Novel Adaptive Exon Predictor for DNA Analysis Using Singular Value Decomposition

This article describes how a realistic prediction of the exon regions in deoxyribonucleic acid (DNA) is a key task in the field of genomics. Learning of the protein coding regions is a key aspect of disease identification and designing drugs. These sections of DNA are known as exons, that show three base periodicity (TBP) which serves as a base for all exon locating methods. Many techniques have been applied successfully, but development is still needed in this area. We develop a novel adaptive exon predictor (AEP) using singular value decomposition (SVD) which notably reduces computational complexity and provides better performance in terms of accuracy. Finally, the exon locating capability of proposed SVD based AEP is tested using a real DNA sequence with accession AF099922, obtained from the National Center for Biotechnology Information (NCBI) database and compared with the existing LMS methods. It was shown that proposed AEP is more efficient for locating the exon regions in a DNA sequence.

Gene Prediction Based on One-Dimensional Image Segmentation

In the current study, using methods of signal processing to manage gene prediction has attracted great attention. At first, the voss mapping which can map the DNA alphabetic sequence into the numerical sequence and the 3-base periodicity of exon are introduced. Then a fixed-length sliding window approach and its feasibility are analyzed. It can be proved that when two exons are very close, gene prediction by only setting a threshold to the spectrum could not have good effect. To overcome this shortcoming, a new method based on one-dimensional image segmentation is proposed. Finally, simulation shows the short introns are culled commendably. Two evaluation indices are also introduced to demonstrate the effectiveness of this method.