Local structure-aware graph contrastive representation learning.

Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information. However, Graph Contrastive Learning (GCL) methods, which tackles the label problem effectively, mainly focus on the feature information of the global graph or small subgraph structure (e.g., the first-order neighborhood). In this paper, we propose a Local Structure-aware Graph Contrastive representation Learning method (LS-GCL) to model the structural information of nodes from multiple views. Specifically, we construct the semantic subgraphs that are not limited to the first-order neighbors. For the local view, the semantic subgraph of each target node is input into a shared GNN encoder to obtain the target node embeddings at the subgraph-level. Then, we use a pooling function to generate the subgraph-level graph embeddings. For the global view, considering the original graph preserves indispensable semantic information of nodes, we leverage the shared GNN encoder to learn the target node embeddings at the global graph-level. The proposed LS-GCL model is optimized to maximize the common information among similar instances at three various perspectives through a multi-level contrastive loss function. Experimental results on six datasets illustrate that our method outperforms state-of-the-art graph representation learning approaches for both node classification and link prediction tasks.

Two-stream vision transformer based multi-label recognition for TCM prescriptions construction.

Traditional Chinese medicine (TCM) observation diagnosis images (including facial and tongue images) provide essential human body information, holding significant importance in clinical medicine for diagnosis and treatment. TCM prescriptions, known for their simplicity, non-invasiveness, and low side effects, have been widely applied worldwide. Exploring automated herbal prescription construction based on visual diagnosis holds vital value in delving into the correlation between external features and herbal prescriptions and offering medical services in mobile healthcare systems. To effectively integrate multi-perspective visual diagnosis images and automate prescription construction, this study proposes a multi-herb recommendation framework based on Visual Transformer and multi-label classification. The framework comprises three key components: image encoder, label embedding module, and cross-modal fusion classification module. The image encoder employs a dual-stream Visual Transformer to learn dependencies between different regions of input images, capturing both local and global features. The label embedding module utilizes Graph Convolutional Networks to capture associations between diverse herbal labels. Finally, two Multi-Modal Factorized Bilinear modules are introduced as effective components to fuse cross-modal vectors, creating an end-to-end multi-label image-herb recommendation model. Through experimentation with real facial and tongue images and generating prescription data closely resembling real samples. The precision is 50.06 %, the recall rate is 48.33 %, and the F1-score is 49.18 %. This study validates the feasibility of automated herbal prescription construction from the perspective of visual diagnosis. Simultaneously, it provides valuable insights for constructing herbal prescriptions automatically from more physical information.

Gynura divaricata (L.) DC. promotes diabetic wound healing by activating Nrf2 signaling in diabetic rats.

THE ETHNOPHARMACOLOGICAL SIGNIFICANCE: Diabetic chronic foot ulcers pose a significant therapeutic challenge as a result of the oxidative stress caused by hyperglycemia. Which impairs angiogenesis and delays wound healing, potentially leading to amputation. Gynura divaricata (L.) DC. (GD), a traditional Chinese herbal medicine with hypoglycemic effects, has been proposed as a potential therapeutic agent for diabetic wound healing. However, the underlying mechanisms of its effects remain unclear. AIM OF THE STUDY: In this study, we aimed to reveal the effect and potential mechanisms of GD on accelerating diabetic wound healing in vitro and in vivo. MATERIALS AND METHODS: The effects of GD on cell proliferation, apoptosis, reactive oxygen species (ROS) production, migration, mitochondrial membrane potential (MMP), and potential molecular mechanisms were investigated in high glucose (HG) stimulated human umbilical vein endothelial cells (HUVECs) using CCK-8, flow cytometry assay, wound healing assay, immunofluorescence, DCFH-DA staining, JC-1 staining, and Western blot. Full-thickness skin defects were created in STZ-induced diabetic rats, and wound healing rate was tracked by photographing them every day. HE staining, immunohistochemistry, and Western blot were employed to investigate the effect and molecular mechanism of GD on wound healing in diabetic rats. RESULTS: GD significantly improved HUVEC survival, decreased apoptosis, lowered ROS production, restored MMP, improved migration ability, and raised VEGF expression. The use of Nrf2-siRNA completely abrogated these effects. Topical application of GD promoted angiogenesis and granulation tissue growth, resulting in faster healing of diabetic wounds. The expression of VEGF, CD31, and VEGFR was elevated in the skin tissue of diabetic rats after GD treatment, which upregulated HO-1, NQO-1, and Bcl-2 expression while downregulating Bax expression via activation of the Nrf2 signaling pathway. CONCLUSION: The findings of this study indicate that GD has the potential to serve as a viable alternative treatment for diabetic wounds. This potential arises from its ability to mitigate the negative effects of oxidative stress on angiogenesis, which is regulated by the Nrf2 signaling pathway. The results of our study offer valuable insights into the therapeutic efficacy of GD in the treatment of diabetic wounds, emphasizing the significance of directing interventions towards the Nrf2 signaling pathway to mitigate oxidative stress and facilitate the process of angiogenesis.

Graph Neural Network for representation learning of lung cancer.

The emergence of image-based systems to improve diagnostic pathology precision, involving the intent to label sets or bags of instances, greatly hinges on Multiple Instance Learning for Whole Slide Images(WSIs). Contemporary works have shown excellent performance for a neural network in MIL settings. Here, we examine a graph-based model to facilitate end-to-end learning and sample suitable patches using a tile-based approach. We propose MIL-GNN to employ a graph-based Variational Auto-encoder with a Gaussian mixture model to discover relations between sample patches for the purposes to aggregate patch details into an individual vector representation. Using the classical MIL dataset MUSK and distinguishing two lung cancer sub-types, lung cancer called adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), we exhibit the efficacy of our technique. We achieved a 97.42% accuracy on the MUSK dataset and a 94.3% AUC on the classification of lung cancer sub-types utilizing features.

Photoelectrochemical detection of superoxide anions released from mitochondria in HepG2 cells based on the synergistic effect of MnO2@Co3O4 core-shell p-n heterojunction.

The detection and comparison of the amount of superoxide anion (O2.-) released by different complexes in mitochondrial electron transport chain (ETC) can locate the main electron leakage sites in mitochondria. In order to realize this, we designed an ultrasensitive photoelectrochemical (PEC) sensor by in situ hydrothermal growth of MnO2 nanosheets on Co3O4 nanowires array modified Ti substrate (NWA|Ti). Due to the formation of a core-shell p-n heterojunction with high specific surface area, tight surface contact and plentiful oxygen vacancies (OVs), MnO2@Co3O4 NWA|Ti possesses a strong visible light absorption, high charges transfer and separation ability. The proposed PEC sensor exhibited a wide linear range of 0.1-50000 nM and a low detection limit of 0.025 nM towards H2O2. Due to the rapid conversion of O2.- to H2O2 inside mitochondria, the PEC sensor can indirectly monitor the electron leakage in the ETC. Specifically, four selected mitochondrial inhibitors specifically inhibited the corresponding complex in mitochondria extracted from living HepG2 cells (hepatocellular carcinoma cells), and the H2O2 levels converted from O2.- was measured by the PEC sensor. It is evident that IQ (ubiquinone binding) site of complex I and Qo (ubiquinol oxidation) site of complex III are the key sites at which electron leakage occurred. This study could provide meaningful information for the diagnosis and treatment of certain disease caused by oxidative stress due to the electron leakage.

Biomass-Derived Bifunctional Cathode Electrocatalyst and Multiadaptive Gel Electrolyte for High-Performance Flexible Zn-Air Batteries in Wide Temperature Range.

High-efficiency and low-cost bifunctional electrocatalysts for oxygen reduction reaction (ORR) and oxygen evolution reaction (OER), as well as gel electrolytes with high thermal and mechanical adaptability are required for the development of flexible batteries. Herein, abundant Setaria Viridis (SV) biomass is selected as the precursor to prepare porous N-doped carbon tubes with high specific surface area and the 900 °C calcination product of SV (SV-900) shows the optimum ORR/OER activities with a small EOER -EORR of 0.734 V. Meanwhile, a new multifunctional gel electrolyte named C20E2G5 is prepared using cellulose extracted from another widely distributed biomass named flax as the skeleton, epichlorohydrin as the cross-linker and glycerol as the antifreezing agent. C20E2G5 possesses high ionic conductivity from -40 to + 60 °C, excellent tensile and compressive resistance, high adhesion, strong freezing and heat resistance. Moreover, the symmetrical cell assembled with C20E2G5 can significantly inhibit Zn dendrite growth. Finally, flexible solid-state Zn-air batteries assembled with SV-900 and C20E2G5 show high open circuit voltage, large energy density, and long-term operation stability between -40 and + 60 °C. This biomass-based approach is generic and can be used for the development of diverse next-generation electrochemical energy conversion and storage devices.

Weakly supervised label propagation algorithm classifies lung cancer imaging subtypes.

Aiming at the problems of long time, high cost, invasive sampling damage, and easy emergence of drug resistance in lung cancer gene detection, a reliable and non-invasive prognostic method is proposed. Under the guidance of weakly supervised learning, deep metric learning and graph clustering methods are used to learn higher-level abstract features in CT imaging features. The unlabeled data is dynamically updated through the k-nearest label update strategy, and the unlabeled data is transformed into weak label data and continue to update the process of strong label data to optimize the clustering results and establish a classification model for predicting new subtypes of lung cancer imaging. Five imaging subtypes are confirmed on the lung cancer dataset containing CT, clinical and genetic information downloaded from the TCIA lung cancer database. The successful establishment of the new model has a significant accuracy rate for subtype classification (ACC = 0.9793), and the use of CT sequence images, gene expression, DNA methylation and gene mutation data from the cooperative hospital in Shanxi Province proves the biomedical value of this method. The proposed method also can comprehensively evaluate intratumoral heterogeneity based on the correlation between the final lung CT imaging features and specific molecular subtypes.

TCM Prescription Generation via Knowledge Source Guidance Network Combined with Herbal Candidate Mechanism.

Traditional Chinese medicine (TCM) prescriptions have made great contributions to the treatment of diseases and health preservation. To alleviate the shortage of TCM resources and improve the professionalism of automatically generated prescriptions, this paper deeply explores the connection between symptoms and herbs through deep learning technology, and realizes the automatic generation of TCM prescriptions. Particularly, this paper considers the significance of referring to similar underlying prescriptions as herbal candidates in the TCM prescribing process. Moreover, this paper incorporates the idea of referring to the potential guidance information of corresponding prescriptions when model extracts symptoms representations. To provide a reference for inexperienced young TCM doctors when they prescribe, this paper proposes a dual-branch guidance strategy combined with candidate attention model (DGSCAM) to automatically generate TCM prescriptions based on symptoms text. The format of the data used this paper is the "symptoms-prescription" data pair. The specific method is as follows. First, DGSCAM realizes the extraction of key information of prescription-guided symptoms through a dual-branch network. Then, herbal candidates in the form of prescriptions that can treat symptoms are proposed in view of the compatibility knowledge of TCM prescriptions. To our knowledge, this is the first attempt to use prescriptions as herbal candidates in the prescription generation process. We conduct extensive experiments on a mixed public and clinical dataset, achieving 37.39% precision, 25.04% recall, and 29.99% F1 score, with an average doctor score of 7.7 out of 10. The experimental results show that our proposed model is valid and can generate more specialized TCM prescriptions than the baseline models. The DGSCAM developed by us has broad application scenarios and greatly promotes the research on intelligent TCM prescribing.

A multitask dual-stream attention network for the identification of KRAS mutation in colorectal cancer.

PURPOSE: It is of great significance to accurately identify the KRAS gene mutation status for patients in tumor prognosis and personalized treatment. Although the computer-aided diagnosis system based on deep learning has gotten all-round development, its performance still cannot meet the current clinical application requirements due to the inherent limitations of small-scale medical image data set and inaccurate lesion feature extraction. Therefore, our aim is to propose a deep learning model based on T2 MRI of colorectal cancer (CRC) patients to identify whether KRAS gene is mutated. METHODS: In this research, a multitask attentive model is proposed to identify KRAS gene mutations in patients, which is mainly composed of a segmentation subnetwork and an identification subnetwork. Specifically, at first, the features extracted by the encoder of segmentation model are used as guidance information to guide the two attention modules in the identification network for precise activation of the lesion area. Then the original image of the lesion and the segmentation result are concatenated for feature extraction. Finally, features extracted from the second step are combined with features activated by the attention modules to identify the gene mutation status. In this process, we introduce the interlayer loss function to encourage the similarity of the two subnetwork parameters and ensure that the key features are fully extracted to alleviate the overfitting problem caused by small data set to some extent. RESULTS: The proposed identification model is benchmarked primarily using 15-fold cross validation. Three hundred and eighty-two images from 36 clinical cases were used to test the model. For the identification of KRAS mutation status, the average accuracy is 89.95 ± 1.23%, the average sensitivity is 89.29 ± 1.79%, the average specificity is 90.53 ± 2.45%, and the average area under the curve (AUC) is 95.73 ± 0.52%. For segmentation of lesions, the average dice is 88.11 ± 0.86%. CONCLUSIONS: We developed a novel deep learning-based model to identify the KRAS status in CRC. We demonstrated the excellent properties of the proposed identification through comparison with ground truth gene mutation status of 36 clinical cases. And all these results show that the novel method has great potential for clinical application.

Multitask Interactive Attention Learning Model Based on Hand Images for Assisting Chinese Medicine in Predicting Myocardial Infarction.

Acute myocardial infarction (AMI) is one of the most serious and dangerous cardiovascular diseases. In recent years, the number of patients around the world has been increasing significantly, among which people under the age of 45 have become the high-risk group for sudden death of AMI. AMI occurs quickly and does not show obvious symptoms before onset. In addition, postonset clinical testing is also a complex and invasive test, which may cause some postoperative complications. Therefore, it is necessary to propose a noninvasive and convenient auxiliary diagnostic method. In traditional Chinese medicine (TCM), it is an effective auxiliary diagnostic strategy to complete the disease diagnosis through some body surface features. It is helpful to observe whether the palmar thenar undergoes hypertrophy and whether the metacarpophalangeal joint is swelling in detecting acute myocardial infarction. Combined with deep learning, we propose a depth model based on traditional palm image (MTIALM), which can help doctors of traditional Chinese medicine to predict myocardial infarction. By building the shared network, the model learns information that covers all the tasks. In addition, task-specific attention branch networks are built to simultaneously detect the symptoms of different parts of the palm. The information interaction module (IIM) is proposed to further integrate the information between task branches to ensure that the model learns as many features as possible. Experimental results show that the accuracy of our model in the detection of metacarpophalangeal joints and palmar thenar is 83.16% and 84.15%, respectively, which are significantly improved compared with the traditional classification methods.

Research progress of epigallocatechin-3-gallate (EGCG) on anti-pathogenic microbes and immune regulation activities.

At the end of 2019, the COVID-19 virus spread worldwide, infecting millions of people. Infectious diseases induced by pathogenic microorganisms such as the influenza virus, hepatitis virus, and Mycobacterium tuberculosis are also a major threat to public health. The high mortality caused by infectious pathogenic microorganisms is due to their strong virulence, which leads to the excessive counterattack by the host immune system and severe inflammatory damage of the immune system. This paper reviews the efficacy, mechanism and related immune regulation of epigallocatechin-3-gallate (EGCG) as an anti-pathogenic microorganism drug. EGCG mainly shows both direct and indirect anti-infection effects. EGCG directly inhibits early infection by interfering with the adsorption on host cells, inhibiting virus replication and reducing bacterial biofilm formation and toxin release; EGCG indirectly inhibits infection by regulating immune inflammation and antioxidation. At the same time, we reviewed the bioavailability and safety of EGCG in vivo. At present, the bioavailability of EGCG can be improved to some extent using nanostructured drug delivery systems and molecular modification technology in combination with other drugs. This study provides a theoretical basis for the development of EGCG as an adjuvant drug for anti-pathogenic microorganisms.

MLW-gcForest: a multi-weighted gcForest model towards the staging of lung adenocarcinoma based on multi-modal genetic data.

BACKGROUND: Lung cancer is one of the most common types of cancer, among which lung adenocarcinoma accounts for the largest proportion. Currently, accurate staging is a prerequisite for effective diagnosis and treatment of lung adenocarcinoma. Previous research has used mainly single-modal data, such as gene expression data, for classification and prediction. Integrating multi-modal genetic data (gene expression RNA-seq, methylation data and copy number variation) from the same patient provides the possibility of using multi-modal genetic data for cancer prediction. A new machine learning method called gcForest has recently been proposed. This method has been proven to be suitable for classification in some fields. However, the model may face challenges when applied to small samples and high-dimensional genetic data. RESULTS: In this paper, we propose a multi-weighted gcForest algorithm (MLW-gcForest) to construct a lung adenocarcinoma staging model using multi-modal genetic data. The new algorithm is based on the standard gcForest algorithm. First, different weights are assigned to different random forests according to the classification performance of these forests in the standard gcForest model. Second, because the feature vectors generated under different scanning granularities have a diverse influence on the final classification result, the feature vectors are given weights according to the proposed sorting optimization algorithm. Then, we train three MLW-gcForest models based on three single-modal datasets (gene expression RNA-seq, methylation data, and copy number variation) and then perform decision fusion to stage lung adenocarcinoma. Experimental results suggest that the MLW-gcForest model is superior to the standard gcForest model in constructing a staging model of lung adenocarcinoma and is better than the traditional classification methods. The accuracy, precision, recall, and AUC reached 0.908, 0.896, 0.882, and 0.96, respectively. CONCLUSIONS: The MLW-gcForest model has great potential in lung adenocarcinoma staging, which is helpful for the diagnosis and personalized treatment of lung adenocarcinoma. The results suggest that the MLW-gcForest algorithm is effective on multi-modal genetic data, which consist of small samples and are high dimensional.

Improving Sequence-Based Prediction of Protein-Peptide Binding Residues by Introducing Intrinsic Disorder and a Consensus Method.

Protein-peptide interaction is crucial for many cellular processes. It is difficult to determine the interaction by experiments as peptides are often very flexible in structure. Accurate sequence-based prediction of peptide-binding residues can facilitate the study of this interaction. In this work, we developed two novel sequence-based methods SVMpep and PepBind to identify the peptide-binding residues. Recent studies demonstrate that the protein-peptide binding is closely associated with intrinsic disorder. We thus introduced intrinsic disorder in our feature design and developed the ab initio method SVMpep. Experiments show that intrinsic disorder contributes to 1.2-5.2% improvement in area under the receiver operating characteristic curve (AUC). Comparison to the recent sequence-based method SPRINT-Seq reveals that SVMpep improves the AUC and Matthews correlation coefficient (MCC) by at least 7.7% and 70%, respectively. In addition, by combining SVMpep with two template-based methods S-SITE and TM-SITE, we next proposed the consensus-based method PepBind. Remarkably, compared with the latest structure-based method SPRINT-Str, PepBind improves the AUC and MCC by 1.7% and 28.3%, respectively, on the same independent test set of SPRINT-Str. The success of PepBind is attributed to the improved prediction of the ab initio method SVMpep by introducing intrinsic disorder and the consensus prediction by combining three complementary methods. A web server that implements the proposed methods is freely available at http://yanglab.nankai.edu.cn/PepBind/ .