Institute of Cage Sciences. Allen (Seattle) presented his new project to create the first predictive (predictive, probabilistic) 3D model of a living human cell.
The Allen Integrated Cell project combines two technologies that broaden our understanding of how differentiated pluripotent stem cells can differ (hiPSC). The first technology is a model showing the organization of organelles in specific cells, and the other, predicted, reflects the probable shape and location of organelles in any cell, even an unknown science.
Before creating a 3D model of a cell, scientists “edited” a huge array of human cells, and then introduced some of them fluorescent protein labels to highlight specific intracellular structures. Then the scientists shot tens of thousands of frames of the “highlighted” cells and “passed” them through the AI, which on their basis created a probabilistic model of a living cell.
In the next stage, the researchers applied another machine learning algorithm to the images obtained. On the basis of information from experiments with “illuminated” cells, AI came to the conclusion that cells that are not labeled with protein tags are virtually indistinguishable from them. This is very important in conducting such experiments, since fluorescence microscopy is quite toxic and costly.
The Allen Integrated Cell project is in free public access on the Internet. With its help, scientists will be able to better understand intracellular processes, which will help predict and track various negative changes leading to severe, in particular, cancer.js.src = “&version=v2.8”; 'script', 'facebook-jssdk'));