Automated High-Throughput\nAtomic Force Microscopy\nSingle-Cell Nanomechanical Assay Enabled by Deep Learning-Based Optical\nImage Recognition

Mechanical forces are essential for life activities,\nand the mechanical\nphenotypes of single cells are increasingly gaining attention. Atomic\nforce microscopy (AFM) has been a standard method for single-cell\nnanomechanical assays, but its efficiency is limited due to its reliance\non manual operation. Here, we present a study of deep learning image\nrecognition-assisted AFM that enables automated high-throughput single-cell\nnanomechanical measurements. On the basis of the label-free identification\nof the cell structures and the AFM probe in optical bright-field images\nas well as the consequent automated movement of the sample stage and\nAFM probe, the AFM probe tip could be accurately and sequentially\nmoved onto the specific parts of individual living cells to perform\na single-cell indentation assay or single-cell force spectroscopy\nin a time-efficient manner. The study illustrates a promising method\nbased on deep learning for achieving operator-independent high-throughput\nAFM single-cell nanomechanics, which will benefit the application\nof AFM in mechanobiology.