The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Domain Adaptation and Generative Models for Single Cell Genomics with Gerald Quon - TWiML Talk #251
Apr 15, 2019
Gerald Quon, an assistant professor at UC Davis, specializes in leveraging deep learning for genomics and single-cell data analysis. He shares his insights on how deep domain adaptation and generative models are revolutionizing disease identification and treatment. Discover the novel methodologies he's developing to analyze complex diseases like schizophrenia and cancer. Quon also discusses the challenges of integrating multimodal data to enhance genomic analysis and the importance of user-friendly tools for biologists in this intricate field.
AI Snips
Chapters
Transcript
Episode notes
Career Start
- Gerald Quon's computational biology career began during his undergrad.
- Initially rejecting bioinformatics, he later found protein analysis fascinating.
Single-Cell Genomics
- Single-cell genomics provides high-resolution snapshots of human tissues, enabling disease identification.
- This technology generates significantly more data than traditional methods, allowing for deep learning applications.
Disease Research
- Researchers study diseases like cancer, Alzheimer's, and schizophrenia using single-cell genomics.
- Comparing data from healthy and diseased individuals reveals changes at different disease stages.