The Multi-Scale Integrated Cell (MuSIC), a technique that combines microscopy, biochemistry and artificial intelligence, may provide new clues to human development and disease. The artist has a conceptual rendering. Credit: UC San Diego Health Sciences
Most human diseases can be traced to malfunctioning parts of a cell, for example a tumor is able to grow because a gene wasn't translated into a particularProtein or a metabolic disease arises because mitochondria aren't firing properly. To understand what parts of a cell can go wrong in a disease, scientists need a complete list of parts.
Researchers at the University of California San Diego School of Medicine and their partners have taken what they think may be a significant leap forward in understanding human cells by combining microscopy, biochemistry and artificial intelligence.
The Multi-Scale Integrated Cell technique is described in Nature.
If you imagine a cell, you'll probably see the colorful diagram in your cell biology textbook. Is that the whole story? Ideker is a professor at the UC San Diego School of Medicine and the Moores Cancer Center. Scientists have long realized that there is more that they don't know, but now they have a way to look deeper.
Ideker was the leader of the study with Emma Lundberg of the KTH Royal Institute of Technology.
Half of the components contained within a human kidney cell line had never been seen before, according to the pilot study. The researchers spotted a group of proteins. The structure was determined by working with UC San Diego colleague Gene Yeo. The complex is likely involved in a cellular event that helps determine which genes are activated at which times.
The insides of cells can be studied using either a microscope or a biophysical association. Researchers use florescent tags to track the movements of various colors to the microscope's field of view. To look at biophysical associations, researchers might use an antibody specific to a specificprotein to pull it out of the cell and see what else is attached to it.
The textbook cell diagrams imply that all parts are visible. Credit: OpenStax A new cell map shows many novel components. The purple and gold nodes represent new components. The size of the component shows the number of distinct proteins. Credit: UC San Diego Health Sciences
The team has been interested in the inner workings of cells for a long time. The use of deep learning to map the cell directly from cellular microscopy images is different to MuSIC.
The combination of these technologies is unique and powerful because it's the first time measurements at vastly different scales have been brought together.
Scientists can use microscopes to see down to the level of a single micron. The small elements can't be seen through a microscope. Scientists can get down to the nanometer scale with the help of biochemistry techniques.
How do you bridge the gap from nanometer to micron scale? Ideker is the founder of the UC Cancer Cell Map Initiative and the UC San Diego Center for Computational Biology and Bioinformatics. It's possible to do it with artificial intelligence, looking at data from multiple sources and asking the system to assemble it into a model of a cell.
The team trained the artificial intelligence platform to look at the data and build a model of the cell. The system doesn't yet map the cell contents to specific locations, like a textbook diagram, because their locations aren't necessarily fixed. Component locations are not static and can change depending on the situation.
Ideker said this was a pilot study to test MuSIC. They only looked at 661 and one cell type.
Ideker said that the next step was to blow through the entire human cell. We might be able to better understand the basis of many diseases by comparing healthy and sick cells.
There is a multi-scale map of cell structure. www.nature.com/articles/s41586-021-04115-9
Nature journal information.
A new artificial intelligence technique reveals that we might not know half of what's in our cells.
The document is copyrighted. Any fair dealing for the purpose of private study or research cannot be reproduced without written permission. The content is not intended to be used for anything other than information purposes.
