Common progenitor origin for Rosai-Dorfman disease and clear cell sarcoma.

Histiocytic neoplasms (HNs) in adults have been reported to be associated with a high prevalence of coexisting haematological and solid malignancies. While a proportion of coexisting HNs and haematological malignancies share identical genetic alterations, the genetic association between HNs and solid malignancies has scarcely been reported. We report a case of Rosai-Dorfman disease (RDD) complicated by coexisting clear cell sarcoma (CCS). RDD is a rare HN. CCS is an ultrarare soft tissue sarcoma with a poor prognosis. Mutation analysis with whole-exome sequencing revealed six shared somatic alterations including NRAS p.G12S and TP53 c.559+1G>A in both the RDD and CCS tissue. This is the first evidence of a clonal relationship between RDD and solid malignancies using mutational analysis. We hypothesise that neural crest cells, which originate in CCS, are likely the common cells of origin for RDD and CCS. This case helps to unravel the underlying clinicopathological mechanisms of increased association of solid malignancies in HNs. © 2024 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Preexisting senescent fibroblasts in the aged bladder create a tumor-permissive niche through CXCL12 secretion.

Aging is a major risk factor for cancer, but the precise mechanism by which aging promotes carcinogenesis remains largely unknown. Here, using genetically modified mouse models, we show that p16high senescent (p16h-sn) fibroblasts accumulate with age, constitute inflammatory cancer-associated fibroblasts (CAFs) and promote tumor growth in bladder cancer models. Single-cell RNA sequencing of fibroblasts from aged mice revealed higher expression of the C-X-C motif chemokine 12 gene (Cxcl12) in p16h-sn fibroblasts than in p16low fibroblasts. Elimination of p16h-sn cells or inhibition of CXCL12 signaling notebly suppressed bladder tumor growth in vivo. We identified high expression levels of SMOC2, GUCY1A1 (GUCY1A3), CXCL12, CRISPLD2, GAS1 and LUM as a signature of p16h-sn CAFs in humans and mice, which was associated with age and poor prognosis in patients with advanced and nonadvanced bladder cancer. Here we show that p16h-sn fibroblasts in the aged bladder create a cancer-permissive niche and promote tumor growth by secreting CXCL12.

Deep learning approaches for non-coding genetic variant effect prediction: current progress and future prospects.

Recent advancements in high-throughput sequencing technologies have significantly enhanced our ability to unravel the intricacies of gene regulatory processes. A critical challenge in this endeavor is the identification of variant effects, a key factor in comprehending the mechanisms underlying gene regulation. Non-coding variants, constituting over 90% of all variants, have garnered increasing attention in recent years. The exploration of gene variant impacts and regulatory mechanisms has spurred the development of various deep learning approaches, providing new insights into the global regulatory landscape through the analysis of extensive genetic data. Here, we provide a comprehensive overview of the development of the non-coding variants models based on bulk and single-cell sequencing data and their model-based interpretation and downstream tasks. This review delineates the popular sequencing technologies for epigenetic profiling and deep learning approaches for discerning the effects of non-coding variants. Additionally, we summarize the limitations of current approaches in variant effect prediction research and outline opportunities for improvement. We anticipate that our study will offer a practical and useful guide for the bioinformatic community to further advance the unraveling of genetic variant effects.

IVEA: an integrative variational Bayesian inference method for predicting enhancer-gene regulatory interactions.

Motivation: Enhancers play critical roles in cell-type-specific transcriptional control. Despite the identification of thousands of candidate enhancers, unravelling their regulatory relationships with their target genes remains challenging. Therefore, computational approaches are needed to accurately infer enhancer-gene regulatory relationships. Results: In this study, we propose a new method, IVEA, that predicts enhancer-gene regulatory interactions by estimating promoter and enhancer activities. Its statistical model is based on the gene regulatory mechanism of transcriptional bursting, which is characterized by burst size and frequency controlled by promoters and enhancers, respectively. Using transcriptional readouts, chromatin accessibility, and chromatin contact data as inputs, promoter and enhancer activities were estimated using variational Bayesian inference, and the contribution of each enhancer-promoter pair to target gene transcription was calculated. Our analysis demonstrates that the proposed method can achieve high prediction accuracy and provide biologically relevant enhancer-gene regulatory interactions. Availability and implementation: The IVEA code is available on GitHub at https://github.com/yasumasak/ivea. The publicly available datasets used in this study are described in Supplementary Table S4.

Genome analysis through image processing with deep learning models.

Genomic sequences are traditionally represented as strings of characters: A (adenine), C (cytosine), G (guanine), and T (thymine). However, an alternative approach involves depicting sequence-related information through image representations, such as Chaos Game Representation (CGR) and read pileup images. With rapid advancements in deep learning (DL) methods within computer vision and natural language processing, there is growing interest in applying image-based DL methods to genomic sequence analysis. These methods involve encoding genomic information as images or integrating spatial information from images into the analytical process. In this review, we summarize three typical applications that use image processing with DL models for genome analysis. We examine the utilization and advantages of these image-based approaches.

An enterococcal phage-derived enzyme suppresses graft-versus-host disease.

Changes in the gut microbiome have pivotal roles in the pathogenesis of acute graft-versus-host disease (aGVHD) after allogenic haematopoietic cell transplantation (allo-HCT)1-6. However, effective methods for safely resolving gut dysbiosis have not yet been established. An expansion of the pathogen Enterococcus faecalis in the intestine, associated with dysbiosis, has been shown to be a risk factor for aGVHD7-10. Here we analyse the intestinal microbiome of patients with allo-HCT, and find that E. faecalis escapes elimination and proliferates in the intestine by forming biofilms, rather than by acquiring drug-resistance genes. We isolated cytolysin-positive highly pathogenic E. faecalis from faecal samples and identified an anti-E. faecalis enzyme derived from E. faecalis-specific bacteriophages by analysing bacterial whole-genome sequencing data. The antibacterial enzyme had lytic activity against the biofilm of E. faecalis in vitro and in vivo. Furthermore, in aGVHD-induced gnotobiotic mice that were colonized with E. faecalis or with patient faecal samples characterized by the domination of Enterococcus, levels of intestinal cytolysin-positive E. faecalis were decreased and survival was significantly increased in the group that was treated with the E. faecalis-specific enzyme, compared with controls. Thus, administration of a phage-derived antibacterial enzyme that is specific to biofilm-forming pathogenic E. faecalis-which is difficult to eliminate with existing antibiotics-might provide an approach to protect against aGVHD.

Dual-stream multi-dependency graph neural network enables precise cancer survival analysis.

Histopathology image-based survival prediction aims to provide a precise assessment of cancer prognosis and can inform personalized treatment decision-making in order to improve patient outcomes. However, existing methods cannot automatically model the complex correlations between numerous morphologically diverse patches in each whole slide image (WSI), thereby preventing them from achieving a more profound understanding and inference of the patient status. To address this, here we propose a novel deep learning framework, termed dual-stream multi-dependency graph neural network (DM-GNN), to enable precise cancer patient survival analysis. Specifically, DM-GNN is structured with the feature updating and global analysis branches to better model each WSI as two graphs based on morphological affinity and global co-activating dependencies. As these two dependencies depict each WSI from distinct but complementary perspectives, the two designed branches of DM-GNN can jointly achieve the multi-view modeling of complex correlations between the patches. Moreover, DM-GNN is also capable of boosting the utilization of dependency information during graph construction by introducing the affinity-guided attention recalibration module as the readout function. This novel module offers increased robustness against feature perturbation, thereby ensuring more reliable and stable predictions. Extensive benchmarking experiments on five TCGA datasets demonstrate that DM-GNN outperforms other state-of-the-art methods and offers interpretable prediction insights based on the morphological depiction of high-attention patches. Overall, DM-GNN represents a powerful and auxiliary tool for personalized cancer prognosis from histopathology images and has great potential to assist clinicians in making personalized treatment decisions and improving patient outcomes.

HLA Typing and Mutation Calling from Normal and Tumor Whole Genome Sequencing Data with ALPHLARD-NT.

HLA somatic mutations can alter the expression and function of HLA molecules, which in turn affect the ability of the immune system to recognize and respond to cancer cells. Therefore, it is crucial to accurately identify HLA somatic mutations to enhance our understanding of the interaction between cancer and the immune system and improve cancer treatment strategies. ALPHLARD-NT is a reliable tool that can accurately identify HLA somatic mutations as well as HLA genotypes from whole genome sequencing data of paired normal and tumor samples. Here, we provide a comprehensive guide on how to use ALPHLARD-NT and interpret the results.

biotextgraph: graphical summarization of functional similarities from textual information.

SUMMARY: Functional interpretation of biological entities such as differentially expressed genes is one of the fundamental analyses in bioinformatics. The task can be addressed by using biological pathway databases with enrichment analysis (EA). However, textual description of biological entities in public databases is less explored and integrated in existing tools and it has a potential to reveal new mechanisms. Here, we present a new R package biotextgraph for graphical summarization of omics' textual description data which enables assessment of functional similarities of the lists of biological entities. We illustrate application examples of annotating gene identifiers in addition to EA. The results suggest that the visualization based on words and inspection of biological entities with text can reveal a set of biologically meaningful terms that could not be obtained by using biological pathway databases alone. The results suggest the usefulness of the package in the routine analysis of omics-related data. The package also offers a web-based application for convenient querying. AVAILABILITY AND IMPLEMENTATION: The package, documentation, and web server are available at: https://github.com/noriakis/biotextgraph.

Prognostic significance of chronic kidney disease and impaired renal function in Japanese patients with COVID-19.

BACKGROUND: Renal impairment is a predictor of coronavirus disease (COVID-19) severity. No studies have compared COVID-19 outcomes in patients with chronic kidney disease (CKD) and patients with impaired renal function without a prior diagnosis of CKD. This study aimed to identify the impact of pre-existing impaired renal function without CKD on COVID-19 outcomes. METHODS: This retrospective study included 3,637 patients with COVID-19 classified into three groups by CKD history and estimated glomerular filtration rate (eGFR) on referral: Group 1 (n = 2,460), normal renal function without a CKD history; Group 2 (n = 905), impaired renal function without a CKD history; and Group 3 (n = 272), history of CKD. We compared the clinical characteristics of these groups and assessed the effect of CKD and impaired renal function on critical outcomes (requirement for respiratory support with high-flow oxygen devices, invasive mechanical ventilation, or extracorporeal membrane oxygen, and death during hospitalization) using multivariable logistic regression. RESULTS: The prevalence of comorbidities (hypertension, diabetes, and cardiovascular disease) and incidence of inflammatory responses (white blood counts, and C-reactive protein, procalcitonin, and D-dimer levels) and complications (bacterial infection and heart failure) were higher in Groups 2 and 3 than that in Group 1. The incidence of critical outcomes was 10.8%, 17.7%, and 26.8% in Groups 1, 2, and 3, respectively. The mortality rate and the rate of requiring IMV support was lowest in Group 1 and highest in Group 3. Compared with Group 1, the risk of critical outcomes was higher in Group 2 (adjusted odds ratio [aOR]: 1.32, 95% confidence interval [CI]: 1.03-1.70, P = 0.030) and Group 3 (aOR: 1.94, 95% CI: 1.36-2.78, P < 0.001). Additionally, the eGFR was significantly associated with critical outcomes in Groups 2 (odds ratio [OR]: 2.89, 95% CI: 1.64-4.98, P < 0.001) and 3 (OR: 1.87, 95% CI: 1.08-3.23, P = 0.025) only. CONCLUSIONS: Clinicians should consider pre-existing CKD and impaired renal function at the time of COVID-19 diagnosis for the management of COVID-19.

Pathogenicity Prediction of Gene Fusion in Structural Variations: A Knowledge Graph-Infused Explainable Artificial Intelligence (XAI) Framework.

When analyzing cancer sample genomes in clinical practice, many structural variants (SVs), other than single nucleotide variants (SNVs), have been identified. To identify driver variants, the leading candidates must be narrowed down. When fusion genes are involved, selection is particularly difficult, and highly accurate predictions from AI is important. Furthermore, we also wanted to determine how the prediction can make more reliable diagnoses. Here, we developed an explainable AI (XAI) suitable for SVs with gene fusions, based on the XAI technology we previously developed for the prediction of SNV pathogenicity. To cope with gene fusion variants, we added new data to the previous knowledge graph for SVs and we improved the algorithm. Its prediction accuracy was as high as that of existing tools. Moreover, our XAI could explain the reasons for these predictions. We used some variant examples to demonstrate that the reasons are plausible in terms of pathogenic basic mechanisms. These results can be seen as a hopeful step toward the future of genomic medicine, where efficient and correct decisions can be made with the support of AI.

CT-derived vertebral bone mineral density is a useful biomarker to predict COVID-19 outcome.

The low vertebral bone computed tomography (CT) Hounsfield unit values measured on CT scans reflect low bone mineral density (BMD) and are known as diagnostic indicators for osteoporosis. The potential prognostic significance of low BMD defined by vertebral bone CT values for the coronavirus disease 2019 (COVID-19) remains unclear. This study aimed to assess the impact of BMD on the clinical outcome in Japanese patients with COVID-19 and evaluate the association between BMD and critical outcomes, such as high-flow nasal cannula, non-invasive and invasive positive pressure ventilation, extracorporeal membrane oxygenation, or death. We examined the effects of COVID-19 severity on the change of BMD over time. This multicenter retrospective cohort study enrolled 1132 inpatients with COVID-19 from the Japan COVID-19 Task Force database between February 2020 and September 2022. The bone CT values of the 4th, 7th, and 10th thoracic vertebrae were measured from chest CT images. The average of these values was defined as BMD. Furthermore, a comparative analysis was conducted between the BMD on admission and its value 3 months later. The low BMD group had a higher proportion of critical outcomes than did the high BMD group. In a subanalysis stratifying patients by epidemic wave according to onset time, critical outcomes were higher in the low BMD group in the 1st-4th waves. Multivariable logistic analysis of previously reported factors associated with COVID-19 severity revealed that low BMD, chronic kidney disease, and diabetes were independently associated with critical outcomes. At 3 months post-infection, patients with oxygen demand during hospitalization showed markedly decreased BMD than did those on admission. Low BMD in patients with COVID-19 may help predict severe disease after the disease onset. BMD may decrease over time in patients with severe COVID-19, and the impact on sequelae symptoms should be investigated in the future.

Lung volume measurement using chest CT in COVID-19 patients: a cohort study in Japan.

OBJECTIVE: This study aimed to investigate the utility of CT quantification of lung volume for predicting critical outcomes in COVID-19 patients. METHODS: This retrospective cohort study included 1200 hospitalised patients with COVID-19 from 4 hospitals. Lung fields were extracted using artificial intelligence-based segmentation, and the percentage of the predicted (%pred) total lung volume (TLC (%pred)) was calculated. The incidence of critical outcomes and posthospitalisation complications was compared between patients with low and high CT lung volumes classified based on the median percentage of predicted TLCct (n=600 for each). Prognostic factors for residual lung volume loss were investigated in 208 patients with COVID-19 via a follow-up CT after 3 months. RESULTS: The incidence of critical outcomes was higher in the low TLCct (%pred) group than in the high TLCct (%pred) group (14.2% vs 3.3%, p<0.0001). Multivariable analysis of previously reported factors (age, sex, body mass index and comorbidities) demonstrated that CT-derived lung volume was significantly associated with critical outcomes. The low TLCct (%pred) group exhibited a higher incidence of bacterial infection, heart failure, thromboembolism, liver dysfunction and renal dysfunction than the high TLCct (%pred) group. TLCct (%pred) at 3 months was similarly divided into two groups at the median (71.8%). Among patients with follow-up CT scans, lung volumes showed a recovery trend from the time of admission to 3 months but remained lower in critical cases at 3 months. CONCLUSION: Lower CT lung volume was associated with critical outcomes, posthospitalisation complications and slower improvement of clinical conditions in COVID-19 patients.

M2 macrophage-derived TGF-ß induces age-associated loss of adipogenesis through progenitor cell senescence.

OBJECTIVES: Adipose tissue is an endocrine and energy storage organ composed of several different cell types, including mature adipocytes, stromal cells, endothelial cells, and a variety of immune cells. Adipose tissue aging contributes to the pathogenesis of metabolic dysfunction and is likely induced by crosstalk between adipose progenitor cells (APCs) and immune cells, but the underlying molecular mechanisms remain largely unknown. In this study, we revealed the biological role of p16high senescent APCs, and investigated the crosstalk between each cell type in the aged white adipose tissue. METHODS: We performed the single-cell RNA sequencing (scRNA-seq) analysis on the p16high adipose cells sorted from aged p16-CreERT2/Rosa26-LSL-tdTomato mice. We also performed the time serial analysis on the age-dependent bulk RNA-seq datasets of human and mouse white adipose tissues to infer the transcriptome alteration of adipogenic potential within aging. RESULTS: We show that M2 macrophage-derived TGF-ß induces APCs senescence which impairs adipogenesis in vivo. p16high senescent APCs increase with age and show loss of adipogenic potential. The ligand-receptor interaction analysis reveals that M2 macrophages are the donors for TGF-ß and the senescent APCs are the recipients. Indeed, treatment of APCs with TGF-ß1 induces senescent phenotypes through mitochondrial ROS-mediated DNA damage in vitro. TGF-ß1 injection into gonadal white adipose tissue (gWAT) suppresses adipogenic potential and induces fibrotic genes as well as p16 in APCs. A gWAT atrophy is observed in cancer cachexia by APCs senescence, whose induction appeared to be independent of TGF-ß induction. CONCLUSIONS: Our results suggest that M2 macrophage-derived TGF-ß induces age-related lipodystrophy by APCs senescence. The TGF-ß treatment induced DNA damage, mitochondrial ROS, and finally cellular senescence in APCs.

[Durable remission of T-cell prolymphocytic leukemia with CLEC16A::IL2 after allogeneic hematopoietic stem cell transplantation].

A 64-year-old woman presented with fine motor impairment in both hands. MRI revealed a contrast-enhanced lesion in the medulla oblongata. Lymphoid cells with abnormal blebs were observed and a CD4+/CD8+ double positive (DP) T cell population was detected by flow cytometry (FCM) in the bone marrow (BM) and the peripheral blood (PB). CLEC16A::IL2 fusion gene was identified by whole exome sequencing with DNA prepared from DP T cells. Clonal rearrangement of the T-cell receptor gene and expression of TCL1A protein were detected. This led to a diagnosis of T-cell prolymphocytic leukemia (T-PLL) with central nervous system (CNS) infiltration. Abnormal cells in BM and PB became undetectable on microscopy and FCM, and the CNS lesion disappeared on MRI after second-line therapy with alemtuzumab. Meanwhile, the CLEC16A::IL2 fusion mRNA remained detectable in PB. Allogeneic hematopoietic stem-cell transplantation was performed, and the fusion mRNA has now been undetectable for more than 5 years since transplantation. This is the first report of a T-PLL case with a CLEC16A::IL2 fusion gene.

Integrated assessment of computed tomography density in pectoralis and erector spinae muscles as a prognostic biomarker for coronavirus disease 2019.

BACKGROUND ＆ AIMS: Muscle quantification using chest computed tomography (CT) is a useful prognostic biomarker for coronavirus disease 2019 (COVID-19). However, no studies have evaluated the clinical course through comprehensive assessment of the pectoralis and erector spinae muscles. Therefore, we compared the impact of the areas and densities of these muscles on COVID-19 infection outcome. METHODS: This multicenter retrospective cohort study was conducted by the COVID-19 Task Force. A total of 1410 patients with COVID-19 were included, and data on the area and density of the pectoralis and erector spinae muscles on chest CT were collected. The impact of each muscle parameter on the clinical outcome of COVID-19 was stratified according to sex. The primary outcome was the percentage of patients with severe disease, including those requiring oxygen supplementation and those who died. Additionally, 167 patients were followed up for changes in muscle parameters at three months and for the clinical characteristics in case of reduced CT density. RESULTS: For both muscles, low density rather than muscle area was associated with COVID-19 severity. Regardless of sex, lower erector spinae muscle density was associated with more severe disease than pectoralis muscle density. The muscles were divided into two groups using the receiver operating characteristic curve of CT density, and the population was classified into four (Group A: high CT density for both muscles, Group B: low CT density for pectoralis and high for erector spinae muscle. Group C: high CT density for pectoralis and low for erector spinae muscle, Group D: low CT density for both muscles). In univariate analysis, Group D patients exhibited worse outcomes than Group A (OR: 2.96, 95% CI: 2.03-4.34 in men; OR: 3.02, 95% CI: 2.66-10.4 in women). Multivariate analysis revealed that men in Group D had a significantly more severe prognosis than those in Group A (OR: 1.82, 95% CI: 1.16-2.87). Moreover, Group D patients tended to have the highest incidence of other complications due to secondary infections and acute kidney injury during the clinical course. Longitudinal analysis of both muscle densities over three months revealed that patients with decreased muscle density over time were more likely to have severe cases than those who did not. CONCLUSIONS: Muscle density, rather than muscle area, predicts the clinical outcomes of COVID-19. Integrated assessment of pectoralis and erector spinae muscle densities demonstrated higher accuracy in predicting the clinical course of COVID-19 than individual assessments.

Machine Learning Prediction Model for Neutrophil Recovery after Unrelated Cord Blood Transplantation.

Delayed neutrophil recovery is an important limitation to the administration of cord blood transplantation (CBT) and leaves the recipient vulnerable to life-threatening infection and increases the risk of other complications. A predictive model for neutrophil recovery after single-unit CBT was developed by using a machine learning method, which can handle large and complex datasets, allowing for the analysis of massive amounts of information to uncover patterns and make accurate predictions. Japanese registry data, the largest real-world dataset of CBT, was selected as the data source. Ninety-eight variables with observed values for >80% of the subjects known at the time of CBT were selected. Model building was performed with a competing risk regression model with lasso penalty. Prediction accuracy of the models was evaluated by calculating the area under the receiver operating characteristic curve (AUC) using a test dataset. The primary outcome was neutrophil recovery at day (D) 28, with recovery at D14 and D42 analyzed as secondary outcomes. The final cord blood engraftment prediction (CBEP) models included 2991 single-unit CBT recipients with acute leukemia. The median AUC of a D28-CBEP lasso regression model run 100 times was .74, and those for D14 and D42 were .88 and .68, respectively. The predictivity of the D28-CBEP model was higher than that of 4 different legacy models constructed separately. A highly predictive model for neutrophil recovery by 28 days after CBT was constructed using machine learning techniques; however, identification of significant risk factors was insufficient for outcome prediction for an individual patient, which is necessary for improving therapeutic outcomes. Notably, the prediction accuracy for post-transplantation D14, D28, and D42 decreased, and the model became more complex with more associated factors with increased time after transplantation.

Gastrointestinal symptoms in COVID-19 and disease severity: a Japanese registry-based retrospective cohort study.

BACKGROUND: Research on whether gastrointestinal symptoms correlate with the severity of Coronavirus Disease 2019 (COVID-19) has been inconclusive. This study aimed to clarify any associations between gastrointestinal symptoms and the prognosis of COVID-19. METHODS: We collected data from the Japanese nationwide registry for COVID-19 to conduct a retrospective cohort study. Data from 3498 Japanese COVID-19 patients, diagnosed at 74 facilities between February 2020 and August 2022, were analyzed in this study. Hospitalized patients were followed up until discharge or transfer to another hospital. Outpatients were observed until the end of treatment. Associations between gastrointestinal symptoms and clinical outcomes were investigated using multivariable-adjusted logistic regression models. RESULTS: The prevalence of diarrhea, nausea/vomiting, abdominal pain, and melena were 16.6% (581/3498), 8.9% (311/3498), 3.5% (121/3498), and 0.7% (23/3498), respectively. In the univariable analysis, admission to intensive care unit (ICU) and requirement for mechanical ventilation were less common in patients with diarrhea than those without (ICU, 15.7% vs. 20.6% (p = 0.006); mechanical ventilation, 7.9% vs. 11.4% (p = 0.013)). In the multivariable-adjusted analysis, diarrhea was associated with lower likelihood of ICU admission (adjusted odds ratio (aOR), 0.70; 95% confidence interval (CI), 0.53-0.92) and mechanical ventilation (aOR, 0.61; 95% CI, 0.42-0.89). Similar results were obtained in a sensitivity analysis with another logistic regression model that adjusted for 14 possible covariates with diarrhea (ICU; aOR, 0.70; 95% CI, 0.53-0.93; mechanical ventilation; aOR 0.62; 95% CI, 0.42-0.92). CONCLUSIONS: Diarrhea was associated with better clinical outcomes in COVID-19 patients.

Predicting cell types with supervised contrastive learning on cells and their types.

Single-cell RNA-sequencing (scRNA-seq) is a powerful technique that provides high-resolution expression profiling of individual cells. It significantly advances our understanding of cellular diversity and function. Despite its potential, the analysis of scRNA-seq data poses considerable challenges related to multicollinearity, data imbalance, and batch effect. One of the pivotal tasks in single-cell data analysis is cell type annotation, which classifies cells into discrete types based on their gene expression profiles. In this work, we propose a novel modeling formalism for cell type annotation with a supervised contrastive learning method, named SCLSC (Supervised Contrastive Learning for Single Cell). Different from the previous usage of contrastive learning in single cell data analysis, we employed the contrastive learning for instance-type pairs instead of instance-instance pairs. More specifically, in the cell type annotation task, the contrastive learning is applied to learn cell and cell type representation that render cells of the same type to be clustered in the new embedding space. Through this approach, the knowledge derived from annotated cells is transferred to the feature representation for scRNA-seq data. The whole training process becomes more efficient when conducting contrastive learning for cell and their types. Our experiment results demonstrate that the proposed SCLSC method consistently achieves superior accuracy in predicting cell types compared to five state-of-the-art methods. SCLSC also performs well in identifying cell types in different batch groups. The simplicity of our method allows for scalability, making it suitable for analyzing datasets with a large number of cells. In a real-world application of SCLSC to monitor the dynamics of immune cell subpopulations over time, SCLSC demonstrates a capability to discriminate cell subtypes of CD19+ B cells that were not present in the training dataset.