RESUMO
Single-cell Hi-C (scHi-C) is a collection of protocols for studying genomic interactions within individual cells. Although data analysis for scHi-C resembles data analysis for bulk Hi-C, the unique challenges of scHi-C, such as high noise and protocol-specific biases, require specialized data processing strategies. In this tutorial chapter, we focus on using pairtools, a suite of tools optimized for scHi-C data, demonstrating its application on a Drosophila snHi-C dataset. While centered on pairtools for snHi-C data, the principles outlined are applicable across scHi-C variants with minor adjustments. This educational chapter aims to guide researchers in using open-source tools for scHi-C analysis, emphasizing critical steps of contact pair extraction, detection of ligation junctions, filtration, and deduplication.
Assuntos
Genômica , Análise de Célula Única , Software , Fluxo de Trabalho , Análise de Célula Única/métodos , Animais , Genômica/métodos , Drosophila/genética , Sequenciamento de Nucleotídeos em Larga Escala/métodos , Biologia Computacional/métodosRESUMO
We describe an approach for reconstructing three-dimensional (3D) structures from single-cell Hi-C data. This approach has been inspired by a method of recurrence plots and visualization tools for nonlinear time series data. Some examples are also presented.
Assuntos
Análise de Célula Única , Análise de Célula Única/métodos , Imageamento Tridimensional/métodos , Humanos , Software , Cromossomos/genética , AlgoritmosRESUMO
Mass spectrometry imaging (MSI) allows for label-free spatial molecular interrogation of tissues. With advances in the field over recent years, the spatial resolution at which MSI data can be recorded has reached the single-cell level. This makes MSI complementary to other single-cell omics technologies. As metabolism is a highly dynamic process, capturing the metabolic turnover adds a valuable layer of information. Here, we describe how to set up in situ stable isotope tracing followed by MSI-enabled spatial metabolomics to perform dynamic metabolomics at the single-cell level.
Assuntos
Marcação por Isótopo , Metabolômica , Análise de Célula Única , Análise de Célula Única/métodos , Metabolômica/métodos , Marcação por Isótopo/métodos , Espectrometria de Massas/métodos , Animais , Humanos , Imagem Molecular/métodosRESUMO
Transcriptomics is an extremely important area of molecular biology and is a powerful tool for studying all RNA molecules in an organism. Conventional transcriptomic technologies include microarrays and RNA sequencing, and the rapid development of single-cell sequencing and spatial transcriptomics in recent years has provided an enormous scope for research in this field. This chapter describes the application, significance, and experimental procedures of a variety of transcriptomic technologies in antiviral natural immunity.
Assuntos
Perfilação da Expressão Gênica , Imunidade Inata , Transcriptoma , Imunidade Inata/genética , Humanos , Perfilação da Expressão Gênica/métodos , Animais , Viroses/imunologia , Viroses/genética , Análise de Sequência de RNA/métodos , Análise de Célula Única/métodos , Análise de Sequência com Séries de Oligonucleotídeos/métodosRESUMO
Recent technological advances in single-cell RNA sequencing (scRNA-Seq) have enabled scientists to answer novel questions in biology with unparalleled precision. Indeed, in the field of ocular development and regeneration, scRNA-Seq studies have resulted in a number of exciting discoveries that have begun to revolutionize the way we think about these processes. Despite the widespread success of scRNA-Seq, many scientists are wary to perform scRNA-Seq experiments due to the uncertainty of obtaining high-quality viable cell populations that are necessary for the generation of usable data that enable rigorous computational analyses. Here, we describe methodology to reproducibility generate high-quality single-cell suspensions from embryonic zebrafish eyes. These single-cell suspensions served as inputs to the 10× Genomics v3.1 system and yielded high-quality scRNA-Seq data in proof-of-principle studies. In describing methodology to quantitatively assess cell yields, cell viability, and other critical quality control parameters, this protocol can serve as a useful starting point for others in designing their scRNA-Seq experiments in the zebrafish eye and in other developing or regenerating tissues in zebrafish or other model systems.
Assuntos
Retina , Análise de Sequência de RNA , Análise de Célula Única , Peixe-Zebra , Animais , Peixe-Zebra/genética , Peixe-Zebra/embriologia , Análise de Célula Única/métodos , Retina/citologia , Retina/embriologia , Retina/metabolismo , Análise de Sequência de RNA/métodos , Separação Celular/métodosRESUMO
The generation of quality data from a single-nucleus profiling experiment requires nuclei to be isolated from tissues in a gentle and efficient manner. Nuclei isolation must be carefully optimized across tissue types to preserve nuclear architecture, prevent nucleic acid degradation, and remove unwanted contaminants. Here, we present an optimized workflow for generating a single-nucleus suspension from ocular tissues of the embryonic chicken that is compatible with various downstream workflows. The described protocol enables the rapid isolation of a high yield of aggregate-free nuclei from the embryonic chicken eye without compromising nucleic acid integrity, and the nuclei suspension is compatible with single-nucleus RNA and ATAC sequencing. We detail several stopping points, either via cryopreservation or fixation, to enhance workflow adaptability. Further, we provide a guide through multiple QC points and demonstrate proof-of-principle using two commercially available kits. Finally, we demonstrate that existing in silico genotyping methods can be adopted to computationally derive biological replicates from a single pool of chicken nuclei, greatly reducing the cost of biological replication and allowing researchers to consider sex as a variable during analysis. Together, this tutorial represents a cost-effective, simple, and effective approach to single-nucleus profiling of embryonic chicken eye tissues and is likely to be easily modified to be compatible with similar tissue types.
Assuntos
Núcleo Celular , Galinhas , Análise de Célula Única , Animais , Núcleo Celular/metabolismo , Núcleo Celular/genética , Embrião de Galinha , Análise de Célula Única/métodos , Olho/embriologia , Olho/metabolismo , Criopreservação/métodos , Sequenciamento de Cromatina por Imunoprecipitação/métodosRESUMO
Retinal degenerative diseases including age-related macular degeneration and glaucoma are estimated to currently affect more than 14 million people in the United States, with an increased prevalence of retinal degenerations in aged individuals. An expanding aged population who are living longer forecasts an increased prevalence and economic burden of visual impairments. Improvements to visual health and treatment paradigms for progressive retinal degenerations slow vision loss. However, current treatments fail to remedy the root cause of visual impairments caused by retinal degenerations-loss of retinal neurons. Stimulation of retinal regeneration from endogenous cellular sources presents an exciting treatment avenue for replacement of lost retinal cells. In multiple species including zebrafish and Xenopus, Müller glial cells maintain a highly efficient regenerative ability to reconstitute lost cells throughout the organism's lifespan, highlighting potential therapeutic avenues for stimulation of retinal regeneration in humans. Here, we describe how the application of single-cell RNA-sequencing (scRNA-seq) has enhanced our understanding of Müller glial cell-derived retinal regeneration, including the characterization of gene regulatory networks that facilitate/inhibit regenerative responses. Additionally, we provide a validated experimental framework for cellular preparation of mouse retinal cells as input into scRNA-seq experiments, including insights into experimental design and analyses of resulting data.
Assuntos
Células Ependimogliais , Retina , Análise de Célula Única , Animais , Camundongos , Análise de Célula Única/métodos , Retina/metabolismo , Células Ependimogliais/metabolismo , Regeneração/genética , Análise de Sequência de RNA/métodos , Degeneração Retiniana/genética , Degeneração Retiniana/terapia , RNA-Seq/métodos , Modelos Animais de DoençasRESUMO
Single-cell technology depicts integrated tumor profiles including both tumor cells and tumor microenvironments, which theoretically enables more robust diagnosis than traditional diagnostic standards based on only pathology. However, the inherent challenges of single-cell RNA sequencing (scRNA-seq) data, such as high dimensionality, low signal-to-noise ratio (SNR), sparse and non-Euclidean nature, pose significant obstacles for traditional diagnostic approaches. The diagnostic value of single-cell technology has been largely unexplored despite the potential advantages. Here, we present a graph neural network-based framework tailored for molecular diagnosis of primary liver tumors using scRNA-seq data. Our approach capitalizes on the biological plausibility inherent in the intercellular communication networks within tumor samples. By integrating pathway activation features within cell clusters and modeling unidirectional inter-cellular communication, we achieve robust discrimination between malignant tumors (including hepatocellular carcinoma, HCC, and intrahepatic cholangiocarcinoma, iCCA) and benign tumors (focal nodular hyperplasia, FNH) by scRNA data of all tissue cells and immunocytes only. The efficacy to distinguish iCCA from HCC was further validated on public datasets. Through extending the application of high-throughput scRNA-seq data into diagnosis approaches focusing on integrated tumor microenvironment profiles rather than a few tumor markers, this framework also sheds light on minimal-invasive diagnostic methods based on migrating/circulating immunocytes.
Assuntos
Neoplasias Hepáticas , Redes Neurais de Computação , Análise de Célula Única , Humanos , Neoplasias Hepáticas/diagnóstico , Neoplasias Hepáticas/genética , Neoplasias Hepáticas/patologia , Análise de Célula Única/métodos , RNA/metabolismo , Carcinoma Hepatocelular/diagnóstico , Carcinoma Hepatocelular/genética , Carcinoma Hepatocelular/patologia , Análise de Sequência de RNARESUMO
A recent paper claimed that t-SNE and UMAP embeddings of single-cell datasets are "specious" and fail to capture true biological structure. The authors argued that such embeddings are as arbitrary and as misleading as forcing the data into an elephant shape. Here we show that this conclusion was based on inadequate and limited metrics of embedding quality. More appropriate metrics quantifying neighborhood and class preservation reveal the elephant in the room: while t-SNE and UMAP embeddings of single-cell data do not preserve high-dimensional distances, they can nevertheless provide biologically relevant information.
Assuntos
Biologia Computacional , Análise de Célula Única , Análise de Célula Única/métodos , Análise de Célula Única/estatística & dados numéricos , Biologia Computacional/métodos , Algoritmos , Humanos , AnimaisRESUMO
Single-cell RNA sequencing (scRNA-seq) technologies can generate transcriptomic profiles at a single-cell resolution in large patient cohorts, facilitating discovery of gene and cellular biomarkers for disease. Yet, when the number of biomarker genes is large, the translation to clinical applications is challenging due to prohibitive sequencing costs. Here, we introduce scPanel, a computational framework designed to bridge the gap between biomarker discovery and clinical application by identifying a sparse gene panel for patient classification from the cell population(s) most responsive to perturbations (e.g. diseases/drugs). scPanel incorporates a data-driven way to automatically determine a minimal number of informative biomarker genes. Patient-level classification is achieved by aggregating the prediction probabilities of cells associated with a patient using the area under the curve score. Application of scPanel to scleroderma, colorectal cancer, and COVID-19 datasets resulted in high patient classification accuracy using only a small number of genes (<20), automatically selected from the entire transcriptome. In the COVID-19 case study, we demonstrated cross-dataset generalizability in predicting disease state in an external patient cohort. scPanel outperforms other state-of-the-art gene selection methods for patient classification and can be used to identify parsimonious sets of reliable biomarker candidates for clinical translation.
Assuntos
COVID-19 , Análise de Célula Única , Humanos , COVID-19/genética , COVID-19/virologia , Análise de Célula Única/métodos , Biologia Computacional/métodos , Transcriptoma , RNA-Seq/métodos , Neoplasias Colorretais/genética , Neoplasias Colorretais/classificação , Perfilação da Expressão Gênica/métodos , SARS-CoV-2/genética , Análise de Sequência de RNA/métodos , Software , Análise da Expressão Gênica de Célula ÚnicaRESUMO
The field of computational drug repurposing aims to uncover novel therapeutic applications for existing drugs through high-throughput data analysis. However, there is a scarcity of drug repurposing methods leveraging the cellular-level information provided by single-cell RNA sequencing data. To address this need, we propose DrugReSC, an innovative approach to drug repurposing utilizing single-cell RNA sequencing data, intending to target specific cell subpopulations critical to disease pathology. DrugReSC constructs a drug-by-cell matrix representing the transcriptional relationships between individual cells and drugs and utilizes permutation-based methods to assess drug contributions to cellular phenotypic changes. We demonstrate DrugReSC's superior performance compared to existing drug repurposing methods based on bulk or single-cell RNA sequencing data across multiple cancer case studies. In summary, DrugReSC offers a novel perspective on the utilization of single-cell sequencing data in drug repurposing methods, contributing to the advancement of precision medicine for cancer.
Assuntos
Reposicionamento de Medicamentos , Neoplasias , Análise de Célula Única , Transcriptoma , Reposicionamento de Medicamentos/métodos , Humanos , Neoplasias/tratamento farmacológico , Neoplasias/genética , Neoplasias/patologia , Neoplasias/metabolismo , Análise de Célula Única/métodos , Biologia Computacional/métodos , Análise de Sequência de RNA/métodos , Antineoplásicos/farmacologia , Antineoplásicos/uso terapêuticoRESUMO
Solid tumours exhibit a well-defined architecture, comprising a differentiated core and a dynamic border that interfaces with the surrounding tissue. This border, characterised by distinct cellular morphology and molecular composition, serves as a critical determinant of the tumour's invasive behaviour. Notably, the invasive border of the primary tumour represents the principal site for intravasation of metastatic cells. These cells, known as circulating tumour cells (CTCs), function as 'seeds' for distant dissemination and display remarkable heterogeneity. Advancements in spatial sequencing technology are progressively unveiling the spatial biological features of tumours. However, systematic investigations specifically targeting the characteristics of the tumour border remain scarce. In this comprehensive review, we illuminate key biological insights along the tumour body-border-haematogenous metastasis axis over the past five years. We delineate the distinctive landscape of tumour invasion boundaries and delve into the intricate heterogeneity and phenotype of CTCs, which orchestrate haematogenous metastasis. These insights have the potential to explain the basis of tumour invasion and distant metastasis, offering new perspectives for the development of more complex and precise clinical interventions and treatments.
Assuntos
Invasividade Neoplásica , Metástase Neoplásica , Células Neoplásicas Circulantes , Análise de Célula Única , Humanos , Metástase Neoplásica/genética , Análise de Célula Única/métodos , Invasividade Neoplásica/genética , Células Neoplásicas Circulantes/metabolismo , Células Neoplásicas Circulantes/patologia , Neoplasias/patologia , Neoplasias/metabolismo , Neoplasias/genéticaRESUMO
This study investigates the impact of Hashimoto's thyroiditis (HT), an autoimmune disorder, on the papillary thyroid cancer (PTC) microenvironment using a dataset of 140,456 cells from 11 patients. By comparing PTC cases with and without HT, we identify HT-specific cell populations (HASCs) and their role in creating a TSH-suppressive environment via mTE3, nTE0, and nTE2 thyroid cells. These cells facilitate intricate immune-stromal communication through the MIF-(CD74+CXCR4) axis, emphasizing immune regulation in the TSH context. In the realm of personalized medicine, our HASC-focused analysis within the TCGA-THCA dataset validates the utility of HASC profiling for guiding tailored therapies. Moreover, we introduce a novel, objective method to determine K-means clustering coefficients in copy number variation inference from bulk RNA-seq data, mitigating the arbitrariness in conventional coefficient selection. Collectively, our research presents a detailed single-cell atlas illustrating HT-PTC interactions, deepening our understanding of HT's modulatory effects on PTC microenvironments. It contributes to our understanding of autoimmunity-carcinogenesis dynamics and charts a course for discovering new therapeutic targets in PTC, advancing cancer genomics and immunotherapy research.
Assuntos
Doença de Hashimoto , Análise de Célula Única , Câncer Papilífero da Tireoide , Neoplasias da Glândula Tireoide , Microambiente Tumoral , Humanos , Doença de Hashimoto/patologia , Câncer Papilífero da Tireoide/patologia , Neoplasias da Glândula Tireoide/patologia , Análise de Célula Única/métodos , Feminino , MasculinoRESUMO
Dysregulated DNA replication is a cause and a consequence of aneuploidy in cancer, yet the interplay between copy number alterations (CNAs), replication timing (RT) and cell cycle dynamics remain understudied in aneuploid tumors. We developed a probabilistic method, PERT, for simultaneous inference of cell-specific replication and copy number states from single-cell whole genome sequencing (scWGS) data. We used PERT to investigate clone-specific RT and proliferation dynamics in >50,000 cells obtained from aneuploid and clonally heterogeneous cell lines, xenografts and primary cancers. We observed bidirectional relationships between RT and CNAs, with CNAs affecting X-inactivation producing the largest RT shifts. Additionally, we found that clone-specific S-phase enrichment positively correlated with ground-truth proliferation rates in genomically stable but not unstable cells. Together, these results demonstrate robust computational identification of S-phase cells from scWGS data, and highlight the importance of RT and cell cycle properties in studying the genomic evolution of aneuploid tumors.
Assuntos
Aneuploidia , Proliferação de Células , Variações do Número de Cópias de DNA , Período de Replicação do DNA , Análise de Célula Única , Humanos , Análise de Célula Única/métodos , Proliferação de Células/genética , Neoplasias/genética , Neoplasias/patologia , Fase S/genética , Animais , Linhagem Celular Tumoral , Sequenciamento Completo do Genoma , Ciclo Celular/genética , Análise de Sequência de DNA/métodos , Replicação do DNA/genética , CamundongosRESUMO
Isogenic bacterial cell populations are phenotypically heterogenous and may include subpopulations of antibiotic tolerant or heteroresistant cells. The reversibility of these phenotypes and lack of biomarkers to differentiate functionally different, but morphologically identical cells is a challenge for research and clinical detection. To overcome this, we present ´Cellular Phenotypic Profiling and backTracing (CPPT)´, a fluorescence-activated cell sorting platform that uses fluorescent probes to visualize and quantify cellular traits and connects this phenotypic profile with a cell´s experimentally determined fate in single cell-derived growth and antibiotic susceptibility analysis. By applying CPPT on Staphylococcus aureus we phenotypically characterized dormant cells, exposed bimodal growth patterns in colony-derived cells and revealed different culturability of single cells on solid compared to liquid media. We demonstrate that a fluorescent vancomycin conjugate marks cellular subpopulations of vancomycin-intermediate S. aureus with increased likelihood to survive antibiotic exposure, showcasing the value of CPPT for discovery of clinically relevant biomarkers.
Assuntos
Antibacterianos , Fenótipo , Análise de Célula Única , Staphylococcus aureus , Staphylococcus aureus/genética , Staphylococcus aureus/efeitos dos fármacos , Análise de Célula Única/métodos , Antibacterianos/farmacologia , Citometria de Fluxo/métodos , Vancomicina/farmacologia , Testes de Sensibilidade Microbiana , Humanos , Infecções Estafilocócicas/microbiologiaRESUMO
BACKGROUND: Single-cell RNA sequencing (scRNA-seq) technology has emerged as a crucial tool for studying cellular heterogeneity. However, dropouts are inherent to the sequencing process, known as dropout events, posing challenges in downstream analysis and interpretation. Imputing dropout data becomes a critical concern in scRNA-seq data analysis. Present imputation methods predominantly rely on statistical or machine learning approaches, often overlooking inter-sample correlations. RESULTS: To address this limitation, We introduced SAE-Impute, a new computational method for imputing single-cell data by combining subspace regression and auto-encoders for enhancing the accuracy and reliability of the imputation process. Specifically, SAE-Impute assesses sample correlations via subspace regression, predicts potential dropout values, and then leverages these predictions within an autoencoder framework for interpolation. To validate the performance of SAE-Impute, we systematically conducted experiments on both simulated and real scRNA-seq datasets. These results highlight that SAE-Impute effectively reduces false negative signals in single-cell data and enhances the retrieval of dropout values, gene-gene and cell-cell correlations. Finally, We also conducted several downstream analyses on the imputed single-cell RNA sequencing (scRNA-seq) data, including the identification of differential gene expression, cell clustering and visualization, and cell trajectory construction. CONCLUSIONS: These results once again demonstrate that SAE-Impute is able to effectively reduce the droupouts in single-cell dataset, thereby improving the functional interpretability of the data.
Assuntos
Análise de Sequência de RNA , Análise de Célula Única , Análise de Célula Única/métodos , Análise de Sequência de RNA/métodos , Biologia Computacional/métodos , Algoritmos , Humanos , Aprendizado de Máquina , SoftwareRESUMO
BACKGROUND: Single-cell RNA sequencing (scRNAseq) offers powerful insights, but the surge in sample sizes demands more computational power than local workstations can provide. Consequently, high-performance computing (HPC) systems have become imperative. Existing web apps designed to analyze scRNAseq data lack scalability and integration capabilities, while analysis packages demand coding expertise, hindering accessibility. RESULTS: In response, we introduce scRNAbox, an innovative scRNAseq analysis pipeline meticulously crafted for HPC systems. This end-to-end solution, executed via the SLURM workload manager, efficiently processes raw data from standard and Hashtag samples. It incorporates quality control filtering, sample integration, clustering, cluster annotation tools, and facilitates cell type-specific differential gene expression analysis between two groups. We demonstrate the application of scRNAbox by analyzing two publicly available datasets. CONCLUSION: ScRNAbox is a comprehensive end-to-end pipeline designed to streamline the processing and analysis of scRNAseq data. By responding to the pressing demand for a user-friendly, HPC solution, scRNAbox bridges the gap between the growing computational demands of scRNAseq analysis and the coding expertise required to meet them.
Assuntos
Análise de Sequência de RNA , Análise de Célula Única , Software , Análise de Célula Única/métodos , Análise de Sequência de RNA/métodos , Humanos , Biologia Computacional/métodosRESUMO
BACKGROUND: Breast cancer (BC) is the most common cancer in women and poses a significant health burden, especially in China. Despite advances in diagnosis and treatment, patient variability and limited early detection contribute to poor outcomes. This study examines the role of CD8 + T cells in the tumor microenvironment to identify new biomarkers that improve prognosis and guide treatment strategies. METHODS: CD8 + T-cell marker genes were identified using single-cell RNA sequencing (scRNA-seq), and a CD8 + T cell-related gene prognostic signature (CTRGPS) was developed using 10 machine-learning algorithms. The model was validated across seven independent public datasets from the GEO database. Clinical features and previously published signatures were also analyzed for comparison. The clinical applications of CTRGPS in biological function, immune microenvironment, and drug selection were explored, and the role of hub genes in BC progression was further investigated. RESULTS: We identified 71 CD8 + T cell-related genes and developed the CTRGPS, which demonstrated significant prognostic value, with higher risk scores linked to poorer overall survival (OS). The model's accuracy and robustness were confirmed through Kaplan-Meier and ROC curve analyses across multiple datasets. CTRGPS outperformed existing prognostic signatures and served as an independent prognostic factor. The role of the hub gene TTK in promoting malignant proliferation and migration of BC cells was validated. CONCLUSION: The CTRGPS enhances early diagnosis and treatment precision in BC, improving clinical outcomes. TTK, a key gene in the signature, shows promise as a therapeutic target, supporting the CTRGPS's potential clinical utility.
Assuntos
Biomarcadores Tumorais , Neoplasias da Mama , Linfócitos T CD8-Positivos , Aprendizado de Máquina , Microambiente Tumoral , Humanos , Linfócitos T CD8-Positivos/imunologia , Linfócitos T CD8-Positivos/metabolismo , Feminino , Neoplasias da Mama/genética , Neoplasias da Mama/terapia , Neoplasias da Mama/imunologia , Neoplasias da Mama/patologia , Prognóstico , Microambiente Tumoral/imunologia , Microambiente Tumoral/genética , Biomarcadores Tumorais/genética , Imunoterapia/métodos , Marcadores Genéticos , Regulação Neoplásica da Expressão Gênica , Análise de Célula Única/métodosRESUMO
Single-cell cross-modal joint clustering has been extensively utilized to investigate the tumor microenvironment. Although numerous approaches have been suggested, accurate clustering remains the main challenge. First, the gene expression matrix frequently contains numerous missing values due to measurement limitations. The majority of existing clustering methods treat it as a typical multi-modal dataset without further processing. Few methods conduct recovery before clustering and do not sufficiently engage with the underlying research, leading to suboptimal outcomes. Additionally, the existing cross-modal information fusion strategy does not ensure consistency of representations across different modes, potentially leading to the integration of conflicting information, which could degrade performance. To address these challenges, we propose the 'Recover then Aggregate' strategy and introduce the Unified Cross-Modal Deep Clustering model. Specifically, we have developed a data augmentation technique based on neighborhood similarity, iteratively imposing rank constraints on the Laplacian matrix, thus updating the similarity matrix and recovering dropout events. Concurrently, we integrate cross-modal features and employ contrastive learning to align modality-specific representations with consistent ones, enhancing the effective integration of diverse modal information. Comprehensive experiments on five real-world multi-modal datasets have demonstrated this method's superior effectiveness in single-cell clustering tasks.
Assuntos
Análise de Célula Única , Análise por Conglomerados , Análise de Célula Única/métodos , Humanos , Algoritmos , Microambiente Tumoral , Biologia Computacional/métodosRESUMO
Lupus nephritis (LN) is a challenging condition with limited diagnostic and treatment options. In this study, we applied 12 distinct machine learning algorithms along with Non-negative Matrix Factorization (NMF) to analyze single-cell datasets from kidney biopsies, aiming to provide a comprehensive profile of LN. Through this analysis, we identified various immune cell populations and their roles in LN progression and constructed 102 machine learning-based immune-related gene (IRG) predictive models. The most effective models demonstrated high predictive accuracy, evidenced by Area Under the Curve (AUC) values, and were further validated in external cohorts. These models highlight six hub IRGs (CD14, CYBB, IFNGR1, IL1B, MSR1, and PLAUR) as key diagnostic markers for LN, showing remarkable diagnostic performance in both renal and peripheral blood cohorts, thus offering a novel approach for noninvasive LN diagnosis. Further clinical correlation analysis revealed that expressions of IFNGR1, PLAUR, and CYBB were negatively correlated with the glomerular filtration rate (GFR), while CYBB also positively correlated with proteinuria and serum creatinine levels, highlighting their roles in LN pathophysiology. Additionally, protein-protein interaction (PPI) analysis revealed significant networks involving hub IRGs, emphasizing the importance of the interleukin family and chemokines in LN pathogenesis. This study highlights the potential of integrating advanced genomic tools and machine learning algorithms to improve diagnosis and personalize management of complex autoimmune diseases like LN.