Accurate solubility prediction with error bars for electrolytes

A machine learning approach

Anton Schwaighofer, Timon Schroeter, Sebastian Mika, Julian Laub, Antonius Ter Laak, Detlev Sülzle, Ursula Ganzer, Nikolaus Heinrich, Klaus Muller

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.

Original languageEnglish
Pages (from-to)407-424
Number of pages18
JournalJournal of Chemical Information and Modeling
Volume47
Issue number2
DOIs
Publication statusPublished - 2007 Mar 1
Externally publishedYes

Fingerprint

Electrolytes
Learning systems
Solubility
learning
drug
regression
Pharmaceutical Preparations

ASJC Scopus subject areas

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

Cite this

Schwaighofer, A., Schroeter, T., Mika, S., Laub, J., Ter Laak, A., Sülzle, D., ... Muller, K. (2007). Accurate solubility prediction with error bars for electrolytes: A machine learning approach. Journal of Chemical Information and Modeling, 47(2), 407-424. https://doi.org/10.1021/ci600205g

Accurate solubility prediction with error bars for electrolytes : A machine learning approach. / Schwaighofer, Anton; Schroeter, Timon; Mika, Sebastian; Laub, Julian; Ter Laak, Antonius; Sülzle, Detlev; Ganzer, Ursula; Heinrich, Nikolaus; Muller, Klaus.

In: Journal of Chemical Information and Modeling, Vol. 47, No. 2, 01.03.2007, p. 407-424.

Research output: Contribution to journalArticle

Schwaighofer, A, Schroeter, T, Mika, S, Laub, J, Ter Laak, A, Sülzle, D, Ganzer, U, Heinrich, N & Muller, K 2007, 'Accurate solubility prediction with error bars for electrolytes: A machine learning approach', Journal of Chemical Information and Modeling, vol. 47, no. 2, pp. 407-424. https://doi.org/10.1021/ci600205g
Schwaighofer, Anton ; Schroeter, Timon ; Mika, Sebastian ; Laub, Julian ; Ter Laak, Antonius ; Sülzle, Detlev ; Ganzer, Ursula ; Heinrich, Nikolaus ; Muller, Klaus. / Accurate solubility prediction with error bars for electrolytes : A machine learning approach. In: Journal of Chemical Information and Modeling. 2007 ; Vol. 47, No. 2. pp. 407-424.
@article{c3db8d565f774c898c8512566c0afa41,
title = "Accurate solubility prediction with error bars for electrolytes: A machine learning approach",
abstract = "Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.",
author = "Anton Schwaighofer and Timon Schroeter and Sebastian Mika and Julian Laub and {Ter Laak}, Antonius and Detlev S{\"u}lzle and Ursula Ganzer and Nikolaus Heinrich and Klaus Muller",
year = "2007",
month = "3",
day = "1",
doi = "10.1021/ci600205g",
language = "English",
volume = "47",
pages = "407--424",
journal = "Journal of Chemical Information and Computer Sciences",
issn = "0095-2338",
publisher = "American Chemical Society",
number = "2",

}

TY - JOUR

T1 - Accurate solubility prediction with error bars for electrolytes

T2 - A machine learning approach

AU - Schwaighofer, Anton

AU - Schroeter, Timon

AU - Mika, Sebastian

AU - Laub, Julian

AU - Ter Laak, Antonius

AU - Sülzle, Detlev

AU - Ganzer, Ursula

AU - Heinrich, Nikolaus

AU - Muller, Klaus

PY - 2007/3/1

Y1 - 2007/3/1

N2 - Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.

AB - Accurate in silico models for predicting aqueous solubility are needed in drug design and discovery and many other areas of chemical research. We present a statistical modeling of aqueous solubility based on measured data, using a Gaussian Process nonlinear regression model (GPsol). We compare our results with those of 14 scientific studies and 6 commercial tools. This shows that the developed model achieves much higher accuracy than available commercial tools for the prediction of solubility of electrolytes. On top of the high accuracy, the proposed machine learning model also provides error bars for each individual prediction.

UR - http://www.scopus.com/inward/record.url?scp=34247186391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34247186391&partnerID=8YFLogxK

U2 - 10.1021/ci600205g

DO - 10.1021/ci600205g

M3 - Article

VL - 47

SP - 407

EP - 424

JO - Journal of Chemical Information and Computer Sciences

JF - Journal of Chemical Information and Computer Sciences

SN - 0095-2338

IS - 2

ER -