scholarly journals Unsupervised machine learning reveals key immune cell subsets in COVID-19, rhinovirus infection, and cancer therapy

eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Sierra M Barone ◽  
Alberta GA Paul ◽  
Lyndsey M Muehling ◽  
Joanne A Lannigan ◽  
William W Kwok ◽  
...  
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Immune Cell ◽  
Single Cell Analysis ◽  
Blast Crisis ◽  
Therapy Response ◽  
Immune Monitoring ◽  
Emerging Diseases ◽  
Rhinovirus Infection ◽  
Systems Immunology

For an emerging disease like COVID-19, systems immunology tools may quickly identify and quantitatively characterize cells associated with disease progression or clinical response. With repeated sampling, immune monitoring creates a real-time portrait of the cells reacting to a novel virus before disease specific knowledge and tools are established. However, single cell analysis tools can struggle to reveal rare cells that are under 0.1% of the population. Here, the machine learning workflow Tracking Responders Expanding (T-REX) was created to identify changes in both very rare and common cells in diverse human immune monitoring settings. T-REX identified cells that were highly similar in phenotype and localized to hotspots of significant change during rhinovirus and SARS-CoV-2 infections. Specialized reagents used to detect the rhinovirus-specific CD4+ cells, MHCII tetramers, were not used during unsupervised analysis and instead 'left out' to serve as a test of whether T-REX identified biologically significant cells. In the rhinovirus challenge study, T-REX identified virus-specific CD4+ T cells based on these cells being a distinct phenotype that expanded by ≥95% following infection. T-REX successfully identified hotspots containing virus-specific T cells using pairs of samples comparing Day 7 of infection to samples taken either prior to infection (Day 0) or after clearing the infection (Day 28). Mapping pairwise comparisons in samples according to both the direction and degree of change provided a framework to compare systems level immune changes during infectious disease or therapy response. This revealed that the magnitude and direction of systemic immune change in some COVID-19 patients was comparable to that of blast crisis acute myeloid leukemia patients undergoing induction chemotherapy and characterized the identity of the immune cells that changed the most. Other COVID-19 patients instead matched an immune trajectory like that of individuals with rhinovirus infection or melanoma patients receiving checkpoint inhibitor therapy. T-REX analysis of paired blood samples provides an approach to rapidly identify and characterize mechanistically significant cells and to place emerging diseases into a systems immunology context.

scholarly journals Unsupervised machine learning reveals key immune cell subsets in COVID-19, rhinovirus infection, and cancer therapy

2020 ◽  
Author(s):  
Sierra M. Barone ◽  
Alberta G.A. Paul ◽  
Lyndsey M. Muehling ◽  
Joanne A. Lannigan ◽  
William W. Kwok ◽  
...  
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Immune Cell ◽  
Single Cell Analysis ◽  
Blast Crisis ◽  
Therapy Response ◽  
Immune Monitoring ◽  
Emerging Diseases ◽  
Rhinovirus Infection ◽  
Systems Immunology

AbstractFor an emerging disease like COVID-19, systems immunology tools may quickly identify and quantitatively characterize cells associated with disease progression or clinical response. With repeated sampling, immune monitoring creates a real-time portrait of the cells reacting to a novel virus before disease specific knowledge and tools are established. However, single cell analysis tools can struggle to reveal rare cells that are under 0.1% of the population. Here, the machine learning workflow Tracking Responders Expanding (T-REX) was created to identify changes in both very rare and common cells in diverse human immune monitoring settings. T-REX identified cells that were highly similar in phenotype and localized to hotspots of significant change during rhinovirus and SARS-CoV-2 infections. Specialized reagents used to detect the rhinovirus-specific CD4+ cells, MHCII tetramers, were not used during unsupervised analysis and instead ‘left out’ to serve as a test of whether T-REX identified biologically significant cells. In the rhinovirus challenge study, T-REX identified virus-specific CD4+ T cells based on these cells being a distinct phenotype that expanded by ≥95% following infection. T-REX successfully identified hotspots containing virus-specific T cells using pairs of samples comparing Day 7 of infection to samples taken either prior to infection (Day 0) or after clearing the infection (Day 28). Mapping pairwise comparisons in samples according to both the direction and degree of change provided a framework to compare systems level immune changes during infectious disease or therapy response. This revealed that the magnitude and direction of systemic immune change in some COVID-19 patients was comparable to that of blast crisis acute myeloid leukemia patients undergoing induction chemotherapy and characterized the identity of the immune cells that changed the most. Other COVID-19 patients instead matched an immune trajectory like that of individuals with rhinovirus infection or melanoma patients receiving checkpoint inhibitor therapy. T-REX analysis of paired blood samples provides an approach to rapidly identify and characterize mechanistically significant cells and to place emerging diseases into a systems immunology context.

scholarly journals Immune Monitoring during Therapy Reveals Activitory and Regulatory Immune Responses in High-Risk Neuroblastoma

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2096
Author(s):  
Celina L. Szanto ◽  
Annelisa M. Cornel ◽  
Sara M. Tamminga ◽  
Eveline M. Delemarre ◽  
Coco C. H. de Koning ◽  
...  
Keyword(s):  
T Cells ◽  
High Risk ◽  
Nk Cells ◽  
Immune Cell ◽  
High Dose Chemotherapy ◽  
Immune Monitoring ◽  
High Dose ◽  
Effector Cells ◽  
Gm Csf ◽  
Immune Cell Subsets

Despite intensive treatment, including consolidation immunotherapy (IT), prognosis of high-risk neuroblastoma (HR-NBL) is poor. Immune status of patients over the course of treatment, and thus immunological features potentially explaining therapy efficacy, are largely unknown. In this study, the dynamics of immune cell subsets and their function were explored in 25 HR-NBL patients at diagnosis, during induction chemotherapy, before high-dose chemotherapy, and during IT. The dynamics of immune cells varied largely between patients. IL-2- and GM-CSF-containing IT cycles resulted in significant expansion of effector cells (NK-cells in IL-2 cycles, neutrophils and monocytes in GM-CSF cycles). Nonetheless, the cytotoxic phenotype of NK-cells was majorly disturbed at the start of IT, and both IL-2 and GM-CSF IT cycles induced preferential expansion of suppressive regulatory T-cells. Interestingly, proliferative capacity of purified patient T-cells was impaired at diagnosis as well as during therapy. This study indicates the presence of both immune-enhancing as well as regulatory responses in HR-NBL patients during (immuno)therapy. Especially the double-edged effects observed in IL-2-containing IT cycles are interesting, as this potentially explains the absence of clinical benefit of IL-2 addition to IT cycles. This suggests that there is a need to combine anti-GD2 with more specific immune-enhancing strategies to improve IT outcome in HR-NBL.

scholarly journals Single-Cell Analysis of the Neonatal Immune System Across the Gestational Age Continuum

2021 ◽  
Vol 12 ◽  
Author(s):  
Laura S. Peterson ◽  
Julien Hedou ◽  
Edward A. Ganio ◽  
Ina A. Stelzer ◽  
Dorien Feyaerts ◽  
...  
Keyword(s):  
T Cells ◽  
Immune System ◽  
Single Cell ◽  
Gestational Age ◽  
Immune Cell ◽  
Single Cell Analysis ◽  
Inflammatory Diseases ◽  
Interferon Α ◽  
Cytotoxic Lymphocytes ◽  
Neonatal Immune System

Although most causes of death and morbidity in premature infants are related to immune maladaptation, the premature immune system remains poorly understood. We provide a comprehensive single-cell depiction of the neonatal immune system at birth across the spectrum of viable gestational age (GA), ranging from 25 weeks to term. A mass cytometry immunoassay interrogated all major immune cell subsets, including signaling activity and responsiveness to stimulation. An elastic net model described the relationship between GA and immunome (R=0.85, p=8.75e-14), and unsupervised clustering highlighted previously unrecognized GA-dependent immune dynamics, including decreasing basal MAP-kinase/NFκB signaling in antigen presenting cells; increasing responsiveness of cytotoxic lymphocytes to interferon-α; and decreasing frequency of regulatory and invariant T cells, including NKT-like cells and CD8+CD161+ T cells. Knowledge gained from the analysis of the neonatal immune landscape across GA provides a mechanistic framework to understand the unique susceptibility of preterm infants to both hyper-inflammatory diseases and infections.

scholarly journals The Study of the Association between Immune Monitoring and Pneumonia in Kidney Transplant Recipients Through Machine Learning Models

2020 ◽  
Author(s):  
Bo Peng ◽  
Hang Gong ◽  
Han Tian ◽  
Quan Zhuang ◽  
Junhui Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Nk Cells ◽  
Kidney Transplant ◽  
Immune Monitoring ◽  
Learning Models ◽  
Kidney Transplant Recipients ◽  
Cell Counts ◽  
Hla Dr ◽  
Machine Learning Models

Abstract Background: Kidney transplantation is the optimal treatment to cure the patients with end-stage renal disease (ESRD). However, the infectious complication, especially pneumonia, is the main cause of mortality in the early stage. Immune monitoring by relevant biomarkers provides direct evidence of immune status. We aimed to study the association between immune monitoring and pneumonia in kidney transplant patients through machine learning models. Methods: A total of 146 patients receiving the immune monitoring panel in our center, including 46 pneumonia recipients and 100 stable recipients, were retrospectively reviewed to develop the models. All the models were validated by external data containing 10 pneumonia recipients and 32 stable recipients. The immune monitoring panel consisted of the percentages and absolute cell counts of CD3+CD4+ T cells, CD3+CD8+ T cells, CD19+ B cells and natural killer (NK) cells, and median fluorescence intensity (MFI) of human leukocyte antigen (HLA)-DR on monocytes and CD64 on neutrophils. The machine learning models of support vector machine (SVM), logistic regression (LR), multi-layer perceptron (MLP) and random forest (RF) were applied for analysis.Results: The pneumonia and stable groups showed significant difference in cell counts of each subpopulation and MFI of monocyte HLA-DR and neutrophil CD64. The SVM model by monocyte HLA-DR (MFI), neutrophil CD64 (MFI), CD8+ T cells (cells/μl), NK cells (cell/μl) and TBNK (T cells, B cells and NK cells, cells/μl) had the best performance with the average area under the curve (AUC) of 0.940. The RF model best predicted the patients who would progress into severe pneumonia, with the average AUC of 0.760. All the models had good performance validated by external data.Conclusions: The immune monitoring panel was tightly associated with pneumonia in kidney transplant recipients. The models developed by machine learning techniques identified patients at risk and predicted the prognosis. Based on the results of immune monitoring, better individualized therapy might be achieved.

scholarly journals The study of the association between immune monitoring and pneumonia in kidney transplant recipients through machine learning models

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Bo Peng ◽  
Hang Gong ◽  
Han Tian ◽  
Quan Zhuang ◽  
Junhui Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Nk Cells ◽  
Kidney Transplant ◽  
Immune Monitoring ◽  
Learning Models ◽  
Kidney Transplant Recipients ◽  
Cell Counts ◽  
Hla Dr ◽  
Machine Learning Models

Abstract Background Kidney transplantation is the optimal treatment to cure the patients with end-stage renal disease (ESRD). However, the infectious complication, especially pneumonia, is the main cause of mortality in the early stage. Immune monitoring by relevant biomarkers provides direct evidence of immune status. We aimed to study the association between immune monitoring and pneumonia in kidney transplant patients through machine learning models. Methods A total of 146 patients receiving the immune monitoring panel in our center, including 46 pneumonia recipients and 100 stable recipients, were retrospectively reviewed to develop the models. All the models were validated by external data containing 10 pneumonia recipients and 32 stable recipients. The immune monitoring panel consisted of the percentages and absolute cell counts of CD3+CD4+ T cells, CD3+CD8+ T cells, CD19+ B cells and natural killer (NK) cells, and median fluorescence intensity (MFI) of human leukocyte antigen (HLA)-DR on monocytes and CD64 on neutrophils. The machine learning models including support vector machine (SVM), logistic regression (LR), multi-layer perceptron (MLP) and random forest (RF) were applied for analysis. Results The pneumonia and stable groups showed significant difference in cell counts of each subpopulation and MFI of monocyte HLA-DR and neutrophil CD64. The SVM model by monocyte HLA-DR (MFI), neutrophil CD64 (MFI), CD8+ T cells (cells/μl), NK cells (cell/μl) and TBNK (T cells, B cells and NK cells, cells/μl) had the best performance with the average area under the curve (AUC) of 0.940. The RF model best predicted the patients who would progress into severe pneumonia, with the average AUC of 0.760. All the models had good performance validated by external data. Conclusions The immune monitoring panel was tightly associated with pneumonia in kidney transplant recipients. The models developed by machine learning techniques identified patients at risk and predicted the prognosis. Based on the results of immune monitoring, better individualized therapy might be achieved.

scholarly journals Blood-Based Immune Profiling Combined with Machine Learning Discriminates Psoriatic Arthritis from Psoriasis Patients

2021 ◽  
Vol 22 (20) ◽  
pp. 10990
Author(s):  
Michelle L. M. Mulder ◽  
Xuehui He ◽  
Juul M. P. A. van den Reek ◽  
Paulo C. M. Urbano ◽  
Charlotte Kaffa ◽  
...  
Keyword(s):  
Machine Learning ◽  
T Cells ◽  
Psoriatic Arthritis ◽  
Immune Cell ◽  
Joint Damage ◽  
Classification Model ◽  
T Cell Subsets ◽  
Correct Identification ◽  
Random Forest Classification ◽  
Disease Specific

Psoriasis (Pso) is a chronic inflammatory skin disease, and up to 30% of Pso patients develop psoriatic arthritis (PsA), which can lead to irreversible joint damage. Early detection of PsA in Pso patients is crucial for timely treatment but difficult for dermatologists to implement. We, therefore, aimed to find disease-specific immune profiles, discriminating Pso from PsA patients, possibly facilitating the correct identification of Pso patients in need of referral to a rheumatology clinic. The phenotypes of peripheral blood immune cells of consecutive Pso and PsA patients were analyzed, and disease-specific immune profiles were identified via a machine learning approach. This approach resulted in a random forest classification model capable of distinguishing PsA from Pso (mean AUC = 0.95). Key PsA-classifying cell subsets selected included increased proportions of differentiated CD4+CD196+CD183-CD194+ and CD4+CD196-CD183-CD194+ T-cells and reduced proportions of CD196+ and CD197+ monocytes, memory CD4+ and CD8+ T-cell subsets and CD4+ regulatory T-cells. Within PsA, joint scores showed an association with memory CD8+CD45RA-CD197- effector T-cells and CD197+ monocytes. To conclude, through the integration of in-depth flow cytometry and machine learning, we identified an immune cell profile discriminating PsA from Pso. This immune profile may aid in timely diagnosing PsA in Pso.

scholarly journals Discovery of CD80 and CD86 as recent activation markers on regulatory T cells by protein-RNA single-cell analysis

2019 ◽  
Author(s):  
Dominik Trzupek ◽  
Melanie Dunstan ◽  
Antony J. Cutler ◽  
Mercede Lee ◽  
Leila Godfrey ◽  
...  
Keyword(s):  
T Cells ◽  
Single Cell ◽  
Immune Cell ◽  
Single Cell Analysis ◽  
Single Cells ◽  
Cost Effective ◽  
Activated T Cells ◽  
Activation Markers ◽  
High Resolution Map ◽  
Treg Differentiation

AbstractThe transcriptomic and proteomic characterisation of CD4+ T cells at the single-cell level has been performed traditionally by two largely exclusive types of technologies: single cell RNA-sequencing (scRNA-seq) technologies and antibody-based cytometry. Here we demonstrate that the simultaneous targeted quantification of mRNA and protein expression in single-cells provides a high-resolution map of human primary CD4+ T cells, and identified precise trajectories of Th1, Th17 and regulatory T-cell (Treg) differentiation in blood and tissue. Furthermore, the sensitivity provided by this massively-parallel multi-omics approach revealed novel insight into the mechanism of expression of CD80 and CD86 on the surface of activated CD4+ Tregs and demonstrate their potential to identify recently activated T cells in circulation. This transcriptomic and proteomic hybrid technology provides a cost-effective solution to dissect the heterogeneity of immune cell populations, including more precise and detailed descriptions of the differentiation and activation of circulating and tissue-resident cells in response to therapies and in stratification of patients.

scholarly journals 661 Five immunotypic signatures identified in human glioblastoma correlate with tumor contact with the lateral ventricle, immune suppression, and patient outcome

2020 ◽  
Vol 8 (Suppl 3) ◽  
pp. A698-A698
Author(s):  
Todd Bartkowiak ◽  
Sierra Barone ◽  
Madeline Hayes ◽  
Allison Greenplate ◽  
Justine Sinnaeve ◽  
...  
Keyword(s):  
Machine Learning ◽  
Patient Outcome ◽  
T Cells ◽  
Single Cell ◽  
Lateral Ventricle ◽  
Immune Cell ◽  
Cell Mass ◽  
Γδ T Cells ◽  
Survival Outcomes ◽  
Mass Cytometry

BackgroundGlioblastomas make up more than 60% of adult primary brain tumors and carry a median survival of less than 15 months despite aggressive therapy. Immunotherapy, now standard of care for many peripheral solid tumors, offers an appealing alternative platform that may improve survival outcomes for patients with glioblastoma; however, predictive features that could inform responsiveness to different immunotherapeutic modalities remains to be elucidated. Recent studies have demonstrated that patients whose tumors show radiographic contact with the lateral ventricle have diminished survival outcomes compared to patients whose tumors do not contact the lateral ventricle. While greater immune infiltrate correlates with more favorable outcomes and more effectual responses to immunotherapy, the anti-tumor immune response in the ventricle is unknown. We hypothesized that ventricle contact may provide a uniquely immunosuppressive microenvironment within the brain that promotes tumor growth by suppressing anti-tumor immunity, that may be overcome with appropriate targeting strategies.MethodsPrimary glioblastoma tumors obtained in accordance with the Declaration of Helsinki and with institutional IRB approval (#131870) were disaggregated into single-cell suspensions. Radiographic contact with the LV was identified by MRI imaging and confirmed by a trained neurosurgeon. Multi-dimensional single-cell mass cytometry (CyTOF) then measured >30 immune parameters in thirteen immune subpopulations infiltrating human glioblastomas, including T cells, natural killer cells, B cells, microglia, peripheral macrophages, and myeloid-derived suppressors cells (MDSC). Computational machine-learning pipelines including Citrus, t-SNE, FlowSOM, and MEM identified key differences in the abundance and phenotypes of immune infiltrates.ResultsOn the basis of glioblastoma contact with the ventricle, we computationally identified consequential distinctions in the abundance of T cell, macrophage, and microglia subsets constituting five immunotype signatures among glioblastoma patients. Immunotypes associated with CD69+CD32+CD44+ peripheral macrophages and PD-1+TIGIT+ CD8 T cells correlated with ventricle contact, whereas immunotypes associated with enriched γδ T cells, B, NK cell, and tissue-resident microglial cells correlated with tumors distal to the ventricle. Further, immune infiltration in the tumor microenvironment correlated with patient outcome, with higher lymphocyte infiltrates correlating with more favorable outcomes, and immune exhaustion correlating with less favorable outcomes.ConclusionsSingle-cell mass cytometry in conjunction with the machine learning tools identified key differences in immune cell abundance between lateral ventricle contacting and non-contacting glioblastomas. These results provide key insights into the immune microenvironment of glioblastomas and elucidate several clinically actionable immunotherapeutic targets that may be used to optimize treatment strategies for glioblastomas based on ventricle contact status.Ethics ApprovalThis study was approved by Vanderbilt University’s Institutional Ethics Board, approval number 131870

scholarly journals Immune Monitoring in Melanoma and Urothelial Cancer Patients Treated with Anti-PD-1 Immunotherapy and SBRT Discloses Tumor Specific Immune Signatures

Cancers ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2630
Author(s):  
Annabel Meireson ◽  
Simon J. Tavernier ◽  
Sofie Van Gassen ◽  
Nora Sundahl ◽  
Annelies Demeyer ◽  
...  
Keyword(s):  
T Cells ◽  
Clinical Outcome ◽  
Cd8 T Cells ◽  
Immune Cell ◽  
Stage Iv ◽  
Progression Free Survival ◽  
Fixed Time ◽  
Immune Monitoring ◽  
Tumor Burden ◽  
Durable Response

(1) Background: Blockade of the PD-1/PD-L1 pathway has revolutionized the oncology field in the last decade. However, the proportion of patients experiencing a durable response is still limited. In the current study, we performed an extensive immune monitoring in patients with stage III/IV melanoma and stage IV UC who received anti-PD-1 immunotherapy with SBRT. (2) Methods: In total 145 blood samples from 38 patients, collected at fixed time points before and during treatment, were phenotyped via high-parameter flow cytometry, luminex assay and UPLC-MS/MS. (3) Results: Baseline systemic immunity in melanoma and UC patients was different with a more prominent myeloid compartment and a higher neutrophil to lymphocyte ratio in UC. Proliferation (Ki67+) of CD8+ T-cells and of the PD-1+/PD-L1+ CD8+ subset at baseline correlated with progression free survival in melanoma. In contrast a higher frequency of PD-1/PD-L1 expressing non-proliferating (Ki67−) CD8+ and CD4+ T-cells before treatment was associated with worse outcome in melanoma. In UC, the expansion of Ki67+ CD8+ T-cells and of the PD-L1+ subset relative to tumor burden correlated with clinical outcome. (4) Conclusion: This study reveals a clearly different immune landscape in melanoma and UC at baseline, which may impact immunotherapy response. Signatures of proliferation in the CD8+ T-cell compartment prior to and early after anti-PD-1 initiation were positively correlated with clinical outcome in both cohorts. PD-1/PD-L1 expression on circulating immune cell subsets seems of clinical relevance in the melanoma cohort.

Sign in / Sign up

Export Citation Format

Share Document