Researchers from the Hatzakis lab at the University of Copenhagen’s Department of Chemistry have developed a machine learning algorithm that can track clumping under the microscope in real-time, allowing for the automatic mapping and tracking of the important characteristics of clumped-up building blocks that cause Alzheimer’s and other neurodegenerative disorders. This breakthrough will make it easier to study microscopic images of clumping proteins, which could lead to the development of new therapies for neurodegenerative brain disorders. The algorithm can spot protein clumps down to a billionth of a meter in microscopy images, count and group them according to their shapes and sizes, and track their development over time.
Understanding why clumps form is crucial for developing new drugs and therapies to combat these disorders. The ability to see, track, and quantify clumps over time is essential for gaining a fundamental understanding of these structures. The algorithm developed by the researchers at the Department of Chemistry allows for this information to be gathered automatically and effectively, enabling researchers to better understand diseases and try to stop them. The researchers are currently using the tool to conduct experiments with insulin molecules to understand how clumps are affected by different compounds and develop new drugs once the microscopic building blocks have been clearly identified.
The new algorithm will facilitate the gathering of comprehensive knowledge about the shapes and functions of proteins and molecules, helping to create a large library of molecule and protein structures related to various disorders and biology in general. This will contribute to a better understanding of diseases and aid in developing strategies to combat them. The algorithm is freely available on the internet as open source, allowing scientific researchers and others working to understand the clumping of proteins and other molecules to use the tool for their research. With this tool, researchers hope to make significant progress in the field of neurodegenerative disorders and other diseases related to protein clumping.
Nearly 100,000 Danes over the age of 65 and more than 55 million people around the world live with dementia-related disorders, such as Alzheimer’s and Parkinson’s. These diseases occur when proteins clump together and destroy vital functions in the body, leading to neurodegenerative disorders. Studying this phenomenon has been challenging and limited due to a lack of proper tools. The machine learning algorithm developed by the researchers at the University of Copenhagen’s Department of Chemistry addresses this issue by allowing for the real-time tracking and characterization of clumping proteins under the microscope.
The researchers hope that their work will contribute to the development of new therapies for neurodegenerative brain disorders by providing a better understanding of the clumping of proteins. The algorithm can identify protein clumps at a microscopic level, count and group them based on their shapes and sizes, and track their development over time. By studying clumps through a microscope, researchers can observe variations in shape and structure that are associated with different disorders, allowing for a more comprehensive understanding of the processes involved. The tool developed by the researchers will enable researchers to automatically and effectively study clumping proteins, paving the way for new insights and potential treatments for neurodegenerative disorders and other diseases caused by protein clumping.