Title :
Mining the functional relations in the neighborhood of splice sites
Author :
Wang, Ying ; Peng, Qinke ; Xu, Tao ; Lv, Jia
Author_Institution :
Syst. Eng. Inst., Xi´´an Jiaotong Univ., Xi´´an, China
Abstract :
Accurate identification of splice site is a critical component of bioinformatics and efficient feature representation plays an utmost important role in splice site identification. We proposed a new feature representing method utilizing neural networks to generate the new feature by modeling the possible functional relations in the neighborhood of splice sites. The experimental results on HS3D dataset and the homo sapiens dataset of EID showed that the features represented by our method were effective. And this might indicate that the functional relations in the neighborhood of splice sites are existed.
Keywords :
bioinformatics; data mining; neural nets; accurate identification; bioinformatics; data mining; feature representation; functional relations; homo sapiens dataset; neural networks; splice site identification; splice sites; Accuracy; Bioinformatics; DNA; Feature extraction; Frequency selective surfaces; Neural networks; Support vector machines; bioinformatics; neural network; splice site identification;
Conference_Titel :
Information and Automation (ICIA), 2012 International Conference on
Conference_Location :
Shenyang
Print_ISBN :
978-1-4673-2238-6
Electronic_ISBN :
978-1-4673-2236-2
DOI :
10.1109/ICInfA.2012.6246926