Classifying 'drug-likeness' with kernel-based learning methods

Klaus Muller, Gunnar Rätsch, Sören Sonnenburg, Sebastian Mika, Michael Grimm, Nikolaus Heinrich

Research output: Contribution to journalArticle

70 Citations (Scopus)

Abstract

In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the 'drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7% on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.

Original languageEnglish
Pages (from-to)249-253
Number of pages5
JournalJournal of Chemical Information and Modeling
Volume45
Issue number2
DOIs
Publication statusPublished - 2005 Mar 1
Externally publishedYes

Fingerprint

learning method
Support vector machines
Learning systems
Computational chemistry
drug
Pharmaceutical Preparations
learning
chemistry
Drug Discovery

ASJC Scopus subject areas

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

Cite this

Muller, K., Rätsch, G., Sonnenburg, S., Mika, S., Grimm, M., & Heinrich, N. (2005). Classifying 'drug-likeness' with kernel-based learning methods. Journal of Chemical Information and Modeling, 45(2), 249-253. https://doi.org/10.1021/ci049737o

Classifying 'drug-likeness' with kernel-based learning methods. / Muller, Klaus; Rätsch, Gunnar; Sonnenburg, Sören; Mika, Sebastian; Grimm, Michael; Heinrich, Nikolaus.

In: Journal of Chemical Information and Modeling, Vol. 45, No. 2, 01.03.2005, p. 249-253.

Research output: Contribution to journalArticle

Muller, K, Rätsch, G, Sonnenburg, S, Mika, S, Grimm, M & Heinrich, N 2005, 'Classifying 'drug-likeness' with kernel-based learning methods', Journal of Chemical Information and Modeling, vol. 45, no. 2, pp. 249-253. https://doi.org/10.1021/ci049737o
Muller K, Rätsch G, Sonnenburg S, Mika S, Grimm M, Heinrich N. Classifying 'drug-likeness' with kernel-based learning methods. Journal of Chemical Information and Modeling. 2005 Mar 1;45(2):249-253. https://doi.org/10.1021/ci049737o
Muller, Klaus ; Rätsch, Gunnar ; Sonnenburg, Sören ; Mika, Sebastian ; Grimm, Michael ; Heinrich, Nikolaus. / Classifying 'drug-likeness' with kernel-based learning methods. In: Journal of Chemical Information and Modeling. 2005 ; Vol. 45, No. 2. pp. 249-253.
@article{d3de7eb434e14b0e86dd6329c58ea54c,
title = "Classifying 'drug-likeness' with kernel-based learning methods",
abstract = "In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the 'drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7{\%} on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.",
author = "Klaus Muller and Gunnar R{\"a}tsch and S{\"o}ren Sonnenburg and Sebastian Mika and Michael Grimm and Nikolaus Heinrich",
year = "2005",
month = "3",
day = "1",
doi = "10.1021/ci049737o",
language = "English",
volume = "45",
pages = "249--253",
journal = "Journal of Chemical Information and Computer Sciences",
issn = "0095-2338",
publisher = "American Chemical Society",
number = "2",

}

TY - JOUR

T1 - Classifying 'drug-likeness' with kernel-based learning methods

AU - Muller, Klaus

AU - Rätsch, Gunnar

AU - Sonnenburg, Sören

AU - Mika, Sebastian

AU - Grimm, Michael

AU - Heinrich, Nikolaus

PY - 2005/3/1

Y1 - 2005/3/1

N2 - In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the 'drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7% on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.

AB - In this article we report about a successful application of modern machine learning technology, namely Support Vector Machines, to the problem of assessing the 'drug-likeness' of a chemical from a given set of descriptors of the substance. We were able to drastically improve the recent result by Byvatov et al. (2003) on this task and achieved an error rate of about 7% on unseen compounds using Support Vector Machines. We see a very high potential of such machine learning techniques for a variety of computational chemistry problems that occur in the drug discovery and drug design process.

UR - http://www.scopus.com/inward/record.url?scp=18344381621&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=18344381621&partnerID=8YFLogxK

U2 - 10.1021/ci049737o

DO - 10.1021/ci049737o

M3 - Article

VL - 45

SP - 249

EP - 253

JO - Journal of Chemical Information and Computer Sciences

JF - Journal of Chemical Information and Computer Sciences

SN - 0095-2338

IS - 2

ER -