国家自然科学基金资助项目(90403010)和内蒙古自治区自然科学基金资助项目(200308020102)
This work was supported by grants from The National Natural Sciences Foundation of China (90403010) and Inner Mongolia Science Foundation(200308020102)
依据基因启动子区和非启动子区碱基分布的特征,应用基于多样性增量的二次判别分析 (IDQD),对人类polⅡ启动子进行识别,识别精度达到90%以上的水平,优于其他已发表的 (包括SVM分类器等) 识别算法. 使用IDQD算法也能对转录起始位点 (TSS) 进行较准确的预测,10-fold交叉检验结果的敏感性和特异性分别为86%和91%. 这些结果表明IDQD是一个有效的分类器.
Based on the characteristics of base distribution in promoter and non-promoter region the method of Increment of Diversity with Quadratic Discriminant analysis (IDQD) was used to predict the pol Ⅱ promoter in human genome. The prediction has attained accuracy higher than 90%. The transcription start sites have also been predicted successfully with sensitivity 86% and specificity 91%, better than other top softwares currently published.
吕 军,罗辽复.人类polⅡ启动子的识别[J].生物化学与生物物理进展,2005,32(12):1185-1191
复制生物化学与生物物理进展 ® 2025 版权所有 ICP:京ICP备05023138号-1 京公网安备 11010502031771号