Quantitative analysis of non-alcoholic fatty liver in rats via combining multiple ultrasound parameters.

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease. The noninvasive and accurate classification of NAFLD is still a challenging problem. In this study we pro- posed a new quantitative ultrasound (QUS) technique, which combined multiple QUS parameters for distinguishing steatosis stages. NAFLD was induced in the livers of 57 rats by gavage feeding with a high fat emulsion, while 8 rats were given a standard diet to serve as controls. Ex vivo ultrasound mea- surement was conducted for capturing the radiofrequency signal. Six QUS parameters were extracted and selected for linear combination. The results show that the overall performance of the combined parameter is better than that of the single QUS parameter. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) while using our proposed method to distinguish mild steatosis (stage S1) from the steatosis under stage S0 are 90.1%, 0.93, 0.88 and 0.97 respectively. In conclusion, the proposed method in this study can make up for the deficiency of single parameter and improve the quantitative staging ability of fatty liver, and thus could play an important role in the diagnosis of NAFLD.

Prediction of protein-protein interactions by label propagation with protein evolutionary and chemical information derived from heterogeneous network.

Prediction of protein-protein interactions (PPIs) is of great significance. To achieve this, we propose a novel computational method for PPIs prediction based on a similarity network fusion (SNF) model for integrating the physical and chemical properties of proteins. Specifically, the physical and chemical properties of protein are the protein amino acid mutation rate and its hydrophobicity, respectively. The amino acid mutation rate is extracted using a BLOSUM62 matrix, which puts the protein sequence into block substitution matrix. The SNF model is exploited to fuse protein physical and chemical features of multiple data by iteratively updating each original network. Finally, the complementary features from the fused network are fed into a label propagation algorithm (LPA) for PPIs prediction. The experimental results show that the proposed method achieves promising performance and outperforms the traditional methods for the public dataset of H. pylori, Human, and Yeast. In addition, our proposed method achieves average accuracy of 76.65%, 81.98%, 84.56%, 84.01% and 84.38% on E. coli, C. elegans, H. sapien, H. pylori and M. musculus datasets, respectively. Comparison results demonstrate that the proposed method is very promising and provides a cost-effective alternative for predicting PPIs. The source code and all datasets are available at http://pan.baidu.com/s/1dF7rp7N.