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

Three dissimilarity measures to contrast dendrograms.

Guillermo Restrepo1, Héber Mesa, Eugenio J Llanos

  • 1Laboratorio de Química Teórica, Universidad de Pamplona, Pamplona, Colombia.

Journal of Chemical Information and Modeling
|May 1, 2007
PubMed
Summary

This study introduces a novel cluster index for comparing dendrograms, proving most effective for chemical data analysis. It outperforms existing methods in similarity studies and evaluating clustering algorithms on molecular databases.

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

Computational History of Chemistry - Part 1: Challenges and Opportunities.

Ambix·2026
Same author

Expanding diversity in chemical space.

Nature chemistry·2026
Same author

Spaces of mathematical chemistry.

Theory in biosciences = Theorie in den Biowissenschaften·2024
Same author

The Uncertain Role of Nominations for the Nobel Prize in Chemistry<sup>†</sup>.

Chemistry (Weinheim an der Bergstrasse, Germany)·2023
Same author

The six stages of the convergence of the periodic system to its final structure.

Communications chemistry·2023
Same author

The expansion of chemical space in 1826 and in the 1840s prompted the convergence to the periodic system.

Proceedings of the National Academy of Sciences of the United States of America·2022

Area of Science:

  • Computational Chemistry
  • Data Mining
  • Bioinformatics

Background:

  • Dendrograms are crucial for visualizing hierarchical relationships in data.
  • Comparing dendrograms requires robust dissimilarity measures.
  • Existing measures like triples and partition indices have limitations.

Purpose of the Study:

  • To introduce and evaluate a novel cluster index for dendrogram dissimilarity.
  • To compare the cluster index with existing methods (triples, partition indices).
  • To demonstrate the suitability of the cluster index for chemical applications and hierarchical clustering algorithm evaluation.

Main Methods:

  • Decomposition of dendrograms into subsets (clusters or binary partitions).
  • Introduction of the cluster index as a dissimilarity measure focusing exclusively on clusters.

Related Experiment Videos

  • Application and comparison of triples, partition, and cluster indices on chemical datasets.
  • Evaluation of five common hierarchical clustering algorithms using the cluster index on a molecular database.

    • Main Results:

    • The cluster index effectively decomposes dendrograms into distinct clusters.
    • The cluster index demonstrates superior performance in chemical similarity studies compared to triples and partition indices.
    • The cluster index successfully measured differences between dendrograms from various hierarchical clustering algorithms.

    Conclusions:

    • The cluster index is the most suitable dissimilarity measure for dendrograms in chemical investigations.
    • The novel cluster index offers advantages for evaluating clustering algorithms and similarity studies.
    • This method provides a valuable tool for analyzing complex datasets in chemistry and related fields.