Improving Protein Optimization with Smoothed Fitness Landscapes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909125611356160 |
|---|---|
| author | Kirjner, Andrew Yim, Jason Samusevich, Raman Bracha, Shahar Jaakkola, Tommi Barzilay, Regina Fiete, Ila |
| author_facet | Kirjner, Andrew Yim, Jason Samusevich, Raman Bracha, Shahar Jaakkola, Tommi Barzilay, Regina Fiete, Ila |
| contents | The ability to engineer novel proteins with higher fitness for a desired property would be revolutionary for biotechnology and medicine. Modeling the combinatorially large space of sequences is infeasible; prior methods often constrain optimization to a small mutational radius, but this drastically limits the design space. Instead of heuristics, we propose smoothing the fitness landscape to facilitate protein optimization. First, we formulate protein fitness as a graph signal then use Tikunov regularization to smooth the fitness landscape. We find optimizing in this smoothed landscape leads to improved performance across multiple methods in the GFP and AAV benchmarks. Second, we achieve state-of-the-art results utilizing discrete energy-based models and MCMC in the smoothed landscape. Our method, called Gibbs sampling with Graph-based Smoothing (GGS), demonstrates a unique ability to achieve 2.5 fold fitness improvement (with in-silico evaluation) over its training set. GGS demonstrates potential to optimize proteins in the limited data regime. Code: https://github.com/kirjner/GGS |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_00494 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Improving Protein Optimization with Smoothed Fitness Landscapes Kirjner, Andrew Yim, Jason Samusevich, Raman Bracha, Shahar Jaakkola, Tommi Barzilay, Regina Fiete, Ila Biomolecules Machine Learning Quantitative Methods The ability to engineer novel proteins with higher fitness for a desired property would be revolutionary for biotechnology and medicine. Modeling the combinatorially large space of sequences is infeasible; prior methods often constrain optimization to a small mutational radius, but this drastically limits the design space. Instead of heuristics, we propose smoothing the fitness landscape to facilitate protein optimization. First, we formulate protein fitness as a graph signal then use Tikunov regularization to smooth the fitness landscape. We find optimizing in this smoothed landscape leads to improved performance across multiple methods in the GFP and AAV benchmarks. Second, we achieve state-of-the-art results utilizing discrete energy-based models and MCMC in the smoothed landscape. Our method, called Gibbs sampling with Graph-based Smoothing (GGS), demonstrates a unique ability to achieve 2.5 fold fitness improvement (with in-silico evaluation) over its training set. GGS demonstrates potential to optimize proteins in the limited data regime. Code: https://github.com/kirjner/GGS |
| title | Improving Protein Optimization with Smoothed Fitness Landscapes |
| topic | Biomolecules Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2307.00494 |