Descriptor-based profile analysis of kinase inhibitors to predict inhibitory activity and to grasp kinase selectivity

Hyejin Park, Kyeung Kyu Kim, Chang Hoon Kim, Jae Min Shin, Kyoung Tai No

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Protein kinases (PKs) are an important source of drug targets, especially in oncology. With 500 or more kinases in the human genome and only few kinase inhibitors approved, kinase inhibitor discovery is becoming more and more valuable. Because the discovery of kinase inhibitors with an increased selectivity is an important therapeutic concept, many researchers have been trying to address this issue with various methodologies. Although many attempts to predict the activity and selectivity of kinase inhibitors have been made, the issue of selectivity has not yet been resolved. Here, we studied kinase selectivity by generating predictive models and analyzing their descriptors by using kinase-profiling data. The 5-fold cross-validation accuracies for the 51 models were between 72.4% and 93.7% and the ROC values for all the 51 models were over 0.7. The phylogenetic tree based on the descriptor distance is quite different from that generated on the basis of sequence alignment.

Original languageEnglish
Pages (from-to)2680-2684
Number of pages5
JournalBulletin of the Korean Chemical Society
Volume34
Issue number9
DOIs
Publication statusPublished - 2013 Sep 20

Fingerprint

Phosphotransferases
Oncology
Protein Kinases
Genes
Pharmaceutical Preparations

All Science Journal Classification (ASJC) codes

  • Chemistry(all)

Cite this

@article{2c9b7c882f6f4090994cedaea56e2788,
title = "Descriptor-based profile analysis of kinase inhibitors to predict inhibitory activity and to grasp kinase selectivity",
abstract = "Protein kinases (PKs) are an important source of drug targets, especially in oncology. With 500 or more kinases in the human genome and only few kinase inhibitors approved, kinase inhibitor discovery is becoming more and more valuable. Because the discovery of kinase inhibitors with an increased selectivity is an important therapeutic concept, many researchers have been trying to address this issue with various methodologies. Although many attempts to predict the activity and selectivity of kinase inhibitors have been made, the issue of selectivity has not yet been resolved. Here, we studied kinase selectivity by generating predictive models and analyzing their descriptors by using kinase-profiling data. The 5-fold cross-validation accuracies for the 51 models were between 72.4{\%} and 93.7{\%} and the ROC values for all the 51 models were over 0.7. The phylogenetic tree based on the descriptor distance is quite different from that generated on the basis of sequence alignment.",
author = "Hyejin Park and Kim, {Kyeung Kyu} and Kim, {Chang Hoon} and Shin, {Jae Min} and No, {Kyoung Tai}",
year = "2013",
month = "9",
day = "20",
doi = "10.5012/bkcs.2013.34.9.2680",
language = "English",
volume = "34",
pages = "2680--2684",
journal = "Bulletin of the Korean Chemical Society",
issn = "0253-2964",
publisher = "Korean Chemical Society",
number = "9",

}

Descriptor-based profile analysis of kinase inhibitors to predict inhibitory activity and to grasp kinase selectivity. / Park, Hyejin; Kim, Kyeung Kyu; Kim, Chang Hoon; Shin, Jae Min; No, Kyoung Tai.

In: Bulletin of the Korean Chemical Society, Vol. 34, No. 9, 20.09.2013, p. 2680-2684.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Descriptor-based profile analysis of kinase inhibitors to predict inhibitory activity and to grasp kinase selectivity

AU - Park, Hyejin

AU - Kim, Kyeung Kyu

AU - Kim, Chang Hoon

AU - Shin, Jae Min

AU - No, Kyoung Tai

PY - 2013/9/20

Y1 - 2013/9/20

N2 - Protein kinases (PKs) are an important source of drug targets, especially in oncology. With 500 or more kinases in the human genome and only few kinase inhibitors approved, kinase inhibitor discovery is becoming more and more valuable. Because the discovery of kinase inhibitors with an increased selectivity is an important therapeutic concept, many researchers have been trying to address this issue with various methodologies. Although many attempts to predict the activity and selectivity of kinase inhibitors have been made, the issue of selectivity has not yet been resolved. Here, we studied kinase selectivity by generating predictive models and analyzing their descriptors by using kinase-profiling data. The 5-fold cross-validation accuracies for the 51 models were between 72.4% and 93.7% and the ROC values for all the 51 models were over 0.7. The phylogenetic tree based on the descriptor distance is quite different from that generated on the basis of sequence alignment.

AB - Protein kinases (PKs) are an important source of drug targets, especially in oncology. With 500 or more kinases in the human genome and only few kinase inhibitors approved, kinase inhibitor discovery is becoming more and more valuable. Because the discovery of kinase inhibitors with an increased selectivity is an important therapeutic concept, many researchers have been trying to address this issue with various methodologies. Although many attempts to predict the activity and selectivity of kinase inhibitors have been made, the issue of selectivity has not yet been resolved. Here, we studied kinase selectivity by generating predictive models and analyzing their descriptors by using kinase-profiling data. The 5-fold cross-validation accuracies for the 51 models were between 72.4% and 93.7% and the ROC values for all the 51 models were over 0.7. The phylogenetic tree based on the descriptor distance is quite different from that generated on the basis of sequence alignment.

UR - http://www.scopus.com/inward/record.url?scp=84885395833&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885395833&partnerID=8YFLogxK

U2 - 10.5012/bkcs.2013.34.9.2680

DO - 10.5012/bkcs.2013.34.9.2680

M3 - Article

AN - SCOPUS:84885395833

VL - 34

SP - 2680

EP - 2684

JO - Bulletin of the Korean Chemical Society

JF - Bulletin of the Korean Chemical Society

SN - 0253-2964

IS - 9

ER -