After clicking “Watch Now” you will be prompted to login or join.
Deep Learning-Based Subcellular Phenotyping of Cell Edge Dynamics Reveals Fine-Grained Drug Responses
Kwonmoo Lee, Worcester Polytechnic Institute
GTC 2020
We'll highlight how unsupervised deep learning can reveal subcellular drug responses hidden in the heterogeneity in live cell images. We'll present a feature-learning method for time-series data, which combines long short-term memory autoencoder and the prior information from traditional machine-learning analysis. We'll discuss how feature learning can be used to identify drug-related rare phenotypes and accelerate drug discovery. You need to have basic knowledge about autoencoder, clustering, microscopy, and cell biology.