The enormous amount of data obtained by filming biological processes using a microscope used to be an obstacle to analyses. Thanks to artificial intelligence (AI), researchers at the University of Gothenburg can now follow the movement of cells in time and space. The method might be very useful for developing more effective cancer drugs.
Studying the movements and behaviors of cells and biological molecules under the microscope provides fundamental information to better understand the processes related to our health. Studies of cell behavior in different scenarios are important for the development of new medical technologies and treatments.
“Over the past two decades, optical microscopy has advanced considerably. It allows us to study biological life in great detail, both in space and time. Living systems move in all possible directions and at different speeds,” explains Jesús Pineda, PhD student. at the University of Gothenburg and first author of the scientific article in Intelligence of natural machines.
Mathematics describes the relationships of particles
Advances have provided researchers today with such vast amounts of data that analysis is nearly impossible. But now researchers at the University of Gothenburg have developed an AI method combining graph theory and neural networks that can select reliable information from video clips.
Graph theory is a mathematical structure used to describe the relationships between different particles in the sample under study. It is comparable to a social network in which particles interact and influence the behavior of others directly or indirectly.
“The AI method uses the graph information to adapt to different situations and can solve multiple tasks in different experiments. For example, our AI can reconstruct the path that individual cells or molecules take as they move to achieve a certain biological function. This means that researchers can test the effectiveness of different drugs and see how well they work as potential cancer treatments,” says Jesús Pineda.
Pharmaceutical companies are already using AI
AI also makes it possible to describe all the dynamic aspects of particles in situations where other methods would not be effective. For this reason, pharmaceutical companies have already incorporated this method into their research and development process.
Facts: Neural Networks Neural networks learn to collect the specific information a researcher is looking for from an image using self-supervised learning. The tool simplifies the analysis process and enables the collection of large amounts of detailed information from the data-rich videos.
