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

Locating protein-coding regions in human DNA sequences by a multiple sensor-neural network approach.

E C Uberbacher1, R J Mural

  • 1Biology Division, Oak Ridge National Laboratory, TN.

Proceedings of the National Academy of Sciences of the United States of America
|December 15, 1991
PubMed
Summary

Researchers developed a computational method to identify protein-coding regions in DNA. This gene identification approach uses sensor algorithms and a neural network, achieving high accuracy with fewer false positives for DNA sequence analysis.

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 tools for protein modeling.

Current protein & peptide science·2002
Same author

ARTEMIS: a tool for displaying and annotating DNA sequence.

Briefings in bioinformatics·2001
Same author

The sequence of the human genome.

Science (New York, N.Y.)·2001
Same author

Sequence-structure specificity of a knowledge based energy function at the secondary structure level.

Bioinformatics (Oxford, England)·2000
Same author

Current status of computational gene finding: a perspective.

Methods in enzymology·1999
Same author

The Genome Channel: a browser to a uniform first-pass annotation of genomic DNA.

Trends in genetics : TIG·1999

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Eukaryotic genes are large, with protein-coding regions comprising a small fraction of the total DNA sequence.
  • Identifying genes within extensive uncharacterized DNA regions presents a significant challenge in current research.

Purpose of the Study:

  • To present a reliable computational strategy for locating protein-coding gene segments within anonymous DNA sequences.
  • To develop a robust method for gene identification applicable to large genomic datasets.

Main Methods:

  • A novel approach combining multiple sensor algorithms to analyze local DNA sequence characteristics.
  • Integration of a neural network with sensor algorithms to accurately localize coding regions.
  • Development of a 'coding recognition module' for automated gene feature detection.

Related Experiment Videos

Main Results:

  • The 'coding recognition module' successfully identifies 90% of coding exons that are 100 bases or longer.
  • The method achieves a low false positive rate, with fewer than one false positive per five identified coding exons.
  • Demonstrates superior performance compared to existing gene identification methods.

Conclusions:

  • The developed computational approach offers a reliable and accurate solution for identifying protein-coding regions in DNA.
  • This method has broad applicability to various sequence-pattern recognition challenges in bioinformatics.
  • The 'coding recognition module' is available for use in ongoing genetic research.