University of Washington
Deep Learning and Cloud Science for the Engineering of Biological Molecules and Systems
Abstract
dc:description.abstractSolving many of the greatest challenges facing our industrial landscape and therapeutic de- velopment will require innovations in both computational and experimental biology alike. Deep learning has demonstrated it capacity to model complex systems in Natural Language Processing, Computer Vision, and Protein Modeling, and is poised to continue pioneering state-of-the-art results for modeling biological molecules and networks. Furthermore, cloud science laboratories have the potential to become a significant driving force in the acquisi- tion of massive biological datasets, as well as in the future of reproducible and accessible life science research. The following document discusses a list of research projects focused on these emerging fields. Chapters 1 and 2 investigate novel deep learning models and workflows for the design of protein minibinders. Chapter 3 considers a new protocol for the computational design of protein-binding macrocycle therapeutics. Chapter 4 explores the utility of cloud laboratories for experimental biology, and illustrates a low-cost, high- throughput protocol for enzyme characterization. Finally, Chapter 5 details a new deep learning approach for simulating metabolic systems.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Armer, Chase
- Advisor dc:contributor.advisor
-
- Sauro, Herbert
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- CC BY
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1773/49607