Combined machine learning models, docking analysis, ADMET studies and molecular dynamics simulations for the design of novel FAK inhibitors against glioblastoma

IF 4.3 2区 化学 Q2 CHEMISTRY, MULTIDISCIPLINARY BMC Chemistry Pub Date : 2024-10-18 DOI:10.1186/s13065-024-01316-x
Yihuan Zhao, Xiaoyu He, Qianwen Wan
{"title":"Combined machine learning models, docking analysis, ADMET studies and molecular dynamics simulations for the design of novel FAK inhibitors against glioblastoma","authors":"Yihuan Zhao,&nbsp;Xiaoyu He,&nbsp;Qianwen Wan","doi":"10.1186/s13065-024-01316-x","DOIUrl":null,"url":null,"abstract":"<div><p>Gliomas, particularly glioblastoma (GBM), are highly aggressive brain tumors with poor prognosis and high recurrence rates. This underscores the urgent need for novel therapeutic approaches. One promising target is Focal adhesion kinase (FAK), a key regulator of tumor progression currently in clinical trials for glioma treatment. Drug development, however, is both challenging and costly, necessitating efficient strategies. Computer-Aided Drug Design (CADD), especially when combined with machine learning (ML), streamlines the processes of virtual screening and optimization, significantly enhancing the efficiency and accuracy of drug discovery. Our study integrates ML, docking analysis, ADMET (absorption, distribution, metabolism, elimination, and toxicity) studies to identify novel FAK inhibitors specific to GBM. Predictive models showed strong performance, with an R<sup>2</sup> of 0.892, MAE of 0.331, and RMSE of 0.467 using protein-level IC<sub>50</sub> data in combined CDK, CDK extended fingerprints, and substructure fingerprint counts derived from 1280 FAK inhibitors. Another model, based on IC<sub>50</sub> data from 2608 compounds tested on U87-MG cells, achieved an R<sup>2</sup> of 0.789, MAE of 0.395, and RMSE of 0.536. Using these models, we efficiently identified 275 potentially active compounds out of 5107 candidates. Subsequent ADMET analysis narrowed this down to 16 potential FAK inhibitors that meet the established drug-likeness criteria. Moreover, molecular dynamics (MD) simulations validated the stable binding interactions between the selected compounds and the FAK protein. This study highlights the effectiveness of combining ML, docking analysis, and ADMET studies to rapidly identify potential FAK inhibitors from large databases, providing valuable insights for the systematic design of FAK inhibitors.</p></div>","PeriodicalId":496,"journal":{"name":"BMC Chemistry","volume":"18 1","pages":""},"PeriodicalIF":4.3000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://bmcchem.biomedcentral.com/counter/pdf/10.1186/s13065-024-01316-x","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Chemistry","FirstCategoryId":"92","ListUrlMain":"https://link.springer.com/article/10.1186/s13065-024-01316-x","RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Gliomas, particularly glioblastoma (GBM), are highly aggressive brain tumors with poor prognosis and high recurrence rates. This underscores the urgent need for novel therapeutic approaches. One promising target is Focal adhesion kinase (FAK), a key regulator of tumor progression currently in clinical trials for glioma treatment. Drug development, however, is both challenging and costly, necessitating efficient strategies. Computer-Aided Drug Design (CADD), especially when combined with machine learning (ML), streamlines the processes of virtual screening and optimization, significantly enhancing the efficiency and accuracy of drug discovery. Our study integrates ML, docking analysis, ADMET (absorption, distribution, metabolism, elimination, and toxicity) studies to identify novel FAK inhibitors specific to GBM. Predictive models showed strong performance, with an R2 of 0.892, MAE of 0.331, and RMSE of 0.467 using protein-level IC50 data in combined CDK, CDK extended fingerprints, and substructure fingerprint counts derived from 1280 FAK inhibitors. Another model, based on IC50 data from 2608 compounds tested on U87-MG cells, achieved an R2 of 0.789, MAE of 0.395, and RMSE of 0.536. Using these models, we efficiently identified 275 potentially active compounds out of 5107 candidates. Subsequent ADMET analysis narrowed this down to 16 potential FAK inhibitors that meet the established drug-likeness criteria. Moreover, molecular dynamics (MD) simulations validated the stable binding interactions between the selected compounds and the FAK protein. This study highlights the effectiveness of combining ML, docking analysis, and ADMET studies to rapidly identify potential FAK inhibitors from large databases, providing valuable insights for the systematic design of FAK inhibitors.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
结合机器学习模型、对接分析、ADMET 研究和分子动力学模拟,设计新型 FAK 抑制剂对抗胶质母细胞瘤
胶质瘤,尤其是胶质母细胞瘤(GBM),是一种侵袭性极强的脑肿瘤,预后差且复发率高。这凸显了对新型治疗方法的迫切需求。病灶粘附激酶(FAK)是一个很有希望的靶点,它是肿瘤进展的一个关键调节因子,目前正处于胶质瘤治疗的临床试验阶段。然而,药物开发既具有挑战性,又成本高昂,因此需要高效的策略。计算机辅助药物设计(CADD),尤其是与机器学习(ML)相结合时,可以简化虚拟筛选和优化过程,显著提高药物发现的效率和准确性。我们的研究整合了 ML、对接分析、ADMET(吸收、分布、代谢、消除和毒性)研究,以确定针对 GBM 的新型 FAK 抑制剂。利用从 1280 种 FAK 抑制剂中获得的 CDK、CDK 扩展指纹和亚结构指纹计数的组合蛋白质级 IC50 数据,预测模型显示出很强的性能,R2 为 0.892,MAE 为 0.331,RMSE 为 0.467。另一个模型基于在 U87-MG 细胞上测试的 2608 种化合物的 IC50 数据,R2 为 0.789,MAE 为 0.395,RMSE 为 0.536。利用这些模型,我们从 5107 个候选化合物中有效地鉴定出了 275 个具有潜在活性的化合物。随后的 ADMET 分析将范围缩小到 16 种符合既定药物相似性标准的潜在 FAK 抑制剂。此外,分子动力学(MD)模拟验证了所选化合物与 FAK 蛋白之间稳定的结合相互作用。这项研究强调了结合分子动力学、对接分析和 ADMET 研究从大型数据库中快速鉴定潜在 FAK 抑制剂的有效性,为系统设计 FAK 抑制剂提供了有价值的见解。
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 去求助
来源期刊
BMC Chemistry
BMC Chemistry Chemistry-General Chemistry
CiteScore
5.30
自引率
2.20%
发文量
92
审稿时长
27 weeks
期刊介绍: BMC Chemistry, formerly known as Chemistry Central Journal, is now part of the BMC series journals family. Chemistry Central Journal has served the chemistry community as a trusted open access resource for more than 10 years – and we are delighted to announce the next step on its journey. In January 2019 the journal has been renamed BMC Chemistry and now strengthens the BMC series footprint in the physical sciences by publishing quality articles and by pushing the boundaries of open chemistry.
期刊最新文献
Pharmacophore-based virtual screening, molecular docking, and molecular dynamics investigation for the identification of novel, marine aromatase inhibitors Molecular exploration of natural and synthetic compounds databases for promising hypoxia inducible factor (HIF) Prolyl-4- hydroxylase domain (PHD) inhibitors using molecular simulation and free energy calculations Olive mill wastewater treatment using vertical flow constructed wetlands (VFCWs) Simultaneously quantifying a novel five-component anti- migraine formulation containing ergotamine, propyphenazone, caffeine, camylofin, and mecloxamine using UV spectrophotometry and chemometric models New chemometrics-assisted spectrophotometric methods for simultaneous determination of co-formulated drugs montelukast, rupatadine, and desloratadine in their different dosage combinations
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1