• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Molecular Biology >Topology Prediction Improvement of alpha-helical Transmembrane Proteins Through Helix-tail Modeling and Multiscale Deep Learning Fusion
【24h】

Topology Prediction Improvement of alpha-helical Transmembrane Proteins Through Helix-tail Modeling and Multiscale Deep Learning Fusion

机译：通过螺旋尾模拟和多尺度深度学习融合α-螺旋跨膜蛋白的拓扑预测改进

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Transmembrane proteins (TMPs) play important roles in many biological processes, such as cell recognition and communication. Their structures are crucial for revealing complex functions but are hard to obtain. A variety of computational algorithms have been proposed to fill the gap by predicting structures from primary sequences. In this study, we mainly focus on alpha-helical TMP and develop a multiscale deep learning pipeline, MemBrain 3.0, to improve topology prediction. This new protocol includes two submodules. The first module is transmembrane helix (TMH) prediction, which features the capability of accurately predicting TMH with the tail part through the incorporation of tail modeling. The prediction engine contains a multiscale deep learning model and a dynamic threshold strategy. The deep learning model is comprised of a small-scale residue based residual neural network and a large-scale entire-sequence-based residual neural network. Dynamic threshold strategy is designed to binarize the raw prediction scores and solve the under-split problem. The second module is orientation prediction, which consists of a support vector machine (SVM) classifier and a new Max-Min assignment (MMA) strategy. One typical merit of MemBrain 3.0 is the decision mode composed of the dynamic threshold strategy and the MMA strategy, which makes it more effective for hard TMHs, such as half-TMH, back-to-back TMH, and long-TMH. Systematic experiments have demonstrated the efficacy of the new model, which is available at: www.csbio.sjtu.edu.cn/bioinf/MemBrain/. (C) 2020 Elsevier Ltd. All rights reserved.
机译：跨膜蛋白（TMPS）在许多生物过程中起重要作用，例如细胞识别和通信。它们的结构对于揭示复杂的功能来说至关重要，但很难获得。已经提出了各种计算算法来通过预测来自初级序列的结构来填充间隙。在这项研究中，我们主要专注于α-螺旋TMP并开发多尺度深度学习管道，膜3.0，以改善拓扑预测。此新协议包括两个子模块。第一模块是跨膜螺旋（TMH）预测，其通过掺入尾部建模来具有准确地预测TMH的能力。预测引擎包含多尺度深度学习模型和动态阈值策略。深度学习模型由基于小型残留的残余神经网络和基于大规模的基于序列的残余神经网络组成。动态阈值策略旨在二值化原始预测分数并解决破裂问题。第二模块是取向预测，其由支持向量机（SVM）分类器和新的MAX-MIN分配（MMA）策略组成。膜3.0的一个典型优点是由动态阈值策略和MMA策略组成的决策模式，这使得硬TMHS更有效，例如半TMH，背对背TMH和LONG-TMH。系统实验表明了新模型的功效，可提供：www.csbio.sjtu.edu.cn/bioinf/membrain/。 （c）2020 elestvier有限公司保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号