HN-PPISP: a hybrid network based on MLP-Mixer for protein-protein interaction site prediction.

MOTIVATION: Biological experimental approaches to protein-protein interaction (PPI) site prediction are critical for understanding the mechanisms of biochemical processes but are time-consuming and laborious. With the development of Deep Learning (DL) techniques, the most popular Convolutional Neural Networks (CNN)-based methods have been proposed to address these problems. Although significant progress has been made, these methods still have limitations in encoding the characteristics of each amino acid in protein sequences. Current methods cannot efficiently explore the nature of Position Specific Scoring Matrix (PSSM), secondary structure and raw protein sequences by processing them all together. For PPI site prediction, how to effectively model the PPI context with attention to prediction remains an open problem. In addition, the long-distance dependencies of PPI features are important, which is very challenging for many CNN-based methods because the innate ability of CNN is difficult to outperform auto-regressive models like Transformers. RESULTS: To effectively mine the properties of PPI features, a novel hybrid neural network named HN-PPISP is proposed, which integrates a Multi-layer Perceptron Mixer (MLP-Mixer) module for local feature extraction and a two-stage multi-branch module for global feature capture. The model merits Transformer, TextCNN and Bi-LSTM as a powerful alternative for PPI site prediction. On the one hand, this is the first application of an advanced Transformer (i.e. MLP-Mixer) with a hybrid network for sequence-based PPI prediction. On the other hand, unlike existing methods that treat global features altogether, the proposed two-stage multi-branch hybrid module firstly assigns different attention scores to the input features and then encodes the feature through different branch modules. In the first stage, different improved attention modules are hybridized to extract features from the raw protein sequences, secondary structure and PSSM, respectively. In the second stage, a multi-branch network is designed to aggregate information from both branches in parallel. The two branches encode the features and extract dependencies through several operations such as TextCNN, Bi-LSTM and different activation functions. Experimental results on real-world public datasets show that our model consistently achieves state-of-the-art performance over seven remarkable baselines. AVAILABILITY: The source code of HN-PPISP model is available at https://github.com/ylxu05/HN-PPISP.

ABCNet: A comprehensive highway visibility prediction model based on attention, Bi-LSTM and CNN.

Meteorological disasters along highways significantly reduce road traffic efficiency. Low visibility caused by heavy fog is a severe meteorological disaster that greatly increases highway traffic accidents. Accurately predicting highway visibility and taking timely response measures can reduce the impact of meteorological disasters and improve traffic safety. We proposed an Attention-based BiLSTM-CNN (ABCNet) model, which synergized attention mechanisms with BiLSTM and CNN technologies to forecast atmospheric visibility more accurately. First, the Bi-LSTM module processed information both forward and backward, capturing intricate temporal dependencies in the model. Second, the multi-head attention mechanism following the Bi-LSTM distilled and prioritized salient features from multiple aspects of the sequence data. Third, the CNN module recognized local spatial features, and a singular attention mechanism refined the feature map after the CNN module, further enhancing the model's accuracy and predictive capability. Experiments showed that the model was accurate, effective, and significantly advanced compared to conventional models. It could fully extract the spatiotemporal characteristics of meteorological elements. The model was integrated into practical systems with positive results. Additionally, this study provides a self-collected meteorological dataset for highways in high-altitude mountainous areas.

ZNF217: An Oncogenic Transcription Factor and Potential Therapeutic Target for Multiple Human Cancers.

Zinc finger protein 217 (ZNF217) is one of the well-researched members of the Krüppel-like factor transcription factor family. ZNF217 possesses a characteristic structure of zinc finger motifs and plays a crucial role in regulating the biological activities of cells. Recent findings have revealed that ZNF217 is strongly associated with multiple aspects of cancer progression, impacting patient prognosis. Notably, ZNF217 is subject to regulation by non-coding RNAs, suggesting the potential for targeted manipulation of such RNAs as a robust therapeutic avenue for managing cancer in the future. The main purpose of this article is to provide a detailed examination of the role of ZNF217 in human malignant tumors and the regulation of its expression, and to offer new perspectives for cancer treatment.

Pan-cancer and single-cell analysis reveal THRAP3 as a prognostic and immunological biomarker for multiple cancer types.

Background: Thyroid hormone receptor-associated protein 3 (THRAP3) is of great significance in DNA damage response, pre-mRNA processing, and nuclear export. However, the biological activities of THRAP3 in pan-cancer remain unexplored. We aimed to conduct a comprehensive analysis of THRAP3 and validate its expression levels in lung cancer. Methods: A pan-cancer analysis was conducted to study the correlation of THRAP3 expression with clinical outcome and the tumor microenvironment based on the available bioinformatics databases. The protein levels of THRAP3 were explored in lung cancer by immunohistochemistry (IHC) analysis. Single-cell sequencing (ScRNA-seq) analysis was employed to investigate the proportions of each cell type in lung adenocarcinoma (LUAD) and adjacent normal tissues, along with the expression levels of THRAP3 within each cell type. Results: THRAP3 is upregulated in multiple cancer types but exhibits low expression in lung squamous cell carcinoma (LUSC). immunohistochemistry results showed that THRAP3 is a lowly expression in LUAD and LUSC. THRAP3 elevation had a poor prognosis in kidney renal clear cell carcinoma and a prolonged survival time in kidney chromophobe, brain lower-grade glioma and skin cutaneous melanoma, as indicated by the KM curve. Single-cell analysis confirmed that the proportions of T/B cells, macrophages, and fibroblasts were significantly elevated in LUAD tissues, and THRAP3 is specifically overexpressed in mast cells. Conclusion: Our findings uncover that THRAP3 is a promising prognostic biomarker and immunotherapeutic target in multiple cancers, but in LUAD and LUSC, it may be a protective gene.

Thermoresponsive Self-Healing Zwitterionic Hydrogel as an In Situ Gelling Wound Dressing for Rapid Wound Healing.

It is highly desired yet challenging to fabricate biocompatible injectable self-healing hydrogels with anti-bacterial adhesion properties for complex wounds that can autonomously adapt to different shapes and depths and can promote angiogenesis and dermal collagen synthesis for rapid wound healing. Herein, an injectable zwitterionic hydrogel with excellent self-healing property, good cytocompatibility, and antibacterial adhesion was developed from a thermoresponsive ABA triblock copolymer poly[(N-isopropyl acrylamide)-co-(butyl acrylate)-co-(sulfobetaine methacrylate)]-b-poly(ethylene glycol)-b-poly[(N-isopropyl acrylamide)-co-(butyl acrylate)-co-(sulfobetaine methacrylate)] (PZOPZ). The prepared PZOPZ hydrogel exhibits a distinct thermal-induced sol-gel transition around physiological temperature and could be easily applied in a sol state and in situ gelled to adapt complex wounds of different shapes and depths for complete coverage. Meanwhile, the hydrogel possesses a rapid self-healing ability and can recover autonomously from damage to maintain structural and functional integrity. In addition, the CCK-8 and 2D/3D cell culture experiments revealed that the PZOPZ hydrogel dressing shows low cytotoxicity to L929 cells and can effectively prevent the adhesion of Staphylococcus aureus and Escherichia coli. In vivo investigations verified that the PZOPZ hydrogel could increase angiogenesis and dermal collagen synthesis and shorten the transition from the inflammatory to the proliferative stage, thereby providing more favorable conditions for faster wound healing. Overall, this work provides a promising strategy to develop injectable zwitterionic hydrogel dressings with multiple functions for clinic wound management.