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

Search for predictive generic model of aqueous solubility using Bayesian neural nets.

P Bruneau1

  • 1AstraZeneca Centre de Recherche, Parc Industriel Pompelle, BP 1050, 51689 Reims, France. Pierre.Bruneau@astrazeneca.com

Journal of Chemical Information and Computer Sciences
|December 26, 2001
PubMed
Summary

Developing accurate aqueous solubility prediction models is crucial for drug discovery. A diverse dataset and Bayesian neural networks with automatic relevance determination (ARD) yielded the most effective predictive model for drug hunting applications.

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

SEIS: Insight's Seismic Experiment for Internal Structure of Mars.

Space science reviews·2019
Same author

[Magnetic resonance angiography. Value for evaluating the patency of aortocoronary bypass].

Presse medicale (Paris, France : 1983)·1996
Same author

Glucuronidation associated with intrinsic resistance to mycophenolic acid in human colorectal carcinoma cells.

Cancer research·1996
Same author

Glucuronidation by human colorectal adenocarcinoma cells as a mechanism of resistance to mycophenolic acid.

Advances in enzyme regulation·1995
Same author

Conformational analysis of 5-lipoxygenase inhibitors: role of the substituents in chiral recognition and on the active conformations of the (methoxyalkyl)thiazole and methoxytetrahydropyran series.

Journal of medicinal chemistry·1994
Same author

[Prognostic value of thallium-201 myocardial scintigraphy in patients with hypertension, suspected of coronary disease].

Annales de cardiologie et d'angeiologie·1993

Area of Science:

  • Computational Chemistry
  • Drug Discovery
  • Machine Learning

Background:

  • Existing aqueous solubility models often lack applicability in drug hunting due to limited structural diversity in training data.
  • There is a need for robust predictive models that generalize well to novel chemical structures relevant to drug research.

Purpose of the Study:

  • To develop and evaluate predictive models for aqueous solubility using diverse chemical datasets.
  • To assess the performance of different modeling approaches, including Bayesian neural networks and descriptor selection methods.

Main Methods:

  • Gathered a diverse dataset of compounds from literature and proprietary sources, divided into literature (I), proprietary (II), and mixed (III) sets.
  • Calculated approximately 100 surface-property descriptors for each compound.

Related Experiment Videos

  • Employed Bayesian learning of neural networks with descriptor selection via Gram-Schmidt (GS) or automatic relevance determination (ARD) on datasets I, II, and III.
  • Validated model performance using unrelated datasets and introduced new metrics: Normalized Descriptor Distance (NDD) and Combination of Descriptor Distance (CD).

    • Main Results:

    • A generic predictive model could be derived from the literature dataset (I).
    • The proprietary dataset (II) was too limited in diversity to produce a model with good generalization ability.
    • The automatic relevance determination (ARD) method applied to the mixed dataset (III) yielded the best predictive model.

    Conclusions:

    • The study highlights the importance of dataset diversity for developing generalizable predictive models in drug discovery.
    • Bayesian neural networks combined with ARD on a mixed dataset offer a promising approach for accurate aqueous solubility prediction.
    • The developed model demonstrates improved applicability for drug hunting compared to models trained on less diverse datasets.