Support Vector Machine Based Classification Model for Screening Plasmodium falciparum Proliferation Inhibitors and Non-Inhibitors

IF 2.3 Q3 ENGINEERING, BIOMEDICAL
S. Subramaniam, Monica Mehrotra, D. Gupta
{"title":"Support Vector Machine Based Classification Model for Screening Plasmodium falciparum Proliferation Inhibitors and Non-Inhibitors","authors":"S. Subramaniam, Monica Mehrotra, D. Gupta","doi":"10.4137/BECB.S7503","DOIUrl":null,"url":null,"abstract":"There is an urgent need to develop novel anti-malarials in view of the increasing disease burden and growing resistance of the currently used drugs against the malarial parasites. Proliferation inhibitors targeting P. falciparum intraerythrocytic cycle are one of the important classes of compounds being explored for its potential to be novel antimalarials. Support Vector Machine (SVM) based model developed by us can facilitate rapid screening of large and diverse chemical libraries by reducing false hits and prioritising compounds before setting up expensive High Throughput Screening experiment. The SVM model, trained with molecular descriptors of proliferation inhibitors and non-inhibitors, displayed a satisfactory performance on cross validations and independent data set, with an average accuracy of 83% and AUC of 0.88. Intriguingly, the method displayed remarkable accuracy for the recently submitted P. falciparum whole cell screening datasets. The method also predicted several inhibitors in the National Cancer Institute diversity set, mostly similar to the known inhibitors.","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"3 1","pages":""},"PeriodicalIF":2.3000,"publicationDate":"2011-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.4137/BECB.S7503","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomedical Engineering and Computational Biology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4137/BECB.S7503","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 7

Abstract

There is an urgent need to develop novel anti-malarials in view of the increasing disease burden and growing resistance of the currently used drugs against the malarial parasites. Proliferation inhibitors targeting P. falciparum intraerythrocytic cycle are one of the important classes of compounds being explored for its potential to be novel antimalarials. Support Vector Machine (SVM) based model developed by us can facilitate rapid screening of large and diverse chemical libraries by reducing false hits and prioritising compounds before setting up expensive High Throughput Screening experiment. The SVM model, trained with molecular descriptors of proliferation inhibitors and non-inhibitors, displayed a satisfactory performance on cross validations and independent data set, with an average accuracy of 83% and AUC of 0.88. Intriguingly, the method displayed remarkable accuracy for the recently submitted P. falciparum whole cell screening datasets. The method also predicted several inhibitors in the National Cancer Institute diversity set, mostly similar to the known inhibitors.
基于支持向量机的恶性疟原虫增殖抑制剂和非抑制剂筛选分类模型
鉴于疾病负担的增加和目前使用的抗疟疾药物的耐药性日益增强,迫切需要开发新的抗疟疾药物。针对恶性疟原虫红细胞内周期的增殖抑制剂是一类重要的化合物,因其潜在的新型抗疟药物而被探索。我们开发的基于支持向量机(SVM)的模型可以在建立昂贵的高通量筛选实验之前,通过减少错误命中和对化合物进行优先排序,促进大型和多样化化学文库的快速筛选。使用增殖抑制剂和非抑制剂分子描述符训练的SVM模型在交叉验证和独立数据集上表现出令人满意的性能,平均准确率为83%,AUC为0.88。有趣的是,该方法对最近提交的恶性疟原虫全细胞筛选数据集显示出显著的准确性。该方法还预测了国家癌症研究所多样性集中的几种抑制剂,大多数与已知抑制剂相似。
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
自引率
0.00%
发文量
1
审稿时长
8 weeks
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信