A UNIFIED MULTITASK ARCHITECTURE FOR PREDICTING LOCAL PROTEIN PROPERTIES

这个子项目是许多利用资源的研究子项目之一 由NIH/NCRR资助的中心拨款提供。子项目的主要支持 而子项目的主要调查员可能是由其他来源提供的， 包括其它NIH来源。 列出的子项目总成本可能 代表子项目使用的中心基础设施的估计数量， 而不是由NCRR赠款提供给子项目或子项目工作人员的直接资金。 多种功能上重要的蛋白质特性，例如 二级结构、跨膜拓扑结构和溶剂可及性， 可以被编码为氨基酸的标记。 事实上， 一级氨基酸序列的这种性质是其中之一， 计算生物学的核心项目。 因此， 已经开发了用于预测这些性质的方法; 然而，大多数这样的方法集中在解决一个单一的任务， 时间 受最近自然语言方面成功工作的启发 处理，我们建议使用多任务学习来训练一个 一个单一的联合模型，利用这些不同的依赖关系， 标签任务。 我们描述了一个深度神经网络架构 给定一个蛋白质序列， 性质，包括二级结构，溶剂可及性， 跨膜拓扑结构、信号肽和DNA结合残基。 的 网络以监督的方式在所有这些任务上联合训练， 增强了一种新形式的半监督学习， 训练模型以区分局部模式和自然模式。 和合成蛋白质序列。的任务无关架构 该网络消除了对特定于任务的特征的需要 工程.我们证明，对于我们所做的所有任务， 考虑到，我们的方法导致统计显著 相对于单任务神经网络，性能的改进 方法，并且由此产生的模型实现了最先进的 性能

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. Primary support for the subproject and the subproject's principal investigator may have been provided by other sources, including other NIH sources. The Total Cost listed for the subproject likely represents the estimated amount of Center infrastructure utilized by the subproject, not direct funding provided by the NCRR grant to the subproject or subproject staff. A variety of functionally important protein properties, such as secondary structure, transmembrane topology and solvent accessibility, can be encoded as a labeling of amino acids. Indeed, the prediction of such properties from the primary amino acid sequence is one of the core projects of computational biology. Accordingly, a panoply of approaches have been developed for predicting such properties; however, most such approaches focus on solving a single task at a time. Motivated by recent, successful work in natural language processing, we propose to use multitask learning to train a single, joint model that exploits the dependencies among these various labeling tasks. We describe a deep neural network architecture that, given a protein sequence, outputs a host of predicted local properties, including secondary structure, solvent accessibility, transmembrane topology, signal peptides and DNA-binding residues. The network is trained jointly on all these tasks in a supervised fashion, augmented with a novel form of semi-supervised learning in which the model is trained to distinguish between local patterns from natural and synthetic protein sequences. The task-independent architecture of the network obviates the need for task-specific feature engineering. We demonstrate that, for all of the tasks that we considered, our approach leads to statistically significant improvements in performance, relative to a single task neural network approach, and that the resulting model achieves state-of-the-art performance.