Analysis of Similarity/Dissimilarity of DNA Sequences Based on Pulse Coupled Neural Network

• Published in: Multi-disciplinary Trends in Artificial Intelligence pp. 279 - 287
• Main Authors: Jin, Xin, Zhou, Dongming, Yao, Shaowen, Nie, Rencan, Wang, Quan, He, Kangjian
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: DNA sequences; Euclidean distance; Pulse coupled neural network
• ISBN: 3319493965; 9783319493961
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-49397-8_24

To calculate the similarity or dissimilarity of DNA sequences, a new method is proposed based on pulse coupled neural network (PCNN) model. First, according to the characteristics of PCNN model, we encode DNA primary sequences using a simple coding method. Then we use PCNN model to extract the entropy sequence (ES) of the encoded DNA sequence; the ES expresses the features of the DNA sequences. At last, we calculate the similarity of the ES by Euclidean distance to get the similarity of DNA sequences. We take several sets of data to test our method. The experimental results demonstrate that our method is effective.