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

The neural network as a tool for multispectral interpretation

M E Munk1, M S Madison, E W Robb

  • 1Department of Chemistry and Biochemistry, Arizona State University, Tempe 85287-1604, USA.

Journal of Chemical Information and Computer Sciences
|March 1, 1996
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

HOUDINI: a new approach to computer-based structure generation.

Journal of chemical information and computer sciences·2003
Same author

Applications of a HOUDINI-based structure elucidation system.

Journal of chemical information and computer sciences·2003
Same author

A novel formalism to characterize the degree of unsaturation of organic molecules.

Journal of chemical information and computer sciences·2001
Same author

Performance of whole blood IFN-gamma test for tuberculosis diagnosis based on PPD or the specific antigens ESAT-6 and CFP-10.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2001
Same author

Numbers of IFN-gamma-producing cells against ESAT-6 increase in tuberculosis patients during chemotherapy.

The international journal of tuberculosis and lung disease : the official journal of the International Union against Tuberculosis and Lung Disease·2001
Same author

Use of ESAT-6 and CFP-10 antigens for diagnosis of extrapulmonary tuberculosis.

The Journal of infectious diseases·2000
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
See all related articles

A new neural network accurately identifies organic compound substructures using combined spectroscopic data (infrared, carbon-13 NMR) and molecular formulas. This approach significantly improves accuracy compared to single-data methods.

Area of Science:

  • Computational chemistry
  • Spectroscopy
  • Machine learning

Background:

  • Organic compound structure elucidation is crucial in chemistry.
  • Traditional methods can be time-consuming and complex.
  • Spectroscopic data (IR, NMR) and molecular formulas are key inputs.

Purpose of the Study:

  • To develop a neural network model for enhanced structure elucidation of organic compounds.
  • To evaluate the performance of a multi-modal data approach versus single-data methods.

Main Methods:

  • Development of a single-hidden-layer neural network.
  • Training the network using backpropagation and simplex optimization.
  • Utilizing a database of 1560 organic compounds with IR spectra, C-13 NMR spectra, and molecular formulas.

Related Experiment Videos

Main Results:

  • The trained neural network achieved high accuracy in identifying substructural features.
  • Combining data from IR, C-13 NMR, and molecular formulas yielded superior results.
  • Performance significantly surpassed networks trained on single spectroscopic data types.

Conclusions:

  • Multi-modal data integration in neural networks enhances the accuracy of organic compound structure elucidation.
  • This approach has significant implications for computer-aided structure elucidation systems like SESAMI.