Promoter Sequences Prediction Using Relational Association Rule Mining

In this paper we are approaching, from a computational perspective, the problem of promoter sequences prediction, an important problem within the field of bioinformatics. As the conditions for a DNA sequence to function as a promoter are not known, machine learning based classification models are st...

Full description

Saved in:
Bibliographic Details
Published in:Evolutionary Bioinformatics 2012-01, Vol.2012 (2012), p.181-196
Main Authors: Czibula, Gabriela, Bocicor, Maria-Iuliana, Czibula, Istvan Gergely
Format: Article
Language:English
Subjects:
Analysis
Bioinformatics
Classification
Classifiers
Computational linguistics
Deoxyribonucleic acid
DNA sequencing
Evolutionary
Language processing
Machine learning
Mathematical analysis
Mathematical models
Mining
Natural language interfaces
Nucleotide sequencing
Original Research
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we are approaching, from a computational perspective, the problem of promoter sequences prediction, an important problem within the field of bioinformatics. As the conditions for a DNA sequence to function as a promoter are not known, machine learning based classification models are still developed to approach the problem of promoter identification in the DNA. We are proposing a classification model based on relational association rules mining. Relational association rules are a particular type of association rules and describe numerical orderings between attributes that commonly occur over a data set. Our classifier is based on the discovery of relational association rules for predicting if a DNA sequence contains or not a promoter region. An experimental evaluation of the proposed model and comparison with similar existing approaches is provided. The obtained results show that our classifier overperforms the existing techniques for identifying promoter sequences, confirming the potential of our proposal.
ISSN:1176-9343
1176-9343
DOI:10.4137/EBO.S9376