积极学习酶的功能Active and guided learning of enzyme function |
|
课程网址: | http://videolectures.net/mlsb2012_ferrari_active/ |
主讲教师: | Luna De Ferrari |
开课单位: | 圣安德鲁斯大学 |
开课时间: | 2012-10-23 |
课程语种: | 英语 |
中文简介: | 手动注释无法跟上酶序列发现。在这项工作中,我们模拟了主动和指导学习的使用,以支持酶功能策划。我们对5,750种大肠杆菌蛋白质进行了评估,对9种策略进行了分类。我们发现按照发生频率的顺序选择InterPro功能集可以将策展工作量减少近三分之二,同时保持非常高的准确度和召回率。由于其有限的计算要求,并行化,稀有类的良好覆盖以及选择注释实例的灵活性,该方法可应用于数百万种蛋白质的真实数据集。 |
课程简介: | Manual annotation cannot keep up with enzyme sequence discovery. In this work, we modelled the use of active and guided learning to support enzyme function curation. We evaluated, on 5,750 E. coli proteins, nine strategies to sort instances for curation. We found that selecting sets of InterPro features in order of frequency of occurrence can cut the curation effort by almost two thirds, while maintaining very high accuracy and recall. The method can be applied to real-life datasets of millions of proteins thanks to its limited computational requirements, parallelisation, good coverage of rare classes and flexibility in selecting instances for annotation. |
关 键 词: | 酶序列; 蛋白质; 策展工作 |
课程来源: | 视频讲座网 |
最后编审: | 2019-07-03:cwx |
阅读次数: | 78 |