使用神经网络进行蛋白质二级结构预测。
Protein secondary structure prediction with a neural network.
作者信息
Holley L H, Karplus M
机构信息
Department of Chemistry, Harvard University, Cambridge, MA 02138.
出版信息
Proc Natl Acad Sci U S A. 1989 Jan;86(1):152-6. doi: 10.1073/pnas.86.1.152.
Abstract
A method is presented for protein secondary structure prediction based on a neural network. A training phase was used to teach the network to recognize the relation between secondary structure and amino acid sequences on a sample set of 48 proteins of known structure. On a separate test set of 14 proteins of known structure, the method achieved a maximum overall predictive accuracy of 63% for three states: helix, sheet, and coil. A numerical measure of helix and sheet tendency for each residue was obtained from the calculations. When predictions were filtered to include only the strongest 31% of predictions, the predictive accuracy rose to 79%.
摘要
提出了一种基于神经网络的蛋白质二级结构预测方法。在一个由48个已知结构蛋白质组成的样本集上，使用训练阶段来训练网络识别二级结构与氨基酸序列之间的关系。在一个由14个已知结构蛋白质组成的单独测试集上，该方法对于螺旋、折叠和卷曲三种状态的总体预测准确率最高达到了63%。通过计算得出了每个残基的螺旋和折叠倾向的数值度量。当预测结果仅筛选出最强的31%的预测时，预测准确率提高到了79%。
相似文献
1
Protein secondary structure prediction with a neural network.使用神经网络进行蛋白质二级结构预测。
Proc Natl Acad Sci U S A. 1989 Jan;86(1):152-6. doi: 10.1073/pnas.86.1.152.
2
Protein secondary structure and homology by neural networks. The alpha-helices in rhodopsin.利用神经网络分析蛋白质二级结构和同源性。视紫红质中的α螺旋。
FEBS Lett. 1988 Dec 5;241(1-2):223-8. doi: 10.1016/0014-5793(88)81066-4.
3
Prediction of secondary structural content of proteins from their amino acid composition alone. I. New analytic vector decomposition methods.仅根据氨基酸组成预测蛋白质的二级结构含量。I. 新的分析向量分解方法。
Proteins. 1996 Jun;25(2):157-68. doi: 10.1002/(SICI)1097-0134(199606)25:2<157::AID-PROT2>3.0.CO;2-F.
4
Predicting the secondary structure of globular proteins using neural network models.使用神经网络模型预测球状蛋白质的二级结构。
J Mol Biol. 1988 Aug 20;202(4):865-84. doi: 10.1016/0022-2836(88)90564-5.
5
Protein secondary structure prediction with partially recurrent neural networks.基于部分循环神经网络的蛋白质二级结构预测
SAR QSAR Environ Res. 1993;1(2-3):153-9. doi: 10.1080/10629369308028826.
6
Predicting protein secondary structure using neural net and statistical methods.使用神经网络和统计方法预测蛋白质二级结构。
J Mol Biol. 1992 May 20;225(2):363-77. doi: 10.1016/0022-2836(92)90927-c.
7
Protein secondary structure prediction with SPARROW.利用 SPARROW 进行蛋白质二级结构预测。
J Chem Inf Model. 2012 Feb 27;52(2):545-56. doi: 10.1021/ci200321u. Epub 2012 Jan 23.
8
Highly accurate and consistent method for prediction of helix and strand content from primary protein sequences.一种从蛋白质一级序列预测螺旋和链含量的高度准确且一致的方法。
Artif Intell Med. 2005 Sep-Oct;35(1-2):19-35. doi: 10.1016/j.artmed.2005.02.006.
9
Limits on alpha-helix prediction with neural network models.神经网络模型在α-螺旋预测方面的局限性。
Proteins. 1992 Nov;14(3):372-81. doi: 10.1002/prot.340140306.
10
Protein secondary structure prediction using local alignments.利用局部比对进行蛋白质二级结构预测。
J Mol Biol. 1997 Apr 25;268(1):31-6. doi: 10.1006/jmbi.1997.0958.
引用本文的文献
1
Combining knowledge distillation and neural networks to predict protein secondary structure.结合知识蒸馏与神经网络预测蛋白质二级结构。
Sci Rep. 2025 Aug 31;15(1):32031. doi: 10.1038/s41598-025-17513-0.
2
Chemosensory Receptors in Vertebrates: Structure and Computational Modeling Insights.脊椎动物的化学感受器：结构与计算建模见解
Int J Mol Sci. 2025 Jul 10;26(14):6605. doi: 10.3390/ijms26146605.
3
MHTAPred-SS: A Highly Targeted Autoencoder-Driven Deep Multi-Task Learning Framework for Accurate Protein Secondary Structure Prediction.MHTAPred-SS：一种用于准确蛋白质二级结构预测的高度靶向的自动编码器驱动的深度多任务学习框架。
Int J Mol Sci. 2024 Dec 15;25(24):13444. doi: 10.3390/ijms252413444.
4
AlphaFold2, SPINE-X, and Seder on Four Hard CASP Targets.AlphaFold2、SPINE-X 和 Seder 对四个困难的 CASP 目标的研究。
Methods Mol Biol. 2025;2867:141-152. doi: 10.1007/978-1-0716-4196-5_8.
5
Deep Learning for Genomics: From Early Neural Nets to Modern Large Language Models.深度学习在基因组学中的应用：从早期神经网络到现代大型语言模型。
Int J Mol Sci. 2023 Nov 1;24(21):15858. doi: 10.3390/ijms242115858.
6
Illuminating the "Twilight Zone": Advances in Difficult Protein Modeling.阐明“混沌地带”：困难蛋白建模的进展。
Methods Mol Biol. 2023;2627:25-40. doi: 10.1007/978-1-0716-2974-1_2.
7
Deep learning for protein secondary structure prediction: Pre and post-AlphaFold.用于蛋白质二级结构预测的深度学习：AlphaFold之前与之后。
Comput Struct Biotechnol J. 2022 Nov 11;20:6271-6286. doi: 10.1016/j.csbj.2022.11.012. eCollection 2022.
8
Glycoinformatics in the Artificial Intelligence Era.人工智能时代的糖组学信息学。
Chem Rev. 2022 Oct 26;122(20):15971-15988. doi: 10.1021/acs.chemrev.2c00110. Epub 2022 Aug 12.
9
Ensemble of Template-Free and Template-Based Classifiers for Protein Secondary Structure Prediction.无模板和基于模板的分类器集成方法用于蛋白质二级结构预测。
Int J Mol Sci. 2021 Oct 23;22(21):11449. doi: 10.3390/ijms222111449.
10
Drug Discovery of Spinal Muscular Atrophy (SMA) from the Computational Perspective: A Comprehensive Review.从计算角度看脊髓性肌萎缩症（SMA）的药物发现：全面综述。
Int J Mol Sci. 2021 Aug 20;22(16):8962. doi: 10.3390/ijms22168962.
本文引用的文献
1
Neural networks and physical systems with emergent collective computational abilities.具有涌现集体计算能力的神经网络与物理系统。
Proc Natl Acad Sci U S A. 1982 Apr;79(8):2554-8. doi: 10.1073/pnas.79.8.2554.
2
How good are predictions of protein secondary structure?蛋白质二级结构的预测准确性如何？
FEBS Lett. 1983 May 8;155(2):179-82. doi: 10.1016/0014-5793(82)80597-8.
3
Dictionary of protein secondary structure: pattern recognition of hydrogen-bonded and geometrical features.蛋白质二级结构词典：氢键和几何特征的模式识别
Biopolymers. 1983 Dec;22(12):2577-637. doi: 10.1002/bip.360221211.
4
Algorithms for prediction of alpha-helical and beta-structural regions in globular proteins.预测球状蛋白质中α螺旋和β结构区域的算法。
J Mol Biol. 1974 Oct 5;88(4):873-94. doi: 10.1016/0022-2836(74)90405-7.
5
Prediction of protein conformation.蛋白质构象预测
Biochemistry. 1974 Jan 15;13(2):222-45. doi: 10.1021/bi00699a002.
6
An attempt to evaluate the influence of neighboring amino acids (n-1) and (n+1) on the backbone conformation of amino acid (n) in proteins. Use in predicting the three-dimensional structure of the polypeptide backbone of other proteins.评估相邻氨基酸（n-1）和（n+1）对蛋白质中氨基酸（n）主链构象的影响的尝试。用于预测其他蛋白质多肽主链的三维结构。
J Mol Biol. 1973 Mar 25;75(1):13-31. doi: 10.1016/0022-2836(73)90526-3.
7
Computing with neural circuits: a model.利用神经回路进行计算：一种模型。
Science. 1986 Aug 8;233(4764):625-33. doi: 10.1126/science.3755256.
8
Turn prediction in proteins using a pattern-matching approach.使用模式匹配方法预测蛋白质中的转角。
Biochemistry. 1986 Jan 14;25(1):266-75. doi: 10.1021/bi00349a037.
9
An algorithm for secondary structure determination in proteins based on sequence similarity.一种基于序列相似性的蛋白质二级结构测定算法。
FEBS Lett. 1986 Sep 15;205(2):303-8. doi: 10.1016/0014-5793(86)80917-6.
10
Amino acid sequence homology applied to the prediction of protein secondary structures, and joint prediction with existing methods.应用于蛋白质二级结构预测的氨基酸序列同源性，以及与现有方法的联合预测。
Biochim Biophys Acta. 1986 May 12;871(1):45-54. doi: 10.1016/0167-4838(86)90131-7.
Zotero 插件