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

Mismatch string kernels for discriminative protein classification.

Christina S Leslie1, Eleazar Eskin, Adiel Cohen

  • 1Department of Computer Science, Columbia University, 1214 Amsterdam Avenue, Mail Code 0401, New York, NY 10027, USA. cleslie@cs.columbia.edu

Bioinformatics (Oxford, England)
|March 3, 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

Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells.

bioRxiv : the preprint server for biology·2026
Same author

<i>SPP1</i><sup>hi</sup> macrophages in fibrin niches promote hyperplastic tissue remodeling in rheumatoid arthritis synovium.

Science translational medicine·2026
Same author

Automated implementation of the SwabSeq COVID-19 diagnostic assay on the opentrons flex liquid-handling robot.

Diagnostic microbiology and infectious disease·2026
Same author

Single-cell profiling of DNA methylation in autism spectrum disorder prefrontal cortex reveals distinct regulatory and aging signatures.

Cell genomics·2026
Same author

Interleukin-12 induces rapid STAT4/DDX5-dependent remodeling of RNA polymerase II occupancy in NK cells.

The Journal of experimental medicine·2026
Same author

Human pancreatic progenitor organoids define genetic and epigenetic barriers to early PDAC transformation.

Developmental cell·2026
Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026
Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026
Same journal

EDEL: Enhancing Dense Retrievers for Curation of Biomedical Knowledge Bases.

Bioinformatics (Oxford, England)·2026
Same journal

Informative Relational Learning for Adverse Reaction Prediction with Enhanced Generalization to Novel Drugs.

Bioinformatics (Oxford, England)·2026
Same journal

An interpretable deep learning framework uncovers features governing CRISPR-Cas9 genome-editing efficiency.

Bioinformatics (Oxford, England)·2026
Same journal

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

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

We developed mismatch kernels for protein sequence classification and homology detection. This machine learning approach efficiently compares protein sequences, identifying important biological motifs with competitive performance.

Area of Science:

  • Computational Biology
  • Bioinformatics
  • Machine Learning

Background:

  • Protein sequence classification is crucial for understanding protein function and structure.
  • Existing machine learning methods offer good performance but can be computationally intensive.
  • There is a need for efficient and biologically relevant methods for protein sequence comparison.

Purpose of the Study:

  • To introduce a novel class of string kernels, termed mismatch kernels, for protein classification.
  • To enable efficient and accurate remote homology detection using machine learning.
  • To provide a biologically motivated alternative to traditional generative models.

Main Methods:

  • Developed mismatch kernels that quantify sequence similarity based on shared, mutable patterns.

Related Experiment Videos

  • Utilized a mismatch tree data structure for efficient kernel computation.
  • Integrated mismatch kernels with Support Vector Machines (SVMs) for discriminative classification.

    • Main Results:

    • Mismatch kernels with SVMs demonstrate competitive performance in protein classification and homology detection on benchmark datasets.
    • The method is particularly effective when limited training data is available.
    • Analysis of learned patterns identified biologically significant motifs within protein families.

    Conclusions:

    • Mismatch kernels offer an efficient and biologically relevant approach to protein sequence analysis.
    • This method advances discriminative machine learning applications in bioinformatics.
    • The approach facilitates the discovery of functional protein motifs.