$22 for talk and buffet lunch.
$5 for talk only. Please state “talk only” after your name when you register. You could order separately from Baylands Café.
Registration deadline: 4pm on the Monday preceding the talk. If you miss the deadline, please pay $5 at the door and you could order food from Baylands Café.
"Deep Learning for a Single Cell."
Deep learning is transforming the ability of life scientists to extract information from images. While these techniques have superior accuracy in comparison to conventional approaches and enable previously impossible analyses, their unique hardware and software requirements have prevented widespread adoption by life scientists. Specifically, they require significant amounts of training data and computational power.
In this talk, I will relay our group’s experience—both the successes and challenges—in adapting deep learning for single-cell analysis. By leveraging crowdsourcing, we have constructed datasets with over 250,000 unique cellular annotations. These data enable even simple deep learning models to perform accurate segmentation and tracking of single-cells in live-cell imaging experiments. Based on such methods, we have accurately quantified single cells in genomics experiments that retain spatial information, and have constructed an immune cell atlas of solid tumors.
I will also discuss our lab’s new software, DeepCell (http://www.deepcell.org), to train and deploy deep learning models for cells in the cloud. By scaling compute power to meet analysis demand, we can significantly reduce the time necessary for large-scale cellular image analysis.
About our speaker
David is an Assistant Professor of Biology and Biological Engineering at Caltech. His group studies the quantitative and physical principles underlying the behavior of complex biological systems using host-virus interactions as a model system.
David received his undergraduate degrees in Mathematics and Physics from MIT in 2003. He then matriculated into the UCLA/Caltech MD/PhD program where he completed his PhD in Applied Physics in 2011 and his MD degree in 2013. David was a postdoctoral fellow in the Bioengineering department at Stanford for four years prior to joining the faculty at Caltech.
David's recent work includes adapting deep learning methods to perform single cell analysis, and techniques to measure signaling dynamics and RNA sequencing in the same individual cell. At Caltech, David and his group seek to understand how living systems and their respective viruses encode and decode information about their internal state and their environment. To do so, they combine ideas from cell biology and physics with recent advances in imaging, machine learning, and genomics to make novel measurements of the interactions between viruses and their hosts.