Predicting lipophilicity of drug-discovery molecules using Gaussian process models

Timon S. Schroeter; Anton Schwaighofer; Sebastian Mika; Antonius Ter Laak; Detlev Suelzle; Ursula Ganzer; Nikolaus Heinrich; Klaus Robert Müller

doi:10.1002/cmdc.200700041

Predicting lipophilicity of drug-discovery molecules using Gaussian process models

Timon S. Schroeter, Anton Schwaighofer, Sebastian Mika, Antonius Ter Laak, Detlev Suelzle, Ursula Ganzer, Nikolaus Heinrich, Klaus Robert Müller

Research output: Contribution to journal › Article › peer-review

26 Citations (Scopus)

Abstract

(Figure Presented) The lipophilicity of 14556 library compounds at Bayer Schering was modeled using Gaussian process methodology. In a blind test with 7013 new drug-discovery molecules from the last few months, 81% were predicted correctly within one log unit,compared with only 44% achieved by commercial software. Predicted error bars exhibit close to ideal statistical properties, thereby allowing assessment of the model's domain of applicability.

Original language	English
Pages (from-to)	1265-1267
Number of pages	3
Journal	ChemMedChem
Volume	2
Issue number	9
DOIs	https://doi.org/10.1002/cmdc.200700041
Publication status	Published - 2007 Sept 10
Externally published	Yes

Keywords

Domain of applicability
Drug design
Gaussian process
Lipophilicity
Machine learning

ASJC Scopus subject areas

Biochemistry
Molecular Medicine
Pharmacology
Drug Discovery
Pharmacology, Toxicology and Pharmaceutics(all)
Organic Chemistry

Access to Document

10.1002/cmdc.200700041

Cite this

@article{5fb05717bdc5432a9fff5d05becee53d,

title = "Predicting lipophilicity of drug-discovery molecules using Gaussian process models",

abstract = "(Figure Presented) The lipophilicity of 14556 library compounds at Bayer Schering was modeled using Gaussian process methodology. In a blind test with 7013 new drug-discovery molecules from the last few months, 81% were predicted correctly within one log unit,compared with only 44% achieved by commercial software. Predicted error bars exhibit close to ideal statistical properties, thereby allowing assessment of the model's domain of applicability.",

keywords = "Domain of applicability, Drug design, Gaussian process, Lipophilicity, Machine learning",

author = "Schroeter, {Timon S.} and Anton Schwaighofer and Sebastian Mika and {Ter Laak}, Antonius and Detlev Suelzle and Ursula Ganzer and Nikolaus Heinrich and M{\"u}ller, {Klaus Robert}",

year = "2007",

month = sep,

day = "10",

doi = "10.1002/cmdc.200700041",

language = "English",

volume = "2",

pages = "1265--1267",

journal = "ChemMedChem",

issn = "1860-7179",

publisher = "John Wiley and Sons Ltd",

number = "9",

}

TY - JOUR

T1 - Predicting lipophilicity of drug-discovery molecules using Gaussian process models

AU - Schroeter, Timon S.

AU - Schwaighofer, Anton

AU - Mika, Sebastian

AU - Ter Laak, Antonius

AU - Suelzle, Detlev

AU - Ganzer, Ursula

AU - Heinrich, Nikolaus

AU - Müller, Klaus Robert

PY - 2007/9/10

Y1 - 2007/9/10

N2 - (Figure Presented) The lipophilicity of 14556 library compounds at Bayer Schering was modeled using Gaussian process methodology. In a blind test with 7013 new drug-discovery molecules from the last few months, 81% were predicted correctly within one log unit,compared with only 44% achieved by commercial software. Predicted error bars exhibit close to ideal statistical properties, thereby allowing assessment of the model's domain of applicability.

AB - (Figure Presented) The lipophilicity of 14556 library compounds at Bayer Schering was modeled using Gaussian process methodology. In a blind test with 7013 new drug-discovery molecules from the last few months, 81% were predicted correctly within one log unit,compared with only 44% achieved by commercial software. Predicted error bars exhibit close to ideal statistical properties, thereby allowing assessment of the model's domain of applicability.

KW - Domain of applicability

KW - Drug design

KW - Gaussian process

KW - Lipophilicity

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=44449148610&partnerID=8YFLogxK

U2 - 10.1002/cmdc.200700041

DO - 10.1002/cmdc.200700041

M3 - Article

C2 - 17576646

AN - SCOPUS:44449148610

SN - 1860-7179

VL - 2

SP - 1265

EP - 1267

JO - ChemMedChem

JF - ChemMedChem

IS - 9

ER -

Predicting lipophilicity of drug-discovery molecules using Gaussian process models

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this