Predicting subcellular protein localization has become a popular topic due to its utility in understanding disease mechanisms and developing innovative drugs. With the rapid advancement of automated microscopic imaging technology, approaches using bio-images for protein subcellular localization have gained a lot of interest. The Human Protein Atlas (HPA) project is a macro-initiative that aims to map the human proteome utilizing antibody-based proteomics and related c. Millions of images have been tagged with single or multiple labels in the HPA database. However, fewer techniques for predicting the location of proteins have been devised, with the majority of them relying on automatic single-label classification. As a result, there is a need for an automatic and sustainable system capable of multi-label classification of the HPA database. Deep learning presents a potential option for automatic labeling of protein’s subcellular localization, given the vast image number generated by high-content microscopy and the fact that manual labeling is both time-consuming and error-prone. Hence, this research aims to use an ensemble technique for the improvement in the performance of existing state-of-art convolutional neural networks and pretrained models were applied; finally, a stacked ensemble-based deep learning model was presented, which delivers a more reliable and robust classifier. The F1-score, precision, and recall have been used for the evaluation of the proposed model’s efficiency. In addition, a comparison of existing deep learning approaches has been conducted with respect to the proposed method. The results show the proposed ensemble strategy performed exponentially well on the multi-label classification of Human Protein Atlas images, with recall, precision, and F1-score of 0.70, 0.72, and 0.71, respectively.

/pdf/an-artificial-intelligence-based-stacked-ensemble-approach-200d85y8.pdf

An Artificial Intelligence-Based Stacked Ensemble Approach for Prediction of Protein Subcellular Localization in Confocal Microscopy Images

Doxorubicin (DOX) is an effective and widely used anticancer drug but has limited clinical applicability because of its cardiotoxicity. Ferroptosis plays a key role in DOX-induced cardiac damage and cardiomyocyte cell death. The inhibition of ferroptosis reverses DOX-induced cardiotoxicity (DIC). LCZ696, a first-in-class angiotensin receptor neprilysin inhibitor, protects against DIC. However, the mechanism of action of LCZ696, especially its effect on ferroptosis, is incompletely understood. This study investigates the cardioprotective effects of LCZ696 on DIC in vivo and in vitro.Cardiotoxicity was induced in Wistar rats by tail intravenous injection of 2.5 mg/kg DOX once a week for six weeks. Rats and H9c2 cells were treated with or without LCZ696 to determine the cardioprotective role and underlying mechanisms of LCZ696 against DIC. To assess the role of SIRT3 and correlated pathways in ferroptosis, SIRT3 knockout was performed using lentiviral vectors, and AKT was inhibited with LY294002. LCZ696 significantly attenuated DIC by decreasing the concentrations of lipid reactive oxygen species and malondialdehyde and increasing the levels of glutathione peroxidase-4 and reduced glutathione in cells and heart tissues. Moreover, LCZ696 remodeled myocardial structures and improved heart ventricular function in DOX-treated rats. LCZ696 treatment increased SIRT3 expression and deacetylated its target gene SOD2, and these changes were mediated by AKT activation. SIRT3 knockdown and AKT inhibition induced lipid peroxidation and reduced the protective effect of LCZ696 in H9c2 cells. Collectively,LCZ696 prevents DIC by inhibiting ferroptosis via AKT/SIRT3/SOD2 signaling pathway activation. Thus, LZC696 is a potential therapeutic strategy for DIC.

LCZ696 protects against doxorubicin-induced cardiotoxicity by inhibiting ferroptosis via AKT/SIRT3/SOD2 signaling pathway activation.

Cardiovascular diseases have become a major clinical burden globally. Heart failure is one of the diseases that commonly emanates from progressive uncontrolled hypertension. This gives rise to the need for a new treatment for the disease. Sacubitril/valsartan is a new drug combination that has been approved for patients with heart failure. This review aims to detail the mechanism of action for sacubitril/valsartan in cardiac remodeling, a cellular and molecular process that occurs during the development of heart failure. Accumulating evidence has unveiled the cardioprotective effects of sacubitril/valsartan on cellular and molecular modulation in cardiac remodeling, with recent large-scale randomized clinical trials confirming its supremacy over other traditional heart failure treatments. However, its molecular mechanism of action in cardiac remodeling remains obscure. Therefore, comprehending the molecular mechanism of action of sacubitril/valsartan could help future research to study the drug’s potential therapy to reduce the severity of heart failure.

/pdf/molecular-mechanisms-of-sacubitril-valsartan-in-cardiac-3nkq5zfq.pdf

Molecular mechanisms of sacubitril/valsartan in cardiac remodeling

LCZ696 protects against doxorubicin-induced cardiotoxicity by inhibiting ferroptosis via AKT/SIRT3/SOD2 signaling pathway activation

The SPATA2/CYLD pathway contributes to doxorubicin-induced cardiomyocyte ferroptosis via enhancing ferritinophagy.

Exploring the role of ferroptosis in the doxorubicin-induced chronic cardiotoxicity using a murine model.

The task of multi-label image classification is to recognize all the object labels presented in an image. Though advancing for years, small objects, similar objects and objects with high conditional probability are still the main bottlenecks of previous convolutional neural network(CNN) based models, limited by convolutional kernels' representational capacity. Recent vision transformer networks utilize the self-attention mechanism to extract the feature of pixel granularity, which expresses richer local semantic information, while is insufficient for mining global spatial dependence. In this paper, we point out the three crucial problems that CNN-based methods encounter and explore the possibility of conducting specific transformer modules to settle them. We put forward a Multi-label Transformer architecture(MlTr) constructed with windows partitioning, in-window pixel attention, cross-window attention, particularly improving the performance of multi-label image classification tasks. The proposed MlTr shows state-of-the-art results on various prevalent multi-label datasets such as MS-COCO, Pascal-VOC, and NUS-WIDE with 88.5%, 95.8%, and 65.5% respectively. The code will be available soon at this https URL

MlTr: Multi-label Classification with Transformer

Abstract Statins are considered as the cornerstone of the prevention and treatment of atherosclerotic cardiovascular disease, where pleiotropic effects are thought to contribute greatly in addition to the lipid-lowering effect. Bile acid metabolism has been gradually reported to be involved in the antihyperlipidemic and antiatherosclerotic effects of statins, but with inconsistent results and few studies carried out on animal models of atherosclerosis. The study aimed to examine the possible role of bile acid metabolism in the lipid-lowering and antiatherosclerotic effects of atorvastatin (ATO) in high-fat diet–fed ApoE−/− mice. The results showed that the levels of liver and faecal TC as well as ileal and faecal TBA were significantly increased in mice of the model group after 20 weeks of high-fat diet feeding compared with the control group, with significantly downregulated mRNA expression of liver LXR-α, CYP7A1, BSEP, and NTCP. ATO treatment further increased the levels of ileal and faecal TBA and faecal TC, but no obvious effect was observed on serum and liver TBA. In addition, ATO significantly reversed the mRNA levels of liver CYP7A1 and NTCP, and no obvious changes were observed in the expression of LXR-α and BSEP. Our study suggested that statins may enhance the synthesis of bile acids and facilitate the reabsorption of bile acids from the ileum via portal into the liver, possibly through the upregulation of the expression of CYP7A1 and NTCP. The results are helpful in enriching the theoretical basis for the clinical use of statins and have good translational value.

Honglin Liu

Papers

Exploring the role of ferroptosis in the doxorubicin-induced chronic cardiotoxicity using a murine model.

MlTr: Multi-label Classification with Transformer

Effects of Atorvastatin on Bile Acid Metabolism in High-fat Diet–fed ApoE−/− Mice