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

Fold-specific substitution matrices for protein classification.

R B Vilim1, R M Cunningham, B Lu

  • 1Argonne National Laboratory, 9700 S. Cass Avenue, Argonne, IL 60439, USA. rvilim@anl.gov

Bioinformatics (Oxford, England)
|February 7, 2004
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

Adapting a Youth Sexual Violence Prevention Logic Model and Evaluation to Asian American and Pacific Islander Youth in Iowa: a Case Study.

Prevention science : the official journal of the Society for Prevention Research·2025
Same author

[Reinforcement of personalized management of type 2 diabetes mellitus].

Zhonghua yi xue za zhi·2025
Same author

[Interpretation of the "Technical Guidelines for Disinfection in Epidemic Prevention and Control of Large-Scale Events"].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2025
Same author

[A real-world study of first-line albumin-bound paclitaxel in the treatment of advanced pancreatic cancer in China].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2024
Same author

[Brenner tumor of the vagina: report of a case].

Zhonghua bing li xue za zhi = Chinese journal of pathology·2024
Same author

[Research progress on the impact of diet on the early-onset colorectal cancer].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2024
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

We introduce Class Attribute Substitution Matrices (CLASSUM) to improve protein classification within families. CLASSUM significantly outperforms generic matrices like BLOSUM-62, achieving over 90% accuracy in classifying immunoglobulin sequences.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Protein Science

Background:

  • Traditional methods like Position Specific Scoring Matrices and Hidden Markov Models are effective for protein family assignment but can be parameter-heavy for subclassifications.
  • Within protein families, sequence variability is limited, suggesting a need for more refined, family-specific classification tools.
  • Existing generic substitution matrices may lack the specificity required for accurate attribute class assignment within protein families.

Purpose of the Study:

  • To develop a novel method for organizing proteins within families that reduces the number of parameters compared to existing approaches.
  • To create a new type of substitution matrix, Class Attribute Substitution Matrices (CLASSUM), tailored for attribute differentiation within protein families.
  • To enhance the resolution and accuracy of automated protein classification methods.

Related Experiment Videos

Main Methods:

  • Adapted the log odds ratio, a common measure of similarity, to characterize sequence dissimilarities relevant to attribute differentiation.
  • Developed Class Attribute Substitution Matrices (CLASSUM) as a dual to BLOSUM, specifically designed for intra-family classification.
  • Applied CLASSUM to hierarchically classify sequences within the lambda and kappa subgroups of the immunoglobulin superfamily.

Main Results:

  • Identified key positions for class determination based on amino acid variability.
  • CLASSUM achieved over 90% correct classification of test data in immunoglobulin subgroups, significantly outperforming BLOSUM-62 (35-50%).
  • The performance of CLASSUM substantially exceeded the expected value for a random matrix (14%).

Conclusions:

  • Family-specific, data-derived substitution matrices like CLASSUM can significantly improve the accuracy of automated protein classification.
  • CLASSUM offers a more parameter-efficient and higher-resolution approach for classifying proteins within families compared to generic methods.
  • This approach holds promise for advancing automated protein searching and classification in bioinformatics.