Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents

Hu Li, C. W. Yap, Y. Xue, Z. R. Li, C. Y. Ung, L. Y. Han, Y. Z. Chen

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Pharmaceutical agents have been developed and tested for possessing desirable pharmacodynamic, pharmacokinetic, and minimal level of toxicological properties. Computational methods have been explored for predicting these properties aimed at the discovery of promising leads and the elimination of unsuitable ones in early stages of drug development. Statistical learning methods have shown their potential for predicting these properties for structurally diverse sets of agents by using both conventional (quantitative structure-activity and structure-property relationships) and more recently explored (such as neural networks and support vector machines) statistical models. These methods have been used for predicting agents of a variety of pharmacodynamic (such as inhibitors or agonists of a therapeutic target), pharmacokinetic (such as P-glycoprotein substrates, human intestine absorption, and blood-brain barrier penetrating capabilities), and toxicological (such as genotoxicity) properties. The strategies, current progresses, and the underlying difficulties and future prospects of the application of the recently explored statistical learning methods are discussed.

Original languageEnglish (US)
Pages (from-to)245-259
Number of pages15
JournalDrug Development Research
Volume66
Issue number4
DOIs
StatePublished - Dec 2005
Externally publishedYes

Fingerprint

Pharmacodynamics
Pharmacokinetics
Toxicology
Learning
P-Glycoprotein
Computational methods
Pharmaceutical Preparations
Support vector machines
Neural networks
Statistical Models
Substrates
Structure-Activity Relationship
Blood-Brain Barrier
Intestines

Keywords

  • Feature selection
  • Molecular descriptors
  • Pharmacodynamic
  • Pharmacokinetic
  • QSAR
  • Statistical learning methods
  • Toxicology

ASJC Scopus subject areas

  • Drug Discovery
  • Organic Chemistry
  • Pharmacology

Cite this

Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents. / Li, Hu; Yap, C. W.; Xue, Y.; Li, Z. R.; Ung, C. Y.; Han, L. Y.; Chen, Y. Z.

In: Drug Development Research, Vol. 66, No. 4, 12.2005, p. 245-259.

Research output: Contribution to journalArticle

Li, Hu ; Yap, C. W. ; Xue, Y. ; Li, Z. R. ; Ung, C. Y. ; Han, L. Y. ; Chen, Y. Z. / Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents. In: Drug Development Research. 2005 ; Vol. 66, No. 4. pp. 245-259.
@article{ddb48a879d5d437daff1048d688322c2,
title = "Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents",
abstract = "Pharmaceutical agents have been developed and tested for possessing desirable pharmacodynamic, pharmacokinetic, and minimal level of toxicological properties. Computational methods have been explored for predicting these properties aimed at the discovery of promising leads and the elimination of unsuitable ones in early stages of drug development. Statistical learning methods have shown their potential for predicting these properties for structurally diverse sets of agents by using both conventional (quantitative structure-activity and structure-property relationships) and more recently explored (such as neural networks and support vector machines) statistical models. These methods have been used for predicting agents of a variety of pharmacodynamic (such as inhibitors or agonists of a therapeutic target), pharmacokinetic (such as P-glycoprotein substrates, human intestine absorption, and blood-brain barrier penetrating capabilities), and toxicological (such as genotoxicity) properties. The strategies, current progresses, and the underlying difficulties and future prospects of the application of the recently explored statistical learning methods are discussed.",
keywords = "Feature selection, Molecular descriptors, Pharmacodynamic, Pharmacokinetic, QSAR, Statistical learning methods, Toxicology",
author = "Hu Li and Yap, {C. W.} and Y. Xue and Li, {Z. R.} and Ung, {C. Y.} and Han, {L. Y.} and Chen, {Y. Z.}",
year = "2005",
month = "12",
doi = "10.1002/ddr.20044",
language = "English (US)",
volume = "66",
pages = "245--259",
journal = "Drug Development Research",
issn = "0272-4391",
publisher = "John Wiley and Sons Inc.",
number = "4",

}

TY - JOUR

T1 - Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents

AU - Li, Hu

AU - Yap, C. W.

AU - Xue, Y.

AU - Li, Z. R.

AU - Ung, C. Y.

AU - Han, L. Y.

AU - Chen, Y. Z.

PY - 2005/12

Y1 - 2005/12

N2 - Pharmaceutical agents have been developed and tested for possessing desirable pharmacodynamic, pharmacokinetic, and minimal level of toxicological properties. Computational methods have been explored for predicting these properties aimed at the discovery of promising leads and the elimination of unsuitable ones in early stages of drug development. Statistical learning methods have shown their potential for predicting these properties for structurally diverse sets of agents by using both conventional (quantitative structure-activity and structure-property relationships) and more recently explored (such as neural networks and support vector machines) statistical models. These methods have been used for predicting agents of a variety of pharmacodynamic (such as inhibitors or agonists of a therapeutic target), pharmacokinetic (such as P-glycoprotein substrates, human intestine absorption, and blood-brain barrier penetrating capabilities), and toxicological (such as genotoxicity) properties. The strategies, current progresses, and the underlying difficulties and future prospects of the application of the recently explored statistical learning methods are discussed.

AB - Pharmaceutical agents have been developed and tested for possessing desirable pharmacodynamic, pharmacokinetic, and minimal level of toxicological properties. Computational methods have been explored for predicting these properties aimed at the discovery of promising leads and the elimination of unsuitable ones in early stages of drug development. Statistical learning methods have shown their potential for predicting these properties for structurally diverse sets of agents by using both conventional (quantitative structure-activity and structure-property relationships) and more recently explored (such as neural networks and support vector machines) statistical models. These methods have been used for predicting agents of a variety of pharmacodynamic (such as inhibitors or agonists of a therapeutic target), pharmacokinetic (such as P-glycoprotein substrates, human intestine absorption, and blood-brain barrier penetrating capabilities), and toxicological (such as genotoxicity) properties. The strategies, current progresses, and the underlying difficulties and future prospects of the application of the recently explored statistical learning methods are discussed.

KW - Feature selection

KW - Molecular descriptors

KW - Pharmacodynamic

KW - Pharmacokinetic

KW - QSAR

KW - Statistical learning methods

KW - Toxicology

UR - http://www.scopus.com/inward/record.url?scp=33646420101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33646420101&partnerID=8YFLogxK

U2 - 10.1002/ddr.20044

DO - 10.1002/ddr.20044

M3 - Article

AN - SCOPUS:33646420101

VL - 66

SP - 245

EP - 259

JO - Drug Development Research

JF - Drug Development Research

SN - 0272-4391

IS - 4

ER -