Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method

Beilei Lei; Yimeng Ma; Jiazhong Li; Huanxiang Liu; Xiaojun Yao; Paola Gramatica

doi:10.1016/j.atmosenv.2010.05.021

Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method

Beilei Lei, Yimeng Ma, Jiazhong Li, Huanxiang Liu, Xiaojun Yao, Paola Gramatica

Research output: Contribution to journal › Article › peer-review

21 Citations (Scopus)

Abstract

Accurate quantitative structure-property relationship (QSPR) models based on a large data set containing a total of 3483 organic compounds were developed to predict chemicals' adsorption capability onto activated carbon in gas phrase. Both global multiple linear regression (MLR) method and local lazy regression (LLR) method were used to develop QSPR models. The results proved that LLR has prediction accuracy 10% higher than that of MLR model. By applying LLR method we can predict the test set (787 compounds) with Q²_ext of 0.900 and root mean square error (RMSE) of 0.129. The accurate model based on this large data set could be useful to predict adsorption property of new compounds since such model covers a highly diverse structural space.

Original language	English
Pages (from-to)	2954-2960
Number of pages	7
Journal	Atmospheric Environment
Volume	44
Issue number	25
DOIs	https://doi.org/10.1016/j.atmosenv.2010.05.021
Publication status	Published - Aug 2010
Externally published	Yes

Keywords

Activated carbon adsorption capability
Genetic algorithm (GA)
Local lazy regression (LLR)
Quantitative structure-property relationship (QSPR)

Access to Document

10.1016/j.atmosenv.2010.05.021

Cite this

@article{0c932c9a742746428662a1ff97ebdbaa,

title = "Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method",

abstract = "Accurate quantitative structure-property relationship (QSPR) models based on a large data set containing a total of 3483 organic compounds were developed to predict chemicals' adsorption capability onto activated carbon in gas phrase. Both global multiple linear regression (MLR) method and local lazy regression (LLR) method were used to develop QSPR models. The results proved that LLR has prediction accuracy 10% higher than that of MLR model. By applying LLR method we can predict the test set (787 compounds) with Q2ext of 0.900 and root mean square error (RMSE) of 0.129. The accurate model based on this large data set could be useful to predict adsorption property of new compounds since such model covers a highly diverse structural space.",

keywords = "Activated carbon adsorption capability, Genetic algorithm (GA), Local lazy regression (LLR), Quantitative structure-property relationship (QSPR)",

author = "Beilei Lei and Yimeng Ma and Jiazhong Li and Huanxiang Liu and Xiaojun Yao and Paola Gramatica",

note = "Funding Information: This work was supported by the Program for New Century Excellent Talents in University (Grant No. NCET-07-0399 ), the Project Sponsored by the Scientific Research Foundation for the Returned Overseas Chinese Scholars and the National Natural Science Foundation of China ( J0730425 ). ",

year = "2010",

month = aug,

doi = "10.1016/j.atmosenv.2010.05.021",

language = "English",

volume = "44",

pages = "2954--2960",

journal = "Atmospheric Environment",

issn = "1352-2310",

publisher = "Elsevier Ltd.",

number = "25",

}

TY - JOUR

T1 - Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method

AU - Lei, Beilei

AU - Ma, Yimeng

AU - Li, Jiazhong

AU - Liu, Huanxiang

AU - Yao, Xiaojun

AU - Gramatica, Paola

N1 - Funding Information: This work was supported by the Program for New Century Excellent Talents in University (Grant No. NCET-07-0399 ), the Project Sponsored by the Scientific Research Foundation for the Returned Overseas Chinese Scholars and the National Natural Science Foundation of China ( J0730425 ).

PY - 2010/8

Y1 - 2010/8

N2 - Accurate quantitative structure-property relationship (QSPR) models based on a large data set containing a total of 3483 organic compounds were developed to predict chemicals' adsorption capability onto activated carbon in gas phrase. Both global multiple linear regression (MLR) method and local lazy regression (LLR) method were used to develop QSPR models. The results proved that LLR has prediction accuracy 10% higher than that of MLR model. By applying LLR method we can predict the test set (787 compounds) with Q2ext of 0.900 and root mean square error (RMSE) of 0.129. The accurate model based on this large data set could be useful to predict adsorption property of new compounds since such model covers a highly diverse structural space.

AB - Accurate quantitative structure-property relationship (QSPR) models based on a large data set containing a total of 3483 organic compounds were developed to predict chemicals' adsorption capability onto activated carbon in gas phrase. Both global multiple linear regression (MLR) method and local lazy regression (LLR) method were used to develop QSPR models. The results proved that LLR has prediction accuracy 10% higher than that of MLR model. By applying LLR method we can predict the test set (787 compounds) with Q2ext of 0.900 and root mean square error (RMSE) of 0.129. The accurate model based on this large data set could be useful to predict adsorption property of new compounds since such model covers a highly diverse structural space.

KW - Activated carbon adsorption capability

KW - Genetic algorithm (GA)

KW - Local lazy regression (LLR)

KW - Quantitative structure-property relationship (QSPR)

UR - http://www.scopus.com/inward/record.url?scp=77954309618&partnerID=8YFLogxK

U2 - 10.1016/j.atmosenv.2010.05.021

DO - 10.1016/j.atmosenv.2010.05.021

M3 - Article

AN - SCOPUS:77954309618

SN - 1352-2310

VL - 44

SP - 2954

EP - 2960

JO - Atmospheric Environment

JF - Atmospheric Environment

IS - 25

ER -

Prediction of the adsorption capability onto activated carbon of a large data set of chemicals by local lazy regression method

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this