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

Recognizing exons in genomic sequence using GRAIL II

Y Xu1, R Mural, M Shah

  • 1Engineering Physics and Mathematics Division, Oak Ridge National Laboratory, TN 37831-6364.

Genetic Engineering
|January 1, 1994
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

Stakeholder engagement to identify barriers to implementation and inform the development of point-of-care diagnostics for TB.

IJTLD open·2026
Same author

Geriatric Assessment-guided therapy modification and outcomes in patients with non-metastatic gastroesophageal cancer: a retrospective cohort study.

ESMO gastrointestinal oncology·2026
Same author

The impact of co-occurring tumor suppressor mutations with mEGFR as early indicators of relapse in lung cancer.

ESMO open·2025
Same author

Navigating the labyrinth: Phenotypes of IgG4-related disease.

Journal of postgraduate medicine·2025
Same author

Neoadjuvant Chemotherapy and Low Dose Immunotherapy in Resectable Non-small Cell Lung Cancer: A Multi-center Retrospective Cohort Analysis.

Clinical oncology (Royal College of Radiologists (Great Britain))·2025
Same author

Clinical symptoms and surgical outcome of colloid cysts of the third ventricle: A multicenter retrospective study.

Brain & spine·2025
Same journal

Paired-end genomic signature tags: a method for the functional analysis of genomes and epigenomes.

Genetic engineering·2006
Same journal

New mass-spectrometry-based strategies for lipids.

Genetic engineering·2006
Same journal

A high-throughput approach to protein structure analysis.

Genetic engineering·2006
Same journal

Protein overexpression in mammalian cell lines.

Genetic engineering·2006
Same journal

Proximity ligation: a specific and versatile tool for the proteomic era.

Genetic engineering·2006
Same journal

Salicylic acid-, jasmonic acid- and ethylene-mediated regulation of plant defense signaling.

Genetic engineering·2006
See all related articles

GRAIL II, an improved neural network system, accurately identifies human protein-coding regions (exons) in DNA. This system enhances exon recognition, achieving high accuracy and a low false positive rate for genomic analysis.

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Accurate identification of protein-coding regions (exons) in genomic DNA is crucial for understanding gene function.
  • Previous computational methods for exon recognition had limitations in accuracy and performance across varying exon lengths.

Purpose of the Study:

  • To describe an improved neural network system, GRAIL II, for enhanced recognition of protein-coding regions in human genomic DNA.
  • To significantly improve upon the coding recognition performance of earlier GRAIL systems.

Main Methods:

  • GRAIL II employs a multi-step process including generating exon candidate pools and applying heuristic rules.
  • Utilizes three trained neural networks to evaluate coding potential and edge accuracy of exon candidates.

Related Experiment Videos

  • Incorporates variable-length windows and diverse features like splice junction scores and GC composition for improved discrimination.

    • Main Results:

    • GRAIL II successfully located 93% of all exons across a large dataset with a 12% false positive rate.
    • Achieved exact base-pair matching for 62% of true positive exons and correct edge matching for 93%.
    • Performance is largely independent of exon length, a significant improvement over previous versions.

    Conclusions:

    • GRAIL II represents a substantial advancement in identifying protein-coding regions within human genomic sequences.
    • The system's high accuracy and robustness make it a valuable tool for genomic research.
    • Further improvements in accuracy and false positive rates are achievable through integrated gene model construction using the Gene Assembly Program (GAP III).