HUMAN PROMOTER PREDICTION BASED ON REGION FEATURES AND NEURAL NETWORK

摘要：

Human promoter prediction is a very important problem in DNA sequence analysis. In this paper, we present a novel human promoter prediction algorithm. We extract sample sequences of 250bp from promote, exon, intron and 3-UTR sequences and each sample is divided into two regions whose boundary is number 201bp relative to the beginning of the sample sequence. A promoter sample is a section from 200 bp upstream to 50 bp downstream of the TSS and its region boundary is the TSS. And then we extract the most effective region features which can maximally distinguish between promoter sequences and non-promoter sequences. Finally, we design three classifiers by BP neural network, namely promoter-exon classifier, promoter-intron classifier and promoter-UTR classifier. The results of testing show that our algorithm is efficient.

关键词： Promoter prediction Region feature BP Neural network

作者: WENJU LI HONG YAM LI MEI YONGMEI LIU

作者单位: School of Computer and Information Technology, Liaoning Normal University, Dalian, 116029, China Sch School of Electrical and Information Engineering, University of Sydney, NSW 2006, Australia Departme School of Computer and Information Technology, Liaoning Normal University, Dalian, 116029, China School of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China

会议类型: 国际会议

会议名称: The Second International Conference on Information & Systems Sciences(ICISS2008)(第二届信息与系统科学国际会议)

会议地点: 大连

会议语种:英文

页码: 349-354

在线出版日期: 2008-12-18（万方平台首次上网日期，不代表论文的发表时间）