School of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, Guangdong, China.
Gordon Life Science Institute, Belmont, MA, USA.
Bioinformatics. 2018 Sep 15;34(18):3086-3093. doi: 10.1093/bioinformatics/bty312.
DNA replication is the key of the genetic information transmission, and it is initiated from the replication origins. Identifying the replication origins is crucial for understanding the mechanism of DNA replication. Although several discriminative computational predictors were proposed to identify DNA replication origins of yeast species, they could only be used to identify very tiny parts (250 or 300 bp) of the replication origins. Besides, none of the existing predictors could successfully capture the 'GC asymmetry bias' of yeast species reported by experimental observations. Hence it would not be surprising why their power is so limited. To grasp the CG asymmetry feature and make the prediction able to cover the entire replication regions of yeast species, we develop a new predictor called 'iRO-3wPseKNC'.
Rigorous cross validations on the benchmark datasets from four yeast species (Saccharomyces cerevisiae, Schizosaccharomyces pombe, Kluyveromyces lactis and Pichia pastoris) have indicated that the proposed predictor is really very powerful for predicting the entire DNA duplication origins.
The web-server for the iRO-3wPseKNC predictor is available at http://bioinformatics.hitsz.edu.cn/iRO-3wPseKNC/, by which users can easily get their desired results without the need to go through the mathematical details.
Supplementary data are available at Bioinformatics online.
DNA 复制是遗传信息传递的关键，它从复制起点开始。识别复制起点对于理解 DNA 复制机制至关重要。虽然已经提出了几种有区别的计算预测因子来识别酵母物种的 DNA 复制起点，但它们只能用于识别复制起点的非常小的部分（250 或 300bp）。此外，现有的预测因子都无法成功捕获实验观察到的酵母物种的“GC 不对称性偏差”。因此，它们的功能如此有限也就不足为奇了。为了掌握 CG 不对称性特征，并使预测能够涵盖酵母物种的整个复制区域，我们开发了一种称为“iRO-3wPseKNC”的新预测因子。
在来自四个酵母物种（酿酒酵母、裂殖酵母、乳酸克鲁维酵母和巴斯德毕赤酵母）的基准数据集上进行的严格交叉验证表明，该预测因子对于预测整个 DNA 复制起点非常有效。
iRO-3wPseKNC 预测因子的网络服务器可在 http://bioinformatics.hitsz.edu.cn/iRO-3wPseKNC/ 上获得，用户可以轻松获得所需的结果，而无需了解数学细节。
补充数据可在 Bioinformatics 在线获得。
