Tech M, Morgenstern B, Meinicke P
Abteilung Bioinformatik, Institut für Mikrobiologie und Genetik Georg-August-Universität Göttingen, Goldschmidtstrasse 1, 37077 Göttingen, Germany.
Nucleic Acids Res. 2006 Jul 1;34(Web Server issue):W588-90. doi: 10.1093/nar/gkl313.
Exact localization of the translation initiation sites (TIS) in prokaryotic genomes is difficult to achieve using conventional gene finders. We recently introduced the program TICO for postprocessing TIS predictions based on a completely unsupervised learning algorithm. The program can be utilized through our web interface at http://tico.gobics.de/ and it is also freely available as a commandline version for Linux and Windows. The latest version of our program provides a tool for visualization of the resulting TIS model. Although the underlying method is not based on any specific assumptions about characteristic sequence features of prokaryotic TIS the prediction rates of our tool are competitive on experimentally verified test data.
利用传统的基因预测工具很难精确确定原核生物基因组中翻译起始位点（TIS）的位置。我们最近推出了程序TICO，用于基于完全无监督学习算法对TIS预测结果进行后处理。该程序可通过我们的网页界面（http://tico.gobics.de/ ）使用，也可作为适用于Linux和Windows的命令行版本免费获取。我们程序的最新版本提供了一个用于可视化所得TIS模型的工具。尽管其基础方法并非基于对原核生物TIS特征序列特征的任何特定假设，但我们工具的预测率在经过实验验证的测试数据上具有竞争力。
