<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=1052243361488264&amp;ev=PageView&amp;noscript=1">

Data Dive - Wrangling Big Data Sets from Flow Cytometry

Posted on: November 20, 2019

Immunocology

Advances in immunology data analysis have taken this field into the realm of “Big Data.” Flow cytometers can now measure dozens of parameters, and complementary techniques like mass cytometry can deliver data that requires sophisticated data analysis methods. Modern data analysis approaches have also revolutionized personalized immunotherapy and improved diagnostics.

Data research ScientitstHere’s a primer to newer data analysis approaches that are being widely used to analyze complex data.

  1. Machine learning and t-SNE: Broadly speaking, machine learning is used to build models that make reasonable generalizations from input data. Computational biologists and data scientists have developed machine learning algorithms that can take high-dimensional flow data, and create two dimensional visualizations. T-stochastic neighbor embedding (t-SNE) is a method that uses dimensionality reduction to make bivariate plots that cluster cell subsets based on similar marker expression patterns.
  2. Machine learning and personalized immunotherapy: Machine learning methods have become instrumental in personalized immunotherapy research, and this is particularly evident in the area of identifying tumor antigens that can be immunotherapy targets. Mass spectrometry analysis combined with predictive modeling has allowed researchers to evaluate thousands of tumor peptides to identify candidates that can bind to antigen-presentation models like HLA-II, which is a critical parameter for developing tumor-specific immunotherapies mediated by T cell responses.
  3. Machine learning and improving treatment efficacy. One of the ongoing struggles in the field of immunotherapy is predicting which patients are most likely to be helped by specific treatments. Machine learning algorithms, specifically those suited for multifactorial modeling, are now being developed to analyze clinical trial data and identify parameters associated with better treatment outcomes.

Machine learning is a key area for the advancement of immunotherapy research, but this field can seem foreign to most biomedical researchers. Consider partnering with a contract research organization that has expertise in data analysis and machine learning. This partnership is valuable not only for data analysis, but is essential to protocol design and development in order to assure you have data that can be analyzed using these methods.

New call-to-action

Posted in: , , , , , ,

T Cell Exhaustion in Immuno-oncollogy
 

Recent Blog Posts

Receive Updates By Email

Computational Cytometry | Flow Cytometry Data Analysis in the Era of Quantitative Data Science
Download Accelerated CAR T Cell Therapy with Flow Cytometry
Flow Cytometry & Immunology Research
Flow Cytometry for Clinical Trials