2DCSi: identification of protein secondary structure and redox state using 2D cluster analysis of NMR chemical shifts

2007 ◽  
Vol 38 (1) ◽  
pp. 57-63 ◽  
Author(s):  
Ching-Cheng Wang ◽  
Jui-Hung Chen ◽  
Wen-Chung Lai ◽  
Woei-Jer Chuang
2003 ◽  
Vol 49 (7) ◽  
pp. 1125-1132 ◽  
Author(s):  
Kan-Zhi Liu ◽  
Kam Sze Tsang ◽  
Chi Kong Li ◽  
R Anthony Shaw ◽  
Henry H Mantsch

Abstract Background: The aim of this study was to investigate the potential of infrared (IR) spectroscopy as a fast and reagent-free adjunct tool in the diagnosis and screening of β-thalassemia. Methods: Blood was obtained from 56 patients with β-thalassemia major, 1 patient with hemoglobin H disease, and 35 age-matched controls. Hemolysates of blood samples were centrifuged to remove stroma. IR absorption spectra were recorded for duplicate films dried from 5 μL of hemolysate. Differentiation between the two groups of hemoglobin spectra was by two statistical methods: an unsupervised cluster analysis and a supervised linear discriminant analysis (LDA). Results: The IR spectra revealed changes in the secondary structure of hemoglobin from β-thalassemia patients compared with that from controls, in particular, a decreased α-helix content, an increased content of parallel and antiparallel β-sheets, and changes in the tyrosine ring absorption band. The hemoglobin from β-thalassemia patients also showed an increase in the intensity of the IR bands from the cysteine −SH groups. The unsupervised cluster analysis, statistically separating spectra into different groups according to subtle IR spectral differences, allowed separation of control hemoglobin from β-thalassemia hemoglobin spectra, based mainly on differences in protein secondary structure. The supervised LDA method provided 100% classification accuracy for the training set and 98% accuracy for the validation set in partitioning control and β-thalassemia samples. Conclusion: IR spectroscopy holds promise in the clinical diagnosis and screening of β-thalassemia.


2021 ◽  
Author(s):  
Zhiwei Miao ◽  
Qianqian Wang ◽  
Xiongjie Xiao ◽  
Linhong Song ◽  
Xu Zhang ◽  
...  

The description and understanding of protein structure rely on secondary structure heavily. Secondary structure determination and prediction are widely used in protein structure related research. The secondary structure prediction methods based on NMR chemical shifts are convenient to use, so they are popular in protein NMR research. In recent years, there is significant improvement in deep neural network, which is consequently applied in many search fields. Here we proposed a deep neural network based on bidirectional long short term memory (biLSTM) to predict protein 3-state secondary structure using NMR chemical shifts of backbone nuclei. Compared with the existing methods of the same sort, the accuracy of the proposed method was improved. And a web server was built to provide secondary structure prediction service using this method.


Sign in / Sign up

Export Citation Format

Share Document