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

Pattern recognition display methods for the analysis of computed molecular properties.

B Hudson1, D J Livingstone, E Rahr

  • 1Department of Physical Sciences, Wellcome Research Laboratories, Beckenham, Kent, U.K.

Journal of Computer-Aided Molecular Design
|March 1, 1989
PubMed
Summary

Unsupervised learning methods effectively analyze large datasets in computer chemistry. These pattern recognition techniques, using linear and non-linear displays, aid in exploring biologically active molecules.

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

Investigating the impact of non-gated thoracic CT prior to CTCA to reduce layered testing.

Clinical radiology·2023
Same author

Under-mask beard covers achieve an adequate seal with tight-fitting disposable respirators using quantitative fit testing.

The Journal of hospital infection·2022
Same author

Report from the Annual Conference of the British Society of Echocardiography, October 2018, ACC Liverpool, Liverpool.

Echo research and practice·2020
Same author

Computed tomographic and clinical features of pulmonary veno-occlusive disease: raising the radiologist's awareness.

Clinical radiology·2019
Same author

Clinical Record: A Case of Pulmonary Consolidation of Doubtful Origin.

Bristol medico-chirurgical journal (1883)·2017
Same author

Quenching interactions and nonexponential decay: tryptophan 138 of bacteriophage T4 lysozyme.

Journal of fluorescence·2013

Area of Science:

  • Computational chemistry
  • Cheminformatics
  • Data science

Background:

  • Large datasets are generated in computer chemistry, requiring efficient analysis methods.
  • Preliminary data analysis is crucial for identifying patterns and insights.

Purpose of the Study:

  • To demonstrate the utility of unsupervised learning for preliminary analysis of computer chemistry data.
  • To showcase linear and non-linear display methods for exploratory data analysis.
  • To discuss the pros and cons of these pattern recognition techniques.

Main Methods:

  • Application of unsupervised learning techniques.
  • Utilizing linear and non-linear display methods for data visualization.
  • Analysis of two datasets containing biologically active molecules.

Related Experiment Videos

Main Results:

  • Unsupervised learning proved suitable for exploratory analysis of large chemical datasets.
  • Linear and non-linear display methods effectively visualized patterns in biologically active molecule data.
  • Specific advantages and disadvantages of the employed techniques were identified.

Conclusions:

  • Unsupervised learning and display methods are valuable tools for preliminary analysis in computer chemistry.
  • These methods facilitate the exploration of complex datasets, particularly those involving biologically active molecules.