Protein structure determines function, and structural information is critical for predicting protein thermostability. This study proposes a novel method for protein thermostability prediction by integrating graph embedding features and network topological features. By constructing residue interaction networks (RINs) to characterize protein structures, we calculated network topological features and utilize deep neural networks (DNN) to mine inherent characteristics. Using DeepWalk and Node2vec algorithms, we obtained node embeddings and extracted graph embedding features through a TopN strategy combined with bidirectional long short-term memory (BiLSTM) networks. Additionally, we introduced the Doc2vec algorithm to replace the Word2vec module in graph embedding algorithms, generating graph embedding feature vector encodings. By employing an attention mechanism to fuse graph embedding features with network topological features, we constructed a high-precision prediction model, achieving 87.85% prediction accuracy on a bacterial protein dataset. Furthermore, we analyzed the differences in the contributions of network topological features in the model and the differences among various graph embedding methods, and found that the combination of DeepWalk features with Doc2vec and all topological features was crucial for the identification of thermostable proteins. This study provides a practical and effective new method for protein thermostability prediction, and at the same time offers theoretical guidance for exploring protein diversity, discovering new thermostable proteins, and the intelligent modification of mesophilic proteins.
Neural Networks, Computer ; Algorithms ; Protein Stability ; Proteins/chemistry* ; Protein Conformation ; Temperature

Acute kidney injury (AKI) is a critical clinical condition characterized by rapid renal function decline, with high morbidity, mortality, and healthcare costs. Traditional Chinese medicine (TCM) has shown potential effects on mitigating oxidative stress and programmed cell death in AKI models. Scutellaria barbata D. Don (SB) and Scleromitrion diffusum (Willd.) R. J. Wang (SD), a classic TCM herbal pair exhibited anti-inflammatory and antioxidant activities. Using advanced chromatographic separation technology, we enriched the effective fractions of water extracts from SB-SD, obtaining self-assembled herbal nanoparticles (SB and SD nanoparticles, SSNPs) rich in flavonoids and terpenoids. These SSNPs demonstrated robust antioxidant properties in vitro and mitigated AKI progression in vivo by activating the nuclear factor erythroid 2-related factor 2 (Nrf2) signaling pathway. Oral administration of SSNPs in mice resulted in absorption into the bloodstream, formation of a protein corona, reduced macrophage phagocytosis, and enhanced bioavailability and renal targeting. Furthermore, we investigated the self-assembly principle of SSNPs using representative flavonoids and terpenoids. Kinetic studies and in situ transmission electron microscopy (in situ TEM) revealed that these compounds self-assemble via supramolecular forces like hydrogen bonding and π-π interactions, forming stable nanostructures. This study elucidates the renoprotective effects and mechanisms of SB and SD, and provides a novel approach for the development of TCM-based nanomedicines, highlighting the potential of nano-TCM in AKI treatment.

Objective:The study aimed to assess the scientific rigor, transparency, and practicality of Chinese geriatric medicine guidelines and consensus published in academic journals.Methods:A systematic search was conducted across 8 major Chinese and English databases to identify guidelines and consensus documents from Chinese scholars in 2022.Results:The selected documents were evaluated using the STAR rating tool, resulting in the inclusion of 2 guidelines and 19 expert consensuses.The total scores ranged from 9.0 to 50.6 points, with an average score of 29.6±13.1 points.The highest score rate in the'Consensus Methods’category of expert consensuses was 47.4%, while the lowest score rate in the'Registration’category was 0.For guidelines, the highest score rate in the'Consensus Methods’category was 42.9%, while the lowest score rates were observed in the'Registration’, 'Plan’, and'Others’categories at 0.Conclusions:The overall quality of geriatric medicine guidelines and consensus in China requires enhancement.There is a need to improve training in guideline consensus development, involve methodologists, elevate the standards for journal publication, and strive to enhance the scientific rigor, transparency, and practicality of guidelines and consensus documents.

Objective To discuss the efficacy of the modified falling risks for older people-community setting screening tool and the falling risks of the older people.Methods A cross-sectional study was conducted in 4 communities of Chengdu.A total of 408 people aged 65 years and over from 4 residents communities were selected with convenient sampling.To screen out the people who were in high risk of falls with a self-making questionnaire and the modified falling risks for older people-community setting screening tool.Results After the 408 older people were evaluated by modified falling risks for older people-community screening tool,the result showed the area under curve of receiver operating characteristic of the scale was 0.936.Its sensitivity was 77.6％ (66/85),specificity was 93.2％ (301/323),positive predictive value was 75.0％ (66/88) and negative predictive value was 94.1％ (301/320).Conclusions The using of modified falling risks for older people-community setting screening tool is easy and fast,it has higher sensitivity,specificity and evaluation function.It can be used for screening falling risks among community setting elderly people in China.