CLASS PICTURES: In 2016, CellProfiler Analyst got an upgrade. The 2.0 version comes with a new Image Gallery function (top image) to explore and visualize images. Images can be dropped into the platform’s classifier window (bottom image), which is equipped with several different popular machine-learning algorithms.BIOINFORMATICS, 32:3210-12, 2016It takes a trained eye to determine whether you’ve succeeded in turning a skin cell into a stem cell, or to distinguish between two related cell populations based on a handful of their surface markers. And even when such distinctions become obvious, looking for them in thousands of samples gets tedious. The appeal of machine learning is that a computer program can take over this heavy lifting for you—and do it even better, by seeing what you can’t.
Machine learning aims to make accurate predictions from large sets of data based on prior training using a smaller set of examples. In cell biology, this could mean, for example, being able to predict a cell’s phase or its identity based on its shape, size, or staining pattern.
Cell biology will increasingly rely on machine learning and other computational approaches as automated fluorescence microscopy (high-content screening) continues to capture massive sets of images that can be mined in multiple ways. Imaging applications of machine learning work by breaking an image down into numerical or other descriptors, called “features.” The algorithm then selects and classifies those features. In a branch of machine-learning methods called supervised learning, those classifications are tested for accuracy by measuring against the ...
