Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining.

Accurate prediction of molecular properties is fundamental in drug discovery and development, providing crucial guidance for effective drug design. A critical factor in achieving accurate molecular property prediction lies in the appropriate representation of molecular structures. Presently, prevalent deep learning-based molecular representations rely on 2D structure information as the primary molecular representation, often overlooking essential three-dimensional (3D) conformational information due to the inherent limitations of 2D structures in conveying atomic spatial relationships. In this study, we propose employing the Gram matrix as a condensed representation of 3D molecular structures and for efficient pretraining objectives. Subsequently, we leverage this matrix to construct a novel molecular representation model, Pre-GTM, which inherently encapsulates 3D information. The model accurately predicts the 3D structure of a molecule by estimating the Gram matrix. Our findings demonstrate that Pre-GTM model outperforms the baseline Graphormer model and other pretrained models in the QM9 and MoleculeNet quantitative property prediction task. The integration of the Gram matrix as a condensed representation of 3D molecular structure, incorporated into the Pre-GTM model, opens up promising avenues for its potential application across various domains of molecular research, including drug design, materials science, and chemical engineering.

Fine-tuning large language models for chemical text mining.

Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental and computational chemists. The task is still considered to be extremely challenging due to the complexity of the chemical language and scientific literature. This study explored the power of fine-tuned large language models (LLMs) on five intricate chemical text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data extraction, and the conversion of reaction paragraphs to action sequences. The fine-tuned LLMs demonstrated impressive performance, significantly reducing the need for repetitive and extensive prompt engineering experiments. For comparison, we guided ChatGPT (GPT-3.5-turbo) and GPT-4 with prompt engineering and fine-tuned GPT-3.5-turbo as well as other open-source LLMs such as Mistral, Llama3, Llama2, T5, and BART. The results showed that the fine-tuned ChatGPT models excelled in all tasks. They achieved exact accuracy levels ranging from 69% to 95% on these tasks with minimal annotated data. They even outperformed those task-adaptive pre-training and fine-tuning models that were based on a significantly larger amount of in-domain data. Notably, fine-tuned Mistral and Llama3 show competitive abilities. Given their versatility, robustness, and low-code capability, leveraging fine-tuned LLMs as flexible and effective toolkits for automated data acquisition could revolutionize chemical knowledge extraction.

Discovery of a terpene synthase synthesizing a nearly non-flexible eunicellane reveals the basis of flexibility.

Eunicellane diterpenoids, containing a typical 6,10-bicycle, are bioactive compounds widely present in marine corals, but rarely found in bacteria and plants. The intrinsic macrocycle exhibits innate structural flexibility resulting in dynamic conformational changes. However, the mechanisms controlling flexibility remain unknown. The discovery of a terpene synthase, MicA, that is responsible for the biosynthesis of a nearly non-flexible eunicellane skeleton, enable us to propose a feasible theory about the flexibility in eunicellane structures. Parallel studies of all eunicellane synthases in nature discovered to date, including 2Z-geranylgeranyl diphosphate incubations and density functional theory-based Boltzmann population computations, reveale that a trans-fused bicycle with a 2Z-configuration alkene restricts conformational flexibility resulting in a nearly non-flexible eunicellane skeleton. The catalytic route and the enzymatic mechanism of MicA are also elucidated by labeling experiments, density functional theory calculations, structural analysis of the artificial intelligence-based MicA model, and mutational studies.

Reducing overconfident errors in molecular property classification using Posterior Network.

Deep-learning-based classification models are increasingly used for predicting molecular properties in drug development. However, traditional classification models using the Softmax function often give overconfident mispredictions for out-of-distribution samples, highlighting a critical lack of accurate uncertainty estimation. Such limitations can result in substantial costs and should be avoided during drug development. Inspired by advances in evidential deep learning and Posterior Network, we replaced the Softmax function with a normalizing flow to enhance the uncertainty estimation ability of the model in molecular property classification. The proposed strategy was evaluated across diverse scenarios, including simulated experiments based on a synthetic dataset, ADMET predictions, and ligand-based virtual screening. The results demonstrate that compared with the vanilla model, the proposed strategy effectively alleviates the problem of giving overconfident but incorrect predictions. Our findings support the promising application of evidential deep learning in drug development and offer a valuable framework for further research.

Highly accurate carbohydrate-binding site prediction with DeepGlycanSite.

As the most abundant organic substances in nature, carbohydrates are essential for life. Understanding how carbohydrates regulate proteins in the physiological and pathological processes presents opportunities to address crucial biological problems and develop new therapeutics. However, the diversity and complexity of carbohydrates pose a challenge in experimentally identifying the sites where carbohydrates bind to and act on proteins. Here, we introduce a deep learning model, DeepGlycanSite, capable of accurately predicting carbohydrate-binding sites on a given protein structure. Incorporating geometric and evolutionary features of proteins into a deep equivariant graph neural network with the transformer architecture, DeepGlycanSite remarkably outperforms previous state-of-the-art methods and effectively predicts binding sites for diverse carbohydrates. Integrating with a mutagenesis study, DeepGlycanSite reveals the guanosine-5'-diphosphate-sugar-recognition site of an important G-protein coupled receptor. These findings demonstrate DeepGlycanSite is invaluable for carbohydrate-binding site prediction and could provide insights into molecular mechanisms underlying carbohydrate-regulation of therapeutically important proteins.

Deep representation learning of chemical-induced transcriptional profile for phenotype-based drug discovery.

Artificial intelligence transforms drug discovery, with phenotype-based approaches emerging as a promising alternative to target-based methods, overcoming limitations like lack of well-defined targets. While chemical-induced transcriptional profiles offer a comprehensive view of drug mechanisms, inherent noise often obscures the true signal, hindering their potential for meaningful insights. Here, we highlight the development of TranSiGen, a deep generative model employing self-supervised representation learning. TranSiGen analyzes basal cell gene expression and molecular structures to reconstruct chemical-induced transcriptional profiles with high accuracy. By capturing both cellular and compound information, TranSiGen-derived representations demonstrate efficacy in diverse downstream tasks like ligand-based virtual screening, drug response prediction, and phenotype-based drug repurposing. Notably, in vitro validation of TranSiGen's application in pancreatic cancer drug discovery highlights its potential for identifying effective compounds. We envisage that integrating TranSiGen into the drug discovery and mechanism research holds significant promise for advancing biomedicine.

Synthesis of Highly Substituted Furans via Intermolecular Enynone-Aldehyde Cross-Coupling/Cyclization Catalyzed by N-Heterocyclic Carbenes.

A new strategy for facile access to multifunctionalized furans via N-heterocyclic carbene-catalyzed cross-coupling/cyclization of ynenones with aldehydes has been explored. This protocol features readily obtainable starting materials, mild and metal-free conditions, broad substrate scope, good functional group tolerance, excellent yields, and easy scale-up. Synthetic utility of the protocol has been further corroborated through functionalization of complex substrates and postmodifications of the product.

KinomeMETA: a web platform for kinome-wide polypharmacology profiling with meta-learning.

Kinase-targeted inhibitors hold promise for new therapeutic options, with multi-target inhibitors offering the potential for broader efficacy while minimizing polypharmacology risks. However, comprehensive experimental profiling of kinome-wide activity is expensive, and existing computational approaches often lack scalability or accuracy for understudied kinases. We introduce KinomeMETA, an artificial intelligence (AI)-powered web platform that significantly expands the predictive range with scalability for predicting the polypharmacological effects of small molecules across the kinome. By leveraging a novel meta-learning algorithm, KinomeMETA efficiently utilizes sparse activity data, enabling rapid generalization to new kinase tasks even with limited information. This significantly expands the repertoire of accurately predictable kinases to 661 wild-type and clinically-relevant mutant kinases, far exceeding existing methods. Additionally, KinomeMETA empowers users to customize models with their proprietary data for specific research needs. Case studies demonstrate its ability to discover new active compounds by quickly adapting to small dataset. Overall, KinomeMETA offers enhanced kinome virtual profiling capabilities and is positioned as a powerful tool for developing new kinase inhibitors and advancing kinase research. The KinomeMETA server is freely accessible without registration at https://kinomemeta.alphama.com.cn/.

Design, Synthesis, and Bioevaluation of Transcriptional Enhanced Assocciated Domain (TEAD) PROTAC Degraders.

Dysregulation of the Hippo pathway has been observed in various cancers. The transcription factor TEAD, together with its coactivators YAP/TAZ, plays a crucial role in regulating the transcriptional output of the Hippo pathway. Recently, extensive research has focused on small molecule inhibitors targeting TEAD, but studies on TEAD degraders are comparatively rare. In this study, we designed and synthesized a series of TEAD PROTACs by connecting a pan-TEAD inhibitor with the CRBN ligand thalidomide. A representative compound, 27, exhibited potent antiproliferative activity against NF2-deficient NCI-H226 cells. It dose-dependently induced TEAD degradation dependent on CRBN and proteasome system and decreased key YAP target genes CYR61 and CTGF expressions in NCI-H226 cells. Further degradation selectivity studies revealed that 27 exhibited more potent activity against TEAD2 compared to those of the other three family members in Flag-TEADs transfected 293T cells. Therefore, 27 may serve as a valuable tool for advancing biological studies related to TEAD2.

Design, synthesis, and bioevaluation of SOS1 PROTACs derived from pyrido[2,3-d]pyrimidin-7-one-based SOS1 inhibitor.

Oncogenic KRAS mutations drive an approximately 25 % of all human cancers. Son of Sevenless 1 (SOS1), a critical guanine nucleotide exchange factor, catalyzes the activation of KRAS. Targeting SOS1 degradation has engaged as a promising therapeutic strategy for KRAS-mutant cancers. Herein, we designed and synthesized a series of novel CRBN-recruiting SOS1 PROTACs using the pyrido[2,3-d]pyrimidin-7-one-based SOS1 inhibitor as the warhead. One representative compound 11o effectively induced the degradation of SOS1 in three different KRAS-mutant cancer cell lines with DC50 values ranging from 1.85 to 7.53 nM. Mechanism studies demonstrated that 11o-induced SOS1 degradation was dependent on CRBN and proteasome. Moreover, 11o inhibited the phosphorylation of ERK and displayed potent anti-proliferative activities against SW620, A549 and DLD-1 cells. Further optimization of 11o may provide us promising SOS1 degraders with favorable drug-like properties for developing new chemotherapies targeting KRAS-driven cancers.

Update on the development of TGR5 agonists for human diseases.

The G protein-coupled bile acid receptor 1 (GPBAR1) or TGR5 is widely distributed across organs, including the small intestine, stomach, liver, spleen, and gallbladder. Many studies have established strong correlations between TGR5 and glucose homeostasis, energy metabolism, immune-inflammatory responses, and gastrointestinal functions. These results indicate that TGR5 has a significant impact on the progression of tumor development and metabolic disorders such as diabetes mellitus and obesity. Targeting TGR5 represents an encouraging therapeutic approach for treating associated human ailments. Notably, the GLP-1 receptor has shown exceptional efficacy in clinical settings for diabetes management and weight loss promotion. Currently, numerous TGR5 agonists have been identified through natural product-based approaches and virtual screening methods, with some successfully progressing to clinical trials. This review summarizes the intricate relationships between TGR5 and various diseases emphasizing recent advancements in research on TGR5 agonists, including their structural characteristics, design tactics, and biological activities. We anticipate that this meticulous review could facilitate the expedited discovery and optimization of novel TGR5 agonists.

Comparing the Effect of Early Versus Delayed Metformin Treatment on Glycaemic Parameters Among Australian Adults With Incident Diabetes: Evidence Using a National General Practice Database.

PURPOSE: To compare the effect of early vs delayed metformin treatment for glycaemic management among patients with incident diabetes. METHODS: Cohort study using electronic health records of regular patients (1+ visits per year in 3 consecutive years) aged 40+ years with 'incident' diabetes attending Australian general practices (MedicineInsight, 2011-2018). Patients with incident diabetes were defined as those who had a) 12+ months of medical data before the first recording of a diabetes diagnosis AND b) a diagnosis of 'diabetes' recorded at least twice in their electronic medical records or a diagnosis of 'diabetes' recorded only once combined with at least 1 abnormal glycaemic result (i.e., HbA1c ≥6.5%, fasting blood glucose [FBG] ≥7.0 mmol/L, or oral glucose tolerance test ≥11.1mmol/L) in the preceding 3 months. The effect of early (<3 months), timely (3-6 months), or delayed (6-12 months) initiation of metformin treatment vs no metformin treatment within 12 months of diagnosis on HbA1c and FBG levels 3 to 24 months after diagnosis was compared using linear regression and augmented inverse probability weighted models. Patients initially managed with other antidiabetic medications (alone or combined with metformin) were excluded. FINDINGS: Of 18,856 patients with incident diabetes, 38.8% were prescribed metformin within 3 months, 3.9% between 3 and 6 months, and 6.2% between 6 and 12 months after diagnosis. The untreated group had the lowest baseline parameters (mean HbA1c 6.4%; FBG 6.9mmol/L) and maintained steady levels throughout follow-up. Baseline glycaemic parameters for those on early treatment with metformin (<3 months since diagnosis) were the highest among all groups (mean HbA1c 7.6%; FBG 8.8mmol/L), reaching controlled levels at 3 to 6 months (mean HbA1c 6.5%; FBG 6.9mmol/L) with sustained improvement until the end of follow-up (mean HbA1c 6.4%; FBG 6.9mmol/L at 18-24 months). Patients with timely and delayed treatment also improved their glycaemic parameters after initiating treatment (timely treatment: mean HbA1c 7.3% and FBG 8.3mmol/L at 3-6 months; 6.6% and 6.9mmol/L at 6-12 months; delayed treatment: mean HbA1c 7.2% and FBG 8.4mmol/L at 6-12 months; 6.7% and 7.1mmol/L at 12-18 months). Compared to those not managed with metformin, the corresponding average treatment effect for HbA1c at 18-24 months was +0.04% (95%CI -0.05;0.10) for early, +0.24% (95%CI 0.11;0.37) for timely, and +0.29% (95%CI 0.20;0.39) for delayed treatment. IMPLICATIONS: Early metformin therapy (<3 months) for patients recently diagnosed with diabetes consistently improved HbA1c and FBG levels in the first 24 months of diagnosis.

Assessing the clinical diagnostic value of anti-Müllerian hormone in polycystic ovarian syndrome and its correlation with clinical and metabolism indicators.

BACKGROUND: This study investigated the association between Anti-Müllerian Hormone (AMH) and relevant metabolic parameters and assessed its predictive value in the clinical diagnosis of polycystic ovarian syndrome (PCOS). METHODS: A total of 421 women aged 20-37 years were allocated to the PCOS (n = 168) and control (n = 253) groups, and their metabolic and hormonal parameters were compared. Spearman correlation analysis was conducted to investigate associations, binary logistic regression was used to determine PCOS risk factors, and receiver operating characteristic (ROC) curves were generated to evaluate the predictive value of AMH in diagnosing PCOS. RESULTS: The PCOS group demonstrated significantly higher blood lipid, luteinizing hormone (LH), and AMH levels than the control group. Glucose and lipid metabolism and hormonal disorders in the PCOS group were more significant than in the control group among individuals with and without obesity. LH, TSTO, and AMH were identified as independent risk factors for PCOS. AMH along with LH, and antral follicle count demonstrated a high predictive value for diagnosing PCOS. CONCLUSION: AMH exhibited robust diagnostic use for identifying PCOS and could be considered a marker for screening PCOS to improve PCOS diagnostic accuracy. Attention should be paid to the effect of glucose and lipid metabolism on the hormonal and related parameters of PCOS populations.

Structure-based design of pan-coronavirus inhibitors targeting host cathepsin L and calpain-1.

Respiratory disease caused by coronavirus infection remains a global health crisis. Although several SARS-CoV-2-specific vaccines and direct-acting antivirals are available, their efficacy on emerging coronaviruses in the future, including SARS-CoV-2 variants, might be compromised. Host-targeting antivirals provide preventive and therapeutic strategies to overcome resistance and manage future outbreak of emerging coronaviruses. Cathepsin L (CTSL) and calpain-1 (CAPN1) are host cysteine proteases which play crucial roles in coronaviral entrance into cells and infection-related immune response. Here, two peptidomimetic α-ketoamide compounds, 14a and 14b, were identified as potent dual target inhibitors against CTSL and CAPN1. The X-ray crystal structures of human CTSL and CAPN1 in complex with 14a and 14b revealed the covalent binding of α-ketoamide groups of 14a and 14b to C25 of CTSL and C115 of CAPN1. Both showed potent and broad-spectrum anticoronaviral activities in vitro, and it is worth noting that they exhibited low nanomolar potency against SARS-CoV-2 and its variants of concern (VOCs) with EC50 values ranging from 0.80 to 161.7 nM in various cells. Preliminary mechanistic exploration indicated that they exhibited anticoronaviral activity through blocking viral entrance. Moreover, 14a and 14b exhibited good oral pharmacokinetic properties in mice, rats and dogs, and favorable safety in mice. In addition, both 14a and 14b treatments demonstrated potent antiviral potency against SARS-CoV-2 XBB 1.16 variant infection in a K18-hACE2 transgenic mouse model. And 14b also showed effective antiviral activity against HCoV-OC43 infection in a mouse model with a final survival rate of 60%. Further evaluation showed that 14a and 14b exhibited excellent anti-inflammatory effects in Raw 264.7 mouse macrophages and in mice with acute pneumonia. Taken together, these results suggested that 14a and 14b are promising drug candidates, providing novel insight into developing pan-coronavirus inhibitors with antiviral and anti-inflammatory properties.

Targeting JMJD1C to selectively disrupt tumor Treg cell fitness enhances antitumor immunity.

Regulatory T (Treg) cells are critical for immune tolerance but also form a barrier to antitumor immunity. As therapeutic strategies involving Treg cell depletion are limited by concurrent autoimmune disorders, identification of intratumoral Treg cell-specific regulatory mechanisms is needed for selective targeting. Epigenetic modulators can be targeted with small compounds, but intratumoral Treg cell-specific epigenetic regulators have been unexplored. Here, we show that JMJD1C, a histone demethylase upregulated by cytokines in the tumor microenvironment, is essential for tumor Treg cell fitness but dispensable for systemic immune homeostasis. JMJD1C deletion enhanced AKT signals in a manner dependent on histone H3 lysine 9 dimethylation (H3K9me2) demethylase and STAT3 signals independently of H3K9me2 demethylase, leading to robust interferon-γ production and tumor Treg cell fragility. We have also developed an oral JMJD1C inhibitor that suppresses tumor growth by targeting intratumoral Treg cells. Overall, this study identifies JMJD1C as an epigenetic hub that can integrate signals to establish tumor Treg cell fitness, and we present a specific JMJD1C inhibitor that can target tumor Treg cells without affecting systemic immune homeostasis.

Modifiable and Non-Modifiable Risk Factors for Premature Coronary Heart Disease (PCHD): Systematic Review and Meta-Analysis.

AIM: We aimed to compare the prevalence of modifiable and non-modifiable coronary heart disease (CHD) risk factors among those with premature CHD and healthy individuals. METHODS: PubMed, CINAHL, Embase, and Web of Science databases were searched (review protocol is registered in PROSPERO CRD42020173216). The quality of studies was assessed using the National Heart, Lung and Blood Institute tool for cross-sectional, cohort and case-control studies. Meta-analyses were performed using Review Manager 5.3. Effect sizes for categorical and continuous variables, odds ratio (OR) and mean differences (MD)/standardised mean differences (SMD) with 95% confidence intervals (CI) were reported. RESULTS: A total of n=208 primary studies were included in this review. Individuals presenting with premature CHD (PCHD, age ≤65 years) had higher mean body mass index (MD 0.54 kg/m2, 95% CI 0.24, 0.83), total cholesterol (SMD 0.27, 95% CI 0.17, 0.38), triglycerides (SMD 0.50, 95% CI 0.41, 0.60) and lower high-density lipoprotein cholesterol (SMD 0.79, 95% CI: -0.91, -0.68) compared with healthy individuals. Individuals presenting with PCHD were more likely to be smokers (OR 2.88, 95% CI 2.51, 3.31), consumed excessive alcohol (OR 1.40, 95% CI 1.05, 1.86), had higher mean lipoprotein (a) levels (SMD 0.41, 95% CI 0.28, 0.54), and had a positive family history of CHD (OR 3.65, 95% CI 2.87, 4.66) compared with healthy individuals. Also, they were more likely to be obese (OR 1.59, 95% CI 1.32, 1.91), and to have had dyslipidaemia (OR 2.74, 95% CI 2.18, 3.45), hypertension (OR 2.80, 95% CI 2.28, 3.45), and type 2 diabetes mellitus (OR 2.93, 95% CI 2.50, 3.45) compared with healthy individuals. CONCLUSION: This meta-analysis confirms current knowledge of risk factors for PCHD, and identifying these early may reduce CHD in young adults.

TG468: a text graph convolutional network for predicting clinical response to immune checkpoint inhibitor therapy.

Enhancing cancer treatment efficacy remains a significant challenge in human health. Immunotherapy has witnessed considerable success in recent years as a treatment for tumors. However, due to the heterogeneity of diseases, only a fraction of patients exhibit a positive response to immune checkpoint inhibitor (ICI) therapy. Various single-gene-based biomarkers and tumor mutational burden (TMB) have been proposed for predicting clinical responses to ICI; however, their predictive ability is limited. We propose the utilization of the Text Graph Convolutional Network (GCN) method to comprehensively assess the impact of multiple genes, aiming to improve the predictive capability for ICI response. We developed TG468, a Text GCN model framing drug response prediction as a text classification task. By combining natural language processing (NLP) and graph neural network techniques, TG468 effectively handles sparse and high-dimensional exome sequencing data. As a result, TG468 can distinguish survival time for patients who received ICI therapy and outperforms single gene biomarkers, TMB and some classical machine learning models. Additionally, TG468's prediction results facilitate the identification of immune status differences among specific patient types in the Cancer Genome Atlas dataset, providing a rationale for the model's predictions. Our approach represents a pioneering use of a GCN model to analyze exome data in patients undergoing ICI therapy and offers inspiration for future research using NLP technology to analyze exome sequencing data.

Transfer learning enhanced graph neural network for aldehyde oxidase metabolism prediction and its experimental application.

Aldehyde oxidase (AOX) is a molybdoenzyme that is primarily expressed in the liver and is involved in the metabolism of drugs and other xenobiotics. AOX-mediated metabolism can result in unexpected outcomes, such as the production of toxic metabolites and high metabolic clearance, which can lead to the clinical failure of novel therapeutic agents. Computational models can assist medicinal chemists in rapidly evaluating the AOX metabolic risk of compounds during the early phases of drug discovery and provide valuable clues for manipulating AOX-mediated metabolism liability. In this study, we developed a novel graph neural network called AOMP for predicting AOX-mediated metabolism. AOMP integrated the tasks of metabolic substrate/non-substrate classification and metabolic site prediction, while utilizing transfer learning from 13C nuclear magnetic resonance data to enhance its performance on both tasks. AOMP significantly outperformed the benchmark methods in both cross-validation and external testing. Using AOMP, we systematically assessed the AOX-mediated metabolism of common fragments in kinase inhibitors and successfully identified four new scaffolds with AOX metabolism liability, which were validated through in vitro experiments. Furthermore, for the convenience of the community, we established the first online service for AOX metabolism prediction based on AOMP, which is freely available at https://aomp.alphama.com.cn.

Synthesis and Biological Evaluation of ß-Lactam Derivatives Targeting Speckle-Type POZ Protein (SPOP).

Speckle-type POZ protein (SPOP) acts as a cullin3-RING ubiquitin ligase adaptor, which facilitates the recognition and ubiquitination of substrate proteins. Previous research suggests that targeting SPOP holds promise in the treatment of clear cell renal cell carcinoma (ccRCC). On the basis of the reported SPOP inhibitor 230D7, a series of ß-lactam derivatives were synthesized in this study. The biological activity assessment of these compounds revealed E1 as the most potent inhibitor, which can disrupt the SPOP-substrate interactions in vitro and suppress the colony formation of ccRCC cells. Taken together, this study provided compound E1 as a potent inhibitor against ccRCC and offered insight into the development of the ß-lactam SPOP inhibitor.

DNA-PK-Mediated Cytoplasmic DNA Sensing Stimulates Glycolysis to Promote Lung Squamous Cell Carcinoma Malignancy and Chemoresistance.

Detection of cytoplasmic DNA is an essential biological mechanism that elicits IFN-dependent and immune-related responses. A better understanding of the mechanisms regulating cytoplasmic DNA sensing in tumor cells could help identify immunotherapeutic strategies to improve cancer treatment. Here we identified abundant cytoplasmic DNA accumulated in lung squamous cell carcinoma (LUSC) cells. DNA-PK, but not cGAS, functioned as a specific cytoplasmic DNA sensor to activate downstream ZAK/AKT/mTOR signaling, thereby enhancing the viability, motility, and chemoresistance of LUSC cells. DNA-PK-mediated cytoplasmic DNA sensing boosted glycolysis in LUSC cells, and blocking glycolysis abolished the tumor-promoting activity of cytoplasmic DNA. Elevated DNA-PK-mediated cytoplasmic DNA sensing was positively correlated with poor prognosis of human patients with LUSC. Targeting signaling activated by cytoplasmic DNA sensing with the ZAK inhibitor iZAK2 alone or in combination with STING agonist or anti-PD-1 antibody suppressed the tumor growth and improved the survival of mouse lung cancer models and human LUSC patient-derived xenografts model. Overall, these findings established DNA-PK-mediated cytoplasmic DNA sensing as a mechanism that supports LUSC malignancy and highlight the potential of targeting this pathway for treating LUSC. SIGNIFICANCE: DNA-PK is a cytoplasmic DNA sensor that activates ZAK/AKT/mTOR signaling and boosts glycolysis to enhance malignancy and chemoresistance of lung squamous cell carcinoma.