Comparative Assessment of Multiresponse Regression Methods for Predicting the Mechanisms of Toxic Action of Phenols

Shijin Ren, Hyunjoong Kim

Research output: Contribution to journalReview article

22 Citations (Scopus)

Abstract

The use of regression methods for classifying and predicting the mechanisms of toxic action of phenols was investigated in this study. Multiresponse regression was conducted using a total of six linear and nonlinear regression methods: simple linear regression (LinReg), logistic regression (LogReg), generalized additive model (GAM), locally weighted regression scatter plot smoothing (LOWESS), multivariate adaptive regression splines (MARS), and projection pursuit regression (PPR). A database containing phenols acting by four mechanisms (polar narcosis, weak acid respiratory uncoupling, proelectrophilicity, and soft electrophilicity) was used to assess the performances of the six regression methods in the multiresponse regression approach. For comparison purposes, traditional linear discriminant analysis (LDA) was also conducted as a baseline method to study the potential improvement of prediction accuracy by the multiresponse regression approach. Results showed that compared to LDA, the overall mechanism prediction error rate could be reduced to below 10% by multiresponse regression based on PPR. In addition to prediction accuracy, interpretability of the resultant models was discussed.

Original languageEnglish
Pages (from-to)2106-2110
Number of pages5
JournalJournal of Chemical Information and Computer Sciences
Volume43
Issue number6
DOIs
Publication statusPublished - 2003 Nov 1

Fingerprint

Toxic Actions
Phenols
Discriminant analysis
regression
Linear regression
Splines
Logistics
Acids
discriminant analysis
projection

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

@article{aff0ad41b8064ec08e16ba49488f1a22,
title = "Comparative Assessment of Multiresponse Regression Methods for Predicting the Mechanisms of Toxic Action of Phenols",
abstract = "The use of regression methods for classifying and predicting the mechanisms of toxic action of phenols was investigated in this study. Multiresponse regression was conducted using a total of six linear and nonlinear regression methods: simple linear regression (LinReg), logistic regression (LogReg), generalized additive model (GAM), locally weighted regression scatter plot smoothing (LOWESS), multivariate adaptive regression splines (MARS), and projection pursuit regression (PPR). A database containing phenols acting by four mechanisms (polar narcosis, weak acid respiratory uncoupling, proelectrophilicity, and soft electrophilicity) was used to assess the performances of the six regression methods in the multiresponse regression approach. For comparison purposes, traditional linear discriminant analysis (LDA) was also conducted as a baseline method to study the potential improvement of prediction accuracy by the multiresponse regression approach. Results showed that compared to LDA, the overall mechanism prediction error rate could be reduced to below 10{\%} by multiresponse regression based on PPR. In addition to prediction accuracy, interpretability of the resultant models was discussed.",
author = "Shijin Ren and Hyunjoong Kim",
year = "2003",
month = "11",
day = "1",
doi = "10.1021/ci034092y",
language = "English",
volume = "43",
pages = "2106--2110",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "6",

}

TY - JOUR

T1 - Comparative Assessment of Multiresponse Regression Methods for Predicting the Mechanisms of Toxic Action of Phenols

AU - Ren, Shijin

AU - Kim, Hyunjoong

PY - 2003/11/1

Y1 - 2003/11/1

N2 - The use of regression methods for classifying and predicting the mechanisms of toxic action of phenols was investigated in this study. Multiresponse regression was conducted using a total of six linear and nonlinear regression methods: simple linear regression (LinReg), logistic regression (LogReg), generalized additive model (GAM), locally weighted regression scatter plot smoothing (LOWESS), multivariate adaptive regression splines (MARS), and projection pursuit regression (PPR). A database containing phenols acting by four mechanisms (polar narcosis, weak acid respiratory uncoupling, proelectrophilicity, and soft electrophilicity) was used to assess the performances of the six regression methods in the multiresponse regression approach. For comparison purposes, traditional linear discriminant analysis (LDA) was also conducted as a baseline method to study the potential improvement of prediction accuracy by the multiresponse regression approach. Results showed that compared to LDA, the overall mechanism prediction error rate could be reduced to below 10% by multiresponse regression based on PPR. In addition to prediction accuracy, interpretability of the resultant models was discussed.

AB - The use of regression methods for classifying and predicting the mechanisms of toxic action of phenols was investigated in this study. Multiresponse regression was conducted using a total of six linear and nonlinear regression methods: simple linear regression (LinReg), logistic regression (LogReg), generalized additive model (GAM), locally weighted regression scatter plot smoothing (LOWESS), multivariate adaptive regression splines (MARS), and projection pursuit regression (PPR). A database containing phenols acting by four mechanisms (polar narcosis, weak acid respiratory uncoupling, proelectrophilicity, and soft electrophilicity) was used to assess the performances of the six regression methods in the multiresponse regression approach. For comparison purposes, traditional linear discriminant analysis (LDA) was also conducted as a baseline method to study the potential improvement of prediction accuracy by the multiresponse regression approach. Results showed that compared to LDA, the overall mechanism prediction error rate could be reduced to below 10% by multiresponse regression based on PPR. In addition to prediction accuracy, interpretability of the resultant models was discussed.

UR - http://www.scopus.com/inward/record.url?scp=0344686417&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0344686417&partnerID=8YFLogxK

U2 - 10.1021/ci034092y

DO - 10.1021/ci034092y

M3 - Review article

VL - 43

SP - 2106

EP - 2110

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 6

ER -