中文摘要：

基于启动子的以下特点：（1）启动子区域有一些一致序列，但对于不同的启动子，一致序列在个别碱基上会有所改变，具有多样性；（2）一致序列的位置并不固定，总是在某个范围内波动；（3）大部分的真核生物启动子都和CpG岛有关。提出了一个新的启动子预测方法，即采用了一种新的统计建模策略，并首次提出了区间位置权重矩阵（IPWM）概率模型。大规模序列测试结果表明，新的启动子预测系统具有较好的敏感性和特异性。

英文摘要：

Based on the following features of promoters ： （ 1 ） Promoter regions include some consistent sequences , however, consistent sequence has diversity because of nucleotide variation for different promoters ; （ 2 ） Positions of consistent sequence are not fixed, instead, their positions are actually more likely to fluctuate in an approximate re- gion;（3 ） Most of the eukaryotic promoters are related with CpG island. A new method is presented for promoter prediction which adopts a new statistical modeling, and it is the first time to present a new concept ＂Interval Position Weight Matrix＂ probability model. Experimental results on large sequences show that the new promoter prediction system is efficient with higher sensitivity and specificity.