Journal
GENOME RESEARCH
Volume 32, Issue 9, Pages 1787-1794Publisher
COLD SPRING HARBOR LAB PRESS, PUBLICATIONS DEPT
DOI: 10.1101/gr.276593.122
Keywords
-
Categories
Funding
- National Institutes of Health [R01 CA218094]
- Novartis
Ask authors/readers for more resources
This study proposes a method of creating large libraries of candidate sequences that meet an objective function at low cost, called computationally designed factorizable libraries. By representing objective functions as an inner product of feature vectors, the authors introduce an optimization method called stochastically annealed product spaces (SAPS). Using this approach, they successfully design diverse and efficient libraries of antibody CDR-H3 sequences with various optimized characteristics.
The successful discovery of novel biological therapeutics by selection requires highly diverse libraries of candidate sequences that contain a high proportion of desirable candidates. Here we propose the use of computationally designed factorizable libraries made of concatenated segment libraries as a method of creating large libraries that meet an objective function at low cost. We show that factorizable libraries can be designed efficiently by representing objective functions that describe sequence optimality as an inner product of feature vectors, which we use to design an optimization method we call stochastically annealed product spaces (SAPS). We then use this approach to design diverse and efficient libraries of antibody CDR-H3 sequences with various optimized characteristics.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available