TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions.
TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions.
复制标题
DOI：
10.1371/journal.pcbi.1005690
复制
发表时间：
2017-07
影响因子：
4.3
通讯作者：
Wei GW
中科院分区：
文献类型：
--
作者：
Cang Z;Wei GW
尽管深度学习方法在图像、视频和音频处理、计算机视觉和语音识别方面取得了巨大的成功，但其在三维生物分子结构数据集上的应用受到几何和生物复杂性的阻碍。为了解决这个问题，我们引入了元素特定持久同源(ESPH)方法。ESPH用一维(1D)拓扑不变量表示三维复杂几何结构，并通过多通道类图像表示保留重要的生物信息。这种表示揭示了生物分子中隐藏的结构-功能关系。我们进一步将ESPH和深度卷积神经网络相结合，构建了一个多通道拓扑神经网络(TopologyNet)，用于预测蛋白质-配体结合亲和力和突变后蛋白质稳定性的变化。为了克服训练集小、噪声大的深度学习限制，提出了一种多任务多通道拓扑卷积神经网络。我们证明TopologyNet在预测蛋白质与配体的结合亲和力、突变引起的球状蛋白折叠自由能变化以及突变引起的膜蛋白折叠自由能变化方面优于最新的方法。可用性：weilab.math.msu.edu/tdl/从生物分子结构预测生物分子功能和性质在计算生物物理学中至关重要。生物分子的结构和生物复杂性及其相互作用阻碍了成功的预测。机器学习已成为此类预测的重要工具。深度学习结构的最新进展，特别是卷积神经网络(CNN)，已经深刻地影响了许多学科，如图像分类和语音识别。虽然CNN可以通过使用三维(3D)图像状的蛮力表示直接应用于分子科学，但当应用于大生物分子和大数据集时，它在计算上是困难的。我们提出了一种拓扑策略来显著降低生物分子的结构和生物复杂性，并提供了一种高效的基于拓扑的CNN架构。元素特定的持久同调，一种新的代数拓扑，已经被开发出来，以适合于CNN的多通道图像表示来投射生物分子。提出的基于拓扑的神经网络(TopologyNet)通过辅助描述子和多任务深度学习结构进一步增强了能力。已证明TopologyNet框架在预测蛋白质-配体结合亲和力和突变引起的蛋白质稳定性变化方面优于其他方法。
Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ The predictions of biomolecular functions and properties from biomolecular structures are of fundamental importance in computational biophysics. The structural and biological complexities of biomolecules and their interactions hinder successful predictions. Machine learning has become an important tool for such predictions. Recent advances in deep learning architectures, particularly convolutional neural network (CNN), have profoundly impacted a number of disciplines, such as image classification and voice recognition. Though CNN can be directly applied to molecular sciences by using a three-dimensional (3D) image-like brute-force representation, it is computationally intractable when applied to large biomolecules and large datasets. We propose a topological strategy to significantly reduce the structural and biological complexity of biomolecules and provide an efficient topology based CNN architecture. Element-specific persistent homology, a new algebraic topology, has been developed to cast biomolecules in a multichannel image-like representation suitable for CNN. The power of the proposed topology based neural network (TopologyNet) is further enhanced by auxiliary descriptors and a multi-task deep learning architecture. It has been demonstrated that TopologyNet framework outperforms other methods in the predictions of protein-ligand binding affinities and mutation induced protein stability changes.
登录
查看更多内容
影响因子：
3.7
作者：
Berliner N;Teyra J;Colak R;Garcia Lopez S;Kim PM
通讯作者：
Kim PM
影响因子：
0.8
作者：
Carlsson, Gunnar;Zomorodian, Afra
通讯作者：
Zomorodian, Afra
影响因子：
3.9
作者：
Darcy, Isabel K.;Vazquez, Mariel
通讯作者：
Vazquez, Mariel
I-Mutant2.0：预测蛋白质序列或结构突变的稳定性变化。
影响因子：
14.9
作者：
Capriotti, E;Fariselli, P;Casadio, R
通讯作者：
Casadio, R
DOI：
10.1007/978-1-4615-5529-2_5
发表时间：
1998-01-01
期刊：
LEARNING TO LEARN
影响因子：
--
作者：
Caruana, R
通讯作者：
Caruana, R