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

Nonlinear prediction of quantitative structure-activity relationships.

Peter Tiño1, Ian T Nabney, Bruce S Williams

  • 1School of Computer Science, Birmingham University, Birmingham B15 2TT, U.K. p.tino@cs.bham.ac.uk

Journal of Chemical Information and Computer Sciences
|September 28, 2004
PubMed
Summary

Predicting the octanol-water partition coefficient (logP) is crucial for drug discovery. This study demonstrates that a simple 14-variable molecular representation with advanced machine learning accurately predicts logP, outperforming complex methods.

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

Structure Is Information: Structural Identifiability Mappings for Machine Learning With Partially Observed Dynamical Systems.

IEEE transactions on cybernetics·2026
Same author

Endocrine and metabolic determinants of cardiometabolic risk in mild autonomous cortisol secretion.

EBioMedicine·2026
Same author

AI-guided patient stratification improves outcomes and efficiency in the AMARANTH Alzheimer's Disease clinical trial.

Nature communications·2025
Same author

Whole-genome phenotype prediction with machine learning: open problems in bacterial genomics.

Bioinformatics (Oxford, England)·2025
Same author

Linear simple cycle reservoirs at the edge of stability perform Fourier decomposition of the input driving signals.

Chaos (Woodbury, N.Y.)·2025
Same author

Machine learning reveals sex differences in distinguishing between conduct-disordered and neurotypical youth based on emotion processing dysfunction.

BMC psychiatry·2025

Area of Science:

  • Computational chemistry and cheminformatics.
  • Machine learning applications in drug discovery.

Background:

  • Predicting the octanol-water partition coefficient (logP) is a fundamental challenge in Quantitative Structure-Activity Relationships (QSAR).
  • Accurate logP prediction is vital for assessing drug absorption, distribution, metabolism, and excretion (ADME) properties.

Purpose of the Study:

  • To develop a more accurate and efficient method for predicting logP values.
  • To evaluate the performance of machine learning algorithms using a simplified molecular representation.

Main Methods:

  • Utilized a molecular representation consisting of 14 variables.
  • Applied advanced machine learning algorithms for logP prediction.
  • Compared the predictive accuracy against existing benchmark algorithms.

Related Experiment Videos

Main Results:

  • Achieved higher accuracy in logP prediction compared to traditional benchmark methods.
  • Demonstrated the effectiveness of a simple molecular representation when combined with sophisticated machine learning techniques.
  • The proposed method shows superior performance on new, unseen compounds.

Conclusions:

  • A simplified molecular descriptor set can yield highly accurate logP predictions.
  • Advanced machine learning models offer a powerful approach to QSAR problems.
  • This method provides a more efficient and accurate tool for drug discovery and chemical property assessment.