MOTIVATION: Drug-target binding affinity (DTA) prediction plays a vital role in drug repositioning. The emergence of large language models (LLMs) has introduced new perspectives for predicting DTA. Herein, we present TSEDTA, a Transformer-based neural network with SMILES Transformer and ESM2 embeddings for predicting DTA. It leverages pre-trained LLMs (SMILES Transformer and ESM2) to extract deep evolutionary representations from drug SMILES and protein sequences. The representations are directly fused with raw sequence embeddings and processed via dual Transformer encoders to capture complex local and global dependencies. RESULTS: The experiments demonstrate that TSEDTA outperforms ten advanced models on the Davis and KIBA datasets, and seven on the BindingDB dataset. Ablation studies show that incorporating LLM embeddings significantly improves the performance of TSEDTA. Furthermore, a practical case study demonstrates its real-world applicability. Ultimately, TSEDTA provides a highly accurate, robust tool for DTA prediction, offering new insights into the application of LLMs for DTA tasks. AVAILABILITY: The source code and data are available at: https://github.com/SunXu24Math/TSEDTA. The version of record is archived in Zenodo with the DOI: 10.5281/zenodo.19103249.

In Vehicular Ad-hoc Networks (VANETs), the ability of emergency vehicles (EVs) to reach their destinations quickly can maximize the protection of people’s lives and property safety, and minimize the losses and impacts caused by various emergencies. In this endeavor, the emergency vehicle avoidance protocol is of paramount importance. However, the existing authentication protocol is vulnerable to side-channel attacks, Roadside Units (RSUs) captured attacks, as well as untraceability, etc. Therefore, for wider and more practical realizability, we propose an efficient and secure authentication scheme based on Elliptic Curves Cryptography (ECC), fuzzy extraction algorithm and Physical Unclonable Function (PUF) for EVs avoidance. In the protocols, PUF and biometric key are used for protecting RSUs’ and EVs’ privacy information respectively. Additionally, a conditional privacy-preserving and traceable message authentication strategy is designed for emergency messages propagation, the avoidance messages can be forwarded to ordinary vehicles before the EVs arriving. Compared with related EVs avoidance protocols, our protocol can resist side-channel attacks and other various known attacks. In our scheme, the first authentication efficiencies have increased by 11.72% and the subsequent authentication increased by 25.99% than the previous protocols in the same scenario. Security and performance analysis demonstrate that the proposed scheme is secure, efficient, and practical.

The prediction of virus-drug associations (VDAs) is crucial for drug repositioning, contributing to the identification of latent antiviral drugs. In this study, we developed a graph-based integrated Gaussian kernel similarity (GiGs) method for predicting potential VDAs in drug repositioning. The GiGs model comprises three components: (i) collection of experimentally validated VDA information and calculation virus sequence, drug chemical structure, and drug side effect similarity; (ii) integration of viruses and drugs similarity based on the above information and Gaussian interaction profile kernel (GIPK); and (iii) utilization of similarity-constrained weight graph normalization matrix factorization to predict antiviral drugs. The GiGs model enhances correlation matrix quality through the integration of multiple biological data, improves performance via similarity constraints, and prevents overfitting and predicts missing data more accurately through graph regularization. Extensive experimental results indicated that the GiGs model outperforms five other advanced association prediction methods. A case study identified broad-spectrum drugs for treating highly pathogenic human coronavirus infections, with molecular docking experiments confirming the model's accuracy.

Tuberculosis is a chronic inflammatory disease caused by Mycobacterium tuberculosis. When tuberculosis invades the human body, innate immunity is the first line of defense. However, how the innate immune microenvironment responds remains unclear. In this research, we studied the function of each type of cell and explained the principle of an immune microenvironment. Based on the differences in the innate immune microenvironment, we modularized the analysis of the response of five immune cells and two structural cells. The results showed that in the innate immune stress response, the genes CXCL3, PTGS2 and TNFAIP6 regulated by the nuclear factor kappa B(NK-KB) pathway played a crucial role in fighting against tuberculosis. Based on the active pathway algorithm, each immune cell showed metabolic heterogeneity. Besides, after tuberculosis infection, structural cells showed a chemotactic immunity effect based on the co-expression immunoregulatory module.

The development of the Internet-of-Things (IoT) security is comparatively slower than the pace of the IoT innovations. The seamless IoT network operates in an untrusted environment and is exposed to many malicious active attacks. As the process of identifying the modulation format of signals is corrupted by noise and fading, automatic modulation classification (AMC) can be viewed as an effective approach to counter physical-layer threats for IoT as it can detect and identify the pilot jamming, deceptive jamming, and Sybil attacks. Nowadays, data-driven deep learning (DL) techniques, which are capable of extracting discriminative features and perform better robustness to channel and noise conditions, have drawn widespread attention. The deep residual network (ResNet) has a strong representative ability, which can learn latent information repeatedly from the received signals and improve the classification accuracy. Meanwhile, the gated recurrent unit (GRU), which is capable of exploiting temporal information of the received signal can expand the dimension of the signal features for satisfactory classification performance. Considering the advantages of the above networks, this article proposes a novel gated recurrent residual neural network (GrrNet) for feature-based AMC, where the amplitude and phase of the received signal are utilized as the inputs of GrrNet. In GrrNet, a ResNet extractor module is first designed to extract the highly representative features and then temporal information is obtained by the subsequent GRU module which is capable of processing the representative features with the arbitrary length for modulation classification. Moreover, extensive simulations are conducted to verify the classification performance and robustness of the proposed GrrNet and it is shown that GrrNet outperforms other recent DL-based AMC methods. Moreover, the influence of the network parameters, symbol length, and frequency offset on performance is also explored.