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

Predicting the sub-cellular location of proteins from text using support vector machines.

B J Stapley1, L A Kelley, M J E Sternberg

  • 1Biomolecular Modelling Laboratory, Imperial Cancer Research Fund, 44 Lincoln's Inn Field, London, WC2A 3PX, United Kingdom. b.stapley@icrf.icnet.uk

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|April 4, 2002
PubMed
Summary

This study introduces an automated method using Support Vector Machines (SVM) to predict protein sub-cellular locations from Medline abstract text, outperforming amino acid composition methods.

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

The Effects of Proportional Processing and Multiple Opponents on Contest Assessment in Male Green Swordtail Fish (Xiphophorus hellerii).

Integrative and comparative biology·2025
Same author

Impact of haemophilia with inhibitors on caregiver burden in the United States.

Haemophilia : the official journal of the World Federation of Hemophilia·2014
Same author

Understanding the experience of caring for children with haemophilia: cross-sectional study of caregivers in the United States.

Haemophilia : the official journal of the World Federation of Hemophilia·2014
Same author

Proteomic analysis of Plasmodium in the mosquito: progress and pitfalls.

Parasitology·2012
Same author

The flagellum in malarial parasites.

Current opinion in microbiology·2010
Same author

EMAAS: an extensible grid-based rich internet application for microarray data analysis and management.

BMC bioinformatics·2008

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Molecular Biology

Background:

  • Determining protein sub-cellular localization is crucial for understanding cellular functions.
  • Existing methods may be limited in scope or require extensive domain knowledge.

Purpose of the Study:

  • To develop an automated text-based method for classifying protein sub-cellular locations.
  • To evaluate the performance of this method against existing approaches.

Main Methods:

  • Generated term vectors from Medline abstracts for proteins.
  • Utilized Support Vector Machines (SVM) to classify sub-cellular locations based on textual features.
  • Benchmarked the method on Saccharomyces cerevisiae proteins with known locations.

Related Experiment Videos

Main Results:

  • The text-based SVM method achieved high performance in classifying sub-cellular locations.
  • Outperformed SVMs trained on amino acid composition alone.
  • Combining text features with amino acid composition improved recall for certain locations.

Conclusions:

  • Automated text analysis of Medline abstracts is an effective strategy for predicting protein sub-cellular localization.
  • This approach offers a generalizable tool for various biological classification tasks.
  • Integration with other data types, like amino acid composition, can further enhance predictive accuracy.