A new classification method using array Comparative Genome Hybridization data, based on the concept of Limited Jumping Emerging Patterns

Gambin Tomasz, Walczak, Walczak Krzysztof

Description

Classification using aCGH data is an important and insufficiently investigated problem in bioinformatics. In this paper we propose a new classification method of DNA copy number data based on the concept of limited Jumping Emerging Patterns. We present the comparison of our limJEPClassifier to SVM which is considered the most successful classifier in the case of high-throughput data. Results Our results revealed that the classification performance using limJEPClassifier is significantly higher than other methods. Furthermore, we show that application of the limited JEP's can significantly improve classification, when strongly unbalanced data are given. Conclusion Nowadays, aCGH has become a very important tool, used in research of cancer or genomic disorders. Therefore, improving classification of aCGH data can have a great impact on many medical issues such as the process of diagnosis and finding disease-related genes. The performed experiment shows that the application of Jumping Emerging Patterns can be effective in the classification of high-dimensional data, including these from aCGH experiments.

Informations

• Publié par: biomed
• Publié le: 01 janvier 2009
• Nombre de lectures: 5
• Langue: English

Extrait

BMC Bioinformatics

BioMedCentral

Open Access Research A new classification method using array Comparative Genome Hybridization data, based on the concept of Limited Jumping Emerging Patterns Tomasz Gambin* and Krzysztof Walczak

Address: Faculty of Electronics and Information Technology of Warsaw University of Technology, Institute of Computer Science, Nowowiejska 15/ 19, Warsaw, 00665, Poland Email: Tomasz Gambin*  [e-mail]; Krzysztof Walczak  [e-mail] * Corresponding author

fromThe Seventh Asia Pacific Bioinformatics Conference (APBC 2009) Beijing, China. 13–16 January 2009

Published: 30 January 2009 BMC Bioinformatics2009,10(Suppl 1):S64

doi:10.1186/1471-2105-10-S1-S64

<supplement> <title> <p>Selected papers from the Seventh Asia-Pacific Bioinformatics Conference (APBC 2009)</p> </title> <editor>Michael Q Zhang, Michael S Waterman and Xuegong Zhang</editor> <note>Research</note> </supplement> This article is available from: http://www.biomedcentral.com/1471-2105/10/S1/S64 © 2009 Gambin and Walczak; licensee BioMed Central Ltd. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract Background:Classification using aCGH data is an important and insufficiently investigated problem in bioinformatics. In this paper we propose a new classification method of DNA copy number data based on the concept of limited Jumping Emerging Patterns. We present the comparison of our limJEPClassifier to SVM which is considered the most successful classifier in the case of high-throughput data.

Results:Our results revealed that the classification performance using limJEPClassifier is significantly higher than other methods. Furthermore, we show that application of the limited JEP's can significantly improve classification, when strongly unbalanced data are given.

Conclusion:Nowadays, aCGH has become a very important tool, used in research of cancer or genomic disorders. Therefore, improving classification of aCGH data can have a great impact on many medical issues such as the process of diagnosis and finding disease-related genes. The performed experiment shows that the application of Jumping Emerging Patterns can be effective in the classification of high-dimensional data, including these from aCGH experiments.

Background Introduction Arraybased Comparative Genomic Hybridization (aCGH) is a powerful technique used to detect DNA copy number variations (CNV) across the genome. One of the most important aims of this technique is diagnosis, which can be achieved with help of classification of aCGH data.

One of the most important problems with the classifica tion of aCGH data is dealing with a great number of attributes, which often exceed the number of given sam ples. In a typical experiment one can deal with dozens of samples, while microarray may consist of millions of spots. It is a real challenge to select from the huge amount of data the most interesting features, while most of them are not related to the given classification problem.

Page 1 of 10 (page number not for citation purposes)