Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effec-tive MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models' generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer po-tential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.

Hepatocellular carcinoma(HCC)expresses abundant glycolytic enzymes and displays comprehensive glucose metabolism reprogramming.Aldolase A(ALDOA)plays a prominent role in glycolysis;however,little is known about its role in HCC development.In the present study,we aim to explore how ALDOA is involved in HCC proliferation.HCC proliferation was markedly suppressed both in vitro and in vivo following ALDOA knockout,which is consistent with ALDOA overexpression encouraging HCC prolifera-tion.Mechanistically,ALDOA knockout partially limits the glycolytic flux in HCC cells.Meanwhile,ALDOA translocated to nuclei and directly interacted with c-Jun to facilitate its Thr93 phosphorylation by P21-activated protein kinase;ALDOA knockout markedly diminished c-Jun Thr93 phosphorylation and then dampened c-Jun transcription function.A crucial site Y364 mutation in ALDOA disrupted its interaction with c-Jun,and Y364S ALDOA expression failed to rescue cell proliferation in ALDOA deletion cells.In HCC patients,the expression level of ALDOA was correlated with the phosphorylation level of c-Jun(Thr93)and poor prognosis.Remarkably,hepatic ALDOA was significantly upregulated in the promotion and progression stages of diethylnitrosamine-induced HCC models,and the knockdown of Aldoa strikingly decreased HCC development in vivo.Our study demonstrated that ALDOA is a vital driver for HCC development by activating c-Jun-mediated oncogene transcription,opening additional avenues for anti-cancer therapies.

Artificial intelligence(AI)is revolutionizing traditional drug discovery and development models by seamlessly integrating data,computational power,and algorithms.This synergy enhances the efficiency,accuracy,and success rates of drug research,shortens development timelines,and reduces costs.Coupled with machine learning(ML)and deep learning(DL),AI has demonstrated significant advancements across various domains,including drug characterization,target discovery and validation,small molecule drug design,and the acceleration of clinical trials.Through molecular generation techniques,AI facili-tates the creation of novel drug molecules,predicting their properties and activities,while virtual screening(VS)optimizes drug candidates.Additionally,AI enhances clinical trial efficiency by predicting outcomes,designing trials,and enabling drug repositioning.However,AI's application in drug devel-opment faces challenges,including the need for robust data-sharing mechanisms and the establishment of more comprehensive intellectual property protections for algorithms.AI-driven pharmaceutical companies must also integrate biological sciences and algorithms effectively,ensuring the successful fusion of wet and dry laboratory experiments.Despite these challenges,the potential of AI in drug development remains undeniable.As AI technology evolves and these barriers are addressed,AI-driven therapeutics are poised for a broader and more impactful future in the pharmaceutical industry.

Drug development encompasses multiple processes,wherein protein subcellular localization is essential.It promotes target identification,treatment development,and the design of drug delivery systems.In this research,a deep learning framework called LocPro is presented for predicting protein subcellular localization.Specifically,LocPro is unique in(a)combining protein representations from the pre-trained large language model(LLM)ESM2 and the expert-driven tool PROFEAT,(b)implementing a hybrid deep neural network architecture that integrates convolutional neural network(CNN),fully connected(FC)layer,and bidirectional long short-term memory(BiLSTM)blocks,and(c)developing a multi-label framework for predicting protein subcellular localization at multiple granularity levels.Additionally,a dataset was curated and divided using a homology-based strategy for training and validation.Compar-ative analyses show that LocPro outperforms existing methods in sequence-based multi-label protein subcellular localization prediction.The practical utility of this framework is further demonstrated through case studies on drug target subcellular localization.All in all,LocPro serves as a valuable complement to existing protein localization prediction tools.The web server is freely accessible at https://idrblab.org/LocPro/.

Peptide-based therapeutics hold great promise for the treatment of various diseases;however,their clinical application is often hindered by toxicity challenges.The accurate prediction of peptide toxicity is crucial for designing safe peptide-based therapeutics.While traditional experimental approaches are time-consuming and expensive,computational methods have emerged as viable alternatives,including similarity-based and machine learning(ML)-/deep learning(DL)-based methods.However,existing methods often struggle with robustness and generalizability.To address these challenges,we propose HyPepTox-Fuse,a novel framework that fuses protein language model(PLM)-based embeddings with conventional descriptors.HyPepTox-Fuse integrates ensemble PLM-based embeddings to achieve richer peptide representations by leveraging a cross-modal multi-head attention mechanism and Transformer architecture.A robust feature ranking and selection pipeline further refines conventional descriptors,thus enhancing prediction performance.Our framework outperforms state-of-the-art methods in cross-validation and independent evaluations,offering a scalable and reliable tool for peptide toxicity pre-diction.Moreover,we conducted a case study to validate the robustness and generalizability of HyPepTox-Fuse,highlighting its effectiveness in enhancing model performance.Furthermore,the HyPepTox-Fuse server is freely accessible at https://balalab-skku.org/HyPepTox-Fuse/and the source code is publicly available at https://github.com/cbbl-skku-org/HyPepTox-Fuse/.The study thus presents an intuitive platform for predicting peptide toxicity and supports reproducibility through openly available datasets.

Suboptimal treatment of laryngeal squamous cell carcinoma(LSCC)provides poor survival rate.The poor bioavailability,resistance to cetuximab(Cet),and the instability of small interfering RNA(siRNA)limit their efficacy in LSCC therapy.The present study has been aimed to develop a Cet and focal adhesion kinase(FAK)siRNA(siFAK)co-delivery nanosystem.Zeolitic imidazolate framework-8(ZIF-8),with its large specific surface area and pH-responsive properties,is an ideal delivery carrier allowing controlled drug release in the acidic tumor microenvironment.Therefore,Cet was loaded onto ZIF-8 and encap-sulated in a TU177 cell membrane(TCM)after the electrostatic adsorption of siFAK.Fourier transform infrared(FT1R)spectroscopy,transmission electron microscopy(TEM),scanning electron microscopy(SEM),zeta potential,X-ray diffraction,and particle size analyses were deployed to characterize Cet/siFAK@ZIF-8@TCM.TU177 cells and subcutaneously transplanted tumor-bearing nude mice were used to evaluate the intracellular uptake,cytotoxicity,in vivo biocompatibility,biodistribution,biosafety,pH responsiveness,and anti-LSCC efficacy of Cet/siFAK@ZIF-8@TCM.After ZIF-8@TCM were loaded with Cet and siFAK,alterations in their physical and crystal structures,particle size,and zeta potential were observed.Meanwhile,the co-delivery system increased the loading of Cet through the electrostatic adsorption of siFAK to Cet-loaded ZIF-8.The intracellular uptake of Cet/siFAK@ZIF-8@TCM also protected siFAK from degradation,effectively decreasing the messenger RNA(mRNA)and protein expression levels of FAK in LSCC cells.The ZIF-8@TCM nanosystem for co-delivery of Cet and siFAK exhibited pH-responsiveness and tumor-targeting capabilities,thereby exerting anti-LSCC effects.Co-delivery of Cet and siFAK via the pH-responsive ZIF-8@TCM system enabled the targeted release of the chemothera-peutic and gene,in turn maximizing their anti-LSCC effect while ensuring biosafety.

The dysregulation of cyclin-dependent kinase 12(CDK12),which may result from genomic alterations or modulation by upstream effectors,is implicated in cancer oncogenesis and progression.CDK12 over-expression or activation is sufficient to induce tumor initiation,recurrence,and therapeutic resistance.However,CDK12 may also exert tumor-suppressive functions in a context-dependent manner.Therefore,caution is warranted when targeting CDK12 in future clinical trials.A comprehensive elucidation of the dual roles and underlying mechanisms of CDK12 in carcinogenesis is urgently needed to advance pre-cision oncology.This review provides an overview of the current understanding of the dysregulation and biological roles of CDK12 in cancer.Subsequently,we systematically summarize the functions and mechanisms of the oncogenic and tumor-suppressive roles of CDK12 in different contexts.Finally,we discuss the potential of CDK12 as a novel therapeutic target and its implications in clinical oncology,offering insights into future directions for innovative cancer treatment strategies.

Hyperuricemia(HUA)and gout became typical metabolic disorders characterized by multiple pathogenic factors.Their incidence increased annually,affecting younger populations.Given that uric acid(UA)and inflammation were the primary disease mechanisms,the search for effective and low-side-effect UA-lowering and anti-inflammatory drugs became a pressing scientific priority.Traditional Chinese medi-cine(TCM)encompassed a rich array of theoretical and practical experience,along with a diverse range of chemical substances,making herbs or their components potential sources for therapeutic drugs.Despite the significant role that modern herbal medicines played in treating HUA and gout,the existing research literature remained fragmented,lacking comprehensive and systematic reviews.In this review,we focused on the regulation of UA and summarized the discovery of UA-lowering pharmacodynamic components or ingredients derived from herbs and formulas,as well as their multi-targeted mechanisms of action.Emphasizing this focus,we proposed that,compared to acute inflammation,low-grade inflammation may play a relatively"unnoticed"role in the disease process.In contrast to Western medicine,we discussed the risks and benefits of herbal medicines and their ingredients for treatment,drawing from theoretical insights and clinical practice.This review offered comprehensive perspectives on the research into anti-HUA and gout treatments using herbal medicines and their natural products.Additionally,it provided a forward-looking view on natural product discovery,the exploration of ther-apeutic strategies,and new drug research in this field.

Diabetic kidney disease(DKD)with increasing global prevalence lacks effective therapeutic targets to halt or reverse its progression.Therapeutic targets supported by causal genetic evidence are more likely to succeed in randomized clinical trials.In this study,we integrated large-scale plasma proteomics,genetic-driven causal inference,and experimental validation to identify prioritized targets for DKD using the UK Biobank(UKB)and FinnGen cohorts.Among 2844 diabetic patients(528 with DKD),we identified 37 targets significantly associated with incident DKD,supported by both observational and causal evi-dence.Of these,22％(8/37)of the potential targets are currently under investigation for DKD or other diseases.Our prospective study confirmed that higher levels of three prioritized targets-insulin-like growth factor binding protein 4(IGFBP4),family with sequence similarity 3 member C(FAM3C),and prostaglandin D2 synthase(PTGDS)—were associated with a 4.35,3.51,and 3.57-fold increased likeli-hood of developing DKD,respectively.In addition,population-level protein-altering variants(PAVs)analysis and in vitro experiments cross-validated FAM3C and IGFBP4 as potential new target candidates for DKD,through the classic NLR family pyrin domain containing 3(NLRP3)-caspase-1-gasdermin D(GSDMD)apoptotic axis.Our results demonstrate that integrating omics data mining with causal inference may be a promising strategy for prioritizing therapeutic targets.

Accurate prediction of drug-induced adverse drug reactions(ADRs)is crucial for drug safety evaluation,as it directly impacts public health and safety.While various models have shown promising results in predicting ADRs,their accuracy still needs improvement.Additionally,many existing models often lack interpretability when linking molecular structures to specific ADRs and frequently rely on manually selected molecular fingerprints,which can introduce bias.To address these challenges,we propose ToxBERT,an efficient transformer encoder model that leverages attention and masking mechanisms for simplified molecular input line entry system(SMILES)representations.Our results demonstrate that ToxBERT achieved area under the receiver operating characteristic curve(AUROC)scores of 0.839,0.759,and 0.664 for predicting drug-induced QT prolongation(DIQT),rhabdomyolysis,and liver injury,respectively,outperforming previous studies.Furthermore,ToxBERT can identify drug substructures that are closely associated with specific ADRs.These findings indicate that ToxBERT is not only a valuable tool for understanding the mechanisms underlying specific drug-induced ADRs but also for mitigating potential ADRs in the drug discovery pipeline.