Abstract B028: Label-free Raman signatures of immune cells: A new tool for artificial intelligence in immunotherapy

Abstract

In the emerging era of artificial intelligence mediated immune response analysis, post- imunotherapeutic interventions, monitoring of large pool of data related to different types of immune cells is a critical requirement. Several gold standard methodologies such as flow cytometry, cytoTOF, ELISPOT and other immune-imaging techniques are routinely used for quantifying the phenotypic behavior of immune cells. These techniques involve the use of antibodies for specifically labeling each cell types, which makes the procedure expensive and laborious. Here, we are presenting a novel approach for label free detection of various types of immune cells using their inherent vibrational Raman signatures and a method of using the same data for cluster analysis. Raman spectroscopy is a well-established tool that measures the vibrational fingerprints of the analytes. It has been extensively used in biologic research for differentiating cells and tissues based on their Raman spectral features. Since the basic building block molecules of the cells are the same, variations in the spectral features among cells and tissues are minimal. Mathematical tools such as multivariate statistical analysis and machine learning methods are adopted to identify the significant Raman spectral features that cause the variation among groups (DC, macrophage, NK, T-cell, B cell, neutrophils, etc.). In immunology, no studies have been reported so far in understanding and recording the inherent Raman spectral finger prints of all forms of immune cells, both in the naive and active stage. In this study, we have created a spectral database of various immune cells such as T-cells, B cells, NK cells, dendritic cells, macrophages, neutrophils and their signature variations in activated and naive forms. These spectral databases can be used in machine learning algorithms to predict the treatment response in clinical and preclinical settings. Citation Format: Girish Chundayil Madathil, Raveena Nagareddy, Anjana Ramkumar, Manu Krishnan, Vijay Harish, Anusha Ashokan, Shanti Kumar Nair, Manzoor Koyakutty. Label-free Raman signatures of immune cells: A new tool for artificial intelligence in immunotherapy [abstract]. In: Proceedings of the Fourth CRI-CIMT-EATI-AACR International Cancer Immunotherapy Conference: Translating Science into Survival; Sept 30-Oct 3, 2018; New York, NY. Philadelphia (PA): AACR; Cancer Immunol Res 2019;7(2 Suppl):Abstract nr B028.