Deciphering Abnormal Platelet Subpopulations in Inflammatory Diseases through Machine Learning and Single-Cell Transcriptomics (preprint)

The study focuses on understanding the transcriptional heterogeneity of activated platelets and its impact on diseases like sepsis, COVID-19, and systemic lupus erythematosus (SLE). Recognizing the limited knowledge in this area, our research aims to dissect the complex transcriptional profiles of activated platelets to aid in developing targeted therapies for abnormal and pathogenic platelet subtypes. We analyzed single-cell transcriptional profiles from 47,977 platelets derived from 413 samples of patients with these diseases, utilizing Deep Neural Network (DNN) and eXtreme Gradient Boosting (XGB) to distinguish transcriptomic signatures predictive of fatal or survival outcomes. Our approach included source data annotations and platelet markers, along with SingleR and Seurat for comprehensive profiling. Additionally, we employed Uniform Manifold Approximation and Projection (UMAP) for effective dimensionality reduction and visualization, aiding in the identification of various platelet subtypes and their relation to disease severity and patient outcomes. Our results highlighted distinct platelet subpopulations that correlate with disease severity, revealing that changes in platelet transcription patterns can intensify endotheliopathy, increasing the risk of coagulation in fatal cases. Moreover, these changes also seem to impact lymphocyte function, indicating a more extensive role for platelets in inflammatory and immune responses. This study sheds light on the crucial role of platelet heterogeneity in serious health conditions, paving the way for innovative therapeutic approaches targeting platelet activation, which could potentially improve patient outcomes in diseases characterized by altered platelet function.

Deciphering Abnormal Platelet Subpopulations in Inflammatory Diseases through Machine Learning and Single-Cell Transcriptomics (preprint)

IntroductionThe transcriptional heterogeneity of activated platelets, play a significant role in contributing to negative outcomes in sepsis, COVID-19, and autoimmune diseases such as systemic lupus erythematosus (SLE). Despite this, our understanding of these heterogeneous platelet responses remains limited. In this study, we aim to investigate the diverse transcriptional profiles of activated platelets in these diseases, with the goal of deciphering this platelet heterogeneity for new therapeutic strategies to target abnormal and pathogenic platelet subtypes. Materials and methodsWe obtained the single cell transcriptional profiles of blood platelets from patients with COVID-19, sepsis, and SLE. Utilizing machine learning algorithms, Deep Neural Network (DNN) and eXtreme Gradient Boosting (XGB), we discerned the distinct transcriptomic signatures indicative of fatal versus survival clinical outcomes. Our methodological framework incorporated source data annotations and platelet markers and used SingleR and Seurat for detailed profiling. Additionally, we implemented Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction and visualization, aiding in the detection of various platelet subtypes and their correlation with disease status and patient outcomes. ResultsOur study identified distinct platelet subpopulations that are associated with disease severity. We demonstrated that alterations in platelet transcription patterns can exacerbate endotheliopathy, potentially heightening the risk of coagulation in fatal patients. Moreover, these changes can also influence lymphocyte function, indicating a more extensive role for platelets in inflammatory and immune responses. ConclusionsEnhanced transcriptional heterogeneity in activated platelets is linked to adverse outcomes in conditions such as sepsis, COVID-19, and autoimmune diseases. The discovery of these unique platelet subpopulations paves the way for innovative therapeutic strategies targeting platelet activation, which could potentially improve patient outcomes. Summary sentenceSingle-Cell RNA Sequencing Analysis of Platelets from COVID-19, Sepsis, and SLE Reveals Disease Signatures and Treatment Options to Prevent Patient Mortality. Graphical AbstractsO_LIThe platelet to T cell ratio proportion in PBMC was identified as the most potent predictor for distinguishing survivors from fatal patients, underscores the potential of this ratio as a prognostic biomarker. C_LIO_LIThe discovery of different platelet subgroups, especially active coagulation, hypoxic, and quiescent clusters, in fatal COVID-19 patients, indicates potential targeted treatment strategies. C_LIO_LIIn patients with severe and fatal conditions, we observed three key phenomena: the aggregation of platelets with monocytes, the amplification of endothelial dysfunction by platelets, and a decrease in lymphocyte activation and differentiation due to platelets. C_LI O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=197 SRC="FIGDIR/small/572680v1_ufig1.gif" ALT="Figure 1"> View larger version (64K): org.highwire.dtl.DTLVardef@141ca55org.highwire.dtl.DTLVardef@4ad1aborg.highwire.dtl.DTLVardef@b400forg.highwire.dtl.DTLVardef@9ad44e_HPS_FORMAT_FIGEXP M_FIG C_FIG

Health disparities in COVID-19: Immune and vascular changes are linked to disease severity and persist in a high-risk population in Riverside County, California (preprint)

Background Disparities in COVID-19 disease outcomes exist in Hispanic individuals, especially those with pre-existing health conditions. Infected individuals can develop “long COVID” with sustained impacts on overall quality of life. The goal of this study was to investigate the impact of COVID-19 infection and long COVID in Hispanic individuals and identify immune and endothelial factors that are associated with COVID-19 outcomes.Methods 112 participants in Riverside County, California, were recruited and categorized according to the following criteria: healthy control (n = 23), moderate infection (outpatient, n = 33), and severe infection (hospitalized, n = 33). Differences in outcomes between Hispanic and non-Hispanic individuals and presence/absence of comorbidities were evaluated. Circulating immune and vascular biomarkers and immune cell subsets were measured by ELISA, multiplex analyte assays, and flow cytometry. Follow-up assessments for long COVID, lung health, and immune and vascular changes were conducted (n = 23) including paired analyses of the same participants.Results Compared to uninfected controls, the severe infection group had a higher proportion of Hispanic individuals (n = 23, p = 0.012), but there was no difference between uninfected controls and those with moderate infection (n = 8, p = 0.550). Disease severity was associated with changes in innate monocytes and neutrophils and lymphopenia, disrupted cytokine production (increased IL-8 and IP-10/CXCL10 but reduced IFNλ2/3 and IFNγ), and increased endothelial injury (myoglobin, VCAM-1). In the severe infection group, integration of parameters through machine learning identified NGAL/LCN2, IL-6, and monocyte activation as parameters associated with fatality, whereas anti-coagulant therapy was linked to survival. Recovery from moderate COVID infection resulted in long-term immune changes including increased monocytes/lymphocytes and decreased neutrophils and endothelial markers. This group had a lower proportion of comorbidities (n = 8, p = 1.0) but still reported symptoms associated with long COVID despite recovered lung health.Conclusion This study indicates increased severity of COVID-19 infections in Hispanic individuals of Riverside County, California. Infection resulted in immunological and vascular changes and long COVID symptoms that were sustained for up to 11 months, however, lung function (volume and airflow resistance) was recovered. Given the behavioral and immune impacts of long COVID, the potential for increased susceptibility to infections and decreased quality of life, especially in high-risk populations, warrants further investigation.