In collaboration with the Imaging Platform of the Broad Institute, we develop deep-learning-based methods for detecting and measuring the phenotypes of cells in biomedical images. This includes cell segmentation, feature embeddings, phenotype classification, and image synthesis, with applications in drug discovery and functional genomics.
Combining biological data
Cellular events have multiple dimensions, including time, phenotypic variations, and molecular changes, among others. Modern technologies allow us to observe cells at high resolution in each of those dimensions separately. We want to use machine learning for assembling these pieces together, and for discovering meaningful biological relationships and processes.
Automating biological experiments
From wet lab tests to data processing, there are numerous routine jobs requiring sparse human intervention to be completed. We aim to fully automate these jobs using machine learning to complete experiments faster and more accurately. Intelligent agents can free up researchers’ time to focus on higher level scientific creativity, and also scale up studies and reduce costs.