白质序列信息实现这一目标,优于以前基于序列的方法.
解释性分析证实了该模型识别生物相关相互作用的能力.

结论:

HitScreen为基于序列的DTI预测提供了一个强大,可解释和广泛适用的框架.
该方法显示了增强虚拟药物查和为合理的药物设计提供见解的巨大潜力.

更多相关视频

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation

Published on: February 10, 2023

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Application of I TASSER, trRosetta, UCSF Chimera, HADDOCK server, and HEX loria for De Novo and In Silico Design of Proteins

Published on: July 8, 2025

相关概念视频

Drug Discovery: Overview

Drug Discovery: Overview

Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...