Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors

Casein kinase 2 (CK2) is considered an important target for anti-cancer drugs. Given the structural diversity and broad spectrum of pharmaceutical activities of natural products, numerous studies have been performed to prove them as valuable sources of drugs. However, there has been little study rel...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuting Liu, Mengzhou Bi, Xuewen Zhang, Na Zhang, Guohui Sun, Yue Zhou, Lijiao Zhao, Rugang Zhong
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	CK2 natural products machine learning privileged substructures halogen bonds Chemical technology TP1-1185 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/69bac1d3b8d24e08adfe5b75feaa46a4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:69bac1d3b8d24e08adfe5b75feaa46a4
record_format	dspace
spelling	oai:doaj.org-article:69bac1d3b8d24e08adfe5b75feaa46a42021-11-25T18:52:03ZMachine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors10.3390/pr91120742227-9717https://doaj.org/article/69bac1d3b8d24e08adfe5b75feaa46a42021-11-01T00:00:00Zhttps://www.mdpi.com/2227-9717/9/11/2074https://doaj.org/toc/2227-9717Casein kinase 2 (CK2) is considered an important target for anti-cancer drugs. Given the structural diversity and broad spectrum of pharmaceutical activities of natural products, numerous studies have been performed to prove them as valuable sources of drugs. However, there has been little study relevant to identifying structural factors responsible for their inhibitory activity against CK2 with machine learning methods. In this study, classification studies were conducted on 115 natural products as CK2 inhibitors. Seven machine learning methods along with six molecular fingerprints were employed to develop qualitative classification models. The performances of all models were evaluated by cross-validation and test set. By taking predictive accuracy(CA), the area under receiver operating characteristic (AUC), and (MCC)as three performance indicators, the optimal models with high reliability and predictive ability were obtained, including the Extended Fingerprint-Logistic Regression model (CA = 0.859, AUC = 0.826, MCC = 0.520) for training test andPubChem fingerprint along with the artificial neural model (CA = 0.826, AUC = 0.933, MCC = 0.628) for test set. Meanwhile, the privileged substructures responsible for their inhibitory activity against CK2 were also identified through a combination of frequency analysis and information gain. The results are expected to provide useful information for the further utilization of natural products and the discovery of novel CK2 inhibitors.Yuting LiuMengzhou BiXuewen ZhangNa ZhangGuohui SunYue ZhouLijiao ZhaoRugang ZhongMDPI AGarticleCK2natural productsmachine learningprivileged substructureshalogen bondsChemical technologyTP1-1185ChemistryQD1-999ENProcesses, Vol 9, Iss 2074, p 2074 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	CK2 natural products machine learning privileged substructures halogen bonds Chemical technology TP1-1185 Chemistry QD1-999
spellingShingle	CK2 natural products machine learning privileged substructures halogen bonds Chemical technology TP1-1185 Chemistry QD1-999 Yuting Liu Mengzhou Bi Xuewen Zhang Na Zhang Guohui Sun Yue Zhou Lijiao Zhao Rugang Zhong Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors
description	Casein kinase 2 (CK2) is considered an important target for anti-cancer drugs. Given the structural diversity and broad spectrum of pharmaceutical activities of natural products, numerous studies have been performed to prove them as valuable sources of drugs. However, there has been little study relevant to identifying structural factors responsible for their inhibitory activity against CK2 with machine learning methods. In this study, classification studies were conducted on 115 natural products as CK2 inhibitors. Seven machine learning methods along with six molecular fingerprints were employed to develop qualitative classification models. The performances of all models were evaluated by cross-validation and test set. By taking predictive accuracy(CA), the area under receiver operating characteristic (AUC), and (MCC)as three performance indicators, the optimal models with high reliability and predictive ability were obtained, including the Extended Fingerprint-Logistic Regression model (CA = 0.859, AUC = 0.826, MCC = 0.520) for training test andPubChem fingerprint along with the artificial neural model (CA = 0.826, AUC = 0.933, MCC = 0.628) for test set. Meanwhile, the privileged substructures responsible for their inhibitory activity against CK2 were also identified through a combination of frequency analysis and information gain. The results are expected to provide useful information for the further utilization of natural products and the discovery of novel CK2 inhibitors.
format	article
author	Yuting Liu Mengzhou Bi Xuewen Zhang Na Zhang Guohui Sun Yue Zhou Lijiao Zhao Rugang Zhong
author_facet	Yuting Liu Mengzhou Bi Xuewen Zhang Na Zhang Guohui Sun Yue Zhou Lijiao Zhao Rugang Zhong
author_sort	Yuting Liu
title	Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors
title_short	Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors
title_full	Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors
title_fullStr	Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors
title_full_unstemmed	Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors
title_sort	machine learning models for the classification of ck2 natural products inhibitors with molecular fingerprint descriptors
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/69bac1d3b8d24e08adfe5b75feaa46a4
work_keys_str_mv	AT yutingliu machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT mengzhoubi machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT xuewenzhang machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT nazhang machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT guohuisun machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT yuezhou machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT lijiaozhao machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors AT rugangzhong machinelearningmodelsfortheclassificationofck2naturalproductsinhibitorswithmolecularfingerprintdescriptors
_version_	1718410592388120576

Machine Learning Models for the Classification of CK2 Natural Products Inhibitors with Molecular Fingerprint Descriptors

Ejemplares similares