scholarly journals A Segmentation-Free Machine Learning Architecture for Immune Landscape Phenotyping in Solid Tumors by Multichannel Imaging

2021 ◽  
Author(s):  
Shabaz Sultan ◽  
Mark A. J. Gorris ◽  
Lieke L. van der Woude ◽  
Franka Buytenhuijs ◽  
Evgenia Martynova ◽  
...  
Keyword(s):  
Machine Learning ◽  
Solid Tumors ◽  
Immune Cells ◽  
Multispectral Imaging ◽  
Immune Cell ◽  
Cell Detection ◽  
Tissue Samples ◽  
Primary Tumors ◽  
Tissue Specimens ◽  
Free Machine

Tissue specimens taken from primary tumors or metastases contain important information for diagnosis and treatment of cancer patients. Multispectral imaging allows in situ visualization of heterogeneous cell subsets, such as lymphocytes, in tissue samples. Many image processing pipelines first segment cell boundaries and then measure marker expression to assign cell phenotypes. In dense tissue environments such as solid tumors, segmentation-based phenotyping can be inaccurate due to segmentation errors or overlapping cell boundaries. Here we introduce a machine learning pipeline design called ImmuNet that directly identifies the positions and phenotypes of immune cells without determining their exact boundaries. ImmuNet is easy to train: human annotators only need to click on immune cells and rank their expression of each marker; full annotation of tissue regions is not necessary. We demonstrate that ImmuNet is a suitable approach for immune cell detection and phenotyping in multiplex immunohistochemistry: it compares favourably to segmentation-based methods, especially in dense tissues, and we externally validate ImmuNet results by comparing them to flow cytometric measurements from the same tissue. In summary, ImmuNet performs well on diverse tissue specimens, takes relatively little effort to train and implement, and is a simpler alternative to segmentation-based approaches when only cell positions and phenotypes, but not their shapes are required for downstream analyses. We hope that ImmuNet will help cancer researchers to analyze multichannel tissue images more easily and accurately.

scholarly journals POS0109 IDENTIFICATION OF PRIMARY SJOGREN’S SYNDROME SUBTYPES BY MACHINE LEARNING

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 265.2-266
Author(s):  
M. T. Qiu ◽  
S. X. Zhang ◽  
J. Qiao ◽  
J. Q. Zhang ◽  
S. Song ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sjögren’S Syndrome ◽  
Immune Cells ◽  
Immune Cell ◽  
Sjögren's Syndrome ◽  
Sjogren’S Syndrome ◽  
Sjogren's Syndrome ◽  
Sjögren Syndrome ◽  
Sjogren Syndrome ◽  
Sjögren‘S Syndrome

Background:Sjogren’s syndrome(pSS) is a chronic, progressive, and systematic autoimmune disease characterized by lymphocytic infiltration of exocrine glands 1 2. Sicca symptoms and abnormal fatigue are the main clinical presentation, but those symptoms are non-specific to patients, which lead to delayed diagnosis 1 3. The heterogeneous of clinical manifestation raise challenges regarding diagnosis and therapy in pSS, thus it’s necessary for us to sub-classify pSS.Objectives:To explore new biomarkers for diagnosis and subtypes of pSS based on Machine Learning Primary.Methods:All microarray raw datas (CEL files) were screened and downloaded from Gene Expression Omnibus (GEO). Meta-analysis to identify the consistent DEGs by MetaOmics. Weighted gene co-expression network analysis (WGCNA) was used to the modules related to SS for further analysis. Subclasses were computed using a consensus Non-negative Matrix Factorization (NMF) clustering method. Immune cell infiltration was used to evaluate the expression of immune cells and obtain various immune cell proportions from samples. P value < 0.05 were considered statistically significant. All the analyses were conducted under R environment (version 4.03).Results:A total of 3715 consistent DEGs were identified from the four datasets, including 1748 up-regulated and 1967 down-regulated genes. Tour meaningful modules, including yellow, turquoise, grey60 and bule, were identified (Figure 1A,1B). And 183 overlapping gene were screened from the DEGs and the Hub genes in the four modles for further analysis. We final divided pSS patients into three subtypes, of which yellow and turquoise in Sub1, grey60 in Sub2 and blue in Sub3. Sub1 and Sub3 were related to cell metabolism, while Sub2 had connection with virus infection (Figure 1C,1D). Infiltrated immune cells were also different among these three types (Figure 1E,1F).Conclusion:Patients with pSS could be classified into 3 subtypes, this classification might help for assessing prognosis and guiding precise treatment.References:[1]Ramos-Casals M, Brito-Zerón P, Sisó-Almirall A, et al. Primary Sjogren syndrome. BMJ (Clinical research ed) 2012;344:e3821. doi: 10.1136/bmj.e3821 [published Online First: 2012/06/16].[2]Brito-Zeron P, Baldini C, Bootsma H, et al. Sjogren syndrome. Nat Rev Dis Primers 2016;2:16047. doi: 10.1038/nrdp.2016.47 [published Online First: 2016/07/08].[3]Segal B, Bowman SJ, Fox PC, et al. Primary Sjogren’s Syndrome: health experiences and predictors of health quality among patients in the United States. Health Qual Life Outcomes 2009;7:46. doi: 10.1186/1477-7525-7-46 [published Online First: 2009/05/29].Acknowledgements:This project was supported by National Science Foundation of China (82001740), Open Fund from the Key Laboratory of Cellular Physiology (Shanxi Medical University) (KLCP2019) and Innovation Plan for Postgraduate Education in Shanxi Province (2020BY078).Disclosure of Interests:None declared

scholarly journals In Vitro Evaluation of CD276-CAR NK-92 Functionality, Migration and Invasion Potential in the Presence of Immune Inhibitory Factors of the Tumor Microenvironment

Cells ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 1020
Author(s):  
Stefan Grote ◽  
Guillermo Ureña-Bailén ◽  
Kenneth Chun-Ho Chan ◽  
Caroline Baden ◽  
Markus Mezger ◽  
...  
Keyword(s):  
Tumor Microenvironment ◽  
Solid Tumors ◽  
Immune Cells ◽  
Immune Cell ◽  
Nk Cell ◽  
Migration And Invasion ◽  
Cellular Immunotherapy ◽  
Knock Out ◽  
Immunosuppressive Tumor Microenvironment

Background: Melanoma is the most lethal of all skin-related cancers with incidences continuously rising. Novel therapeutic approaches are urgently needed, especially for the treatment of metastasizing or therapy-resistant melanoma. CAR-modified immune cells have shown excellent results in treating hematological malignancies and might represent a new treatment strategy for refractory melanoma. However, solid tumors pose some obstacles for cellular immunotherapy, including the identification of tumor-specific target antigens, insufficient homing and infiltration of immune cells as well as immune cell dysfunction in the immunosuppressive tumor microenvironment (TME). Methods: In order to investigate whether CAR NK cell-based immunotherapy can overcome the obstacles posed by the TME in melanoma, we generated CAR NK-92 cells targeting CD276 (B7-H3) which is abundantly expressed in solid tumors, including melanoma, and tested their effectivity in vitro in the presence of low pH, hypoxia and other known factors of the TME influencing anti-tumor responses. Moreover, the CRISPR/Cas9-induced disruption of the inhibitory receptor NKG2A was assessed for its potential enhancement of NK-92-mediated anti-tumor activity. Results: CD276-CAR NK-92 cells induced specific cytolysis of melanoma cell lines while being able to overcome a variety of the immunosuppressive effects normally exerted by the TME. NKG2A knock-out did not further improve CAR NK-92 cell-mediated cytotoxicity. Conclusions: The strong cytotoxic effect of a CD276-specific CAR in combination with an “off-the-shelf” NK-92 cell line not being impaired by some of the most prominent negative factors of the TME make CD276-CAR NK-92 cells a promising cellular product for the treatment of melanoma and beyond.

scholarly journals 48 Immune environment correlates with NSCLC and CRC patient survival

2021 ◽  
Vol 9 (Suppl 3) ◽  
pp. A55-A55
Author(s):  
Dannah Miller ◽  
Huong Nguyen ◽  
Kate Hieber ◽  
Charles Caldwell ◽  
Roberto Gianani
Keyword(s):  
T Cells ◽  
Image Analysis ◽  
Immune Cells ◽  
Survival Data ◽  
Immune Cell ◽  
Patient Survival ◽  
Machine Learning Algorithms ◽  
Primary Tumors ◽  
Cell Lung Carcinoma ◽  
Analysis Platform

BackgroundImmune cells within the tumor microenvironment (TME) play a vital role in regulating tumor progression. Therefore, immunotherapies that stimulate anti-tumor responses are of great interest for the treatment of various cancers. PD-L1 expression on immune cells is positively correlated with increased patient survival. Our hypothesis is that non-small cell lung carcinoma (NSCLC) and colorectal cancer (CRC) patients with high immune infiltration and greater amounts of anti-tumor immune cells within the tumor compartment have an increased time of survival compared to cancers with immune excluded or immune desert environments.MethodsOne NSCLC and one CRC tumor microarray (TMA) containing primary tumors, metastases, and normal tissue were stained via multiplex immunofluorescence (mIF) for 6 different immune markers: CD3, CD8, CD56, CD68, CD163, and PD-L1. This multiplex panel was designed to evaluate the immune cell population as well as tumor and immune cell PD-L1 status to aid in research for immunotherapies, specifically anti-PD-L1 therapies. The stained TMAs were analyzed utilizing Flagship Biosciences’ proprietary image analysis platform. Machine learning algorithms stratified cells as belonging to the tumoral or stromal space based on their cellular features. Core level expression data was pulled and represented on a whole-cohort basis. All staining and image analysis outputs were reviewed by a board-certified, MD pathologist. Kaplan-meier curves were generated based on survival data in relation to the levels of immune cells present within the tumor cores as well as the percentage of immune cells infiltrating into the tumor.ResultsThere is a clear correlation between patient survival and the presence or absence of various types of immune cells, including helper T cells, cytotoxic T cells, M1 macrophages, M2, macrophages, NK cells, as well as PDL1 expression on tumor and immune cells. Specifically, the increased presence of anti-tumor immune cells as well as increased expression of PD-L1 on immune cells within the tumor compartment correlates with an increase in patient survival.ConclusionsData generated through Flagship Biosciences’ image analysis platform showed a strong relationship between immune cell presence and localization and NSCLC and CRC patient survival. Altering the immune cells within the tumor to an anti-tumor immune environment could increase patient survival times. Combining immune checkpoint inhibitors with current FDA approved therapies for NSCLC and CRC are of interest to further extend patient survival. Further, utilizing Flagship Biosciences’ image analysis software to understand cancer immune microenvironments should be further utilized to aid in diagnosis and treatment decisions.

scholarly journals Myeloid Immune Cells CARriying a New Weapon Against Cancer

2021 ◽  
Vol 9 ◽  
Author(s):  
Rodrigo Nalio Ramos ◽  
Samuel Campanelli Freitas Couto ◽  
Theo Gremen M. Oliveira ◽  
Paulo Klinger ◽  
Tarcio Teodoro Braga ◽  
...  
Keyword(s):  
Gene Therapy ◽  
T Cells ◽  
Tumor Microenvironment ◽  
Solid Tumors ◽  
Immune Cells ◽  
Scientific Community ◽  
Immune Cell ◽  
Clinical Results ◽  
Mononuclear Phagocytes ◽  
Soluble Factors

Chimeric antigen receptor (CAR) engineering for T cells and natural killer cells (NK) are now under clinical evaluation for the treatment of hematologic cancers. Although encouraging clinical results have been reported for hematologic diseases, pre-clinical studies in solid tumors have failed to prove the same effectiveness. Thus, there is a growing interest of the scientific community to find other immune cell candidate to express CAR for the treatment of solid tumors and other diseases. Mononuclear phagocytes may be the most adapted group of cells with potential to overcome the dense barrier imposed by solid tumors. In addition, intrinsic features of these cells, such as migration, phagocytic capability, release of soluble factors and adaptive immunity activation, could be further explored along with gene therapy approaches. Here, we discuss the elements that constitute the tumor microenvironment, the features and advantages of these cell subtypes and the latest studies using CAR-myeloid immune cells in solid tumor models.

scholarly journals Key chemokines direct migration of immune cells in solid tumors

2021 ◽  
Author(s):  
Karan Kohli ◽  
Venu G. Pillarisetty ◽  
Teresa S. Kim
Keyword(s):  
Solid Tumors ◽  
Immune Cells ◽  
Chemokine Receptors ◽  
Tumor Tissue ◽  
Immune Cell ◽  
Chemokine Signaling ◽  
Immune Cell Migration ◽  
Preclinical And Clinical Studies ◽  
Immunosuppressive Cells

AbstractImmune cell infiltration into solid tumors, their movement within the tumor microenvironment (TME), and interaction with other immune cells are controlled by their directed migration towards gradients of chemokines. Dysregulated chemokine signaling in TME favors the growth of tumors, exclusion of effector immune cells, and abundance of immunosuppressive cells. Key chemokines directing the migration of immune cells into tumor tissue have been identified. In this review, we discuss well-studied chemokine receptors that regulate migration of effector and immunosuppressive immune cells in the context of cancer immunology. We discuss preclinical models that have described the role of respective chemokine receptors in immune cell migration into TME and review preclinical and clinical studies that target chemokine signaling as standalone or combination therapies.

scholarly journals 510 SO-C101, a high-affinity IL-15Rbg agonist, induces safe and potent anti-tumor immune activities in patients with solid tumors and supports further clinical investigations

2021 ◽  
Vol 9 (Suppl 3) ◽  
pp. A541-A541
Author(s):  
Lenka Palová
Keyword(s):  
T Cell ◽  
Solid Tumors ◽  
T Cell Activation ◽  
Immune Cells ◽  
Immune Cell ◽  
Clear Correlation ◽  
High Affinity ◽  
Link Type ◽  
Clinical Investigations ◽  
Dose Dependent

BackgroundSO-C101 is a high affinity superagonist fusion protein of interleukin (IL)-15 and the IL-15 receptor α (IL-15Rα) sushi<+/sup> domain, representing a promising clinical candidate for the treatment of cancer. SO-C101 specifically stimulates natural killer (NK) cells and memory CD8<+/sup> T cells with no significant expansion and activation of regulatory T cell compartment.MethodsBlood and tumor samples from patients with advanced/metastatic solid tumors included in Phase clinical I study (NCT04234113) were analysed by flow cytometry, immunohistochemistry and NanoString analyses for the activation of immune cells induced by SO-C101 monotherapy or in combination with pembrolizumab.ResultsSO-C101 showed a dose-dependent activity in blood of all patients with no clear correlation between the increase of immune cell proliferation and counts in blood and recruitment of immune cells into the tumor tissue. SO-C101 (RLI-15) as a monotherapy or in combination with pembrolizumab increases immune cell infiltration in tumors in clinically responsive patients in Phase clinical I study (NCT04234113) which is accompanied by NK and CD8<+/sup> T cell activation and cytotoxicity, increased proinflammatory chemokines and IFN-gamma signaling genes signatures.ConclusionsAll patients showed dose-dependent pharmacodynamic responses in blood, however SO-C101 activity in the tumor microenvironment might be pivotal for the therapeutic success. Favorable safety profile and potent anti-tumor immune activities in patients with solid tumors support further clinical investigations.Trial RegistrationNCT04234113Ethics ApprovalThis study was approved by the FDA (IND 140011) and by the Ethics Boards of participating institutions. The participants provided written informed consent.

scholarly journals Immune Cell as a Promising Biomarker in the Diagnosis and Prognosis of Cutaneous Melanoma by Using Machine Learning

2021 ◽  
Author(s):  
Jing Tang ◽  
Hongqaun Ye ◽  
Wan qi
Keyword(s):  
Machine Learning ◽  
Immune Cells ◽  
Immune Cell ◽  
Risk Group ◽  
Enrichment Analysis ◽  
High Risk Group ◽  
Gene Set Enrichment Analysis ◽  
Gene Set Enrichment ◽  
Diagnostic Models ◽  
Melanoma Patients

Abstract Background: Tumor infiltration, is known to associate with various cancer initiations and progressions, is potential therapeutic target for this aggressive skin cancer.Methods: single sample gene set enrichment analysis (ssGSEA) algorithm was applied to assess the relative expression of 24 types of immune cell from public database. Firstly, the differentially expressed immune cells between melanomas and normal samples were identified. Next, multiple machine learning algorithms were performed to evaluate the efficiency of immune cells in diagnosis of melanoma. In addition, the feature selection in machine learning methods was used to figure out the most important prognostic immune cells for developing biomarker to predict the prognosis of melanoma.Results: In comparison with the expression of immune cells in tumors and normal controls, we built the immune diagnostic models in training dataset, which can accurately classify melanoma patients from normal (LR AUC= 0.965, RF AUC= 0.99, SVM AUC=0.963, LASSO AUC= 0.964 and NNET AUC=0.989). These diagnostic models also validated in three outside datasets and suggested over 90% sensitivity and specificity to distinguish melanomas from normal patients. Moreover, we also developed a robust immune cell biomarker which could estimate the prognosis of melanoma. This biomarker also further validated in internal and external datasets. Next, we constructed nomogram combined risk score of biomarker and clinical characteristics, which showed good accuracies in predicting 3 and 5 years’ survival. The decision curve of nomogram model manifested a higher net benefit than tumor stage. In addition, melanoma patients divided into high and low risk subgroups by applied risk score system. The high risk group have a significantly shorter survival time than the low risk subgroup. Gene Set Enrichment Analysis (GSEA) analysis revealed that complement, epithelial mesenchymal transition and inflammatory response and so on significantly activated in high risk group. Conclusions: We constructed immune cell related diagnostic and prognostic models, which could provide new clinical applications for diagnosing and predicting the survival of melanoma patients.

scholarly journals Identification of Diagnostic Signatures and Immune Cell Infiltration Characteristics in Rheumatoid Arthritis by Integrating Bioinformatic Analysis and Machine-Learning Strategies

2021 ◽  
Vol 12 ◽  
Author(s):  
Rongguo Yu ◽  
Jiayu Zhang ◽  
Youguang Zhuo ◽  
Xu Hong ◽  
Jie Ye ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Machine Learning ◽  
Nk Cells ◽  
Learning Strategies ◽  
Immune Cells ◽  
Immune Cell ◽  
Bioinformatic Analysis ◽  
Cell Infiltration ◽  
Immune Cell Infiltration ◽  
Qrt Pcr

BackgroundRheumatoid arthritis (RA) refers to an autoimmune rheumatic disease that imposes a huge burden on patients and society. Early RA diagnosis is critical to preventing disease progression and selecting optimal therapeutic strategies more effectively. In the present study, the aim was at examining RA’s diagnostic signatures and the effect of immune cell infiltration in this pathology.MethodsGene Expression Omnibus (GEO) database provided three datasets of gene expressions. Firstly, this study adopted R software for identifying differentially expressed genes (DEGs) and conducting functional correlation analyses. Subsequently, we integrated bioinformatic analysis and machine-learning strategies for screening and determining RA’s diagnostic signatures and further verify by qRT-PCR. The diagnostic values were assessed through receiver operating characteristic (ROC) curves. Moreover, this study employed cell-type identification by estimating relative subsets of RNA transcript (CIBERSORT) website for assessing the inflammatory state of RA, and an investigation was conducted on the relationship of diagnostic signatures and infiltrating immune cells.ResultsOn the whole, 54 robust DEGs received the recognition. Lymphocyte-specific protein 1 (LSP1), Granulysin (GNLY), and Mesenchymal homobox 2 (MEOX2) (AUC = 0.955) were regarded as RA’s diagnostic markers and showed their statistically significant difference by qRT-PCR. As indicated from the immune cell infiltration analysis, resting NK cells, neutrophils, activated NK cells, T cells CD8, memory B cells, and M0 macrophages may be involved in the development of RA. Additionally, all diagnostic signatures might be different degrees of correlation with immune cells.ConclusionsIn conclusion, LSP1, GNLY, and MEOX2 are likely to be available in terms of diagnosing and treating RA, and the infiltration of immune cells mentioned above may critically impact RA development and occurrence.

scholarly journals Immunoprofiling of human uterine mast cells identifies three phenotypes and expression of ERβ and glucocorticoid receptor

F1000Research ◽  
2017 ◽  
Vol 6 ◽  
pp. 667 ◽  
Author(s):  
Bianca De Leo ◽  
Arantza Esnal-Zufiaurre ◽  
Frances Collins ◽  
Hilary O.D. Critchley ◽  
Philippa T.K. Saunders
Keyword(s):  
Mast Cells ◽  
Immune Cells ◽  
Immune Cell ◽  
Rna Extraction ◽  
Endometrial Tissue ◽  
Target Tissue ◽  
Messenger Rnas ◽  
Human Uterus ◽  
Tissue Samples ◽  
The Impact

Background:Human mast cells (MCs) are long-lived tissue-resident immune cells characterised by granules containing the proteases chymase and/or tryptase. Their phenotype is modulated by their tissue microenvironment. The human uterus has an outer muscular layer (the myometrium) surrounding the endometrium, both of which play an important role in supporting a pregnancy. The endometrium is a sex steroid target tissue consisting of epithelial cells (luminal, glandular) surrounded by a multicellular stroma, with the latter containing an extensive vascular compartment as well as fluctuating populations of immune cells that play an important role in regulating tissue function. The role of MCs in the human uterus is poorly understood with little known about their regulation or the impact of steroids on their differentiation status.The current study had two aims: 1) To investigate the spatial and temporal location of uterine MCs and determine their phenotype; 2) To determine whether MCs express receptors for steroids implicated in uterine function, including oestrogen (ERα, ERβ), progesterone (PR) and glucocorticoids (GR).Methods:Tissue samples from women (n=46) were used for RNA extraction or fixed for immunohistochemistry.Results:Messenger RNAs encoded byTPSAB1(tryptase) andCMA1(chymase) were detected in endometrial tissue homogenates. Immunohistochemistry revealed the relative abundance of tryptase MCs was myometrium>basal endometrium>functional endometrium. We show for the first time that uterine MCs are predominantly of the classical MC subtypes: (positive, +; negative, -) tryptase+/chymase- and tryptase+/chymase+, but a third subtype was also identified (tryptase-/chymase+). Tryptase+ MCs were of an ERβ+/ERα-/PR-/GR+ phenotype mirroring other uterine immune cell populations, including natural killer cells.Conclusions:Endometrial tissue resident immune MCs have three protease-specific phenotypes. Expression of both ERβ and GR in MCs mirrors that of other immune cells in the endometrium and suggests that MC function may be altered by the local steroid microenvironment.

scholarly journals Metastatic breast cancers have reduced immune cell recruitment but harbor increased macrophages relative to their matched primary tumors

2019 ◽  
Author(s):  
Li Zhu ◽  
Jessica L. Narloch ◽  
Sayali Onkar ◽  
Marion Joy ◽  
Catherine Luedke ◽  
...  
Keyword(s):  
Breast Cancer ◽  
T Cells ◽  
Immune Cells ◽  
Cancer Metastasis ◽  
Immune Cell ◽  
Immune Escape ◽  
Metastatic Breast ◽  
Exome Capture ◽  
Sequencing Data ◽  
Primary Tumors

AbstractThe interplay between the immune system and tumor progression is well recognized. However, current human breast cancer immunophenotyping studies are mostly focused on primary tumors with metastatic breast cancer lesions remaining largely understudied. To address this gap, we examined exome-capture RNA sequencing data from 50 primary breast tumors (PBTs) and their patient-matched metastatic tumors (METs) in brain, ovary, bone and gastrointestinal tract. We used gene expression signatures as surrogates for tumor infiltrating lymphocytes (TIL) and compared TIL patterns in PBTs and METs. Enrichment analysis and deconvolution methods both revealed that METs have a significantly lower abundance of total immune cells, including CD8+ T cells, regulatory T cells and dendritic cells. An exception was M2-like macrophages, which were significantly higher in METs across the organ sites examined. Multiplex immunohistochemistry results were consistent with data from the in-silico analysis and showed increased macrophages in METs. We confirmed the finding of a significant reduction in immune cells in brain (BRM) METs by pathologic assessment of TILs in a set of 49 patient-matched pairs of PBT/BRMs. These findings indicate that METs have an overall lower infiltration of immune cells relative to their matched PBTs, possibly due to immune escape. RNAseq analysis suggests that the relative levels of M2-like macrophages are increased in METs, and their potential role in promoting breast cancer metastasis warrants further study.

Sign in / Sign up

Export Citation Format

Share Document