scholarly journals Protein subnuclear localization based on a new effective representation and intelligent kernel linear discriminant analysis by dichotomous greedy genetic algorithm

PLoS ONE ◽  
2018 ◽  
Vol 13 (4) ◽  
pp. e0195636 ◽  
Author(s):  
Shunfang Wang ◽  
Yaoting Yue
Keyword(s):  
Genetic Algorithm ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Linear Discriminant ◽  
Subnuclear Localization ◽  
Effective Representation

Collagen remodeling in the extracellular matrix of the cardiomyopathic Syrian hamster heart as assessed by FTIR attenuated total reflectance spectroscopy

1999 ◽  
Vol 77 (11) ◽  
pp. 1843-1855 ◽  
Author(s):  
Pamela S Bromberg ◽  
Kathleen M Gough ◽  
Ian MC Dixon
Keyword(s):  
Genetic Algorithm ◽  
Extracellular Matrix ◽  
Discriminant Analysis ◽  
Left Ventricle ◽  
Linear Discriminant Analysis ◽  
Collagen Content ◽  
Diffuse Fibrosis ◽  
Collagen Deposition ◽  
Linear Discriminant ◽  
Collagen Remodeling

Collagen type I and III deposition in the cardiac extracellular matrix contributes significantly to myocardial dysfunction. Diffuse and focal fibrosis is believed to accompany human congestive cardiomyopathy (CCM) associated with congestive heart failure (CHF). The left ventricle collagen remodeling that occurs in the hamster model of CCM is marked by left ventricle fibrosis, hypertrophy and dilation, proceeded by CHF post 150 days of age. The objectives of our study were to (i) evaluate changes in collagen deposition in the right (RV) and left (LV) ventricular tissue of cardiomyopathic (CMP) and control (CON) myocardium using FTIR ATR spectroscopy, (ii) classify the normal and diseased heart tissue using linear discriminant analysis (LDA) aided by a genetic algorithm (GA) selection of spectroscopically diagnostic regions in the mid-IR region, (iii) rationalize the spectroscopic differences between left/right ventricle tissue as well as CON/CMP tissue according to the pathophysiology documented for the UM-X7.1 strain of CMP hamsters. The presence of collagen in the tissue was confirmed spectroscopically by observation of the collagen IR fingerprint in the 1000-1800 cm-1 region. Difference spectroscopy was utilized to substantiate which tissue under comparison exhibited pronounced collagen content. Multivariate analysis (LDA) was carried out on user-selected spectral subregions and compared to class separation based on spectral subregions chosen nonsubjectively by a GA. Our study confirmed that the animals experienced LV collagen remodeling denoted by focal rather than diffuse fibrosis. In addition, RV collagen remodeling, denoted by decreased RV collagen content, appeared to accompany the increased LV collagen deposition found for the CMP animals.Key words: FTIR spectroscopy, collagen, cardiomyopathy, genetic algorithm, linear discriminant analysis.

scholarly journals Protein Subnuclear Localization Based on Radius-SMOTE and Kernel Linear Discriminant Analysis Combined with Random Forest

Electronics ◽  
2020 ◽  
Vol 9 (10) ◽  
pp. 1566
Author(s):  
Liwen Wu ◽  
Shanshan Huang ◽  
Feng Wu ◽  
Qian Jiang ◽  
Shaowen Yao ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Random Forest ◽  
Linear Discriminant Analysis ◽  
Linear Discriminant ◽  
Jackknife Test ◽  
Subnuclear Localization ◽  
Feature Vectors ◽  
Benchmark Datasets ◽  
Novel Method ◽  
Protein Datasets

Protein subnuclear localization plays an important role in proteomics, and can help researchers to understand the biologic functions of nucleus. To date, most protein datasets used by studies are unbalanced, which reduces the prediction accuracy of protein subnuclear localization—especially for the minority classes. In this work, a novel method is therefore proposed to predict the protein subnuclear localization of unbalanced datasets. First, the position-specific score matrix is used to extract the feature vectors of two benchmark datasets and then the useful features are selected by kernel linear discriminant analysis. Second, the Radius-SMOTE is used to expand the samples of minority classes to deal with the problem of imbalance in datasets. Finally, the optimal feature vectors of the expanded datasets are classified by random forest. In order to evaluate the performance of the proposed method, four index evolutions are calculated by Jackknife test. The results indicate that the proposed method can achieve better effect compared with other conventional methods, and it can also improve the accuracy for both majority and minority classes effectively.

Sign in / Sign up

Export Citation Format

Share Document