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

Markov model recognition and classification of DNA/protein sequences within large text databases.

Jonathan D Wren1, William H Hildebrand, Sreedevi Chandrasekaran

  • 1Advanced Center for Genome Technology, Stephenson Research and Technology Center, Department of Botany and Microbiology, The University of Oklahoma, 101 David L. Boren Blvd., Rm 2025, Norman, OK 73019, USA. Jonathan.Wren@OU.edu

Bioinformatics (Oxford, England)
|September 15, 2005
PubMed
Summary

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

A Non-Canonical Role for Hepatocyte MLKL in Promoting Mitochondrial Dysfunction and Senescence in the Aging Liver.

Aging cell·2026
Same author

Presentation of identical tumor antigen peptides by canine and human MHC class I.

iScience·2026
Same author

NetMHCIIphosPan: A Machine Learning Tool for Predicting HLA Class II Antigen Presentation of Phosphorylated Peptides.

Journal of proteome research·2026
Same author

Mutations outside the MR1 antigen binding groove differentially inhibit presentation of exogenous antigens.

The Journal of biological chemistry·2026
Same author

NetMHCIIphosPan: a machine learning tool for predicting HLA class II antigen presentation of phosphorylated peptides.

bioRxiv : the preprint server for biology·2026
Same author

Hepatocyte MLKL Drives Obesity-Driven Hepatocellular Carcinoma Progression via Mitochondrial Dysfunction Independent of Necroptosis in MASLD.

bioRxiv : the preprint server for biology·2025

This study introduces an n-gram Markov model (MM) to automatically identify and classify biological sequence patterns from scientific literature. The system shows high accuracy for primers and potential for efficient database curation.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Short sequence patterns are crucial for biological functions but are difficult to retrieve from literature.
  • Existing methods for locating sequence information are often manual and inefficient.
  • Automated systems are needed to extract and classify these patterns from large text corpora.

Purpose of the Study:

  • To develop and evaluate an n-gram Markov model (MM) for automated identification and classification of biological sequence patterns.
  • To assess the system's performance on large-scale scientific literature datasets.
  • To compare the system's accuracy with existing curated databases.

Main Methods:

  • Utilized an n-gram Markov model (MM) for sequence pattern identification and classification.

Related Experiment Videos

  • Applied the MM to analyze large corpora, including Medline abstracts and Journal of Virology articles.
  • Benchmarked performance against manually curated databases like VirOligo and the HLA Ligand Database.

    • Main Results:

    • Achieved high accuracy (98% precision/84% recall) for primer identification and classification.
    • Demonstrated moderate accuracy (67% precision/85% recall) for peptide epitope identification.
    • Observed a significant difference in sequence data reporting between abstracts and full-text articles.

    Conclusions:

    • Automated extraction and classification of sequence elements using MM is a viable and cost-effective approach for database curation.
    • The system shows promise for enhancing the accessibility and annotation of biological sequence data.
    • Further development may improve classification accuracy for complex sequence types.