Archival single-cell genomics reveals persistent subclones during DCIS progression.

Ductal carcinoma in situ (DCIS) is a common precursor of invasive breast cancer. Our understanding of its genomic progression to recurrent disease remains poor, partly due to challenges associated with the genomic profiling of formalin-fixed paraffin-embedded (FFPE) materials. Here, we developed Arc-well, a high-throughput single-cell DNA-sequencing method that is compatible with FFPE materials. We validated our method by profiling 40,330 single cells from cell lines, a frozen tissue, and 27 FFPE samples from breast, lung, and prostate tumors stored for 3-31 years. Analysis of 10 patients with matched DCIS and cancers that recurred 2-16 years later show that many primary DCIS had already undergone whole-genome doubling and clonal diversification and that they shared genomic lineages with persistent subclones in the recurrences. Evolutionary analysis suggests that most DCIS cases in our cohort underwent an evolutionary bottleneck, and further identified chromosome aberrations in the persistent subclones that were associated with recurrence.

Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography.

Many COVID-19 patients infected by SARS-CoV-2 virus develop pneumonia (called novel coronavirus pneumonia, NCP) and rapidly progress to respiratory failure. However, rapid diagnosis and identification of high-risk patients for early intervention are challenging. Using a large computed tomography (CT) database from 3,777 patients, we developed an AI system that can diagnose NCP and differentiate it from other common pneumonia and normal controls. The AI system can assist radiologists and physicians in performing a quick diagnosis especially when the health system is overloaded. Significantly, our AI system identified important clinical markers that correlated with the NCP lesion properties. Together with the clinical data, our AI system was able to provide accurate clinical prognosis that can aid clinicians to consider appropriate early clinical management and allocate resources appropriately. We have made this AI system available globally to assist the clinicians to combat COVID-19.

Engineering IscB to develop highly efficient miniature editing tools in mammalian cells and embryos.

The IscB proteins, as the ancestors of Cas9 endonuclease, hold great promise due to their small size and potential for diverse genome editing. However, their activity in mammalian cells is unsatisfactory. By introducing three residual substitutions in IscB, we observed an average 7.5-fold increase in activity. Through fusing a sequence-non-specific DNA-binding protein domain, the eIscB-D variant achieved higher editing efficiency, with a maximum of 91.3%. Moreover, engineered ωRNA was generated with a 20% reduction in length and slightly increased efficiency. The engineered eIscB-D/eωRNA system showed an average 20.2-fold increase in activity compared with the original IscB. Furthermore, we successfully adapted eIscB-D for highly efficient cytosine and adenine base editing. Notably, eIscB-D is highly active in mouse cell lines and embryos, enabling the efficient generation of disease models through mRNA/ωRNA injection. Our study suggests that these miniature genome-editing tools have great potential for diverse applications.

Genome editing of a rice CDP-DAG synthase confers multipathogen resistance.

The discovery and application of genome editing introduced a new era of plant breeding by giving researchers efficient tools for the precise engineering of crop genomes1. Here we demonstrate the power of genome editing for engineering broad-spectrum disease resistance in rice (Oryza sativa). We first isolated a lesion mimic mutant (LMM) from a mutagenized rice population. We then demonstrated that a 29-base-pair deletion in a gene we named RESISTANCE TO BLAST1 (RBL1) caused broad-spectrum disease resistance and showed that this mutation caused an approximately 20-fold reduction in yield. RBL1 encodes a cytidine diphosphate diacylglycerol synthase that is required for phospholipid biosynthesis2. Mutation of RBL1 results in reduced levels of phosphatidylinositol and its derivative phosphatidylinositol 4,5-bisphosphate (PtdIns(4,5)P2). In rice, PtdIns(4,5)P2 is enriched in cellular structures that are specifically associated with effector secretion and fungal infection, suggesting that it has a role as a disease-susceptibility factor3. By using targeted genome editing, we obtained an allele of RBL1, named RBL1Δ12, which confers broad-spectrum disease resistance but does not decrease yield in a model rice variety, as assessed in small-scale field trials. Our study has demonstrated the benefits of editing an LMM gene, a strategy relevant to diverse LMM genes and crops.

Evolutionary insights from profiling LINE-1 activity at allelic resolution in a single human genome.

Transposable elements have created the majority of the sequence in many genomes. In mammals, LINE-1 retrotransposons have been expanding for more than 100 million years as distinct, consecutive lineages; however, the drivers of this recurrent lineage emergence and disappearance are unknown. Most human genome assemblies provide a record of this ancient evolution, but fail to resolve ongoing LINE-1 retrotranspositions. Utilizing the human CHM1 long-read-based haploid assembly, we identified and cloned all full-length, intact LINE-1s, and found 29 LINE-1s with measurable in vitro retrotransposition activity. Among individuals, these LINE-1s varied in their presence, their allelic sequences, and their activity. We found that recently retrotransposed LINE-1s tend to be active in vitro and polymorphic in the population relative to more ancient LINE-1s. However, some rare allelic forms of old LINE-1s retain activity, suggesting older lineages can persist longer than expected. Finally, in LINE-1s with in vitro activity and in vivo fitness, we identified mutations that may have increased replication in ancient genomes and may prove promising candidates for mechanistic investigations of the drivers of LINE-1 evolution and which LINE-1 sequences contribute to human disease.

Development of 2nd generation aminomethyl spectinomycins that overcome native efflux in Mycobacterium abscessus.

Mycobacterium abscessus (Mab), a nontuberculous mycobacterial (NTM) species, is an emerging pathogen with high intrinsic drug resistance. Current standard-of-care therapy results in poor outcomes, demonstrating the urgent need to develop effective antimycobacterial regimens. Through synthetic modification of spectinomycin (SPC), we have identified a distinct structural subclass of N-ethylene linked aminomethyl SPCs (eAmSPCs) that are up to 64-fold more potent against Mab over the parent SPC. Mechanism of action and crystallography studies demonstrate that the eAmSPCs display a mode of ribosomal inhibition consistent with SPC. However, they exert their increased antimicrobial activity through enhanced accumulation, largely by circumventing efflux mechanisms. The N-ethylene linkage within this series plays a critical role in avoiding TetV-mediated efflux, as lead eAmSPC 2593 displays a mere fourfold susceptibility improvement against Mab ΔtetV, in contrast to the 64-fold increase for SPC. Even a minor shortening of the linkage by a single carbon, akin to 1st generation AmSPC 1950, results in a substantial increase in MICs and a 16-fold rise in susceptibility against Mab ΔtetV. These shifts suggest that longer linkages might modify the kinetics of drug expulsion by TetV, ultimately shifting the equilibrium towards heightened intracellular concentrations and enhanced antimicrobial efficacy. Furthermore, lead eAmSPCs were also shown to synergize with various classes of anti-Mab antibiotics and retain activity against clinical isolates and other mycobacterial strains. Encouraging pharmacokinetic profiles coupled with robust efficacy in Mab murine infection models suggest that eAmSPCs hold the potential to be developed into treatments for Mab and other NTM infections.

Antidepressant Augmentation versus Switch in Treatment-Resistant Geriatric Depression.

BACKGROUND: The benefits and risks of augmenting or switching antidepressants in older adults with treatment-resistant depression have not been extensively studied. METHODS: We conducted a two-step, open-label trial involving adults 60 years of age or older with treatment-resistant depression. In step 1, patients were randomly assigned in a 1:1:1 ratio to augmentation of existing antidepressant medication with aripiprazole, augmentation with bupropion, or a switch from existing antidepressant medication to bupropion. Patients who did not benefit from or were ineligible for step 1 were randomly assigned in step 2 in a 1:1 ratio to augmentation with lithium or a switch to nortriptyline. Each step lasted approximately 10 weeks. The primary outcome was the change from baseline in psychological well-being, assessed with the National Institutes of Health Toolbox Positive Affect and General Life Satisfaction subscales (population mean, 50; higher scores indicate greater well-being). A secondary outcome was remission of depression. RESULTS: In step 1, a total of 619 patients were enrolled; 211 were assigned to aripiprazole augmentation, 206 to bupropion augmentation, and 202 to a switch to bupropion. Well-being scores improved by 4.83 points, 4.33 points, and 2.04 points, respectively. The difference between the aripiprazole-augmentation group and the switch-to-bupropion group was 2.79 points (95% CI, 0.56 to 5.02; P = 0.014, with a prespecified threshold P value of 0.017); the between-group differences were not significant for aripiprazole augmentation versus bupropion augmentation or for bupropion augmentation versus a switch to bupropion. Remission occurred in 28.9% of patients in the aripiprazole-augmentation group, 28.2% in the bupropion-augmentation group, and 19.3% in the switch-to-bupropion group. The rate of falls was highest with bupropion augmentation. In step 2, a total of 248 patients were enrolled; 127 were assigned to lithium augmentation and 121 to a switch to nortriptyline. Well-being scores improved by 3.17 points and 2.18 points, respectively (difference, 0.99; 95% CI, -1.92 to 3.91). Remission occurred in 18.9% of patients in the lithium-augmentation group and 21.5% in the switch-to-nortriptyline group; rates of falling were similar in the two groups. CONCLUSIONS: In older adults with treatment-resistant depression, augmentation of existing antidepressants with aripiprazole improved well-being significantly more over 10 weeks than a switch to bupropion and was associated with a numerically higher incidence of remission. Among patients in whom augmentation or a switch to bupropion failed, changes in well-being and the occurrence of remission with lithium augmentation or a switch to nortriptyline were similar. (Funded by the Patient-Centered Outcomes Research Institute; OPTIMUM ClinicalTrials.gov number, NCT02960763.).

CDHu40: a novel marker gene set of neuroendocrine prostate cancer.

Prostate cancer (PCa) is the most prevalent cancer affecting American men. Castration-resistant prostate cancer (CRPC) can emerge during hormone therapy for PCa, manifesting with elevated serum prostate-specific antigen levels, continued disease progression, and/or metastasis to the new sites, resulting in a poor prognosis. A subset of CRPC patients shows a neuroendocrine (NE) phenotype, signifying reduced or no reliance on androgen receptor signaling and a particularly unfavorable prognosis. In this study, we incorporated computational approaches based on both gene expression profiles and protein-protein interaction networks. We identified 500 potential marker genes, which are significantly enriched in cell cycle and neuronal processes. The top 40 candidates, collectively named CDHu40, demonstrated superior performance in distinguishing NE PCa (NEPC) and non-NEPC samples based on gene expression profiles. CDHu40 outperformed most of the other published marker sets, excelling particularly at the prognostic level. Notably, some marker genes in CDHu40, absent in the other marker sets, have been reported to be associated with NEPC in the literature, such as DDC, FOLH1, BEX1, MAST1, and CACNA1A. Importantly, elevated CDHu40 scores derived from our predictive model showed a robust correlation with unfavorable survival outcomes in patients, indicating the potential of the CDHu40 score as a promising indicator for predicting the survival prognosis of those patients with the NE phenotype. Motif enrichment analysis on the top candidates suggests that REST and E2F6 may serve as key regulators in the NEPC progression.

Engineering APOBEC3A deaminase for highly accurate and efficient base editing.

Cytosine base editors (CBEs) are effective tools for introducing C-to-T base conversions, but their clinical applications are limited by off-target and bystander effects. Through structure-guided engineering of human APOBEC3A (A3A) deaminase, we developed highly accurate A3A-CBE (haA3A-CBE) variants that efficiently generate C-to-T conversion with a narrow editing window and near-background level of DNA and RNA off-target activity, irrespective of methylation status and sequence context. The engineered deaminase domains are compatible with PAM-relaxed SpCas9-NG variant, enabling accurate correction of pathogenic mutations in homopolymeric cytosine sites through flexible positioning of the single-guide RNAs. Dual adeno-associated virus delivery of one haA3A-CBE variant to a mouse model of tyrosinemia induced up to 58.1% editing in liver tissues with minimal bystander editing, which was further reduced through single dose of lipid nanoparticle-based messenger RNA delivery of haA3A-CBEs. These results highlight the tremendous promise of haA3A-CBEs for precise genome editing to treat human diseases.

A bromodomain-independent mechanism of gene regulation by the BET inhibitor JQ1: direct activation of nuclear receptor PXR.

Bromodomain and extraterminal (BET) proteins are extensively studied in multiple pathologies, including cancer. BET proteins modulate transcription of various genes, including those synonymous with cancer, such as MYC. Thus, BET inhibitors are a major area of drug development efforts. (+)-JQ1 (JQ1) is the prototype inhibitor and is a common tool to probe BET functions. While showing therapeutic promise, JQ1 is not clinically usable, partly due to metabolic instability. Here, we show that JQ1 and the BET-inactive (-)-JQ1 are agonists of pregnane X receptor (PXR), a nuclear receptor that transcriptionally regulates genes encoding drug-metabolizing enzymes such as CYP3A4, which was previously shown to oxidize JQ1. A PXR-JQ1 co-crystal structure identified JQ1's tert-butyl moiety as a PXR anchor and explains binding by (-)-JQ1. Analogs differing at the tert-butyl lost PXR binding, validating our structural findings. Evaluation in liver cell models revealed both PXR-dependent and PXR-independent modulation of CYP3A4 expression by BET inhibitors. We have characterized a non-BET JQ1 target, a mechanism of physiological JQ1 instability, a biological function of (-)-JQ1, and BET-dependent transcriptional regulation of drug metabolism genes.

Integrating somatic mutation profiles with structural deep clustering network for metabolic stratification in pancreatic cancer: a comprehensive analysis of prognostic and genomic landscapes.

Pancreatic cancer is a globally recognized highly aggressive malignancy, posing a significant threat to human health and characterized by pronounced heterogeneity. In recent years, researchers have uncovered that the development and progression of cancer are often attributed to the accumulation of somatic mutations within cells. However, cancer somatic mutation data exhibit characteristics such as high dimensionality and sparsity, which pose new challenges in utilizing these data effectively. In this study, we propagated the discrete somatic mutation data of pancreatic cancer through a network propagation model based on protein-protein interaction networks. This resulted in smoothed somatic mutation profile data that incorporate protein network information. Based on this smoothed mutation profile data, we obtained the activity levels of different metabolic pathways in pancreatic cancer patients. Subsequently, using the activity levels of various metabolic pathways in cancer patients, we employed a deep clustering algorithm to establish biologically and clinically relevant metabolic subtypes of pancreatic cancer. Our study holds scientific significance in classifying pancreatic cancer based on somatic mutation data and may provide a crucial theoretical basis for the diagnosis and immunotherapy of pancreatic cancer patients.

A computational framework of routine test data for the cost-effective chronic disease prediction.

Chronic diseases, because of insidious onset and long latent period, have become the major global disease burden. However, the current chronic disease diagnosis methods based on genetic markers or imaging analysis are challenging to promote completely due to high costs and cannot reach universality and popularization. This study analyzed massive data from routine blood and biochemical test of 32 448 patients and developed a novel framework for cost-effective chronic disease prediction with high accuracy (AUC 87.32%). Based on the best-performing XGBoost algorithm, 20 classification models were further constructed for 17 types of chronic diseases, including 9 types of cancers, 5 types of cardiovascular diseases and 3 types of mental illness. The highest accuracy of the model was 90.13% for cardia cancer, and the lowest was 76.38% for rectal cancer. The model interpretation with the SHAP algorithm showed that CREA, R-CV, GLU and NEUT% might be important indices to identify the most chronic diseases. PDW and R-CV are also discovered to be crucial indices in classifying the three types of chronic diseases (cardiovascular disease, cancer and mental illness). In addition, R-CV has a higher specificity for cancer, ALP for cardiovascular disease and GLU for mental illness. The association between chronic diseases was further revealed. At last, we build a user-friendly explainable machine-learning-based clinical decision support system (DisPioneer: http://bioinfor.imu.edu.cn/dispioneer) to assist in predicting, classifying and treating chronic diseases. This cost-effective work with simple blood tests will benefit more people and motivate clinical implementation and further investigation of chronic diseases prevention and surveillance program.

A serpin gene from a parasitoid wasp disrupts host immunity and exhibits adaptive alternative splicing.

Alternative splicing (AS) is a major source of protein diversity in eukaryotes, but less is known about its evolution compared to gene duplication (GD). How AS and GD interact is also largely understudied. By constructing the evolutionary trajectory of the serpin gene PpSerpin-1 (Pteromalus puparum serpin 1) in parasitoids and other insects, we found that both AS and GD jointly contribute to serpin protein diversity. These two processes are negatively correlated and show divergent features in both protein and regulatory sequences. Parasitoid wasps exhibit higher numbers of serpin protein/domains than nonparasitoids, resulting from more GD but less AS in parasitoids. The potential roles of AS and GD in the evolution of parasitoid host-effector genes are discussed. Furthermore, we find that PpSerpin-1 shows an exon expansion of AS compared to other parasitoids, and that several isoforms are involved in the wasp immune response, have been recruited to both wasp venom and larval saliva, and suppress host immunity. Overall, our study provides an example of how a parasitoid serpin gene adapts to parasitism through AS, and sheds light on the differential features of AS and GD in the evolution of insect serpins and their associations with the parasitic life strategy.

Acyl-CoA Synthetase Medium-Chain Family Member 5-Mediated Fatty Acid Metabolism Dysregulation Promotes the Progression of Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is the most common primary liver cancer, with high incidence and mortality worldwide. Despite diagnostic and therapeutic advancements, HCC remains poorly responsive to treatment, with a poor prognosis. Understanding the molecular mechanisms driving HCC is crucial for developing effective therapies. Emerging evidence indicates that dysregulated fatty acid metabolism contributes to HCC. Acyl-CoA medium-chain synthetase 5 (ACSM5), involved in fatty acid metabolism, is down-regulated in HCC; however, its role is not well understood. This study was used to analyze ACSM5 expression in HCC patient samples and cell lines. The newly established ACSM5-overexpressing HCC cell lines, Huh7-ACSM5 and Hepa1-6-ACSM5, were used to investigate the effects and regulatory mechanisms of ACSM5. The results showed that ACSM5 was significantly down-regulated in HCC tumor tissues compared with non-tumor tissues. ACSM5 expression was regulated by DNA methylation, with a DNA methyltransferase 1 (DNMT1) inhibitor effectively increasing ACSM5 expression and reducing promoter region methylation. Overexpression of ACSM5 in Huh7 cells reduced fatty acid accumulation, decreased cell proliferation, migration, and invasion in vitro, and inhibited tumor growth in mouse xenografts. Furthermore, ACSM5 overexpression also decreased STAT3 phosphorylation, subsequently affecting downstream cytokine TGFB and FGF12 mRNA levels. These findings suggest that ACSM5 down-regulation contributes to HCC progression, providing insights into its oncogenic role and highlighting its potential as a biomarker and therapeutic target for HCC.

Basic Transcription Factor 3 Like 4 Enhances Malignant Phenotypes through Modulating Tumor Cell Function and Immune Microenvironment in Glioma.

Recent investigations into the tumor microenvironment have provided insights into the limited response of glioma progression to immunotherapy. However, the specific involvement of basic transcription factor 3 like 4 (BTF3L4) in glioma progression and its correlation with immune cell infiltration remain areas of uncertainty that require further exploration. In the current study, BTF3L4 expression was delineated by using gene expression profiling/interactive analysis and multiplex-immunohistologic staining of tissue microarrays. The prognostic value of BTF3L4 was then assessed by using Cox regression models and Kaplan-Meier methods, and in vitro experiments were conducted to investigate how BTF3L4 protein affects the proliferation, migration, and invasion capabilities of glioma cells. Furthermore, the CIBERSORT and ESTIMATE methods were used to quantify immune cells that correlate to BTF3L4 expression, and multiplex-immunohistologic staining was applied to investigate its correlation with infiltrated immune cells in glioma tissues. These findings revealed higher BTF3L4 expression in glioma tissues compared with non-tumor brain tissues, which correlated with clinical characteristics and worse patient prognosis. Furthermore, the down-regulation of BTF3L4 protein in the glioma cell line had a detrimental effect on cell migration, invasion, and proliferation. In addition, the association between BTF3L4 and key immune molecules in glioma, particularly with the infiltration of CD66B+ neutrophils and programmed death ligand 1 expression, was identified. These results highlight the prognostic significance of BTF3L4 and propose BTF3L4 as a potential target for glioma immune therapy.

The orally bioavailable GSPT1/2 degrader SJ6986 exhibits in vivo efficacy in acute lymphoblastic leukemia.

Advancing cure rates for high-risk acute lymphoblastic leukemia (ALL) has been limited by the lack of agents that effectively kill leukemic cells, sparing normal hematopoietic tissue. Molecular glues direct the ubiquitin ligase cellular machinery to target neosubstrates for protein degradation. We developed a novel cereblon modulator, SJ6986, that exhibits potent and selective degradation of GSPT1 and GSPT2 and cytotoxic activity against childhood cancer cell lines. Here, we report in vitro and in vivo testing of the activity of this agent in a panel of ALL cell lines and xenografts. SJ6986 exhibited similar cytotoxicity to the previously described GSPT1 degrader CC-90009 in a panel of leukemia cell lines in vitro, resulting in apoptosis and perturbation of cell cycle progression. SJ6986 was more effective than CC-90009 in suppressing leukemic cell growth in vivo, partly attributable to favorable pharmacokinetic properties, and did not significantly impair differentiation of human CD34+ cells ex vivo. Genome-wide CRISPR/Cas9 screening of ALL cell lines treated with SJ6986 confirmed that components of the CRL4CRBN complex, associated adaptors, regulators, and effectors were integral in mediating the action of SJ6986. SJ6986 is a potent, selective, orally bioavailable GSPT1/2 degrader that shows broad antileukemic activity and has potential for clinical development.

Association of pre-existing depression and anxiety with Omicron variant infection.

Pre-existing psychiatric disorders were linked to an increased susceptibility to COVID-19 during the initial outbreak of the pandemic, while evidence during Omicron prevalence is lacking. Leveraging data from two prospective cohorts in China, we identified incident Omicron infections between January 2023 and April 2023. Participants with a self-reported history or self-rated symptoms of depression or anxiety before the Omicron pandemic were considered the exposed group, whereas the others were considered unexposed. We employed multivariate logistic regression models to examine the association of pre-existing depression or anxiety with the risk of any or severe Omicron infection indexed by medical interventions or severe symptoms. Further, we stratified the analyses by polygenic risk scores (PRSs) for COVID-19 and repeated the analyses using the UK Biobank data. We included 10,802 individuals from the Chinese cohorts (mean age = 51.1 years, 45.6% male), among whom 7841 (72.6%) were identified as cases of Omicron infection. No association was found between any pre-existing depression or anxiety and the overall risk of Omicron infection (odds ratio [OR] =1.04, 95% confidence interval [CI] 0.95-1.14). However, positive associations were noted for severe Omicron infection, either as infections requiring medical interventions (1.26, 1.02-1.54) or with severe symptoms (≥3: 1.73, 1.51-1.97). We obtained comparable estimates when stratified by COVID-19 PRS level. Additionally, using clustering method, we identified eight distinct symptom patterns and found associations between pre-existing depression or anxiety and the patterns characterized by multiple or complex severe symptoms including cough and taste and smell decline (ORs = 1.42-2.35). The results of the UK Biobank analyses corroborated findings of the Chinese cohorts. In conclusion, pre-existing depression and anxiety was not associated with the risk of Omicron infection overall but an elevated risk of severe Omicron infection, supporting the continued efforts on monitoring and possible early intervention in this high-risk population during Omicron prevalence.

Integrated analysis of patients with bladder cancer from prospective transcription factor activity: Implications for personalized treatment approaches.

Transcription factors are a specialized group of proteins that play important roles in regulating gene expression in human. These proteins control the transcription and translation of genes by binding to specific sites on DNA, thereby regulating key biological processes such as cell differentiation, proliferation, immune response, and neural development. Moreover, transcription factors are also involved in apoptosis and the pathogenesis of various diseases. By investigating transcription factors, researchers can uncover the mechanisms of gene regulation in organisms and develop more effective methods for preventing and treating human diseases. In the present study, the Virtual Inference of Protein-activity by Enriched Regulon algorithm was utilized to calculate the protein activity of transcription factors, and the metabolic-related protein activity were used for classifying bladder cancer patients into different subtype. To identify chemotherapy drugs with clinical benefits, the differences in prognosis and drug sensitivity between two distinct subtypes of bladder cancer patients were investigated. Simultaneously, the master regulators that display varying levels of transcription factor activity between two different bladder cancer subtypes were explored. Additionally, the potential transcriptional regulatory mechanisms and targets of these factors were investigated, thereby generating novel insights into bladder cancer research at the transcriptional regulation level.

Machine learning-based prediction of diabetic patients using blood routine data.

Diabetes stands as one of the most prevalent chronic diseases globally. The conventional methods for diagnosing diabetes are frequently overlooked until individuals manifest noticeable symptoms of the condition. This study aimed to address this gap by collecting comprehensive datasets, including 1000 instances of blood routine data from diabetes patients and an equivalent dataset from healthy individuals. To differentiate diabetes patients from their healthy counterparts, a computational framework was established, encompassing eXtreme Gradient Boosting (XGBoost), random forest, support vector machine, and elastic net algorithms. Notably, the XGBoost model emerged as the most effective, exhibiting superior predictive results with an area under the receiver operating characteristic curve (AUC) of 99.90% in the training set and 98.51% in the testing set. Moreover, the model showcased commendable performance during external validation, achieving an overall accuracy of 81.54%. The probability generated by the model serves as a risk score for diabetes susceptibility. Further interpretability was achieved through the utilization of the Shapley additive explanations (SHAP) algorithm, identifying pivotal indicators such as mean corpuscular hemoglobin concentration (MCHC), lymphocyte ratio (LY%), standard deviation of red blood cell distribution width (RDW-SD), and mean corpuscular hemoglobin (MCH). This enhances our understanding of the predictive mechanisms underlying diabetes. To facilitate the application in clinical and real-life settings, a nomogram was created based on the logistic regression algorithm, which can provide a preliminary assessment of the likelihood of an individual having diabetes. Overall, this research contributes valuable insights into the predictive modeling of diabetes, offering potential applications in clinical practice for more effective and timely diagnoses.