The following information was submitted:
Transactions: INTERNATIONAL JOURNAL of MATHEMATICAL MODELS AND METHODS IN APPLIED SCIENCES
Transactions ID Number: 19-601
Full Name: Nittaya Kerdprasop
Position: Associate Professor
Age: ON
Sex: Female
Address: Computer Engineerimg, Suranaree University of Technology
Country: THAILAND
Tel: +66-44-224432
Tel prefix: 66
Fax: +66-44-224602
E-mail address: nittaya@sut.ac.th
Other E-mails: nittaya.k@gmail.com
Title of the Paper: Recognizing DNA splice sites with the frequent pattern mining technique
Authors as they appear in the Paper: Nittaya Kerdprasop and Kittisak Kerdprasop
Email addresses of all the authors: nittaya@sut.ac.th,kittisakThailand@gmail.com
Number of paper pages: 8
Abstract: The completion of Human Genome Project in 2001 yields the entirety of human genetic information, or genome. A genome is organized in chromosomes and composed of thousands of genes, which are the heredity units of traits such as hair color and blood type. Genes in complex organisms such as primates and humans are composed of regions that code for protein, called exons, and non-coding regions, called introns. During the transcription from the DNA template for later translating into amino acid chain of protein structure, introns are to be removed and exons are then joined to form a continuous messenger-RNA strand. Splice sites are the junctions or borders between introns and exons. Accurate detection of splice sites from the fragments of DNA sequence is important to the success of gene prediction. Due to huge amount of genetic information in most genomes, computational techniques are essential for the interpretation and recognition of specific genetic sequences. In th!
is paper, we propose a splice site prediction technique based on frequent pattern analysis. We apply association mining to each splice junction types, that is, exon/intron, intron/exon, and none of the two types. The frequent DNA patterns are then combined and prioritized with respect to their annotated confidence and support values. The final result of our method is a set of cascaded rules to be used for gene prediction. From the experimental results, our method can make a high recall prediction comparative to other classification-based methods. We also demonstrate computational improvement via a concurrency technique. Running time reduction is considerably observable.
Keywords: Gene expression, Splice site prediction, DNA sequence, Frequent pattern analysis, Concurrent programming
EXTENSION of the file: .pdf
Special (Invited) Session: A high recall DNA splice site prediction based on association analysis
Organizer of the Session: 635-508
How Did you learn about congress: Professor Junping Sun, jps@nova.edu
IP ADDRESS: 203.158.4.226
