skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: TLCellClassifier: Machine Learning Based Cell Classification for Bright-Field Time-Lapse Images
Abstract Immunotherapies have shown promising results in treating patients with hematological malignancies like multiple myeloma, which is an incurable but treatable bone marrow-resident plasma cell cancer. Choosing the most efficacious treatment for a patient remains a challenge in such cancers. However, pre-clinical assays involving patient-derived tumor cells co-cultured in anex vivoreconstruction of immune-tumor micro-environment have gained considerable notoriety over the past decade. Such assays can characterize a patient’s response to several therapeutic agents including immunotherapies in a high-throughput manner, where bright-field images of tumor (target) cells interacting with effector cells (T cells, Natural Killer (NK) cells, and macrophages) are captured once every 30 minutes for upto six days. Cell detection, tracking, and classification of thousands of cells of two or more types in each frame is bound to test the limits of some of the most advanced computer vision tools developed to date and requires a specialized approach. We propose TLCellClassifier (time-lapse cell classifier) for live cell detection, cell tracking, and cell type classification, with enhanced accuracy and efficiency obtained by integrating convolutional neural networks (CNN), metric learning, and long short-term memory (LSTM) networks, respectively. State-of-the-art computer vision software like KTH-SE and YOLOv8 are compared with TLCellClassifier, which shows improved accuracy in detection (CNN) and tracking (metric learning). A two-stage LSTM-based cell type classification method is implemented to distinguish between multiple myeloma (tumor/target) cells and macrophages/monocytes (immune/effector cells). Validation of cell type classification was done both using synthetic datasets andex vivoexperiments involving patient-derived tumor/immune cells. Availability and implementationhttps://github.com/QibingJiang/cell classification ml  more » « less
Award ID(s):
2246796
PAR ID:
10525299
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ;
Publisher / Repository:
bioRxiv
Date Published:
Format(s):
Medium: X
Institution:
bioRxiv
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al (, eLife)
    null (Ed.)
    Programmed cell death protein-1 (PD-1) checkpoint immunotherapy efficacy remains unpredictable in glioblastoma (GBM) patients due to the genetic heterogeneity and immunosuppressive tumor microenvironments. Here, we report a microfluidics-based, patient-specific ‘GBM-on-a-Chip’ microphysiological system to dissect the heterogeneity of immunosuppressive tumor microenvironments and optimize anti-PD-1 immunotherapy for different GBM subtypes. Our clinical and experimental analyses demonstrated that molecularly distinct GBM subtypes have distinct epigenetic and immune signatures that may lead to different immunosuppressive mechanisms. The real-time analysis in GBM-on-a-Chip showed that mesenchymal GBM niche attracted low number of allogeneic CD154+CD8+ T-cells but abundant CD163+ tumor-associated macrophages (TAMs), and expressed elevated PD-1/PD-L1 immune checkpoints and TGF-β1, IL-10, and CSF-1 cytokines compared to proneural GBM. To enhance PD-1 inhibitor nivolumab efficacy, we co-administered a CSF-1R inhibitor BLZ945 to ablate CD163+ M2-TAMs and strengthened CD154+CD8+ T-cell functionality and GBM apoptosis on-chip. Our ex vivo patient-specific GBM-on-a-Chip provides an avenue for a personalized screening of immunotherapies for GBM patients. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Advanced Functional Materials)
    Abstract Chimeric antigen receptor (CAR) monocyte and macrophage therapies are promising solid tumor immunotherapies that can overcome the challenges facing conventional CAR T cell therapy. mRNA lipid nanoparticles (mRNA‐LNPs) offer a viable platform for in situ engineering of CAR monocytes with transient and tunable CAR expression to reduce off‐tumor toxicity and streamline cell manufacturing. However, identifying LNPs with monocyte tropism and intracellular delivery potency is difficult using traditional screening techniques. Here, ionizable lipid design and high‐throughput in vivo screening are utilized to identify a new class of oxidized LNPs with innate tropism and mRNA delivery to monocytes. A library of oxidized (oLNPs) and unoxidized LNPs (uLNPs) is synthesized to evaluate mRNA delivery to immune cells. oLNPs demonstrate notable differences in morphology, ionization energy, and pKa, thereby enhancing delivery to human macrophages, but not T cells. Subsequently, in vivo library screening with DNA barcodes identifies an oLNP formulation, C14‐O2, with innate tropism to monocytes. In a proof‐of‐concept study, the C14‐O2 LNP is used to engineer functional CD19‐CAR monocytes in situ for robust B cell aplasia (45%) in healthy mice. This work highlights the utility of oxidized LNPs as a promising platform for engineering CAR macrophages/monocytes for solid tumor CAR monocyte therapy. 
    more » « less
  3. ; ; ; ; ; ; ; (, Advanced Science)
    Abstract Solid tumors develop within a complex environment called the tumor microenvironment (TME), which is sculpted by the presence of other cells, such as cancer‐associated fibroblasts (CAFs) and immune cells like macrophages (Mφs). Despite the presence of immune cells, tumor cells orchestrate a tumor‐supportive environment through intricate interaction with the components of the TME. However, the specific mechanism by which this intercellular dialogue is regulated is not fully understood. To that end, the development of an organotypic 3D breast TME‐on‐a‐chip (TMEC) model, integrated with single‐cell RNA sequencing analysis, is reported to mechanistically evaluate the progression of triple‐negative breast cancer (TNBC) cells in the presence of patient‐derived CAFs and Mφs. Extensive functional assays, including invasion and morphometric characterization, reveal the synergistic influence of CAFs and Mφs on tumor cells. Furthermore, gene expression and pathway enrichment analyses identify the involvement of theKYNUgene, suggesting a potential immune evasion mechanism through the kynurenine pathway. Lastly, the pharmacological targeting of the identified pathway is investigated. 
    more » « less
  4. ; ; ; ; (, Advanced Healthcare Materials)
    Abstract Evolving knowledge about the tumor–immune microenvironment (TIME) is driving innovation in designing novel therapies against hard‐to‐treat breast cancer. Targeting the immune components of TIME has emerged as a promising approach for cancer therapy. While recent immunotherapies aim at restoring antitumor immunity, counteracting tumor escape remains challenging. Hence there is a pressing need to better understand the complex tumor–immune crosstalk within TIME. Considering this imperative, this study aims at investigating the crosstalk between the two abundant immune cell populations within the breast TIME—macrophages and T cells, in driving tumor progression using an organotypic 3D in vitro tumor‐on‐a‐chip (TOC) model. The TOC features distinct yet interconnected organotypic tumor and stromal entities. This triculture platform mimics the complex TIME, embedding the two immune populations in a suitable 3D matrix. Analysis of invasion, morphometric measurements, and flow cytometry results underscores the substantial contribution of macrophages to tumor progression, while the presence of T cells is associated with a deceleration in the migratory behavior of both cancer cells and macrophages. Furthermore, cytokine analyses reveal significant upregulation of leptin and RANTES (regulated on activation, normal T Cell expressed and secreted) in triculture. Overall, this study highlights the complexity of TIME and the critical role of immune cells in cancer progression. 
    more » « less
  5. ; ; ; ; ; (, Advanced Materials)
    Abstract Skeletal metastasis is common in patients with advanced breast cancer and often caused by immune evasion of disseminated tumor cells (DTCs). In the skeleton, tumor cells not only disseminate to the bone marrow but also to osteogenic niches in which they interact with newly mineralizing bone extracellular matrix (ECM). However, it remains unclear how mineralization of collagen type I, the primary component of bone ECM, regulates tumor‐immune cell interactions. Here, a combination of synthetic bone matrix models with controlled mineral content, nanoscale optical imaging, and flow cytometry are utilized to evaluate how collagen type I mineralization affects the biochemical and biophysical properties of the tumor cell glycocalyx, a dense layer of glycosylated proteins and lipids decorating their cell surface. These results suggest that collagen mineralization upregulates mucin‐typeO‐glycosylation and sialylation by tumor cells, which increases their glycocalyx thickness while enhancing resistance to attack by natural killer (NK) cells. These changes are functionally linked as treatment with a sialylation inhibitor decreased mineralization‐dependent glycocalyx thickness and made tumor cells more susceptible to NK cell attack. Together, these results suggest that interference with glycocalyx sialylation may represent a therapeutic strategy to enhance cancer immunotherapies targeting bone‐metastatic breast cancer. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email