Using graph convolutional neural networks to learn a representation for glycans.
Using graph convolutional neural networks to learn a representation for glycans.
复制标题
DOI：
10.1016/j.celrep.2021.109251
复制
发表时间：
2021-06-15
期刊：
影响因子：
8.8
通讯作者：
Bojar, Daniel
中科院分区：
文献类型：
--
作者：
Burkholz, Rebekka;Quackenbush, John;Bojar, Daniel
作为唯一的非线性和最多样化的生物序列，聚糖给计算生物学带来了巨大的挑战。这些碳水化合物几乎参与了所有的生物过程从蛋白质折叠到病毒进入细胞，但仍然没有得到很好的理解。几乎没有将聚糖序列与功能联系起来的计算方法，并且它们不能充分利用关于聚糖的所有可用信息。SweetNet是一个图卷积神经网络，它使用图表示学习来促进对糖生物学的计算理解。SweetNet明确地结合了聚糖的非线性性质，并建立了一个框架，将任何聚糖序列映射到一个表示。我们表明，SweetNet优于其他计算方法在预测所有报告的任务的聚糖属性。更重要的是，我们表明，通过SweetNet学习的聚糖表征可以预测生物体的表型和环境特性。最后，我们使用以聚糖为中心的机器学习来预测病毒聚糖结合，这可用于发现病毒受体。Burkholz等人使用图卷积神经网络开发了一个聚糖分析平台，该平台考虑了这些碳水化合物的分支性质。他们证明，以聚糖为中心的机器学习可以用于各种目的，例如根据其糖组学相似性对物种进行聚类或识别病毒受体。
As the only nonlinear and the most diverse biological sequence, glycans offer substantial challenges for computational biology. These carbohydrates participate in nearly all biological processes—from protein folding to viral cell entry—yet are still not well understood. There are few computational methods to link glycan sequences to functions, and they do not fully leverage all available information about glycans. SweetNet is a graph convolutional neural network that uses graph representation learning to facilitate a computational understanding of glycobiology. SweetNet explicitly incorporates the nonlinear nature of glycans and establishes a framework to map any glycan sequence to a representation. We show that SweetNet outperforms other computational methods in predicting glycan properties on all reported tasks. More importantly, we show that glycan representations, learned by SweetNet, are predictive of organismal phenotypic and environmental properties. Finally, we use glycan-focused machine learning to predict viral glycan binding, which can be used to discover viral receptors. Burkholz et al. develop an analysis platform for glycans, using graph convolutional neural networks, that considers the branched nature of these carbohydrates. They demonstrate that glycan-focused machine learning can be employed for various purposes, such as to cluster species according to their glycomic similarity or to identify viral receptors.
登录
查看更多内容
影响因子：
30.3
作者：
Bojar, Daniel;Powers, Rani K.;Collins, James J.
通讯作者：
Collins, James J.
影响因子：
14.9
作者：
Letunic, Ivica;Bork, Peer
通讯作者：
Bork, Peer
影响因子：
3.9
作者：
Burlak C;Bern M;Brito AE;Isailovic D;Wang ZY;Estrada JL;Li P;Tector AJ
通讯作者：
Tector AJ
影响因子：
3.3
作者：
Cholleti, Sharath R.;Agravat, Sanjay;Smith, David F.
通讯作者：
Smith, David F.
影响因子：
13.6
作者：
Arigoni-Affolter, Ilaria;Scibona, Ernesto;Aebi, Markus
通讯作者：
Aebi, Markus