Improving Classification Performance in Dendritic Neuron Models through Practical Initialization Strategies.

A dendritic neuron model (DNM) is a deep neural network model with a unique dendritic tree structure and activation function. Effective initialization of its model parameters is crucial for its learning performance. This work proposes a novel initialization method specifically designed to improve the performance of DNM in classifying high-dimensional data, notable for its simplicity, speed, and straightforward implementation. Extensive experiments on benchmark datasets show that the proposed method outperforms traditional and recent initialization methods, particularly in datasets consisting of high-dimensional data. In addition, valuable insights into the behavior of DNM during training and the impact of initialization on its learning performance are provided. This research contributes to the understanding of the initialization problem in deep learning and provides insights into the development of more effective initialization methods for other types of neural network models. The proposed initialization method can serve as a reference for future research on initialization techniques in deep learning.

Yellow leaf green tea modulates the AMPK/ACC/SREBP1c signaling pathway and gut microbiota in high-fat diet-induced mice to alleviate obesity.

BACKGROUND: Yellow leaf green tea (YLGT) is a new variety of Camellia sinensis (L.) O. Ktze, which has yellow leaves and the unique qualities of 'three green through three yellow'. The present study aimed to investigate the anti-obesity effect of YLGT in mice fed a high-fat diet (HFD) and to explore the potential mechanisms by regulating the AMPK/ACC/SREBP1c signaling pathways and gut microbiota. RESULTS: The results showed that YLGT aqueous extract reduced body weight, hepatic inflammation, fat accumulation and hyperlipidemia in HFD-induced C57BL/6J mice, and also accelerated energy metabolism, reduced fat synthesis and suppressed obesity by activating the AMPK/CPT-1α signaling pathway and inhibiting the FAS/ACC/SREBP-1c signaling pathway. Fecal microbiota transplantation experiment further confirmed that the alteration of gut microbiota (e.g. increasing unclassified_Muribaculaceae and decreasing Colidextribacter) might be an important cause of YLGT water extract inhibiting obesity. CONCLUSION: In conclusion, YLGT has a broad application prospect in the treatment of obesity and the development of anti-obesity function beverages. © 2024 Society of Chemical Industry.

Pre-trained language models in medicine: A survey.

With the rapid progress in Natural Language Processing (NLP), Pre-trained Language Models (PLM) such as BERT, BioBERT, and ChatGPT have shown great potential in various medical NLP tasks. This paper surveys the cutting-edge achievements in applying PLMs to various medical NLP tasks. Specifically, we first brief PLMS and outline the research of PLMs in medicine. Next, we categorise and discuss the types of tasks in medical NLP, covering text summarisation, question-answering, machine translation, sentiment analysis, named entity recognition, information extraction, medical education, relation extraction, and text mining. For each type of task, we first provide an overview of the basic concepts, the main methodologies, the advantages of applying PLMs, the basic steps of applying PLMs application, the datasets for training and testing, and the metrics for task evaluation. Subsequently, a summary of recent important research findings is presented, analysing their motivations, strengths vs weaknesses, similarities vs differences, and discussing potential limitations. Also, we assess the quality and influence of the research reviewed in this paper by comparing the citation count of the papers reviewed and the reputation and impact of the conferences and journals where they are published. Through these indicators, we further identify the most concerned research topics currently. Finally, we look forward to future research directions, including enhancing models' reliability, explainability, and fairness, to promote the application of PLMs in clinical practice. In addition, this survey also collect some download links of some model codes and the relevant datasets, which are valuable references for researchers applying NLP techniques in medicine and medical professionals seeking to enhance their expertise and healthcare service through AI technology.

Cationicity Enhancement on the Hydrophilic Face of Ctriporin Significantly Reduces Its Hemolytic Activity and Improves the Antimicrobial Activity against Antibiotic-Resistant ESKAPE Pathogens.

The ESKAPE pathogen-associated antimicrobial resistance is a global public health issue, and novel therapeutic strategies are urgently needed. The short cationic antimicrobial peptide (AMP) family represents an important subfamily of scorpion-derived AMPs, but high hemolysis and poor antimicrobial activity hinder their therapeutic application. Here, we recomposed the hydrophilic face of Ctriporin through lysine substitution. We observed non-linear correlations between the physiochemical properties of the peptides and their activities, and significant deviations regarding the changes of antimicrobial activities against different bacterial species, as well as hemolytic activity. Most importantly, we obtained two Ctriporin analogs, CM5 and CM6, these two have significantly reduced hemolytic activity and more potent antimicrobial activities against all tested antibiotic-resistant ESKAPE pathogens. Fluorescence experiments indicated they may perform the bactericidal function through a membrane-lytic action model. Our work sheds light on the potential of CM5 and CM6 in developing novel antimicrobials and gives clues for optimizing peptides from the short cationic AMP family.

Function and Mechanism of Antiviral Wasp Venom Peptide Protopolybia-MP III and Its Derivatives against HSV-1.

Viruses are one of the leading causes of human disease, and many highly pathogenic viruses still have no specific treatment drugs. Therefore, producing new antiviral drugs is an urgent matter. In our study, we first found that the natural wasp venom peptide Protopolybia-MP III had a significant inhibitory effect on herpes simplex virus type 1 (HSV-1) replication in vitro by using quantitative real-time PCR (qPCR), Western blotting, and plaque-forming assays. Immunofluorescence analysis showed Protopolybia-MP III could enter cells, and it inhibited multiple stages of the HSV-1 life cycle, including the attachment, entry/fusion, and post-entry stages. Furthermore, ultracentrifugation and electron microscopy detected that Protopolybia-MP III significantly suppressed HSV-1 virion infectivity at different temperatures by destroying the integrity of the HSV-1 virion. Finally, by comparing the antiviral activity of Protopolybia-MP III and its mutants, a series of peptides with better anti-HSV-1 activity were identified. Overall, this work found the function and mechanism of the antiviral wasp venom peptide Protopolybia-MP III and its derivatives against HSV-1 and laid the foundation for the research and development of wasp venom-derived antiviral candidate peptide drugs.

Differential potassium channel inhibitory activities of a novel thermostable degradation peptide BmKcug1a-P1 from scorpion medicinal material and its N-terminal truncated/restored peptides.

Thermally stable full-length scorpion toxin peptides and partially degraded peptides with complete disulfide bond pairing are valuable natural peptide resources in traditional Chinese scorpion medicinal material. However, their pharmacological activities are largely unknown. This study discovered BmKcug1a-P1, a novel N-terminal degraded peptide, in this medicinal material. BmKcug1a-P1 inhibited hKv1.2 and hKv1.3 potassium channels with IC50 values of 2.12 ± 0.27 µM and 1.54 ± 0.28 µM, respectively. To investigate the influence of N-terminal amino acid loss on the potassium channel inhibiting activities, three analogs (i.e., full-length BmKcug1a, BmKcug1a-P1-D2 and BmKcug1a-P1-D4) of BmKcug1a-P1 were prepared, and their potassium channel inhibiting activities on hKv1.3 channel were verified by whole-cell patch clamp technique. Interestingly, the potassium channel inhibiting activity of full-length BmKcug1a on the hKv1.3 channel was significantly improved compared to its N-terminal degraded form (BmKcug1a-P1), while the activities of two truncated analogs (i.e., BmKcug1a-P1-D2 and BmKcug1a-P1-D4) were similar to that of BmKcug1a-P1. Extensive alanine-scanning experiments identified the bonding interface (including two key functional residues, Asn30 and Arg34) of BmKcug1a-P1. Structural and functional dissection further elucidated whether N-terminal residues of the peptide are located at the bonding interface is important in determining whether the N-terminus significantly influences the potassium channel inhibiting activity of the peptide. Altogether, this research identified a novel N-terminal degraded active peptide, BmKcug1a-P1, from traditional Chinese scorpion medicinal material and elucidated how the N-terminus of peptides influences their potassium channel inhibiting activity, contributing to the functional identification and molecular truncation optimization of full-length and degraded peptides from traditional Chinese scorpion medicinal material Buthus martensii Karsch.

Application of deep learning in the diagnosis and evaluation of ulcerative colitis disease severity.

Background: Achieving endoscopic and histological remission is a critical treatment objective in ulcerative colitis (UC). Nevertheless, interobserver variability can significantly impact overall assessment performance. Objectives: We aimed to develop a deep learning algorithm for the real-time and objective evaluation of endoscopic disease activity and prediction of histological remission in UC. Design: This is a retrospective diagnostic study. Methods: Two convolutional neural network (CNN) models were constructed and trained using 12,257 endoscopic images and biopsy results sourced from 1124 UC patients who underwent colonoscopy at a single center from January 2018 to December 2022. Mayo Endoscopy Subscore (MES) and UC Endoscopic Index of Severity Score (UCEIS) assessments were conducted by two experienced and independent reviewers. Model performance was evaluated in terms of accuracy, sensitivity, and positive predictive value. The output of the CNN models was also compared with the corresponding histological results to assess histological remission prediction performance. Results: The MES-CNN model achieved 97.04% accuracy in diagnosing endoscopic remission of UC, while the MES-CNN and UCEIS-CNN models achieved 90.15% and 85.29% accuracy, respectively, in evaluating endoscopic severity of UC. For predicting histological remission, the CNN models achieved accuracy and kappa values of 91.28% and 0.826, respectively, attaining higher accuracy than human endoscopists (87.69%). Conclusion: The proposed artificial intelligence model, based on MES and UCEIS evaluations from expert gastroenterologists, offered precise assessment of inflammation in UC endoscopic images and reliably predicted histological remission.

Application of deep learning in the diagnosis and evaluation of ulcerative colitis disease severity Why was this study done? This study aimed to develop a real-time and objective diagnostic tool to reduce subjectivity when evaluating ulcerative colitis (UC) endoscopic disease activity and to predict histological remission without mucosal biopsy. What did the researchers do? We developed and validated a deep learning algorithm that uses UC endoscopic images to predict the Mayo Endoscopic Score (MES), US Endoscopic Index of Severity Score (UCEIS), and histological remission. What did the researchers find? The constructed MES- and UCEIS-based models both achieved high accuracy and performance in predicting histological remission, outperforming human endoscopists. What do the findings mean? The efficiency and performance of the deep learning algorithm rivaled that of expert assessments, which may assist endoscopists in making more objective evaluations of UC severity and in predicting histological remission.