Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Accurate solubility prediction with error bars for electrolytes: a machine learning approach.

Anton Schwaighofer1, Timon Schroeter, Sebastian Mika

  • 1Fraunhofer FIRST, Kekuléstrasse 7, 12489 Berlin, Germany. anton@first.fraunhofer.de

Journal of Chemical Information and Modeling
|January 25, 2007
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Towards robust foundation models for digital pathology.

Nature communications·2026
Same author

Beyond attention heatmaps: How to get better explanations for multiple instance learning models in histopathology.

Medical image analysis·2026
Same author

AI-based discovery of functional boundaries in the human brain from intraoperative electrophysiology.

medRxiv : the preprint server for health sciences·2026
Same author

Modeling attention and binding in the brain through bidirectional recurrent gating.

Nature communications·2026
Same author

How simple can you go? An off-the-shelf transformer approach to molecular dynamics.

The Journal of chemical physics·2026
Same author

Software for dataset-wide XAI: From local explanations to global insights with Zennit, CoRelAy, and ViRelAy.

PloS one·2026

This study introduces GPsol, a new machine learning model for predicting aqueous solubility. GPsol offers higher accuracy than commercial tools and provides prediction error bars for better in silico modeling.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning

Background:

  • Accurate prediction of aqueous solubility is crucial for drug design and chemical research.
  • Existing in silico models and commercial tools often lack sufficient accuracy, especially for electrolytes.

Purpose of the Study:

  • To develop a highly accurate statistical model for predicting aqueous solubility.
  • To provide reliable error estimates for solubility predictions.

Main Methods:

  • Utilized a Gaussian Process nonlinear regression model (GPsol) trained on measured solubility data.
  • Compared the performance of GPsol against 14 scientific studies and 6 commercial tools.

Main Results:

  • The GPsol model demonstrated significantly higher accuracy in predicting the solubility of electrolytes compared to commercial tools.

Related Experiment Videos

  • The model successfully provides individual error bars for each prediction, enhancing reliability.

    • Conclusions:

    • GPsol represents a significant advancement in in silico aqueous solubility prediction.
    • The model's accuracy and error quantification offer valuable improvements for drug discovery and chemical research.