Researchers have developed a new Machine Learning technique to accurately classify the state of macrophages, which are key immune cells.
It is important to classify macrophages because they can modify their behaviour and act as pro- or anti-inflammatory agents in the immune response. The Machine Learning technique developed by Trinity College Dublin will support future research and could have a major impact on healthcare and society.
The research has been published in the leading journal eLife.
What is Machine Learning?
According to the University of York, Machine Learning is a branch of both Artificial Intelligence (AI) and computer science. It uses an algorithm that replicates how humans learn and can organise vast amounts of data in a short amount of time.
Machine Learning algorithms are usually written to look for recurring themes and spot anomalies, and focus on making predictions more accurate.
Classifying key immune cells
This new approach could be useful for pharmaceutical companies looking to create treatments for targeted diseases and auto-immune conditions such as diabetes and cancer, which are all affected by cellular metabolism and macrophage function.
The importance of classifying macrophages is that it allows scientists to directly distinguish between macrophage states, which are based only on their metabolic response under certain conditions. This information could be employed as a diagnostic tool or to show the role of cell types in a disease environment.
The landmark used human macrophages in experiments, and was led by Michael Monaghan, Associate Professor in Biomedical Engineering at Trinity. The work brought together biomedical engineers, computer scientists and immunologists. Professor Monaghan comments:
“Currently, there are no other methods that employ artificial intelligence-based, machine learning approaches to macrophage classification. Several different techniques are currently used to classify macrophages, but all of these have significant drawbacks.
“Our method uses a 2-photon fluorescence lifetime imaging microscope (2P-FLIM), which is unique to Trinity and Ireland. 2P-FLIM does not require sample pre-treatment, can be used to follow changes in metabolism non-invasively and in real-time – which opens the door to tracking disease progression and/or physiological response to therapies — and it also requires a lower number of cells compared with conventional techniques.”
Nuno Neto, a PhD Candidate in the School of Engineering, added: “It is becoming increasingly clear that to solve many of society’s greatest problems, we need to take multi-disciplinary approaches to harness the expertise of people working in different fields.
“Trinity is rightly known as a leader in immunometabolism research, with many of our scientists focusing on how it regulates immune cell response, and how immune cell metabolism is impacted in diseases. This study benefits from that expertise, but also bridges the use of advanced computer science approaches and utilises an advanced microscope from the Biomedical Engineering Department with a regime never reported previously. It thus serves as a prime example of inter-departmental collaboration in a multidisciplinary field.”