• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

相似文献

1
Predicting residue-residue contact maps by a two-layer, integrated neural-network method.通过一种双层集成神经网络方法预测残基-残基接触图。
Proteins. 2009 Jul;76(1):176-83. doi: 10.1002/prot.22329.
2
Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network.通过两层神经网络的引导学习提高蛋白质残基溶剂可及性和实值主链扭转角的预测准确性。
Proteins. 2009 Mar;74(4):847-56. doi: 10.1002/prot.22193.
3
SPINE X: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles.SPINE X：通过多步骤学习与溶剂可及表面积和骨架扭转角预测相结合来改进蛋白质二级结构预测。
J Comput Chem. 2012 Jan 30;33(3):259-67. doi: 10.1002/jcc.21968. Epub 2011 Nov 2.
4
A two-stage approach for improved prediction of residue contact maps.一种用于改进残基接触图预测的两阶段方法。
BMC Bioinformatics. 2006 Mar 30;7:180. doi: 10.1186/1471-2105-7-180.
5
Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility.利用长短期记忆双向递归神经网络捕捉非局部相互作用，提高蛋白质二级结构、主链角度、接触数和溶剂可及性的预测能力。
Bioinformatics. 2017 Sep 15;33(18):2842-2849. doi: 10.1093/bioinformatics/btx218.
6
Real-SPINE: an integrated system of neural networks for real-value prediction of protein structural properties.Real-SPINE：用于蛋白质结构特性实值预测的神经网络集成系统。
Proteins. 2007 Jul 1;68(1):76-81. doi: 10.1002/prot.21408.
7
Ab initio and template-based prediction of multi-class distance maps by two-dimensional recursive neural networks.基于二维递归神经网络的多类别距离图的从头预测和基于模板的预测。
BMC Struct Biol. 2009 Jan 30;9:5. doi: 10.1186/1472-6807-9-5.
8
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model.基于超深度学习模型的蛋白质接触图从头精确预测
PLoS Comput Biol. 2017 Jan 5;13(1):e1005324. doi: 10.1371/journal.pcbi.1005324. eCollection 2017 Jan.
9
Improving prediction of protein secondary structure, backbone angles, solvent accessibility and contact numbers by using predicted contact maps and an ensemble of recurrent and residual convolutional neural networks.利用预测的接触图和递归与残差卷积神经网络的集合来改进蛋白质二级结构、主链角度、溶剂可及性和接触数的预测。
Bioinformatics. 2019 Jul 15;35(14):2403-2410. doi: 10.1093/bioinformatics/bty1006.
10
Predicting residue-residue contacts using random forest models.利用随机森林模型预测残基-残基接触。
Bioinformatics. 2011 Dec 15;27(24):3379-84. doi: 10.1093/bioinformatics/btr579. Epub 2011 Oct 20.

引用本文的文献

1
Recent Advances in Computational Prediction of Secondary and Supersecondary Structures from Protein Sequences.从蛋白质序列预测二级和超二级结构的计算方法的最新进展
Methods Mol Biol. 2025;2870:1-19. doi: 10.1007/978-1-0716-4213-9_1.
2
In Silico Protein Folding Prediction of COVID-19 Mutations and Variants.新冠病毒突变和变体的计算机蛋白质折叠预测。
Biomolecules. 2022 Nov 10;12(11):1665. doi: 10.3390/biom12111665.
3
Toward the solution of the protein structure prediction problem.朝着解决蛋白质结构预测问题的方向努力。
J Biol Chem. 2021 Jul;297(1):100870. doi: 10.1016/j.jbc.2021.100870. Epub 2021 Jun 11.
4
Evaluation of residue-residue contact prediction methods: From retrospective to prospective.评估残基残基接触预测方法：从回顾性到前瞻性。
PLoS Comput Biol. 2021 May 24;17(5):e1009027. doi: 10.1371/journal.pcbi.1009027. eCollection 2021 May.
5
Predicting protein inter-residue contacts using composite likelihood maximization and deep learning.利用复合似然最大化和深度学习预测蛋白质残基间的接触。
BMC Bioinformatics. 2019 Oct 29;20(1):537. doi: 10.1186/s12859-019-3051-7.
6
Forecasting residue-residue contact prediction accuracy.预测残差-残基接触预测精度。
Bioinformatics. 2017 Nov 1;33(21):3405-3414. doi: 10.1093/bioinformatics/btx416.
7
Finding the needle in the haystack: towards solving the protein-folding problem computationally.在干草堆中找针：用计算的方法解决蛋白质折叠问题。
Crit Rev Biochem Mol Biol. 2018 Feb;53(1):1-28. doi: 10.1080/10409238.2017.1380596. Epub 2017 Oct 4.
8
RRCRank: a fusion method using rank strategy for residue-residue contact prediction.RRCRank：一种使用排序策略进行残基-残基接触预测的融合方法。
BMC Bioinformatics. 2017 Sep 2;18(1):390. doi: 10.1186/s12859-017-1811-9.
9
Protein Residue Contacts and Prediction Methods.蛋白质残基接触与预测方法
Methods Mol Biol. 2016;1415:463-76. doi: 10.1007/978-1-4939-3572-7_24.
10
Evaluation of residue-residue contact prediction in CASP10.蛋白质结构预测关键评估第10轮（CASP10）中残基-残基接触预测的评估
Proteins. 2014 Feb;82 Suppl 2(0 2):138-53. doi: 10.1002/prot.24340. Epub 2013 Aug 31.

本文引用的文献

1
Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network.通过两层神经网络的引导学习提高蛋白质残基溶剂可及性和实值主链扭转角的预测准确性。
Proteins. 2009 Mar;74(4):847-56. doi: 10.1002/prot.22193.
2
Using inferred residue contacts to distinguish between correct and incorrect protein models.利用推断的残基接触来区分正确和错误的蛋白质模型。
Bioinformatics. 2008 Jul 15;24(14):1575-82. doi: 10.1093/bioinformatics/btn248. Epub 2008 May 29.
3
Real-value prediction of backbone torsion angles.主链扭转角的实值预测。
Proteins. 2008 Jul;72(1):427-33. doi: 10.1002/prot.21940.
4
Contact prediction using mutual information and neural nets.使用互信息和神经网络进行接触预测。
Proteins. 2007;69 Suppl 8:159-64. doi: 10.1002/prot.21791.
5
Critical assessment of methods of protein structure prediction-Round VII.蛋白质结构预测方法的批判性评估——第七轮。
Proteins. 2007;69 Suppl 8(S8):3-9. doi: 10.1002/prot.21767.
6
Assessment of intramolecular contact predictions for CASP7.对CASP7分子内接触预测的评估。
Proteins. 2007;69 Suppl 8:152-8. doi: 10.1002/prot.21637.
7
Improved residue contact prediction using support vector machines and a large feature set.使用支持向量机和大量特征集改进残基接触预测。
BMC Bioinformatics. 2007 Apr 2;8:113. doi: 10.1186/1471-2105-8-113.
8
Real-SPINE: an integrated system of neural networks for real-value prediction of protein structural properties.Real-SPINE：用于蛋白质结构特性实值预测的神经网络集成系统。
Proteins. 2007 Jul 1;68(1):76-81. doi: 10.1002/prot.21408.
9
Achieving 80% ten-fold cross-validated accuracy for secondary structure prediction by large-scale training.通过大规模训练实现二级结构预测的80%十折交叉验证准确率。
Proteins. 2007 Mar 1;66(4):838-45. doi: 10.1002/prot.21298.
10
Predicting residue contacts using pragmatic correlated mutations method: reducing the false positives.使用实用相关突变方法预测残基接触：减少假阳性
BMC Bioinformatics. 2006 Nov 16;7:503. doi: 10.1186/1471-2105-7-503.

通过一种双层集成神经网络方法预测残基-残基接触图。

Predicting residue-residue contact maps by a two-layer, integrated neural-network method.

作者信息

Xue Bin, Faraggi Eshel, Zhou Yaoqi

机构信息

Indiana University School of Informatics, Indiana University-Purdue University, Indianapolis, Indiana 46202, USA.

出版信息

Proteins. 2009 Jul;76(1):176-83. doi: 10.1002/prot.22329.

DOI:10.1002/prot.22329
PMID:19137600
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC2716487/
Abstract

A neural network method (SPINE-2D) is introduced to provide a sequence-based prediction of residue-residue contact maps. This method is built on the success of SPINE in predicting secondary structure, residue solvent accessibility, and backbone torsion angles via large-scale training with overfit protection and a two-layer neural network. SPINE-2D achieved a 10-fold cross-validated accuracy of 47% (+/-2%) for top L/5 predicted contacts between two residues with sequence separation of six or more and an accuracy of 24 +/- 1% for nonlocal contacts with sequence separation of 24 residues or more. The accuracies of 23% and 26% for nonlocal contact predictions are achieved for two independent datasets of 500 proteins and 82 CASP 7 targets, respectively. A comparison with other methods indicates that SPINE-2D is among the most accurate methods for contact-map prediction. SPINE-2D is available as a webserver at http://sparks.informatics.iupui.edu.

摘要

介绍了一种神经网络方法（SPINE-2D），用于基于序列预测残基-残基接触图。该方法基于SPINE通过大规模训练并采用过拟合保护和两层神经网络成功预测二级结构、残基溶剂可及性和主链扭转角。对于序列间隔为六个或更多的两个残基之间预测的前L/5个接触，SPINE-2D在10倍交叉验证中的准确率为47%（±2%）；对于序列间隔为24个残基或更多的非局部接触，准确率为24±1%。对于分别包含500个蛋白质和82个CASP 7目标的两个独立数据集，非局部接触预测的准确率分别为23%和26%。与其他方法的比较表明，SPINE-2D是接触图预测中最准确的方法之一。可通过网络服务器http://sparks.informatics.iupui.edu使用SPINE-2D。