An Introduction to Computational Cytometry for Drug Discovery
Flow cytometry data analysis is evolving. The expanding use of automation in flow cytometry has enabled researchers to harness the capabilities of flow cytometers like the ZE5 Cell Analyzer to an even greater extent. It makes the collection of 30-parameter data, with hundreds of millions of data points, in 24 hours possible. Additionally, high-parameter spectral analysis has led to a huge increase in the volume of data that can be collected from a single sample.
It is becoming increasingly recognized that as the rate of data collection increases, we need to develop efficient strategies to analyze and interpret that data. Machine learning offers the tools we can use to realize the potential that new instrumentation technology brings and quickly convert data into biological insights.
In this webinar, Hefin Rhys, Flow Cytometry Facility Manager at UCB Pharma, published author and expert in machine learning, will introduce the concept of using machine learning techniques to interpret laboratory data with an emphasis on flow cytometry but including points applicable to broader principles.
You will learn:
- The general principles of applying computational techniques to cytometry data
- How to establish the capability for computational cytometry
- What a typical computational pipeline looks like for high-dimensional cytometry
- How computational techniques can be applied to high-throughput cytometry
- About commonly used R packages for computational cytometry
Hefin Rhys,
UCB Pharma
Hefin Rhys completed his PhD at the William Harvey Research Institute at Queen Mary University of London in 2017 following the completion of an MPharmacol degree from The University of Bath in 2013. He then worked as a research assistant at the prestigious Francis Crick Institute in London before joining UCB Pharma where he now co-manages a flow cytometry shared resource laboratory (SRL). His main interests are conventional, spectral, and imaging flow cytometry, and applying computational tools to these datasets. A data science and machine learning enthusiast, in 2020 Hefin published his book "Machine Learning with R, the tidyverse, and mlr" a practical guide to getting beginners started using machine learning tools.