Improving Protein Gamma-Turn Prediction Using Inception Capsule Networks.

Improving Protein Gamma-Turn Prediction Using Inception Capsule Networks.
复制标题

DOI:
10.1038/s41598-018-34114-2
复制
发表时间:
2018-10-24
期刊:
影响因子:
4.6
通讯作者:
Xu D
Xu D
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Fang C;Shang Y;Xu D

文献摘要

参考文献

被引文献

相似文献

蛋白质γ转角预测在蛋白质功能研究和实验设计中具有重要意义。目前已有几种方法对伽玛转弯进行了预测,但结果都不理想,马修相关系数(MCC)在0.2-0.4之间。因此,探索新的预测方法是值得的。一种名为Capsule Network(CapsuleNet)的尖端深度神经网络为伽马转弯预测提供了新的机会。即使输入样本的数量相对较少,CapsuleNet的capsules也能有效地提取分类任务的高级特征。在这里,我们提出了一个用于伽马转弯预测的深度初始胶囊网络。它在伽马转弯基准GT 320上的性能达到了0.45的MCC,大大超过了之前最好的方法,MCC为0.38。这是第一个利用深度神经网络的伽马转弯预测方法。此外,据我们所知,这是第一个利用胶囊网络的生物信息学应用,这将为社区提供一个有用的例子。可执行文件和源代码可以从http://dslsrv8.cs.missouri.edu/~cf797/MUFoldGammaTurn/download.html下载。
Protein gamma-turn prediction is useful in protein function studies and experimental design. Several methods for gamma-turn prediction have been developed, but the results were unsatisfactory with Matthew correlation coefficients (MCC) around 0.2–0.4. Hence, it is worthwhile exploring new methods for the prediction. A cutting-edge deep neural network, named Capsule Network (CapsuleNet), provides a new opportunity for gamma-turn prediction. Even when the number of input samples is relatively small, the capsules from CapsuleNet are effective to extract high-level features for classification tasks. Here, we propose a deep inception capsule network for gamma-turn prediction. Its performance on the gamma-turn benchmark GT320 achieved an MCC of 0.45, which significantly outperformed the previous best method with an MCC of 0.38. This is the first gamma-turn prediction method utilizing deep neural networks. Also, to our knowledge, it is the first published bioinformatics application utilizing capsule network, which will provide a useful example for the community. Executable and source code can be download at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldGammaTurn/download.html.
DOI: 10.1109/memb.2005.1436459
发表时间: 2005-05-01
影响因子: --
作者:
Ison, RE;Hovmöller, S;Kretsinger, RH
通讯作者: Kretsinger, RH
DOI: 10.1034/j.1399-3011.2003.00086.x
发表时间: 2003-10-01
期刊: JOURNAL OF PEPTIDE RESEARCH
影响因子: --
作者:
Guruprasad, K;Rao, MJ;Guruprasad, L
通讯作者: Guruprasad, L
DOI: 10.1016/s0040-4020(01)83261-0
发表时间: 1969-01-01
期刊: TETRAHEDRON
影响因子: 2.1
作者:
BYSTROV, VF;PORTNOVA, SL;OVCHINNIKOV, YA
通讯作者: OVCHINNIKOV, YA
DOI: 10.1016/0022-2836(78)90297-8
发表时间: 1978-01-01
影响因子: 5.6
作者:
GARNIER, J;OSGUTHORPE, DJ;ROBSON, B
通讯作者: ROBSON, B
DOI: 10.1038/nmeth.1818
发表时间: 2012-02-01
期刊: NATURE METHODS
影响因子: 48
作者:
Remmert, Michael;Biegert, Andreas;Soeding, Johannes
通讯作者: Soeding, Johannes