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

Classification of small molecules by two- and three-dimensional decomposition kernels.

Alessio Ceroni1, Fabrizio Costa, Paolo Frasconi

  • 1Machine Learning and Neural Networks Group, Dipartimento di Sistemi e Informatica, Universitá degli Studi di Firenze, Italy.

Bioinformatics (Oxford, England)
|June 7, 2007
PubMed
Summary
This summary is machine-generated.

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 a more reliable assessment of aortic diameters using a Bayesian Z-score.

Scientific reports·2026
Same author

Multi-parental cross design-based QTL mapping approach elucidates fruit firmness and softening genetic control in European pears (Pyrus communis).

Journal of experimental botany·2025
Same author

Deep learning-based localization algorithms on fluorescence human brain 3D reconstruction: a comparative study using stereology as a reference.

Scientific reports·2024
Same author

Corrigendum to "Machine learning approach for prediction of outcomes in anticoagulated patients with atrial fibrillation" [International Journal of Cardiology 407 (2024) 132088].

International journal of cardiology·2024
Same author

Editorial: Omics technologies and fruit postharvest quality.

Frontiers in plant science·2024
Same author

Machine learning approach for prediction of outcomes in anticoagulated patients with atrial fibrillation.

International journal of cardiology·2024

New kernel methods for small molecule classification effectively combine 2D and 3D chemical structure information. This approach enhances prediction accuracy for datasets including cancer screening and HIV drug discovery.

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Machine learning

Background:

  • Kernel-based methods are increasingly used for small molecule classification.
  • Existing methods primarily utilize 2D chemical structure representations.
  • There is a need for kernels that effectively incorporate 3D molecular information.

Purpose of the Study:

  • To develop novel kernel methods for small molecule classification.
  • To integrate and leverage both 2D and 3D chemical structure information.
  • To improve the predictive accuracy of molecular classification models.

Main Methods:

  • Introduction of new kernel construction techniques for small molecules.
  • Combination of 2D and 3D molecular descriptors within kernel functions.

Related Experiment Videos

  • Application of Support Vector Machines (SVM) for binary classification tasks.

    • Main Results:

    • The proposed kernels effectively utilize and combine 2D and 3D molecular information.
    • Consistent improvements in prediction accuracy were observed across multiple datasets.
    • Performance was validated on the 60 NCI cancer screening datasets and the NCI HIV dataset.

    Conclusions:

    • Incorporating 3D information via novel kernels significantly enhances small molecule classification accuracy.
    • The developed methods offer a more comprehensive approach to molecular data analysis.
    • The findings have implications for drug discovery and development through improved predictive modeling.