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 Concept Videos

Protein Families02:47

Protein Families

Protein families are groups of homologous proteins; that is, they have similarities in amino acid sequences and three-dimensional structures. Protein families usually occur because of gene duplication, where an additional copy of a gene is inserted into the genome of an organism.   Mutations that change the amino acids but still allow the protein to be properly synthesized, will lead to new protein family members.   If these new proteins contain similar amino acids in key locations, protein...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Ensemble Deep Learning Models on Raw DNA Sequences for Viral Genome Identification in Human Samples.

Sensors (Basel, Switzerland)·2026
Same author

Matrix-based vector representations in neural networks for classifying molecular biology data.

Bioinformatics advances·2025
Same author

Entropy-Regularized Attention for Explainable Histological Classification with Convolutional and Hybrid Models.

Entropy (Basel, Switzerland)·2025
Same author

Advancing Precision: A Comprehensive Review of MRI Segmentation Datasets from BraTS Challenges (2012-2025).

Sensors (Basel, Switzerland)·2025
Same author

Deep Ensembling of Multiband Images for Earth Remote Sensing and Foramnifera Data.

Sensors (Basel, Switzerland)·2025
Same author

Postprocessing for Skin Detection.

Journal of imaging·2024

Related Experiment Video

Updated: Jun 12, 2026

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

High performance set of PseAAC and sequence based descriptors for protein classification.

Loris Nanni1, Sheryl Brahnam, Alessandra Lumini

  • 1Department of Electronic, Informatics and Systems (DEIS), Università di Bologna, Via Venezia 52, 47023 Cesena, Italy. loris.nanni@unibo.it

Journal of Theoretical Biology
|June 19, 2010
PubMed
Summary

This study introduces a general method for protein classification by fusing multiple feature extraction techniques. This ensemble approach significantly improves classification accuracy across diverse datasets, outperforming existing methods.

More Related Videos

Identification of Protein Complexes in Escherichia coli using Sequential Peptide Affinity Purification in Combination with Tandem Mass Spectrometry
14:58

Identification of Protein Complexes in Escherichia coli using Sequential Peptide Affinity Purification in Combination with Tandem Mass Spectrometry

Published on: November 12, 2012

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates
13:49

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates

Published on: December 6, 2017

Related Experiment Videos

Last Updated: Jun 12, 2026

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
06:50

Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions

Published on: January 26, 2024

Identification of Protein Complexes in Escherichia coli using Sequential Peptide Affinity Purification in Combination with Tandem Mass Spectrometry
14:58

Identification of Protein Complexes in Escherichia coli using Sequential Peptide Affinity Purification in Combination with Tandem Mass Spectrometry

Published on: November 12, 2012

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates
13:49

Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates

Published on: December 6, 2017

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Proteomics

Background:

  • Reliable automatic protein classification is crucial for drug discovery and vaccine development.
  • Existing protein classification methods often lack generalizability across different datasets and applications.
  • There is a need for robust feature extraction and classification strategies that perform well across multiple protein-related problems.

Purpose of the Study:

  • To develop a generalizable method for protein classification that performs well across diverse datasets and problems.
  • To evaluate and compare various feature extraction approaches and their combinations for protein representation.
  • To identify an optimal ensemble of methods for enhancing protein classification accuracy.

Main Methods:

  • Evaluation of multiple protein descriptors derived from amino acid sequences.
  • Utilizing an ensemble of support vector machines (SVMs) as classifiers.
  • Comparison of over ten protein descriptors across nine diverse datasets using a blind testing protocol.
  • Introduction and evaluation of two novel descriptors: one based on wavelets and another on amino acid groups.

Main Results:

  • Ensemble methods, particularly using the weighted sum rule, demonstrate superior performance across all tested datasets compared to stand-alone classifiers.
  • The newly developed wavelet-based and amino acid group-based descriptors outperform their standard implementations.
  • The proposed ensemble method significantly outperforms baseline methods like amino acid composition (AC) and dipeptide composition (2G).

Conclusions:

  • Fusion of different feature extraction methods provides a robust and generalizable approach to protein classification.
  • Novel feature descriptors can significantly enhance classification performance.
  • The developed ensemble system offers a promising solution for reliable automatic protein classification in various biological applications.