Machine learning based cellular contractile force detection: a new approach to predict cell mechanics by images
Combining experiments with artificial intelligence algorithms, we propose a new machine learning based approach to extract the cellular force distributions from the microscope images. The full process can be divided into three steps. First, we culture the cells on a special substrate allowing to measure both the cellular traction force on the substrate and the corresponding substrate wrinkles simultaneously. The cellular forces are obtained using the traction force microscopy (TFM), at the same time that cell-generated contractile forces wrinkle their underlying substrate. Second, the wrinkle positions are extracted from the microscope images. Third, we train the machine learning system with GAN (generative adversarial network) by using sets of corresponding two images, the traction field and the input images (raw microscope images or extracted wrinkle images), as the training data. The network understands the way to convert the input images of the substrate wrinkles to the traction distribution from the training. After sufficient training, the network is utilized to predict the cellular forces just from the input images. Our system provides a powerful tool to evaluate the cellular forces efficiently because the forces can be predicted just by observing the cells under the microscope, which is a way simpler method compared to the TFM experiment. Additionally, the machine learning based approach presented here has the profound potential for being applied to diverse cellular assays for studying mechanobiology of cells. Significance StatementCell-generated forces are indispensable determinants of fundamental cell functions such as motility and cell division. As such, quantifying how the forces change upon perturbations to the cells such as gene mutations and drug administration is of profound importance. Here we present a novel machine learning based system that allows for efficient estimations of the forces that are determined only by "observing" microscope images. Given that the cellular traction forces are regulated downstream of diverse signaling pathways, our system - that helps significantly improve the throughput of the measurements - presents a new, high throughput platform for real time analysis of the effects of a massive number of genetic and molecular perturbations on the forces and resulting cell mechanics.