Reliability of Machine Learning Approaches Towards the Identification of Novel PI4KIIIβ Inhibitors.

IF 3.6 4区医学 Q3 CHEMISTRY, MEDICINAL

Current topics in medicinal chemistry Pub Date : 2026-10-13 DOI:10.2174/0115680266517367261009103151

Priyanka Andola, Prasanna Sagane, Lalitha Guruprasad

{"title":"Reliability of Machine Learning Approaches Towards the Identification of Novel PI4KIIIβ Inhibitors.","authors":"Priyanka Andola, Prasanna Sagane, Lalitha Guruprasad","doi":"10.2174/0115680266517367261009103151","DOIUrl":null,"url":null,"abstract":"Introduction: The type III Phosphatidylinositol 4-kinase (PI4KIIIβ) serves as a key host factor that mediates the replication of RNA viruses and is involved in essential membrane trafficking events. The development of PI4KIIIβ-specific inhibitors could give insights into the enzyme's function and contribute to the treatment of viral diseases. However, the molecular features that determine inhibitor activity and selectivity remain unclear.Methods: PI4KIIIβ inhibitors with reported biological activities (pIC50) were systematically analyzed using machine-learning methods. Molecular characterization was performed using RDKit, Chemopy descriptors, and PubChem fingerprints. Multiple classification and regression models were developed and evaluated using 10-fold cross-validation to establish robust structureactivity relationships.Results: It was suggested that the PubChem fingerprint-based linear regression, SMOreg, and GaussianProcesses models were more appropriate for the studied dataset to deliver the best predictive ability, which showed a correlation coefficient value > 0.7 in the 10-fold crossvalidation. PubChemFP389 and PubChemFP572, representing amidine-like fragments or guanidine- related motifs, and the aromatic amine fragment showed a negative correlation with respect to biological activity.Discussion: The study describes predictive models and provides insights into essential structural features in chemical compounds relevant for inhibitory activity, which could assist in the design and optimization of novel PI4KIIIβ inhibitors for antiviral and anticancer applications. A similar approach may be extended to a larger dataset of molecules or to other related drug targets.Conclusions: The findings suggest that excessive basicity and certain polar functionalities may be detrimental to PI4KIIIβ inhibition, providing important insights into the structural features influencing ligand binding and activity.","PeriodicalId":11076,"journal":{"name":"Current topics in medicinal chemistry","volume":" ","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current topics in medicinal chemistry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2174/0115680266517367261009103151","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CHEMISTRY, MEDICINAL","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: The type III Phosphatidylinositol 4-kinase (PI4KIIIβ) serves as a key host factor that mediates the replication of RNA viruses and is involved in essential membrane trafficking events. The development of PI4KIIIβ-specific inhibitors could give insights into the enzyme's function and contribute to the treatment of viral diseases. However, the molecular features that determine inhibitor activity and selectivity remain unclear.

Methods: PI4KIIIβ inhibitors with reported biological activities (pIC50) were systematically analyzed using machine-learning methods. Molecular characterization was performed using RDKit, Chemopy descriptors, and PubChem fingerprints. Multiple classification and regression models were developed and evaluated using 10-fold cross-validation to establish robust structureactivity relationships.

Results: It was suggested that the PubChem fingerprint-based linear regression, SMOreg, and GaussianProcesses models were more appropriate for the studied dataset to deliver the best predictive ability, which showed a correlation coefficient value > 0.7 in the 10-fold crossvalidation. PubChemFP389 and PubChemFP572, representing amidine-like fragments or guanidine- related motifs, and the aromatic amine fragment showed a negative correlation with respect to biological activity.

Discussion: The study describes predictive models and provides insights into essential structural features in chemical compounds relevant for inhibitory activity, which could assist in the design and optimization of novel PI4KIIIβ inhibitors for antiviral and anticancer applications. A similar approach may be extended to a larger dataset of molecules or to other related drug targets.

Conclusions: The findings suggest that excessive basicity and certain polar functionalities may be detrimental to PI4KIIIβ inhibition, providing important insights into the structural features influencing ligand binding and activity.

查看原文本刊更多论文

机器学习方法在鉴定新型pi4kii β抑制剂中的可靠性。

III型磷脂酰肌醇4-激酶（pi4kii β）是介导RNA病毒复制的关键宿主因子，并参与必要的膜转运事件。pi4kii β特异性抑制剂的开发可以深入了解该酶的功能，并有助于治疗病毒性疾病。然而，决定抑制剂活性和选择性的分子特征仍不清楚。方法：采用机器学习方法系统分析已报道的生物活性（pIC50）的pi4kii β抑制剂。使用RDKit， Chemopy描述符和PubChem指纹进行分子表征。开发了多个分类和回归模型，并使用10倍交叉验证来评估，以建立稳健的结构活性关系。结果：基于PubChem指纹的线性回归、SMOreg和GaussianProcesses模型更适合研究数据集，具有最佳的预测能力，在10倍交叉验证中显示相关系数为> 0.7。PubChemFP389和PubChemFP572分别代表脒类片段或胍相关基序，与芳香胺片段在生物活性方面呈负相关。讨论：该研究描述了预测模型，并提供了与抑制活性相关的化合物的基本结构特征的见解，这可以帮助设计和优化用于抗病毒和抗癌应用的新型pi4kii β抑制剂。类似的方法可以扩展到更大的分子数据集或其他相关的药物靶点。结论：研究结果表明，过度的碱度和某些极性功能可能不利于pi4kii β的抑制，这为了解影响配体结合和活性的结构特征提供了重要的见解。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Current topics in medicinal chemistry 医学-医药化学

CiteScore

6.40

自引率

2.90%

发文量

186

审稿时长

3-8 weeks

期刊介绍： Current Topics in Medicinal Chemistry is a forum for the review of areas of keen and topical interest to medicinal chemists and others in the allied disciplines. Each issue is solely devoted to a specific topic, containing six to nine reviews, which provide the reader a comprehensive survey of that area. A Guest Editor who is an expert in the topic under review, will assemble each issue. The scope of Current Topics in Medicinal Chemistry will cover all areas of medicinal chemistry, including current developments in rational drug design, synthetic chemistry, bioorganic chemistry, high-throughput screening, combinatorial chemistry, compound diversity measurements, drug absorption, drug distribution, metabolism, new and emerging drug targets, natural products, pharmacogenomics, and structure-activity relationships. Medicinal chemistry is a rapidly maturing discipline. The study of how structure and function are related is absolutely essential to understanding the molecular basis of life. Current Topics in Medicinal Chemistry aims to contribute to the growth of scientific knowledge and insight, and facilitate the discovery and development of new therapeutic agents to treat debilitating human disorders. The journal is essential for every medicinal chemist who wishes to be kept informed and up-to-date with the latest and most important advances.