相关实验视频

Updated: Jun 25, 2025

Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery

Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery

Published on: May 16, 2021

摩根指纹在基于结构的虚拟干查中的实用性

Hongyi Zhou¹, Jeffrey Skolnick¹

¹Center for the Study of Systems Biology, School of Biological Sciences, Georgia Institute of Technology, Atlanta, Georgia 30332, United States.

The journal of physical chemistry. B

|May 24, 2024

概括

通过将摩根指纹 (MF) 纳入虚拟带查 (VLS) 方法得到了增强. 与现有的深度学习模型相比,这些改进的方法,如FRAGSITEcombM,在识别候选药物方面表现优越.

科学领域:

计算化学是一种计算化学.
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:

虚拟带查 (VLS) 对于具有成本效益的药物发现至关重要,可以从大型图书馆中识别潜在的药物候选者.
现有的VLS方法,包括FINDSITE套件,结合了联体同质模型 (LHM) 和机器学习,但可以改进.
深度学习和大型语言模型显示出有希望的结果,但在准确性方面往往落后于既定方法.

研究的目的:

通过整合摩根指纹 (MF) 来增强现有的VLS方法.
为了比较新的VLS方法 (FINDSITEcomb2.0M,FRAGSITE M,FRAGSITE2 M,FRAGSITEcombM) 与已建立的数据集的性能.
评估MF对基于结构的VLS整体性能改善的贡献.

主要方法:

在VLS算法中将摩根指纹 (MF) 与现有的PubChem和FP2指纹集成.
在DUD-E和DEKOIS2.0数据集上对四种新型VLS方法 (FINDSITEcomb2.0M,FRAGSITE M,FRAGSITE2 M,FRAGSITEcombM) 的比较.
废弃性研究,以确定MF对性能提升的具体贡献.

主要成果:

增强的元方法FRAGSITEcombM在DUD-E和DEKOIS2.0数据集上显示了丰富系数 (EF1%) 和精度回忆曲线下的面积 (AUPR) 的显著改善.
在DUD-E集上,FRAGSITEcombM获得了0.72的AUPR,超过了深度学习方法DenseFS (AUPR 0.443).
废弃性研究证实,MF是所有四种测试方法中性能增长的主要驱动因素.

结论:

纳入摩根指纹 (MF) 显著提高了基于结构的虚拟连接体查的准确性和效率.
改进的FINDSITE套件,特别是FRAGSITEcombM,代表了在药物发现中进行命中识别的最先进方法.
MF是VLS方法的宝贵补充,为识别潜在的毒品线索提供了一个强大的策略.

更多相关视频

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source

Published on: May 29, 2021

NMR-Based Fragment Screening in a Minimum Sample but Maximum Automation Mode

NMR-Based Fragment Screening in a Minimum Sample but Maximum Automation Mode

Published on: June 4, 2021

相关概念视频

The Equilibrium Binding Constant and Binding Strength

The Equilibrium Binding Constant and Binding Strength

The equilibrium binding constant (Kb) quantifies the strength of a protein-ligand interaction. Kb can be calculated as follows when the reaction is at equilibrium:

Ligand Binding Sites

Ligand Binding Sites

Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...