Search research articles

Search research articles

Related Experiment Videos

A lazy data mining approach for protein classification.

Luiz Merschmann¹, Alexandre Plastino

¹Department of Computer Science, Fluminense Federal University, Niterói, Brazil. lmerschmann@ic.uff.br

IEEE Transactions on Nanobioscience

|March 31, 2007

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

Sentiment analysis in tweets: an assessment study from classical to modern word representation models.

Data mining and knowledge discovery·2022

Same author

Interpretable Ensembles of Classifiers for Uncertain Data With Bioinformatics Applications.

IEEE/ACM transactions on computational biology and bioinformatics·2022

Same author

A Novel Feature Selection Method for Uncertain Features: An Application to the Prediction of Pro-/Anti-Longevity Genes.

IEEE/ACM transactions on computational biology and bioinformatics·2020

See all related 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

We developed a new data mining technique, highest subset probability (HiSP), for protein classification. HiSP accurately predicts protein functional families from sequence motifs and excels on imbalanced datasets.

Area of Science:

Computational biology
Bioinformatics
Machine learning

Background:

Protein classification is crucial for understanding biological function.
Existing methods face challenges with novel sequences and motif composition analysis.
Accurate prediction of protein functional families is an ongoing challenge.

Purpose of the Study:

To introduce a novel computational technique for protein classification.
To predict the functional family of protein sequences using motif composition.
To improve upon existing protein classification approaches.

Main Methods:

A new data mining technique based on Bayes' theorem, named highest subset probability (HiSP), was developed.
Protein classification was performed by analyzing motif composition of protein sequences.

Related Experiment Videos

Experimental datasets were sourced from the Prosite curated protein family database.

Main Results:

The proposed HiSP method demonstrated superior performance compared to existing methods across all tested datasets.
HiSP shows significant promise for addressing similar computational problems in bioinformatics.
The method proved effective even on highly imbalanced datasets.

Conclusions:

The highest subset probability (HiSP) method offers a robust and accurate approach to protein classification.
HiSP provides a valuable tool for predicting protein functional families, especially when dealing with imbalanced data.
This technique advances the field of computational biology by offering improved predictive accuracy.