PIT Bioinformatics Group, Institute of Mathematics, Eötvös University, H-1117 Budapest, Hungary.
Uratim Ltd, H-1118 Budapest, Hungary.
Bioinformatics. 2018 Jul 15;34(14):2487-2489. doi: 10.1093/bioinformatics/bty116.
Artificial intelligence tools are gaining more and more ground each year in bioinformatics. Learning algorithms can be taught for specific tasks by using the existing enormous biological databases, and the resulting models can be used for the high-quality classification of novel, un-categorized data in numerous areas, including biological sequence analysis. Here, we introduce SECLAF, a webserver that uses deep neural networks for hierarchical biological sequence classification. By applying SECLAF for residue-sequences, we have reported [Methods (2018), https://doi.org/10.1016/j.ymeth.2017.06.034] the most accurate multi-label protein classifier to date (UniProt-into 698 classes-AUC 99.99%; Gene Ontology-into 983 classes-AUC 99.45%). Our framework SECLAF can be applied for other sequence classification tasks, as we describe in the present contribution.
The program SECLAF is implemented in Python, and is available for download, with example datasets at the website https://pitgroup.org/seclaf/. For Gene Ontology and UniProt based classifications a webserver is also available at the address above.
人工智能工具在生物信息学中每年都在获得越来越多的关注。通过使用现有的大量生物数据库，可以为特定任务教授学习算法，并且可以将由此产生的模型用于许多领域的新型、未分类数据的高质量分类，包括生物序列分析。在这里，我们介绍了 SECLAF，这是一个使用深度神经网络进行层次生物序列分类的网络服务器。通过应用 SECLAF 进行残基序列，我们报告了[方法（2018 年），https://doi.org/10.1016/j.ymeth.2017.06.034]迄今为止最准确的多标签蛋白质分类器（UniProt 分为 698 类-AUC 99.99%；基因本体论分为 983 类-AUC 99.45%）。正如我们在本研究中所描述的，我们的 SECLAF 框架可应用于其他序列分类任务。
SECLAF 程序是用 Python 编写的，可在网站 https://pitgroup.org/seclaf/ 上下载，同时还提供了示例数据集。对于基因本体论和 UniProt 分类，也可以在上述地址访问网络服务器。
