摘要
背景:药物发现早期阶段的主要挑战之一是蛋白质-配体结合亲和力的计算评估。机器学习技术有助于预测这种类型的交互。我们可以按照两种方法应用这些技术。首先,使用具有亲和力数据的实验结构。其次,使用蛋白质配体对接模拟。 目标:在这篇综述中,我们描述了最近发表的基于晶体结构的机器学习模型,这些模型可以获得结合亲和力和热力学数据。 方法:我们使用蛋白质数据库中可用的实验结构,并通过 BindingDB、Binding MOAD 和 PDBbind 数据库访问结合亲和力和热力学数据。我们回顾了机器学习模型,以预测使用开源程序(例如 SANDReS 和 Taba)创建的绑定。 结果:对由晶体结构复合物组成的数据集训练的机器学习模型的分析表明,与经典评分函数相比,这些模型具有较高的预测性能。 结论:蛋白质-配体复合物晶体结构数量的快速增加为开发机器学习模型以预测结合亲和力创造了有利的局面。这些模型依赖于来自两个来源的实验数据,结构数据和亲和力数据。实验数据的组合生成了优于经典评分函数的计算模型。
关键词: 晶体结构、机器学习、评分函数空间、结合亲和力、SANDReS、Taba。
Current Medicinal Chemistry
Title:The Impact of Crystallographic Data for the Development of Machine Learning Models to Predict Protein-Ligand Binding Affinity
Volume: 28 Issue: 34
关键词: 晶体结构、机器学习、评分函数空间、结合亲和力、SANDReS、Taba。
摘要:
Background: One of the main challenges in the early stages of drug discovery is the computational assessment of protein-ligand binding affinity. Machine learning techniques can contribute to predicting this type of interaction. We may apply these techniques following two approaches. Firstly, using the experimental structures for which affinity data is available. Secondly, using protein-ligand docking simulations.
Objective: In this review, we describe recently published machine learning models based on crystal structures, for which binding affinity and thermodynamic data are available.
Method: We used experimental structures available at the protein data bank and binding affinity and thermodynamic data was accessed through BindingDB, Binding MOAD, and PDBbind databases. We reviewed machine learning models to predict binding created using open source programs, such as SAnDReS and Taba.
Results: Analysis of machine learning models trained against datasets, composed of crystal structure complexes indicated the high predictive performance of these models when compared with classical scoring functions.
Conclusion: The rapid increase in the number of crystal structures of protein-ligand complexes created a favorable scenario for developing machine learning models to predict binding affinity. These models rely on experimental data from two sources, the structural and the affinity data. The combination of experimental data generates computational models that outperform the classical scoring functions.
Export Options
About this article
Cite this article as:
The Impact of Crystallographic Data for the Development of Machine Learning Models to Predict Protein-Ligand Binding Affinity, Current Medicinal Chemistry 2021; 28 (34) . https://dx.doi.org/10.2174/0929867328666210210121320
DOI https://dx.doi.org/10.2174/0929867328666210210121320 |
Print ISSN 0929-8673 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-533X |

- Author Guidelines
- Bentham Author Support Services (BASS)
- Graphical Abstracts
- Fabricating and Stating False Information
- Research Misconduct
- Post Publication Discussions and Corrections
- Publishing Ethics and Rectitude
- Increase Visibility of Your Article
- Archiving Policies
- Peer Review Workflow
- Order Your Article Before Print
- Promote Your Article
- Manuscript Transfer Facility
- Editorial Policies
- Allegations from Whistleblowers
- Announcements
Related Articles
-
Phosphotyrosine Phosphatases in Cancer Diagnostic and Treatment
Recent Patents on DNA & Gene Sequences Obesity-Driven Inflammation and Colorectal Cancer
Current Medicinal Chemistry Therapeutic Options for the Management of Aromatase Inhibitor- Associated Bone Loss
Endocrine, Metabolic & Immune Disorders - Drug Targets The Role of SHP-2 in Cell Signalling and Human Disease
Current Enzyme Inhibition The mTOR Signaling Network: Insights from Its Role During Embryonic Development
Current Medicinal Chemistry Runx1/AML1 is a Guardian of Hematopoietic Stem Cells
Current Cancer Therapy Reviews DNA Methyltransferases Inhibitors from Natural Sources
Current Topics in Medicinal Chemistry Saffron-Based Crocin Prevents Early Lesions of Liver Cancer: In vivo, In vitro and Network Analyses
Recent Patents on Anti-Cancer Drug Discovery Allosteric Inhibitors of SHP2: An Updated Patent Review (2015-2020)
Current Medicinal Chemistry Targeting RAS Signaling Pathways in Juvenile Myelomonocytic Leukemia
Current Drug Targets mTOR, a Potential Target to Treat Autism Spectrum Disorder
CNS & Neurological Disorders - Drug Targets Monoclonal Antibodies in Allergy; Updated Applications and Promising Trials
Recent Patents on Inflammation & Allergy Drug Discovery Progress of Biological Agents on Psoriatic Arthritis
Current Pharmaceutical Biotechnology Endothelial Cell Aging and Apoptosis in Prevention and Disease: E-Selectin Expression and Modulation As A Model
Current Pharmaceutical Design Polysulfated/Sulfonated Compounds for the Development of Drugs at the Crossroad of Viral Infection and Oncogenesis
Current Pharmaceutical Design Mitochondrial Serine Protease HtrA2/Omi as a Potential Therapeutic Target
Current Drug Targets Genetics of Congenital Heart Disease
Current Cardiology Reviews Inflammation and Antiangiogenesis in Cancer
Current Medicinal Chemistry Medical Treatment of Aortic Aneurysms in Marfan Syndrome and other Heritable Conditions
Current Cardiology Reviews Current Role of Leukotriene Receptor Antagonists in Preschool Asthma
Current Respiratory Medicine Reviews