What is it about?
The paper describes a new method to predict the occurrence and exact locations of mitochondrial fission, fusion and depolarisation events in three dimensions using a single image and not a video. This can democratize research and revolutionize drug trials.
Featured Image
Photo by National Cancer Institute on Unsplash
Why is it important?
With mitochondria being recently shown to be at the heart of many diseases and disorders, it is now more important than ever to democratize research and revolutionize drug trials targeting this organelle. This machine learning method allows researchers to predict the occurrence and exact locations of mitochondrial fission, fusion and depolarisation events in three dimensions using a single image. It also indicates that enough information is contained in the morphology (or shape) of the mitochondria to predict its short term fate.
Perspectives
Despite the current method having relatively low accuracies. It should be noted that the machine learning method needed to find the exact location (within about 20 pixels) and the correct type of event (fission, fusion and depolarisation) to be considered a true positive. Therefore, it is surprising that it is capable of detecting a large number of these correctly only using a single z-stack (indicating that the morphology by itself contains all the required information). These accuracies are also expected to increase as larger datasets are used to train the model.
Rensu Theart
Stellenbosch University
Read the Original
This page is a summary of: Predicting mitochondrial fission, fusion and depolarisation event locations from a single z-stack, PLoS ONE, March 2023, PLOS,
DOI: 10.1371/journal.pone.0271151.
You can read the full text:
Resources
Contributors
The following have contributed to this page
