干旱区生态环境知识资源中心(Arid): Mixtures of QSAR models: Learning application domains of pK a predicto rs

Arid

DOI	10.1002/cem.3223
	Mixtures of QSAR models: Learning application domains of pK a predicto rs
	Dorgo, Gyula; Peter Hamadi, Omar; Varga, Tamas; Abonyi, Janos
通讯作者	Abonyi, J (corresponding author), Univ Pannonia, Dept Proc Engn, Egyet Str 10,POB 158, H-8200 Veszprem, Hungary.
会议名称	37th Meeting of Hungarian Chemometricians
会议日期	SEP 08-12, 2019
会议地点	Karcag, HUNGARY
英文摘要	Quantitative structure-activity relationship models (QSAR models) predict the physical properties or biological effects based on physicochemical properties or molecular descriptors of chemical structures. Our work focuses on the construction of optimal linear and nonlinear weighted mixes of individual QSAR models to more accurately predict their performance. How the splitting of the application domain by a nonlinear gating network in a mixture of experts model structure is suitable for the determination of the optimal domain-specific QSAR model and how the optimal QSAR model for certain chemical groups can be determined is highlighted. The input of the gating network is arbitrarily formed by the various molecular structure descriptors and/or even the prediction of the individual QSAR models. The applicability of the method is demonstrated on the pK a values of the OASIS database (1912 chemicals) by the combination of four acidic pK a predictions of the OECD QSAR Toolbox. According to the results, the prediction performance was enhanced by more than 15% (root-mean-square error [RMSE] value) compared with the predictions of the best individual QSAR model.
英文关键词	ensemble models mixture of models model selection pK(a) prediction
来源出版物	JOURNAL OF CHEMOMETRICS
ISSN	0886-9383
EISSN	1099-128X
出版年	2020
卷号	34
期号	4
出版者	WILEY
类型	Article; Proceedings Paper
语种	英语
收录类别	CPCI-S
WOS记录号	WOS:000510555300001
WOS关键词	QUANTITATIVE STRUCTURE-ACTIVITY ; APPLICABILITY DOMAIN ; NEURAL-NETWORK ; DRUG DESIGN ; EXPERTS ; VALUES
WOS类目	Automation & Control Systems ; Chemistry, Analytical ; Computer Science, Artificial Intelligence ; Instruments & Instrumentation ; Mathematics, Interdisciplinary Applications ; Statistics & Probability
WOS研究方向	Automation & Control Systems ; Chemistry ; Computer Science ; Instruments & Instrumentation ; Mathematics
资源类型	会议论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/365527
作者单位	[Dorgo, Gyula; Peter Hamadi, Omar; Varga, Tamas; Abonyi, Janos] Pannon Egyet, MTA PE Lendulet Complex Syst Monitoring Res Grp, Veszprem, Hungary; [Dorgo, Gyula; Peter Hamadi, Omar; Varga, Tamas; Abonyi, Janos] Univ Pannonia, Dept Proc Engn, Egyet Str 10,POB 158, H-8200 Veszprem, Hungary
推荐引用方式 GB/T 7714	Dorgo, Gyula,Peter Hamadi, Omar,Varga, Tamas,et al. Mixtures of QSAR models: Learning application domains of pK a predicto rs[C]:WILEY,2020.