Identification and Analysis of Sex-Biased Copy Number Alterations.

Background: Sex difference has long been recognized at cancer incidence, outcomes, and responses to therapy. Analyzing the somatic mutation profiles of large-scale cancer samples between the sexes have revealed several potential drivers of cancer with sex difference. However, it is still a demand for in-depth scrutinizing the sex-biased characteristics of genome instability to link the clinical differences for individual cancer type. Methods: Here, we utilized a published framework devised to specifically compare the copy number profiles between 2 groups to identify the sex-biased copy number alterations (CNAs) across 16 cancer types from the The Cancer Genome Atlas Program database, and dissected the impact of those CNAs. Results: Totally, 81 male-biased CNA regions and 23 female-biased CNA regions in 16 cancer types were found. Functional annotation analysis showed that several critical biological functions associated with sex-biased CNAs are shared in multiple cancer types, including immune-related pathways and regulation of cellular signaling. Most sex-biased CNAs have a substantial effect on transcriptional consequence, where the average of over 68% of genes have a linear relationship with CNAs across cancer types, and 14% of those genes are affected by the combination of the sex and copy number. Furthermore, 29 sex-biased CNA regions show latent capacity to be sex-specific prognostic biomarker such as CNA on 11q13.4 for head and neck cancer and lung cancer. Conclusions: This analysis offers new insights into the role of sex in cancer etiology and prognosis through a detailed characterization of sex differences in genome instability of diverse cancers.

Aging aggravates aortic aneurysm and dissection via miR-1204-MYLK signaling axis in mice.

The mechanism by which aging induces aortic aneurysm and dissection (AAD) remains unclear. A total of 430 participants were recruited for the screening of differentially expressed plasma microRNAs (miRNAs). We found that miR-1204 is significantly increased in both the plasma and aorta of elder patients with AAD and is positively correlated with age. Cell senescence induces the expression of miR-1204 through p53 interaction with plasmacytoma variant translocation 1, and miR-1204 induces vascular smooth muscle cell (VSMC) senescence to form a positive feedback loop. Furthermore, miR-1204 aggravates angiotensin II-induced AAD formation, and inhibition of miR-1204 attenuates ß-aminopropionitrile monofumarate-induced AAD development in mice. Mechanistically, miR-1204 directly targets myosin light chain kinase (MYLK), leading to the acquisition of a senescence-associated secretory phenotype (SASP) by VSMCs and loss of their contractile phenotype. MYLK overexpression reverses miR-1204-induced VSMC senescence, SASP and contractile phenotypic changes, and the decrease of transforming growth factor-ß signaling pathway. Our findings suggest that aging aggravates AAD via the miR-1204-MYLK signaling axis.

Material basis and pharmacodynamic mechanism of YangshenDingzhi granules in the intervention of viral pneumonia: Based on serum pharmacochemistry and network pharmacology.

BACKGROUND: YangshenDingzhi granules (YSDZ) are clinically effective in preventing and treating COVID-19. The present study elucidates the underlying mechanism of YSDZ intervention in viral pneumonia by employing serum pharmacochemistry and network pharmacology. METHODS: The chemical constituents of YSDZ in the blood were examined using ultra-performance liquid chromatography-quadrupole/orbitrap high-resolution mass spectrometry (UPLC-Q-Exactive Orbitrap MS). Potential protein targets were obtained from the SwissTargetPrediction database, and the target genes associated with viral pneumonia were identified using GeneCards, DisGeNET, and Online Mendelian Inheritance in Man (OMIM) databases. The intersection of blood component-related targets and disease-related targets was determined using Venny 2.1. Protein-protein interaction networks were constructed using the STRING database. The Metascape database was employed to perform enrichment analyses of Gene Ontology (GO) functions and Kyoto Encyclopedia of Genes and Genomes (KEGG) signaling pathways for the targets, while the Cytoscape 3.9.1 software was utilized to construct drug-component-disease-target-pathway networks. Further, in vitro and in vivo experiments were performed to establish the therapeutic effectiveness of YSDZ against viral pneumonia. RESULTS: Fifteen compounds and 124 targets linked to viral pneumonia were detected in serum. Among these, MAPK1, MAPK3, AKT1, EGFR, and TNF play significant roles. In vitro tests revealed that the medicated serum suppressed the replication of H1N1, RSV, and SARS-CoV-2 replicon. Further, in vivo testing analysis shows that YSDZ decreases the viral load in the lungs of mice infected with RSV and H1N1. CONCLUSION: The chemical constituents of YSDZ in the blood may elicit therapeutic effects against viral pneumonia by targeting multiple proteins and pathways.

A BSL-2 compliant mouse model of SARS-CoV-2 infection for efficient and convenient antiviral evaluation.

Animal models of authentic severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection require operation in biosafety level 3 (BSL-3) containment. In the present study, we established a mouse model employing a single-cycle infectious virus replicon particle (VRP) system of SARS-CoV-2 that can be safely handled in BSL-2 laboratories. The VRP [ΔS-VRP(G)-Luc] contains a SARS-CoV-2 genome in which the spike gene was replaced by a firefly luciferase (Fluc) reporter gene (Rep-Luci), and incorporates the vesicular stomatitis virus glycoprotein on the surface. Intranasal inoculation of ΔS-VRP(G)-Luc can successfully transduce the Rep-Luci genome into mouse lungs, initiating self-replication of Rep-Luci and, accordingly, inducing acute lung injury mimicking the authentic SARS-CoV-2 pathology. In addition, the reporter Fluc expression can be monitored using a bioluminescence imaging approach, allowing a rapid and convenient determination of viral replication in ΔS-VRP(G)-Luc-infected mouse lungs. Upon treatment with an approved anti-SARS-CoV-2 drug, VV116, the viral replication in infected mouse lungs was significantly reduced, suggesting that the animal model is feasible for antiviral evaluation. In summary, we have developed a BSL-2-compliant mouse model of SARS-CoV-2 infection, providing an advanced approach to study aspects of the viral pathogenesis, viral-host interactions, as well as the efficacy of antiviral therapeutics in the future.IMPORTANCESevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is highly contagious and pathogenic in humans; thus, research on authentic SARS-CoV-2 has been restricted to biosafety level 3 (BSL-3) laboratories. However, due to the scarcity of BSL-3 facilities and trained personnel, the participation of a broad scientific community in SARS-CoV-2 research had been greatly limited, hindering the advancement of our understanding on the basic virology as well as the urgently necessitated drug development. Previously, our colleagues Jin et al. had generated a SARS-CoV-2 replicon by replacing the essential spike gene in the viral genome with a Fluc reporter (Rep-Luci), which can be safely operated under BSL-2 conditions. By incorporating the Rep-Luci into viral replicon particles carrying vesicular stomatitis virus glycoprotein on their surface, and via intranasal inoculation, we successfully transduced the Rep-Luci into mouse lungs, developing a mouse model mimicking SARS-CoV-2 infection. Our model can serve as a useful platform for SARS-CoV-2 pathological studies and antiviral evaluation under BSL2 containment.

Gap-Δenergy, a New Metric of the Bond Energy State, Assisting to Predict Molecular Toxicity.

Molecular toxicity is a critical feature of drug development. It is thus very important to develop computational models to evaluate the toxicity of small molecules. The accuracy of toxicity prediction largely depends on the quality of molecular representation; however, current methods for this purpose do not address this issue well. Here, we introduce a new metric, gap-Δenergy, which is designed to quantify the intermolecular bond energy difference with atom distance. We next find significant variations in the gap-Δenergy distribution among different types of molecules. Moreover, we show that this metric is able to distinguish the toxic small molecules. We collected data sets of toxic and exogenous small molecules and presented a novel index, namely, global toxicity, to evaluate the overall toxicity of molecules. Based on molecular descriptors and the proposed gap-Δenergy metric, we further constructed machine learning models that were trained with 7816 small molecules. The XGBoost-based model achieved the best performance with an AUC score of 0.965 and an F1 score of 0.849 on the test set (1954 small molecules), which outperformed the model that did not use gap-Δenergy features, with a sensitivity score increase of 3.2%.

Development of a virus-based affinity ultrafiltration method for screening virus-surface-protein-targeted compounds from complex matrixes: Herbal medicines as a case study.

Herbal medicines (HMs) are one of the main sources for the development of lead antiviral compounds. However, due to the complex composition of HMs, the screening of active compounds within these is inefficient and requires a significant time investment. We report a novel and efficient virus-based screening method for antiviral active compounds in HMs. This method involves the centrifugal ultrafiltration of viruses, known as the virus-based affinity ultrafiltration method (VAUM). This method is suitable to identify virus specific active compounds from complex matrices such as HMs. The effectiveness of the VAUM was evaluated using influenza A virus (IAV) H1N1. Using this method, four compounds that bind to the surface protein of H1N1 were identified from dried fruits of Terminalia chebula (TC). Through competitive inhibition assays, the influenza surface protein, neuraminidase (NA), was identified as the target protein of these four TC-derived compounds. Three compounds were identified by high performance liquid chromatography (HPLC) and liquid chromatography/mass spectrometry (LC/MS), and their anti-H1N1 activities were verified by examining the cytopathic effect (CPE) and by performing a virus yield reduction assay. Further mechanistic studies demonstrated that these three compounds directly bind to NA and inhibit its activity. In summary, we describe here a VAUM that we designed, one that can be used to accurately screen antiviral active compounds in HMs and also help improve the efficiency of screening antiviral drugs found in natural products.

Development of SARS-CoV-2 entry antivirals.

The global outbreak of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) threatened human health and public safety. The development of anti-SARS-CoV-2 therapies have been essential to curb the spread of SARS-CoV-2. Particularly, antivirals targeting viral entry have become an attractive target for the development of anti-SARS-CoV-2 therapies. In this review, we elucidate the mechanism of SARS-CoV-2 viral entry and summarize the development of antiviral inhibitors targeting viral entry. Moreover, we speculate upon future directions toward more potent inhibitors of SARS-CoV-2 entry. This study is expected to provide novel insights for the efficient discovery of promising candidate drugs against the entry of SARS-CoV-2, and contribute to the development of broad-spectrum anti-coronavirus drugs.

An orally active entry inhibitor of influenza A viruses protects mice and synergizes with oseltamivir and baloxavir marboxil.

Seasonal or pandemic illness caused by influenza A viruses (IAVs) is a major public health concern due to the high morbidity and notable mortality. Although there are several approved drugs targeting different mechanisms, the emergence of drug resistance calls for new drug candidates that can be used alone or in combinations. Small-molecule IAV entry inhibitor, ING-1466, binds to hemagglutinin (HA) and blocks HA-mediated viral infection. Here, we show that this inhibitor demonstrates preventive and therapeutic effects in a mouse model of IAV with substantial improvement in the survival rate. When administered orally it elicits a therapeutic effect in mice, even after the well-established infection. Moreover, the combination of ING-1466 with oseltamivir phosphate or baloxavir marboxil enhances the therapeutic effect in a synergistic manner. Overall, ING-1466 has excellent oral bioavailability and in vitro absorption, distribution, metabolism, excretion, and toxicity profile, suggesting that it can be developed for monotherapy or combination therapy for the treatment of IAV infections.

Paving new roads toward the advancement of broad-spectrum antiviral agents.

Broad-spectrum antivirals (BSAs) have the advantageous property of being effective against a wide range of viruses with a single drug, offering a promising therapeutic solution for the largely unmet need in treating both existing and emerging viral infections. In this review, we summarize the current strategies for the development of novel BSAs, focusing on either targeting the commonalities during the replication of multiple viruses or the systemic immunity of humans. In comparison to BSAs that target viral replication, these immuno-modulatory agents possess an expanded spectrum of antiviral activity. However, antiviral immunity is a double-edged sword, and maintaining immune homeostasis ultimately dictates the health status of hosts during viral infections. Therefore, establishing an ideal goal for immuno-modulation in antiviral interventions is crucial. Herein we propose a bionic approach for immuno-modulation inspired by mimicking bats, which possess a more robust immune system for combating viral invasions, compared to humans. In addition, we discuss an empirical approach to treat diverse viral infections using traditional Chinese medicines (TCMs), mainly through bidirectional immuno-modulation to restore the disrupted homeostasis. Advancing our understanding of both the immune system of bats and the mechanisms underlying antiviral TCMs will significantly contribute to the future development of novel BSAs.

Integrated serum pharmacochemistry and investigation of the anti-influenza A virus pneumonia effect of Qingjin Huatan decoction.

ETHNOPHARMACOLOGICAL RELEVANCE: Qingjin Huatan Decoction (QJHTT) consists of 11 herbal medicines: Scutellaria baicalensis Georgi, Gardenia jasminoides J. Ellis, Platycodon grandiflorus (Jacq.) A. DC., Ophiopogon japonicus (Thunb.) Ker Gawl., Morus alba L., Fritillaria thunbergii Miq., Anemarrhena asphodeloides Bunge, Trichosanthes kirilowii Maxim., Citrus reticulata Blanco, Poria cocos (Schw.) Wolf, and Glycyrrhiza uralensis Fisch. As a traditional Chinese medicinal formula, QJHTT has been used for more than 400 years in China. It has shown promising results in treating influenza A virus (IAV) pneumonia. AIM OF THE STUDY: To elusive the specific pharmacological constituents and mechanisms underlying its anti-IAV pneumonia effects. MATERIALS AND METHODS: The components in QJHTT were analyzed through the use of a serum pharmacology-based ultra high-performance liquid chromatography Q- Exactive Orbitrap mass spectrometry (UHPLC-Q Exactive Orbitrap-MS) method. Simultaneously, the dynamic changes in IAV-infected mouse lung viral load, lung index, and expression of lung inflammation factors were monitored by qRT-PCR. RESULTS: We successfully identified 152 chemical components within QJHTT, along with 59 absorbed chemical prototype constituents found in the serum of mice treated with QJHTT. 43.45% of these chemical components and 43.10% of the prototype constituents were derived from the monarch drugs, namely Huangqin and Zhizi, aligning perfectly with traditional Chinese medicine theory. Notably, our analysis led to the discovery of 14 compounds within QJHTT for the first time, three of which were absorbed into the bloodstream. Simultaneously, we observed that QJHTT not only reduced the viral load but also modulated the expression of inflammation factors in the lung tissue including TNF-α, IL-1ß, IL-4, IL-6, IFN-γ, and IL17A. A time-effect analysis further revealed that QJHTT intervention effectively suppressed the peak of inflammatory responses, demonstrating a robust anti-IAV pneumonia effect. CONCLUSIONS: We comprehensively analyzed the pharmacological material basis of QJHTT by a highly sensitive and high-resolution UHPLC-Q Exactive Orbitrap-MS method, and demonstrated its efficacy in combating IAV pneumonia by reducing lung viral load and inflammatory factors. This study has significant importance for elucidating the pharmacological basis and pharmacological mechanism of QJHTT in combating IAV pneumonia.

HMDD v4.0: a database for experimentally supported human microRNA-disease associations.

MicroRNAs (miRNAs) are a class of important small non-coding RNAs with critical molecular functions in almost all biological processes, and thus, they play important roles in disease diagnosis and therapy. Human MicroRNA Disease Database (HMDD) represents an important and comprehensive resource for biomedical researchers in miRNA-related medicine. Here, we introduce HMDD v4.0, which curates 53530 miRNA-disease association entries from literatures. In comparison to HMDD v3.0 released five years ago, HMDD v4.0 contains 1.5 times more entries. In addition, some new categories have been curated, including exosomal miRNAs implicated in diseases, virus-encoded miRNAs involved in human diseases, and entries containing miRNA-circRNA interactions. We also curated sex-biased miRNAs in diseases. Furthermore, in a case study, disease similarity analysis successfully revealed that sex-biased miRNAs related to developmental anomalies are associated with a number of human diseases with sex bias. HMDD can be freely visited at http://www.cuilab.cn/hmdd.

LncRNADisease v3.0: an updated database of long non-coding RNA-associated diseases.

Systematic integration of lncRNA-disease associations is of great importance for further understanding their underlying molecular mechanisms and exploring lncRNA-based biomarkers and therapeutics. The database of long non-coding RNA-associated diseases (LncRNADisease) is designed for the above purpose. Here, an updated version (LncRNADisease v3.0) has curated comprehensive lncRNA (including circRNA) and disease associations from the burgeoning literatures. LncRNADisease v3.0 exhibits an over 2-fold increase in experimentally supported associations, with a total of 25440 entries, compared to the last version. Besides, each lncRNA-disease pair is assigned a confidence score based on experimental evidence. Moreover, all associations between lncRNAs/circRNAs and diseases are classified into general associations and causal associations, representing whether lncRNAs or circRNAs can directly lead to the development or progression of corresponding diseases, with 15721 and 9719 entries, respectively. In a case study, we used the data of LncRNADisease v3.0 to calculate the phenotypic similarity between human and mouse lncRNAs. This database will continue to serve as a valuable resource for potential clinical applications related to lncRNAs and circRNAs. LncRNADisease v3.0 is freely available at http://www.rnanut.net/lncrnadisease.

Identification of the Imidazo[1,2-a]pyrazine Derivative A4 as a Potential Influenza Virus Nucleoprotein Inhibitor.

Influenza A viruses (IAVs) have gradually developed resistance to FDA-approved drugs, which increases the need to discover novel antivirals with new mechanisms of action. Here, we used a phenotypic screening strategy and discovered that the imidazo[1,2-a]pyrazine derivative A4 demonstrates potent and broad-spectrum anti-influenza activity, especially for the oseltamivir-resistant H1N1/pdm09 strain. Indirect immunofluorescence assays revealed that A4 induces clustering of the viral nucleoprotein (NP) and prevents its nuclear accumulation. Furthermore, upon conducting binding analyses between A4 and the influenza NP using surface plasmon resonance assays and molecular docking simulations, we were able to confirm that A4 binds directly to the viral NP. Additionally, A4 exhibits high human plasma metabolic stability (remaining120 min > 90%, T1/2 = 990 min) and moderate inhibitory effects on CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4 as well as low acute toxicity in Kunming mice. Overall, this study provides valuable insights and lays the groundwork for future efforts in medicinal chemistry to identify effective drugs against influenza.

Depleting LCAT Aggravates Atherosclerosis in LDLR-deficient Hamster with Reduced LDL-Cholesterol Level.

INTRODUCTION: Lecithin cholesterol acyltransferase (LCAT) plays a crucial role in acyl-esterifying cholesterol in plasma, which is essential for reverse cholesterol transport (RCT). Previous studies indicated that its activity on both α and ß lipoproteins interpret its effects on lipoproteins for many controversial investigations of atherosclerosis. OBJECTIVES: To better understand the relationship between LCAT, diet-induced dyslipidemia and atherosclerosis, we developed a double knockout (LCAT-/-&LDLR-/-, DKO) hamster model to evaluate the specific role of LCAT independent of LDL clearance effects. METHODS: Plasma triglyceride (TG), total cholesterol (TC), high-density lipoprotein-cholesterol (HDL-C), and free cholesterol (FC) levels were measured using biochemical reagent kits. FPLC was performed to analyze the components of lipoproteins. Apolipoprotein content was assessed using western blotting (WB). The hamsters were fed a high cholesterol/high fat diet (HCHFD) to induce atherosclerosis. Oil Red O staining was employed to detect plaque formation. Peritoneal macrophages were studied to investigate the effects of LCAT on cholesterol uptake and efflux. RESULTS: On HCHFD, DKO hamsters exhibited significantly elevated levels of TG and FC, while HDL-C was nearly undetectable without affecting TC levels, as compared to low-density lipoprotein receptor (LDLR)-deficient (LDLR-/-, LKO) hamsters. Lipoprotein profiling revealed a marked increase in plasma chylomicron/very low-density lipoprotein (CM/VLDL) fractions, along with an unexpected reduction in LDL fraction in DKO hamsters. Furthermore, DKO hamsters displayed aggravated atherosclerotic lesions in the aorta, aortic root, and coronary artery relative to LKO hamsters, attributed to a pro-atherogenic lipoprotein profile and impaired cholesterol efflux in macrophages. CONCLUSIONS: Our study demonstrates the beneficial role of LCAT in inhibiting atherosclerotic development and highlights the distinctive lipid metabolism characteristics in hamsters with familial hypercholesterolemia.

Influenza virus cell entry and targeted antiviral development.

Influenza virus infection is currently one of the most prevalent and transmissible diseases in the world causing local outbreaks every year. It has the potential to cause devastating global pandemics as well. The development of anti-influenza drugs possessing novel mechanisms of action is urgently needed to control the spread of influenza infections; thus, drugs that inhibit influenza virus entry into target cells are emerging as a hot research topic. In addition to discussing the biological significance of hemagglutinin in viral replication, this article provides recent updates on the natural products, small molecules, proteins, peptides, and neutralizing antibody-like proteins that have anti-influenza potency.

Defining the single base importance of human mRNAs and lncRNAs.

As the fundamental unit of a gene and its transcripts, nucleotides have enormous impacts on the gene function and evolution, and thus on phenotypes and diseases. In order to identify the key nucleotides of one specific gene, it is quite crucial to quantitatively measure the importance of each base on the gene. However, there are still no sequence-based methods of doing that. Here, we proposed Base Importance Calculator (BIC), an algorithm to calculate the importance score of each single base based on sequence information of human mRNAs and long noncoding RNAs (lncRNAs). We then confirmed its power by applying BIC to three different tasks. Firstly, we revealed that BIC can effectively evaluate the pathogenicity of both genes and single bases through single nucleotide variations. Moreover, the BIC score in The Cancer Genome Atlas somatic mutations is able to predict the prognosis of some cancers. Finally, we show that BIC can also precisely predict the transmissibility of SARS-CoV-2. The above results indicate that BIC is a useful tool for evaluating the single base importance of human mRNAs and lncRNAs.

A fusion framework of deep learning and machine learning for predicting sgRNA cleavage efficiency.

CRISPR/Cas9 system is a powerful tool for genome editing. Numerous studies have shown that sgRNAs can strongly affect the efficiency of editing. However, it is still not clear what rules should be followed for designing sgRNA with high cleavage efficiency. At present, several machine learning or deep learning methods have been developed to predict the cleavage efficiency of sgRNAs, however, the prediction accuracy of these tools is still not satisfactory. Here we propose a fusion framework of deep learning and machine learning, which first deals with the primary sequence and secondary structure features of the sgRNAs using both convolutional neural network (CNN) and recurrent neural network (RNN), and then uses the features extracted by the deep neural network to train a conventional machine learning model with LGBM. As a result, the new approach overwhelmed previous methods. The Spearman's correlation coefficient between predicted and measured sgRNA cleavage efficiency of our model (0.917) is improved by over 5% compared with the most advanced method (0.865), and the mean square error reduces from 7.89 × 10-3 to 4.75 × 10-3. Finally, we developed an online tool, CRISep (http://www.cuilab.cn/CRISep), to evaluate the availability of sgRNAs based on our models.

Allopregnanolone targets nucleoprotein as a novel influenza virus inhibitor.

Influenza A virus (IAV) poses a global public health concern and remains an imminent threat to human health. Emerging antiviral resistance to the currently approved influenza drugs emphasizes the urgent need for new therapeutic entities against IAV. Allopregnanolone (ALLO) is a natural product that has been approved as an antidepressant drug. In the present study, we repurposed ALLO as a novel inhibitor against IAVs. Mechanistic studies demonstrated that ALLO inhibited virus replication by interfering with the nucleus translocation of viral nucleoprotein (NP). In addition, ALLO showed significant synergistic activity with compound 16, a hemagglutinin inhibitor of IAVs. In summary, we have identified ALLO as a novel influenza virus inhibitor targeting NP, providing a promising candidate that deserves further investigation as a useful anti-influenza strategy in the future.

Detection of diabetic patients in people with normal fasting glucose using machine learning.

BACKGROUND: Diabetes mellitus (DM) is a chronic metabolic disease that could produce severe complications threatening life. Its early detection is thus quite important for the timely prevention and treatment. Normally, fasting blood glucose (FBG) by physical examination is used for large-scale screening of DM; however, some people with normal fasting glucose (NFG) actually have suffered from diabetes but are missed by the examination. This study aimed to investigate whether common physical examination indexes for diabetes can be used to identify the diabetes individuals from the populations with NFG. METHODS: The physical examination data from over 60,000 individuals with NFG in three Chinese cohorts were used. The diabetes patients were defined by HbA1c ≥ 48 mmol/mol (6.5%). We constructed the models using multiple machine learning methods, including logistic regression, random forest, deep neural network, and support vector machine, and selected the optimal one on the validation set. A framework using permutation feature importance algorithm was devised to discover the personalized risk factors. RESULTS: The prediction model constructed by logistic regression achieved the best performance with an AUC, sensitivity, and specificity of 0.899, 85.0%, and 81.1% on the validation set and 0.872, 77.9%, and 81.0% on the test set, respectively. Following feature selection, the final classifier only requiring 13 features, named as DRING (diabetes risk of individuals with normal fasting glucose), exhibited reliable performance on two newly recruited independent datasets, with the AUC of 0.964 and 0.899, the balanced accuracy of 84.2% and 81.1%, the sensitivity of 100% and 76.2%, and the specificity of 68.3% and 86.0%, respectively. The feature importance ranking analysis revealed that BMI, age, sex, absolute lymphocyte count, and mean corpuscular volume are important factors for the risk stratification of diabetes. With a case, the framework for identifying personalized risk factors revealed FBG, age, and BMI as significant hazard factors that contribute to an increased incidence of diabetes. DRING webserver is available for ease of application ( http://www.cuilab.cn/dring ). CONCLUSIONS: DRING was demonstrated to perform well on identifying the diabetes individuals among populations with NFG, which could aid in early diagnosis and interventions for those individuals who are most likely missed.