RESUMO
Quantifying cell biology in space and time requires computational methods to detect cells, measure their properties, and assemble these into meaningful trajectories. In this aspect, machine learning (ML) is having a transformational effect on bioimage analysis, now enabling robust cell detection in multidimensional image data. However, the task of cell tracking, or constructing accurate multi-generational lineages from imaging data, remains an open challenge. Most cell tracking algorithms are largely based on our prior knowledge of cell behaviors, and as such, are difficult to generalize to new and unseen cell types or datasets. Here, we propose that ML provides the framework to learn aspects of cell behavior using cell tracking as the task to be learned. We suggest that advances in representation learning, cell tracking datasets, metrics, and methods for constructing and evaluating tracking solutions can all form part of an end-to-end ML-enhanced pipeline. These developments will lead the way to new computational methods that can be used to understand complex, time-evolving biological systems.
RESUMO
Chromatin is highly structured, and changes in its organization are essential in many cellular processes, including cell division. Recently, advances in machine learning have enabled researchers to automatically classify chromatin morphology in fluorescence microscopy images. In this protocol, we develop user-friendly tools to perform this task. We provide an open-source annotation tool, and a cloud-based computational framework to train and utilize a convolutional neural network to automatically classify chromatin morphology. Using cloud compute enables users without significant resources or computational experience to use a machine learning approach to analyze their own microscopy data.
