Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Enzyme classification using multiclass support vector machine and feature subset selection.

Debasmita Pradhan¹, Sudarsan Padhy¹, Biswajit Sahoo²

¹Department of Computer Scienceing and Engineering, Silicon Institute of Technology, Silicon Hills, Patia, Bhubaneswar, 751024, India.

Computational Biology and Chemistry

|September 22, 2017

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

Urinary bladder agenesis presenting with bilateral pelviureteric junction obstruction in an infant: a rare urological anomaly.

BMJ case reports·2026

Same author

Speech impairment detection in children using time frequency features of speech and deep learning techniques.

Frontiers in human neuroscience·2026

Same author

Neuroimaging of Lightning-Related Cerebral Demyelination: A Case Report.

Cureus·2026

Same author

Mastoid Emissary Vein: A Crucial Collateral Pathway For Extracranial Venous Drainage.

Neurology India·2026

Same author

Breast Cancer Landscape In Eastern India: An Institutional Audit of Clinicopathology And Survival Metrics: Authors: As per order.

Indian journal of surgical oncology·2026

Same author

Bleeding ileal conduit varices in a postoperative patient of urinary bladder carcinoma: percutaneous transhepatic variceal embolization to the rescue.

BMJ case reports·2026

Same journal

Mining negative sequential patterns to improve viral genomic feature representation and classification.

Computational biology and chemistry·2026

Same journal

Integrative in silico analysis identifies functionally and regulatively relevant nsSNPs in the TRIB3 gene.

Computational biology and chemistry·2026

Same journal

MARS: Multi-anchor reasoning for reliable toxicity prediction under distribution shift.

Computational biology and chemistry·2026

Same journal

Zadeh-based fuzzy analysis of carreau tri-hybrid nanofluid hemodynamics in a straight artery with irregular triangular stenosis.

Computational biology and chemistry·2026

Same journal

Exploring C<sub>6</sub>N<sub>6</sub> as an effective drug delivery carrier for anticancer drugs mercaptopurine and thiotepa: A DFT and MD approach.

Computational biology and chemistry·2026

Same journal

Role of Artificial Intelligence in bioinformatics: Revolutionizing molecular docking and DNA tokenization.

Computational biology and chemistry·2026

See all related articles

This study introduces a computational model using feature selection and multiclass Support Vector Machines (SVM) to classify protein functions. The model accurately predicts protein function using a reduced set of physico-chemical properties, improving efficiency over traditional methods.

Area of Science:

Computational Biology
Bioinformatics
Protein Science

Background:

Proteins are vital macromolecules driving cellular functions.
Characterizing protein function computationally is crucial due to the volume of sequence data.
Existing computational methods for protein function prediction are time-consuming or limited.

Purpose of the Study:

To develop and evaluate a computational model for multiclass protein functional classification.
To identify key physico-chemical properties that significantly contribute to protein function prediction.
To enhance existing models for broader applicability in protein function determination.

Main Methods:

A model combining feature subset selection with multiclass Support Vector Machines (SVM) was proposed.

Keywords:

Enzyme classification Multiclass SVM Orthogonal Forward Selection (OFS)Random Forest (RF)SVM Recursive Feature Elimination (SVM-RFE)Sequential Forward Floating Selection (SFFS)

Related Experiment Videos

Thirty-two physico-chemical properties of enzymes from six classes were analyzed.

Feature selection algorithms including Sequential Forward Floating Selection (SFFS), Orthogonal Forward Selection (OFS), and SVM Recursive Feature Elimination (SVM-RFE) were employed.

Main Results:

The proposed model achieved high accuracy, ranging from 91% to 94%, in classifying protein functional classes.
Feature subset selection identified 20 significant physico-chemical properties sufficient for accurate classification.
Orthogonal Forward Selection (OFS) followed by SVM demonstrated superior performance compared to other tested methods.

Conclusions:

The developed model effectively predicts protein functional classes using a reduced set of features.
The study highlights the importance of feature selection in improving the efficiency and accuracy of protein function prediction.
This approach offers a generalized and efficient method for multiclass protein function classification.