GEMPLS: A new QSAR method combining generic evolutionary method and partial least squares

Yen Chih Chen; Jinn-Moon Yang; Chi Hung Tsai; Cheng Yan Kao

doi:10.1007/978-3-540-32003-6_13

GEMPLS: A new QSAR method combining generic evolutionary method and partial least squares

Yen Chih Chen^*, Jinn-Moon Yang, Chi Hung Tsai, Cheng Yan Kao

^*Corresponding author for this work

Department of Biological Science and Technology

Research output: Contribution to journal › Conference article › peer-review

Abstract

We have proposed a new method for quantitative structure-activity relationship (QSAR) analysis. This tool, termed GEMPLS, combines a genetic evolutionary method with partial least squares (PLS). We designed a new genetic operator and used Mahalanobis distance to improve predicted accuracy and speed up a solution for QSAR. The number of latent variables (lv) was encoded into the chromosome of GA, instead of scanning the best lv for PLS. We applied GEMPLS on a comparative binding energy (COMBINE) analysis system of 48 inhibitors of the HIV-1 protease. Using GEMPLS, the cross-validated correlation coefficient (q²) is 0.9053 and external SDEP (SDEP_ex) is 0.61. The results indicate that GEMPLS is very comparative to GAPLS and GEMPLS is faster than GAPLS for this data set. GEMPLS yielded the QSAR models, in which selected residues are consistent with some experimental evidences.

Original language	English
Pages (from-to)	125-135
Number of pages	11
Journal	Lecture Notes in Computer Science
Volume	3449
DOIs	https://doi.org/10.1007/978-3-540-32003-6_13
State	Published - 2005
Event	EvoWorkshops 2005: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, and EvoSTOC - Lausanne, Switzerland Duration: 30 Mar 2005 → 1 Apr 2005

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-540-32003-6_13

Cite this

@article{e76e2ba49f9f4b8dbf55fc6779e86185,

title = "GEMPLS: A new QSAR method combining generic evolutionary method and partial least squares",

abstract = "We have proposed a new method for quantitative structure-activity relationship (QSAR) analysis. This tool, termed GEMPLS, combines a genetic evolutionary method with partial least squares (PLS). We designed a new genetic operator and used Mahalanobis distance to improve predicted accuracy and speed up a solution for QSAR. The number of latent variables (lv) was encoded into the chromosome of GA, instead of scanning the best lv for PLS. We applied GEMPLS on a comparative binding energy (COMBINE) analysis system of 48 inhibitors of the HIV-1 protease. Using GEMPLS, the cross-validated correlation coefficient (q2) is 0.9053 and external SDEP (SDEPex) is 0.61. The results indicate that GEMPLS is very comparative to GAPLS and GEMPLS is faster than GAPLS for this data set. GEMPLS yielded the QSAR models, in which selected residues are consistent with some experimental evidences.",

author = "Chen, {Yen Chih} and Jinn-Moon Yang and Tsai, {Chi Hung} and Kao, {Cheng Yan}",

year = "2005",

doi = "10.1007/978-3-540-32003-6_13",

language = "English",

volume = "3449",

pages = "125--135",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Science and Business Media Deutschland GmbH",

note = "EvoWorkshops 2005: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, and EvoSTOC ; Conference date: 30-03-2005 Through 01-04-2005",

}

TY - JOUR

T1 - GEMPLS

T2 - EvoWorkshops 2005: EvoBIO, EvoCOMNET, EvoHOT, EvoIASP, EvoMUSART, and EvoSTOC

AU - Chen, Yen Chih

AU - Yang, Jinn-Moon

AU - Tsai, Chi Hung

AU - Kao, Cheng Yan

PY - 2005

Y1 - 2005

N2 - We have proposed a new method for quantitative structure-activity relationship (QSAR) analysis. This tool, termed GEMPLS, combines a genetic evolutionary method with partial least squares (PLS). We designed a new genetic operator and used Mahalanobis distance to improve predicted accuracy and speed up a solution for QSAR. The number of latent variables (lv) was encoded into the chromosome of GA, instead of scanning the best lv for PLS. We applied GEMPLS on a comparative binding energy (COMBINE) analysis system of 48 inhibitors of the HIV-1 protease. Using GEMPLS, the cross-validated correlation coefficient (q2) is 0.9053 and external SDEP (SDEPex) is 0.61. The results indicate that GEMPLS is very comparative to GAPLS and GEMPLS is faster than GAPLS for this data set. GEMPLS yielded the QSAR models, in which selected residues are consistent with some experimental evidences.

AB - We have proposed a new method for quantitative structure-activity relationship (QSAR) analysis. This tool, termed GEMPLS, combines a genetic evolutionary method with partial least squares (PLS). We designed a new genetic operator and used Mahalanobis distance to improve predicted accuracy and speed up a solution for QSAR. The number of latent variables (lv) was encoded into the chromosome of GA, instead of scanning the best lv for PLS. We applied GEMPLS on a comparative binding energy (COMBINE) analysis system of 48 inhibitors of the HIV-1 protease. Using GEMPLS, the cross-validated correlation coefficient (q2) is 0.9053 and external SDEP (SDEPex) is 0.61. The results indicate that GEMPLS is very comparative to GAPLS and GEMPLS is faster than GAPLS for this data set. GEMPLS yielded the QSAR models, in which selected residues are consistent with some experimental evidences.

UR - http://www.scopus.com/inward/record.url?scp=24644465631&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-32003-6_13

DO - 10.1007/978-3-540-32003-6_13

M3 - Conference article

AN - SCOPUS:24644465631

SN - 0302-9743

VL - 3449

SP - 125

EP - 135

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

Y2 - 30 March 2005 through 1 April 2005

ER -

GEMPLS: A new QSAR method combining generic evolutionary method and partial least squares

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this