Protein lysine β-hydroxybutyrylation (Kbhb) is a newly discovered post-translational modification associated with a wide range of biological processes. Identifying Kbhb sites is critical for a better understanding of its mechanism of action. However, biochemical experimental methods for probing Kbhb sites are costly and have a long cycle. Therefore, a feature embedding learning method based on the Transformer encoder was proposed to predict Kbhb sites. In this method, amino acid residues were mapped into numerical vectors according to their amino acid class and position in a learnable feature embedding method. Then the Transformer encoder was used to extract discriminating features, and the bidirectional long short-term memory network (BiLSTM) was used to capture the correlation between different features. In this paper, a benchmark dataset was constructed, and a Kbhb site predictor, AutoTF-Kbhb, was implemented based on the proposed method. Experimental results showed that the proposed feature embedding learning method could extract effective features. AutoTF-Kbhb achieved an area under curve (AUC) of 0.87 and a Matthews correlation coefficient (MCC) of 0.37 on the independent test set, significantly outperforming other methods in comparison. Therefore, AutoTF-Kbhb can be used as an auxiliary means to identify Kbhb sites.
Protein Processing, Post-Translational ; Lysine/chemistry* ; Proteins/chemistry* ; Machine Learning ; Algorithms

Objective To discuss the clinical application of coronary CT angiography(CCTA)-derived fractional flow reserve(CT-FFR)in evaluating the risk stratification of the coronary artery stenosis and atherosclerotic plaque quantitative parameters.Methods A total of 122 patients,who received CCTA examination at the Xuzhou Municipal Central Hospital of China,were enrolled in this study.The patients were divided into non-ischemia group(CT-FFR＞0.8,n=66)and ischemia group(CT-FFR0.8,n=56).The characteristics of atherosclerotic plaque were compared between the two groups.Logistic regression analysis was used to analyze the correlation between plaque characteristics and ischemic lesions.Results There were 218 vessels having a CT-FFR＞0.8 and 174 vessels having a CT-FFR ≤0.8.Statistically significant differences in the total plaque volume,calcified plaque volume,plaque length,and stenosis ratio＞50％existed between the two groups(all P＜0.05).Logistic regression analysis indicated that the total plaque volume,calcified plaque volume,plaque length,and stenosis ratio＞50％were the risk factors for myocardial ischemia.Conclusion CT-FFR can be used for the risk stratification of coronary stenosis and atherosclerotic plaque characteristics,which can evaluate the local myocardial blood supply condition from the anatomical stenosis and functional level so as to optimize the diagnosis and treatment measures.

Renal fibrosis, especially tubulointerstitial fibrosis, is the most common pathway of all chronic kidney diseases progressing to end-stage renal diseases. Several adaptive reactions occur in renal tubular epithelial cells after chronic injury, such as changes in glycolipid metabolism, unfolded protein response, autophagy and senescence, epithelial-to-mesenchymal transition and G2/M cell cycle arrest. Maladaptive repair mechanisms can induce tubulointerstitial fibrosis. This article will discuss the molecular mechanism of these adaptive responses of renal tubular epithelial cells driving renal tubulointerstitial fibrosis, and provide a basis for exploring new drug targets for renal tubulointerstitial fibrosis.

Objective To study the effects of puerarin on proliferation and apoptosis of human gastric cancer MGC-803 and AGS cells.Methods Human gastric cancer cells were treated with puerarin at different concentrations.MTT assay was used to test cell proliferation and FCM was used to detect cell apoptosis.Results The inhibition rates had upwarded trend with increasing concentrations (MGC-803:1.24 ％,2.80 ％,15.10 ％,18.55 ％,59.65 ％; AGS:15.59 ％,25.31％,30.25 ％,36.91％,64.47 ％),when treated with puerarin at different concentrations (1.5,3.0,6.0 12.0,24.0 mmol/L) for 48 hours.Apoptosis rates gradually increased with increasing concentrations (MGC-803:5.49 ％,9.53 ％,13.81％; AGS:6.23 ％,16.38 ％,25.99 ％),when treated with puerarin at different concentrations (0,12.0,24.0 mmol/L) for 24 hours.Conclusion Puerarin inhibits proliferation and induces apoptosis of human gastric cancer cells MGC-803 and AGS.