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

Enzyme family classification by support vector machines.

C Z Cai1, L Y Han, Z L Ji

  • 1Department of Applied Physics, Chongqing University, Chongqing, Peoples Republic of China.

Proteins
|March 5, 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

Average and Heterogeneous Associations between Secondhand Smoking and Tooth Loss.

Journal of dental research·2026
Same author

[Clinical characteristics and prognostic factors in patients with cerebrospinal fluid torque teno virus positivity after allogeneic hematopoietic stem cell transplantation].

Zhonghua yi xue za zhi·2026
Same author

[Proteomics analysis of the effect and mechanism of ADSCs on full-thickness skin defects in diabetic rats].

Zhonghua shao shang yu chuang mian xiu fu za zhi·2026
Same author

[Plasmid characteristics and genome tracing analysis of a bacterial dysentery outbreak in Shandong Province, originating from <i>Shigella sonnei</i> producing extended spectrum β-lactamase].

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

Physiological and molecular characteristics associated with the anti-senescence in <i>Camellia oleifera</i> Abel.

Photosynthetica·2024
Same author

[Conjecture on the next development direction of colorectal cancer and its minimally invasive surgery].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2024
Same journal

BioMatics 1.0: A Wasserstein Distance Approach for Next-Generation Multiple Sequence Alignment.

Proteins·2026
Same journal

Engineered HSP90-MP65 Bivalent Fusion Antigen: A Novel Vaccine Candidate Against Invasive Candidiasis.

Proteins·2026
Same journal

Physics-Based Energy Functions for Computational Protein Design.

Proteins·2026
Same journal

Impact of Stabilizing Osmolytes on the Conformational Dynamics of Human and Rat Islet Amyloid Polypeptides.

Proteins·2026
Same journal

Stabilization of Bone Morphogenetic Protein-2 at Physiological pH: Contrasting Roles of CHAPS and Arginine in Aggregation Inhibition.

Proteins·2026
Same journal

Structural Insights Into the Function of Leishmania major Adenylosuccinate Lyase.

Proteins·2026
See all related articles

Support vector machines (SVM) effectively classify enzymes into functional families, aiding protein function prediction. This method demonstrates high accuracy and unique prediction capabilities for enzymes, including distantly related ones.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Enzymology

Background:

  • Protein function prediction is crucial in biology.
  • Classifying proteins into functional families aids prediction.
  • Support vector machines (SVM) show promise for protein classification.

Purpose of the Study:

  • To apply and test Support vector machines (SVM) for classifying enzymes into functional families.
  • To evaluate the accuracy and unique prediction capability of SVM for enzyme classification.

Main Methods:

  • SVM classification systems were trained using representative enzymes and Pfam seed proteins.
  • Enzymes from 46 families and non-enzymes were used for testing.
  • A scoring function was employed to assess unique classification capability.

Related Experiment Videos

Main Results:

  • Classification accuracy for enzymes ranged from 50.0% to 95.7%, and for non-enzymes from 79.0% to 100%.
  • Matthews correlation coefficients were between 54.1% and 96.1%.
  • 80.3% of correctly classified enzymes were uniquely assigned to a specific family.

Conclusions:

  • SVM shows potential for accurate and unique enzyme family classification.
  • SVM can facilitate protein function prediction, even for distantly related or functionally diverse homologous enzymes.
  • Further enhancements include using larger training sets and multi-class SVM systems.