During early development, tissues and organs begin to bloom through the shifting, splitting, and growing of many hundreds of cells.
A team of MIT engineers has now developed a technique to predict, minute by minute, how individual cells will fold, divide, and rearrange during a fruit fly’s earliest stage of growth. The brand new method may in the future be applied to predict the event of more complex tissues, organs, and organisms. It could also help scientists discover cell patterns that correspond to early-onset diseases, reminiscent of asthma and cancer.
In a study appearing today within the journal , the team presents a brand new deep-learning model that learns, then predicts, how certain geometric properties of individual cells will change as a fruit fly develops. The model records and tracks properties reminiscent of a cell’s position, and whether it’s touching a neighboring cell at a given moment.
The team applied the model to videos of developing fruit fly embryos, each of which starts as a cluster of about 5,000 cells. They found the model could predict, with 90 percent accuracy, how each of the 5,000 cells would fold, shift, and rearrange, minute by minute, in the course of the first hour of development, because the embryo morphs from a smooth, uniform shape into more defined structures and features.
“This very initial phase is often called gastrulation, which takes place over roughly one hour, when individual cells are rearranging on a time scale of minutes,” says study writer Ming Guo, associate professor of mechanical engineering at MIT. “By accurately modeling this early period, we are able to begin to uncover how local cell interactions give rise to global tissues and organisms.”
The researchers hope to use the model to predict the cell-by-cell development in other species, such zebrafish and mice. Then, they’ll begin to discover patterns which might be common across species. The team also envisions that the tactic could possibly be used to discern early patterns of disease, reminiscent of in asthma. Lung tissue in individuals with asthma looks markedly different from healthy lung tissue. How asthma-prone tissue initially develops is an unknown process that the team’s latest method could potentially reveal.
“Asthmatic tissues show different cell dynamics when imaged live,” says co-author and MIT graduate student Haiqian Yang. “We envision that our model could capture these subtle dynamical differences and supply a more comprehensive representation of tissue behavior, potentially improving diagnostics or drug-screening assays.”
The study’s co-authors are Markus Buehler, the McAfee Professor of Engineering in MIT’s Department of Civil and Environmental Engineering; George Roy and Tomer Stern of the University of Michigan; and Anh Nguyen and Dapeng Bi of Northeastern University.
Points and foams
Scientists typically model how an embryo develops in one among two ways: as some extent cloud, where each point represents a person cell as point that moves over time; or as a “foam,” which represents individual cells as bubbles that shift and slide against one another, just like the bubbles in shaving foam.
Relatively than choose from the 2 approaches, Guo and Yang embraced each.
“There’s a debate about whether to model as some extent cloud or a foam,” Yang says. “But each of them are essentially other ways of modeling the identical underlying graph, which is a chic technique to represent living tissues. By combining these as one graph, we are able to highlight more structural information, like how cells are connected to one another as they rearrange over time.”
At the guts of the brand new model is a “dual-graph” structure that represents a developing embryo as each moving points and bubbles. Through this dual representation, the researchers hoped to capture more detailed geometric properties of individual cells, reminiscent of the situation of a cell’s nucleus, whether a cell is touching a neighboring cell, and whether it’s folding or dividing at a given moment in time.
As a proof of principle, the team trained the brand new model to “learn” how individual cells change over time during fruit fly gastrulation.
“The general shape of the fruit fly at this stage is roughly an ellipsoid, but there are gigantic dynamics happening on the surface during gastrulation,” Guo says. “It goes from entirely smooth to forming a variety of folds at different angles. And we wish to predict all of those dynamics, moment to moment, and cell by cell.”
Where and when
For his or her latest study, the researchers applied the brand new model to high-quality videos of fruit fly gastrulation taken by their collaborators on the University of Michigan. The videos are one-hour recordings of developing fruit flies, taken at single-cell resolution. What’s more, the videos contain labels of individual cells’ edges and nuclei — data which might be incredibly detailed and difficult to return by.
“These videos are of extremely prime quality,” Yang says. “This data may be very rare, where you get submicron resolution of the entire 3D volume at a fairly fast frame rate.”
The team trained the brand new model with data from three of 4 fruit fly embryo videos, such that the model might “learn” how individual cells interact and alter as an embryo develops. They then tested the model on a wholly latest fruit fly video, and located that it was in a position to predict with high accuracy how a lot of the embryo’s 5,000 cells modified from minute to minute.
Specifically, the model could predict properties of individual cells, reminiscent of whether they’ll fold, divide, or proceed sharing an edge with a neighboring cell, with about 90 percent accuracy.
“We find yourself predicting not only whether these items will occur, but in addition when,” Guo says. “As an illustration, will this cell detach from this cell seven minutes from now, or eight? We are able to tell when that may occur.”
The team believes that, in principle, the brand new model, and the dual-graph approach, should give you the chance to predict the cell-by-cell development of other multiceullar systems, reminiscent of more complex species, and even some human tissues and organs. The limiting factor is the supply of high-quality video data.
“From the model perspective, I believe it’s ready,” Guo says. “The actual bottleneck is the info. If we’ve got good quality data of specific tissues, the model could possibly be directly applied to predict the event of many more structures.”
This work is supported, partly, by the U.S. National Institutes of Health.
