Genetic algorithm-optimized QSPR models for bioavailability, protein binding, and urinary excretion

Junmei Wang, George Krudy, Xiang Qun Xie, Chengde Wu, George Holland

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

In this work, a genetic algorithm (GA) was applied to build up a set of QSPR (quantitative structure-property relationship) models for human absolute oral bioavailability, plasma protein binding, and urinary excretion using the counts of molecular fragments as descriptors. For a pharmacokinetic property, the consensus score of a set of models (20 or 30) was found to improve the correlation coefficient and reduce the standard error significantly. Key fragments that may boost or reduce pharmacokinetic properties were also identified. Databases searches were performed for a set of key fragments identified by bioavailability models. The percentage of hit rates of bioavailability-boosting fragments were significantly higher than those of bioavailability-reducing fragments for MDDR (MDL Drug Data Report), a database of drugs and drug leads entered or entering development. On the other hand, the opposite trend was observed for ACD (Available Chemicals Directory), a database of all kinds of available compounds.

Original languageEnglish (US)
Pages (from-to)2674-2683
Number of pages10
JournalJournal of Chemical Information and Modeling
Volume46
Issue number6
DOIs
StatePublished - Nov 2006

Fingerprint

ownership structure
Genetic algorithms
drug
Pharmacokinetics
Pharmaceutical Preparations
Blood Proteins
trend
Plasmas
Biological Availability
Protein Binding

ASJC Scopus subject areas

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

Cite this

Genetic algorithm-optimized QSPR models for bioavailability, protein binding, and urinary excretion. / Wang, Junmei; Krudy, George; Xie, Xiang Qun; Wu, Chengde; Holland, George.

In: Journal of Chemical Information and Modeling, Vol. 46, No. 6, 11.2006, p. 2674-2683.

Research output: Contribution to journalArticle

Wang, Junmei ; Krudy, George ; Xie, Xiang Qun ; Wu, Chengde ; Holland, George. / Genetic algorithm-optimized QSPR models for bioavailability, protein binding, and urinary excretion. In: Journal of Chemical Information and Modeling. 2006 ; Vol. 46, No. 6. pp. 2674-2683.
@article{00bf6d61d3974accadfbfb23e16c3beb,
title = "Genetic algorithm-optimized QSPR models for bioavailability, protein binding, and urinary excretion",
abstract = "In this work, a genetic algorithm (GA) was applied to build up a set of QSPR (quantitative structure-property relationship) models for human absolute oral bioavailability, plasma protein binding, and urinary excretion using the counts of molecular fragments as descriptors. For a pharmacokinetic property, the consensus score of a set of models (20 or 30) was found to improve the correlation coefficient and reduce the standard error significantly. Key fragments that may boost or reduce pharmacokinetic properties were also identified. Databases searches were performed for a set of key fragments identified by bioavailability models. The percentage of hit rates of bioavailability-boosting fragments were significantly higher than those of bioavailability-reducing fragments for MDDR (MDL Drug Data Report), a database of drugs and drug leads entered or entering development. On the other hand, the opposite trend was observed for ACD (Available Chemicals Directory), a database of all kinds of available compounds.",
author = "Junmei Wang and George Krudy and Xie, {Xiang Qun} and Chengde Wu and George Holland",
year = "2006",
month = "11",
doi = "10.1021/ci060087t",
language = "English (US)",
volume = "46",
pages = "2674--2683",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "6",

}

TY - JOUR

T1 - Genetic algorithm-optimized QSPR models for bioavailability, protein binding, and urinary excretion

AU - Wang, Junmei

AU - Krudy, George

AU - Xie, Xiang Qun

AU - Wu, Chengde

AU - Holland, George

PY - 2006/11

Y1 - 2006/11

N2 - In this work, a genetic algorithm (GA) was applied to build up a set of QSPR (quantitative structure-property relationship) models for human absolute oral bioavailability, plasma protein binding, and urinary excretion using the counts of molecular fragments as descriptors. For a pharmacokinetic property, the consensus score of a set of models (20 or 30) was found to improve the correlation coefficient and reduce the standard error significantly. Key fragments that may boost or reduce pharmacokinetic properties were also identified. Databases searches were performed for a set of key fragments identified by bioavailability models. The percentage of hit rates of bioavailability-boosting fragments were significantly higher than those of bioavailability-reducing fragments for MDDR (MDL Drug Data Report), a database of drugs and drug leads entered or entering development. On the other hand, the opposite trend was observed for ACD (Available Chemicals Directory), a database of all kinds of available compounds.

AB - In this work, a genetic algorithm (GA) was applied to build up a set of QSPR (quantitative structure-property relationship) models for human absolute oral bioavailability, plasma protein binding, and urinary excretion using the counts of molecular fragments as descriptors. For a pharmacokinetic property, the consensus score of a set of models (20 or 30) was found to improve the correlation coefficient and reduce the standard error significantly. Key fragments that may boost or reduce pharmacokinetic properties were also identified. Databases searches were performed for a set of key fragments identified by bioavailability models. The percentage of hit rates of bioavailability-boosting fragments were significantly higher than those of bioavailability-reducing fragments for MDDR (MDL Drug Data Report), a database of drugs and drug leads entered or entering development. On the other hand, the opposite trend was observed for ACD (Available Chemicals Directory), a database of all kinds of available compounds.

UR - http://www.scopus.com/inward/record.url?scp=33845748281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845748281&partnerID=8YFLogxK

U2 - 10.1021/ci060087t

DO - 10.1021/ci060087t

M3 - Article

C2 - 17125207

AN - SCOPUS:33845748281

VL - 46

SP - 2674

EP - 2683

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 6

ER -