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

Locally linear embedding for dimensionality reduction in QSAR.

P J L'Heureux1, J Carreau, Y Bengio

  • 1DIRO, Université de Montreal, C.P. 6128, Succ. Centre-Ville, Montreal, Canada. lheureup@iro.umontreal.ca

Journal of Computer-Aided Molecular Design
|February 26, 2005
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

[Clinical characteristics and prognosis of 49 newly diagnosed primary central nervous system diffuse large B-cell lymphoma].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2022
Same author

[Clipping for large paraclinoid internal carotid artery aneurysms by non-fluoroscopic occlusion via a micro-bone window frontolateral approach].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2018
Same author

[Clinical analysis of 10 patients of chronic subdural hematoma associated with arachnoid cyst].

Zhonghua yi xue za zhi·2017
Same author

[Stereotactic brain biopsy guided by iMRI co-registration combined with PET/CT].

Zhonghua yi xue za zhi·2016
Same author

Intracranial aneurysm risk factor genes: relationship with intracranial aneurysm risk in a Chinese Han population.

Genetics and molecular research : GMR·2015
Same author

Adaptive importance sampling to accelerate training of a neural probabilistic language model.

IEEE transactions on neural networks·2008
Same journal

Topological data analysis for antibody-drug conjugate payload discovery: a computational framework for mechanistic classification and target validation.

Journal of computer-aided molecular design·2026
Same journal

Commentary on the fundamentals and development of artificial intelligence models in the life sciences and best research practices.

Journal of computer-aided molecular design·2026
Same journal

RANQSAR: a standalone open-source application for reproducible machine learning-based QSAR analysis.

Journal of computer-aided molecular design·2026
Same journal

Integrating evolutionary and compositional features with ML and DL for robust and interpretable druggable protein prediction.

Journal of computer-aided molecular design·2026
Same journal

QUAD: a composite risk framework integrating uncertainty, applicability domain, and model disagreement for reliable QSAR predictions.

Journal of computer-aided molecular design·2026
Same journal

Comparative quantum-chemical investigation of 2-chloro-N-(4-methoxyphenyl)acetamide and 2-(4-methoxyphenylamino)-2-oxoethyl meth/acrylate: DFT, TD-DFT, and non-covalent interaction analyses.

Journal of computer-aided molecular design·2026
See all related articles

This study introduces Locally Linear Embedding (LLE), a non-linear dimensionality reduction technique, for Quantitative Structure Activity Relationship (QSAR) modeling. LLE offers a more stable and informative approach to chemical data representation compared to traditional methods.

Area of Science:

  • Computational Chemistry
  • Cheminformatics
  • Data Science

Background:

  • Quantitative Structure Activity Relationship (QSAR) methods typically involve extensive descriptor generation and selection.
  • Variable selection, while reducing dimensionality, can lead to loss of valuable chemical information.
  • Existing non-linear dimensionality reduction techniques may not always provide stable representations for chemical data.

Purpose of the Study:

  • To introduce Locally Linear Embedding (LLE) as a novel non-linear dimensionality reduction technique for QSAR.
  • To demonstrate LLE's capability in discovering low-dimensional representations of chemical data.
  • To evaluate the stability and information retention of LLE compared to other methods.

Main Methods:

  • Application of Locally Linear Embedding (LLE), a local non-linear dimensionality reduction algorithm.

Related Experiment Videos

  • Statistical analysis to discover low-dimensional representations of chemical data.
  • Comparative evaluation against other non-linear dimensionality reduction algorithms.

    • Main Results:

    • LLE successfully generates stable low-dimensional representations of chemical data.
    • LLE captures non-linear relationships within chemical datasets more effectively.
    • The method proves more robust than alternative non-linear dimensionality reduction techniques.

    Conclusions:

    • Locally Linear Embedding (LLE) provides a powerful alternative for dimensionality reduction in QSAR.
    • LLE enhances the stability and information content of chemical data representations.
    • This approach advances the development of more accurate and reliable QSAR models.