skip to main content

Development of Dimethyl Sulfoxide Solubility Models Using 163 000 Molecules: Using a Domain Applicability Metric to Select More Reliable Predictions

Tetko, Igor V ; Novotarskyi, Sergii ; Sushko, Iurii ; Ivanov, Vladimir ; Petrenko, Alexander E ; Dieden, Reiner ; Lebon, Florence ; Mathieu, Benoit

Journal of chemical information and modeling, 2013-08-26, Vol.53 (8), p.1990-2000 [Peer Reviewed Journal]

Full text available

Citations Cited by
  • Title:
    Development of Dimethyl Sulfoxide Solubility Models Using 163 000 Molecules: Using a Domain Applicability Metric to Select More Reliable Predictions
  • Author: Tetko, Igor V ; Novotarskyi, Sergii ; Sushko, Iurii ; Ivanov, Vladimir ; Petrenko, Alexander E ; Dieden, Reiner ; Lebon, Florence ; Mathieu, Benoit
  • Subjects: Databases, Pharmaceutical ; Reproducibility of Results ; Artificial Intelligence ; Dimethyl Sulfoxide - chemistry ; Informatics - methods ; Solubility ; Linear Models ; Support Vector Machine ; Neural Networks (Computer) ; Index Medicus
  • Is Part Of: Journal of chemical information and modeling, 2013-08-26, Vol.53 (8), p.1990-2000
  • Description: The dimethyl sulfoxide (DMSO) solubility data from Enamine and two UCB pharma compound collections were analyzed using 8 different machine learning methods and 12 descriptor sets. The analyzed data sets were highly imbalanced with 1.7–5.8% nonsoluble compounds. The libraries’ enrichment by soluble molecules from the set of 10% of the most reliable predictions was used to compare prediction performances of the methods. The highest accuracies were calculated using a C4.5 decision classification tree, random forest, and associative neural networks. The performances of the methods developed were estimated on individual data sets and their combinations. The developed models provided on average a 2-fold decrease of the number of nonsoluble compounds amid all compounds predicted as soluble in DMSO. However, a 4–9-fold enrichment was observed if only 10% of the most reliable predictions were considered. The structural features influencing compounds to be soluble or nonsoluble in DMSO were also determined. The best models developed with the publicly available Enamine data set are freely available online at http://ochem.eu/article/33409.
  • Publisher: United States: American Chemical Society
  • Language: English
  • Identifier: ISSN: 1549-9596
    ISSN: 1549-960X
    EISSN: 1549-960X
    DOI: 10.1021/ci400213d
    PMID: 23855787
  • Source: © ProQuest LLC All rights reserved

Searching Remote Databases, Please Wait