In early drug discovery, virtual screening based on deep learning, virtual screening based on molecular docking, and molecular dynamics are three widely used computational strategies, but they always face a trade-off between throughput, search stability, and physical fidelity. This article discusses how quantum computing can be integrated into these processes under the constraints of Noisy Intermediate-Scale Quantum (NISQ). At present, the most realistic role of quantum computing is not the complete replacement of classical processes, but modular coprocessing for selected decision-sensitive subroutines. In the screening of deep learning, quantum modules are mainly inserted into selected components of the model. In predictive models, they are used to enhance representation learning or feature extraction. In generative models, they serve as priors or generators. In docking screening, quantum integration is suitable for specific substeps such as site recognition, pose search, and flexible docking. In molecular dynamics, representative examples include ground state ab initio molecular dynamics, annealer-based trajectory propagation, and excited state molecular dynamics, while most large-scale sampling is still done by classical methods. The actual problem in these scenarios is not whether the quantum module can be inserted, but whether it can provide repeatable gains related to decision-making under the constraints of actual running time and resources. Therefore, we emphasize strong classical baselines, reliable ranking and calibration, transparent resource reporting, and evaluation at downstream decision points as key criteria for assessing progress in the near term.

Drug-gene interactions (DGIs) influence the toxicity or ineffectiveness of the drug therapy and play an important role in elucidating drug mechanisms, predicting potential adverse effects, and facilitating precision medicine. Existing computational methods typically rely on chemical or genetic sequence features of drugs and genes, limiting their effectiveness for novel entities lacking explicit annotations. To address this, we propose BiGvCL, a framework that predicts DGIs exclusively based on network topology, requiring no explicit feature information for drugs or genes. BiGvCL introduces a lightweight graph attention mechanism (GATLite) to efficiently aggregate local neighborhood information. Additionally, we develop a gated graph convolutional network (GatedGCN) to explicitly learn high-order interactions between drugs and genes, further integrating contrastive learning to enhance the model's generalizability. Comprehensive experiments on DrugBank and DGIdb datasets show that BiGvCL achieves competitive performance across all metrics compared with representative baselines. Cross-domain evaluations on OGB datasets further confirm its adaptability to heterogeneous biomedical networks. Ablation and hyperparameter analyses highlight the key contributions of contrastive and gated mechanisms, while case studies and molecular docking provide supporting evidence for the biological relevance of predictions. Collectively, while BiGvCL is constrained by its reliance on network topology and transductive learning paradigm, it demonstrates the potential of topology-based approaches for discovering novel drug-gene interactions, which may inform drug repurposing and precision medicine efforts.

Secretory effectors from pathogenic microorganisms significantly influence pathogen survival and pathogenicity by manipulating host signalling, immune responses, and metabolic processes. However, because of sequence and structural heterogeneity among bacterial effectors, accurately classifying multiple types simultaneously remains challenging. Therefore, we developed TXSelect, a multi-task learning framework that simultaneously classifies TXSE (types I, II, III, IV and VI secretory effectors) using a shared backbone network with task-specific heads. TXSelect integrates the protein embedding features of evolutionary scale modelling (ESM), particularly the N-terminal mean, with classical descriptors to effectively capture complementary information. These descriptors include distance-based residue (DR) and split amino acid composition general (SC-PseAAC-General). Rigorous evaluation identified ESM N-terminal mean + DR + SC-PseAAC as the optimal feature combination, achieving high accuracy (validation F1 = 0.867, test F1 = 0.8645) and robust generalization. Comprehensive assessments and visualization with Uniform Manifold Approximation and Projection further validated the discriminative capability and interpretability of the model. TXSelect provides an efficient computational tool for accurately classifying bacterial effectors, supporting deeper biological understanding and potential therapeutic development.

Neuropathic pain (NP) is a chronic disease state centred on neuroinflammation with a high prevalence and limited effective treatment options. Peroxisome proliferator-activated receptor α (PPARα) has emerged as a promising target for NP management due to its anti-inflammatory properties. Recent evidence highlights the critical role of the gut microbiome and its metabolites in NP pathogenesis. This study aimed to investigate whether PPARα modulates the development and alleviation of NP by influencing gut microbial communities and serum metabolites. 16S rDNA sequencing and liquid chromatography-mass spectrometry (LC-MS/MS) untargeted metabolomics analyses performed 14 days after the establishment of a chronic constriction injury (CCI) pain model in C57BL/6 J mice showed significant changes in gut microbial and metabolite levels in CCI mice. Intraperitoneal injection of the PPARα agonist GW7647 (5 mg/kg) significantly attenuated mechanical allodynia and thermal hyperalgesia in CCI mice, whereas injection of the PPARα antagonist GW6471 (20 mg/kg) produced the opposite effect. Immunofluorescence analysis revealed that GW7647 effectively suppressed microglial activation. Additionally, PPARα agonist and antagonist treatments markedly altered the composition and abundance of intestinal microbial communities in CCI mice. Further serum LC-MS/MS analysis identified 258 potential serum metabolic biomarkers, many of which correlated with changes in gut microbial composition. These findings demonstrate that PPARα influences serum metabolite profiles by modulating gut microbiota composition, which subsequently affects NP progression. This study provides novel insights into the mechanisms underlying NP and suggests potential therapeutic avenues targeting PPARα and gut microbiota.

Accurate identification of diverse RNA types, including messenger RNAs (mRNAs), long non-coding RNAs (lncRNAs), and circular RNAs (circRNAs), is essential for understanding their roles in gene regulation, disease progression, and epigenetic modification. Existing studies have primarily focused on binary classification tasks, such as distinguishing lncRNAs from mRNAs or identifying specific circRNAs, often overlooking the complex sequence patterns shared across multiple RNA types. To address this limitation, we developed AttenRNA, a multi-class classification model that integrates multi-scale k-mer embeddings and attention mechanisms to simultaneously differentiate between various RNA classes. AttenRNA achieved high weighted F1 scores of 89.8% and 89.6% on the validation and test sets, respectively, demonstrating strong classification performance and robustness. Dimensionality reduction using Uniform Manifold Approximation and Projection further confirmed the model's ability to learn discriminative features among RNA types. Additionally, AttenRNA exhibited strong generalization ability on cross-species data, achieving weighted F1 scores of 83.89% and 83.38% on the mouse RNA validation and test sets, respectively. These results suggest that AttenRNA offers a reliable and scalable solution for systematic RNA function analysis.

Abstract Alzheimer's disease (AD) is an incurable, progressive neurodegenerative disorder, necessitating early diagnosis and intervention. Mild cognitive impairment (MCI) often precedes AD, but not all cases progress to AD, emphasizing the need for predictive biomarkers. We analyzed routine blood test data from 43,981 AD patients and 4,537 MCI subjects in Hong Kong hospitals (2000-2019). Among 31 shared biomarkers, five blood biomarkers (Hemoglobin, Hematocrit, Red blood cell related to oxygen carrying capacity, Neutrophils, and White blood cell related to immunity) significantly differentiated MCI from AD. Subjects were divided into four groups (Female 65 ~ 74, Male 65 ~ 74, Female 75 ~ 89, Male 75 ~ 89) to minimize gender and age bias. Models utilizing the five biomarkers along with machine learning yielded the highest accuracy in the Female 65 ~ 74 group (AUC of 0.76 on an independent test set). The other three models were trained with other biomarkers besides these 5 to optimize predictions, capturing models with AUC close to 0.70. We then constructed a platform predicting the risk of MCI converting to AD (MAP, http://lab.malab.cn/~lijing/MAP.html) to help physicians and MCI subjects with early diagnosis and prevention of AD. In conclusion, this study demonstrates the potential for accurate prediction of MCI to AD conversion using routine blood test data and machine learning, offering an economical and practical approach for early AD screening in MCI individuals.

Subcellular localization is crucial for understanding the functions and regulatory mechanisms of biomolecules. Long non-coding RNAs (lncRNAs) have diverse roles in cellular processes, and their localization within specific subcellular compartments provides insights into their biological functions and implications in health and disease. The nucleolus and nucleoplasm are key hubs for RNA metabolism and cellular regulation. We developed a model, LncDNN, for identifying the localization of lncRNAs in the nucleolus and nucleoplasm. LncDNN uses three different encoding schemes and employs Shapley Additive Explanations for feature analysis and selection. The results show that LncDNN is more accurate than other models. Additionally, an interpretable analysis of the features influencing the model was conducted. LncDNN is applicable for identifying the localization of lncRNA in the nucleolus and nucleoplasm, aiding in the understanding and in-depth study of related biological processes and functions.

BackgroundExisting evidence suggests that the composition of the gut microbiota is associated with neuropathic pain (NP), but the mechanistic link is elusive. Peroxisome proliferator-activated receptor α (PPARα) has been shown to be a pharmacological target for the treatment of metabolic disorders, and its expression is also involved in inflammatory regulation. The aim of this study was to investigate the important modulatory effects of PPARα on gut microbiota and spinal cord metabolites in mice subjected to chronic constriction injury.MethodsWe analyzed fecal microbiota and spinal cord metabolic alterations in mice from the sham, CCI, GW7647 (PPARα agonist) and GW6471 (PPARα antagonist) groups by 16S rRNA amplicon sequencing and untargeted metabolomics analysis. On this basis, the intestinal microbiota and metabolites that were significantly altered between treatment groups were analyzed in a combined multiomics analysis. We also investigated the effect of PPARα on the polarization fractionation of spinal microglia.ResultsPPARα agonist significantly reduce paw withdrawal threshold and paw withdrawal thermal latency, while PPARα antagonist significantly increase paw withdrawal threshold and paw withdrawal thermal latency. 16S rRNA gene sequencing showed that intraperitoneal injection of GW7647 or GW6471 significantly altered the abundance, homogeneity and composition of the gut microbiome. Analysis of the spinal cord metabolome showed that the levels of spinal cord metabolites were shifted after exposure to GW7647 or GW6471. Alterations in the composition of gut microbiota were significantly associated with the abundance of various spinal cord metabolites. The abundance of Licheniformes showed a significant positive correlation with nicotinamide, benzimidazole, eicosanoids, and pyridine abundance. Immunofluorescence results showed that intraperitoneal injection of GW7647 or GW6471 altered microglial activation and polarization levels.ConclusionOur study shows that PPARα can promote M2-type microglia polarization, as well as alter gut microbiota and metabolites in CCI mice. This study enhances our understanding of the mechanism of PPARα in the treatment of neuropathic pain.

BackgroundThe type IV secretion system is widely present in various bacteria, such as Salmonella, Escherichia coli, and Helicobacter pylori. These bacteria use the type IV secretion system to secrete type IV secretion effectors, infect host cells, and disrupt or modulate the communication pathways. In this study, type III and type VI secretion effectors were used as negative samples to train a robust model.ResultsThe area under the curve of T4Seeker on the validation and independent test sets were 0.947 and 0.970, respectively, demonstrating the strong predictive capacity and robustness of T4Seeker. After comparing with the classic and state-of-the-art T4SE identification models, we found that T4Seeker, which is based on traditional features and large language model features, had a higher predictive ability.ConclusionThe T4Seeker proposed in this study demonstrates superior performance in the field of T4SEs prediction. By integrating features at multiple levels, it achieves higher predictive accuracy and strong generalization capability, providing an effective tool for future T4SE research.

Neuropathic pain (NP) is usually treated with analgesics and symptomatic therapy with poor efficacy and numerous side effects, highlighting the urgent need for effective treatment strategies. Recent studies have reported an important role for peroxisome proliferator-activated receptor alpha (PPARα) in regulating metabolism as well as inflammatory responses. Through pain behavioral assessment, we found that activation of PPARα prevented chronic constriction injury (CCI)-induced mechanical allodynia and thermal hyperalgesia. In addition, PPARα ameliorated inflammatory cell infiltration at the injury site and decreased microglial activation, NOD-like receptor protein 3 (NLRP3) inflammasome production, and spinal dendritic spine density, as well as improved serum and spinal cord metabolic levels in mice. Administration of PPARα antagonists eliminates the analgesic effect of PPARα agonists. PPARα relieves NP by inhibiting neuroinflammation and functional synaptic plasticity as well as modulating metabolic mechanisms, suggesting that PPARα may be a potential molecular target for NP alleviation. However, the effects of PPARα on neuroinflammation and synaptic plasticity should be further explored.

Neuropathic pain, which results from damage to the somatosensory nervous system, is a global clinical condition that affects many people. Neuropathic pain imposes significant economic and public health burdens and is often difficult to manage because the underlying mechanisms remain unclear. However, mounting evidence indicates a role for neurogenic inflammation and neuroinflammation in pain pattern development. There is increasing evidence that the activation of neurogenic inflammation and neuroinflammation in the nervous system contribute to neuropathic pain. Altered miRNA expression profiles might be involved in the pathogenesis of both inflammatory and neuropathic pain by regulating neuroinflammation, nerve regeneration, and abnormal ion channel expression. However, the lack of knowledge about miRNA target genes prevents a full understanding of the biological functions of miRNAs. At the same time, an extensive study on exosomal miRNA, a newly discovered role, has advanced our understanding of the pathophysiology of neuropathic pain in recent years. This section provides a comprehensive overview of the current understanding of miRNA research and discusses the potential mechanisms of miRNAs in neuropathic pain.

Subcellular localization is crucial to the study of virus and dis-eases. Specifically, research on protein subcellular localization can help identify clues between virus and host cells that can aid in the design of targeted drugs. Research on RNA subcellu-lar localization is significant for human diseases (such as Alzheimer's disease, colon cancer, etc.). To date, only reviews addressing subcellular localization of proteins have been pub-lished, which are outdated for reference, and reviews of RNA subcellular localization are not comprehensive. Therefore, we collated (the most up-to-date) literature on protein and RNA subcellular localization to help researchers understand changes in the field of protein and RNA subcellular localization. Exten-sive and complete methods for constructing subcellular locali-zation models have also been summarized, which can help readers understand the changes in application of biotechnology and computer science in subcellular localization research and explore how to use biological data to construct improved sub-cellular localization models. This paper is the first review to cover both protein subcellular localization and RNA subcellu-lar localization. We urge researchers from biology and compu-tational biology to jointly pay attention to transformation pat-terns, interrelationships, differences, and causality of protein subcellular localization and RNA subcellular localization.

Horizontal gene transfer (HGT) mediated by conjugative plasmids greatly contributes to bacteria evolution and the transmission of antibiotic resistance genes (ARGs). In addition to the selective pressure imposed by extensive antibiotic use, environmental chemical pollutants facilitate the dissemination of antibiotic resistance, consequently posing a serious threat to the ecological environment. Presently, the majority of studies focus on the effects of environmental compounds on R plasmid-mediated conjugation transfer, and pheromone-inducible conjugation has largely been neglected. In this study, we explored the pheromone effect and potential molecular mechanisms of estradiol in promoting the conjugative transfer of pCF10 plasmid in Enterococcus faecalis. Environmentally relevant concentrations of estradiol significantly increased the conjugative transfer of pCF10 with a maximum frequency of 3.2 × 10-2, up to 3.5-fold change compared to that of control. Exposure to estradiol induced the activation of pheromone signaling cascade by increasing the expression of ccfA. Furthermore, estradiol might directly bind to the pheromone receptor PrgZ and promote pCF10 induction and finally enhance the conjugative transfer of pCF10. These findings cast valuable insights on the roles of estradiol and its homolog in increasing antibiotic resistance and the potential ecological risk.

The enrichment and spread of antibiotic resistance genes (ARGs) induced by environmental chemical pollution further exacerbated the threat to human health and ecological safety. Several compounds are known to induce R plasmid-mediated conjugation through inducing reactive oxygen species (ROS), increasing cell membrane permeability, enhancing regulatory genes expression, and so forth. Up to now, there has been no substantial breakthrough in the studies of models and related mechanisms. Here, we established a new conjugation model using pheromone-responsive plasmid pCF10 and confirmed that five kinds of bisphenols (BPs) at environmentally relevant concentrations could significantly promote the conjugation of ARGs mediated by plasmid pCF10 in E. faecalis by up to 4.5-fold compared with untreated cells. Using qPCR, gene knockout and UHPLC, we explored the mechanisms behind this phenomenon using bisphenol A (BPA) as a model of BPs and demonstrated that BPA could upregulate the expression of pheromone, promote bacterial aggregation, and even directly activate conjugation as a pheromone instead of producing ROS and enhancing cell membrane permeability. Interestingly, the result of mathematical analysis showed that the pheromone effect of most BPs is more potent than that of synthetic pheromone cCF10. These findings provide new insight into the environmental behavior and biological effect of BPs and provided new method and theory to study on enrichment and spread of ARGs induced by environmental chemical pollution.

Cancer has emerged as one of the most severe diseases in modern times, various therapies have advanced remarkably in recent decades. Unlike the direct therapeutic targeting tumor cells, immunotherapy is a promising strategy that stimulate the immune system. In cancer immunotherapy, polymeric-based nanoparticles can serve as deliver systems for antigens and immunostimulatory molecules, and they have attracted increasing attention and revolutionized cancer therapy. Poly (lactic-co-glycolic acid) (PLGA) is the most frequently used clinically approved biodegradable polymer and has a broad scope of modification of its inherent properties. Recent advances in PLGA based drug delivery systems in cancer immunotherapy have been described in this mini review, with special emphasis on cancer vaccines and tumor microenvironment modulation.

The coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, is one of the fastest-evolving viral diseases that has instigated a worldwide pandemic. Severe inflammatory syndrome and venous thrombosis are commonly noted in COVID-19 patients with severe and critical illness, contributing to the poor prognosis. Interleukin (IL)-6, a major complex inflammatory cytokine, is an independent factor in predicting the severity of COVID-19 disease in patients. IL-6 and tumor necrosis factor (TNF)-α participate in COVID-19-induced cytokine storm, causing endothelial cell damage and upregulation of plasminogen activator inhibitor-1 (PAI-1) levels. In addition, IL-6 and PAI-1 form a vicious cycle of inflammation and thrombosis, which may contribute to the poor prognosis of patients with severe COVID-19. Targeted inhibition of IL-6 and PAI-1 signal transduction appears to improve treatment outcomes in severely and critically ill COVID-19 patients suffering from cytokine storms and venous thrombosis. Motivated by studies highlighting the relationship between inflammatory cytokines and thrombosis in viral immunology, we provide an overview of the immunothrombosis and immunoinflammation vicious loop between IL-6 and PAI-1. Our goal is that understanding this ferocious circle will benefit critically ill patients with COVID-19 worldwide.

Type III secretion systems (T3SS) can be found in many pathogenic bacteria, such as Dysentery bacillus, Salmonella typhimurium, Vibrio cholera and pathogenic Escherichia coli. The routes of infection of these bacteria include the T3SS transferring a large number of type III secreted effectors (T3SE) into host cells, thereby blocking or adjusting the communication channels of the host cells. Therefore, the accurate identification of T3SEs is the precondition for the further study of pathogenic bacteria. In this article, a new T3SEs ensemble predictor was developed, which can accurately distinguish T3SEs from any unknown protein. In the course of the experiment, methods and models are strictly trained and tested. Compared with other methods, EP3 demonstrates better performance, including the absence of overfitting, strong robustness and powerful predictive ability. EP3 (an ensemble predictor that accurately identifies T3SEs) is designed to simplify the user’s (especially nonprofessional users) access to T3SEs for further investigation, which will have a significant impact on understanding the progression of pathogenic bacterial infections. Based on the integrated model that we proposed, a web server had been established to distinguish T3SEs from non-T3SEs, where have EP3_1 and EP3_2. The users can choose the model according to the species of the samples to be tested. Our related tools and data can be accessed through the link http://lab.malab.cn/∼lijing/EP3.html.

N6-methyladenosine (m 6A) is a prevalent methylation modification and plays a vital role in various biological processes, such as metabolism, mRNA processing, synthesis, and transport. Recent studies have suggested that m 6A modification is related to common diseases such as cancer, tumours, and obesity. Therefore, accurate prediction of methylation sites in RNA sequences has emerged as a critical issue in the area of bioinformatics. However, traditional high-throughput sequencing and wet bench experimental techniques have the disadvantages of high costs, significant time requirements and inaccurate identification of sites. But through the use of traditional experimental methods, researchers have produced many large databases of m 6A sites. With the support of these basic databases and existing deep learning methods, we developed an m 6A site predictor named DeepM6ASeq-EL, which integrates an ensemble of five LSTM and CNN classifiers with the combined strategy of hard voting. Compared to the state-of-the-art prediction method WHISTLE (average AUC 0.948 and 0.880), the DeepM6ASeq-EL had a lower accuracy in m 6A site prediction (average AUC: 0.861 for the full transcript models and 0.809 for the mature messenger RNA models) when tested on six independent datasets.

Recent studies have shown that RNA methylation modification can affect RNA transcription, metabolism, splicing and stability. In addition, RNA methylation modification has been associated with cancer, obesity and other diseases. Based on information about human genome and machine learning, this paper discusses the effect of the fusion sequence and gene-level feature extraction on the accuracy of methylation site recognition. The significant limitation of existing computing tools was exposed by discovered of new features. (1) Most prediction models are based solely on sequence features and use SVM or random forest as classification methods. (2) Limited by the number of samples, the model may not achieve good performance. In order to establish a better prediction model for methylation sites, we must set specific weighting strategies for training samples and find more powerful and informative feature matrices to establish a comprehensive model. In this paper, we present HSM6AP, a high-precision predictor for the Homo sapiens N6-methyladenosine (m6A) based on multiple weights and feature stitching. Compared with existing methods, HSM6AP samples were creatively weighted during training, and a wide range of features were explored. Max-Relevance-Max-Distance (MRMD) is employed for feature selection, and the feature matrix is generated by fusing a single feature. The extreme gradient boosting (XGBoost), an integrated machine learning algorithm based on decision tree, is used for model training and improves model performance through parameter adjustment. Two rigorous independent data sets demonstrated the superiority of HSM6AP in identifying methylation sites. HSM6AP is an advanced predictor that can be directly employed by users (especially non-professional users) to predict methylation sites. Users can access our related tools and data sets at the following website: http://lab.malab.cn/~lijing/HSM6AP.html The codes of our tool can be publicly accessible at https://github.com/lijingtju/HSm6AP.git

Emerging evidence has documented that multisystem organ failure in coronavirus disease 2019 (COVID-19) patients is strongly associated with various coagulopathies. Treatments for COVID-19-associated coagulopathy are still a clinical challenge. An advancement in the knowledge of mechanisms of the excessive or inappropriate activation of the complement cascade involved in the genesis of COVID-19-associated coagulopathy might be a fundamental approach for developing novel classes of anticoagulant drugs. In this context, there is emerging evidence indicating that C5a, a component of the complement system, and its receptors (C5aRs) play a critical role in the genesis of the COVID-19-associated hypercoagulable state. Thus, this review describes the mechanisms by which C5a/C5aR signaling participates in the cascade of events involved in the pathophysiology of COVID-19-associated coagulopathy. Furthermore, it highlights the current possibilities for the development of a novel therapeutic approach for COVID-19 patients that targets C5a/C5aRs signaling.