Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.13650 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910504877817856 |
|---|---|
| author | Ghaffari, Saba Saleh, Ehsan Schwing, Alexander G. Wang, Yu-Xiong Burke, Martin D. Sinha, Saurabh |
| author_facet | Ghaffari, Saba Saleh, Ehsan Schwing, Alexander G. Wang, Yu-Xiong Burke, Martin D. Sinha, Saurabh |
| contents | Protein design, a grand challenge of the day, involves optimization on a fitness landscape, and leading methods adopt a model-based approach where a model is trained on a training set (protein sequences and fitness) and proposes candidates to explore next. These methods are challenged by sparsity of high-fitness samples in the training set, a problem that has been in the literature. A less recognized but equally important problem stems from the distribution of training samples in the design space: leading methods are not designed for scenarios where the desired optimum is in a region that is not only poorly represented in training data, but also relatively far from the highly represented low-fitness regions. We show that this problem of "separation" in the design space is a significant bottleneck in existing model-based optimization tools and propose a new approach that uses a novel VAE as its search model to overcome the problem. We demonstrate its advantage over prior methods in robustly finding improved samples, regardless of the imbalance and separation between low- and high-fitness samples. Our comprehensive benchmark on real and semi-synthetic protein datasets as well as solution design for physics-informed neural networks, showcases the generality of our approach in discrete and continuous design spaces. Our implementation is available at https://github.com/sabagh1994/PGVAE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_13650 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Robust Model-Based Optimization for Challenging Fitness Landscapes Ghaffari, Saba Saleh, Ehsan Schwing, Alexander G. Wang, Yu-Xiong Burke, Martin D. Sinha, Saurabh Machine Learning Artificial Intelligence Protein design, a grand challenge of the day, involves optimization on a fitness landscape, and leading methods adopt a model-based approach where a model is trained on a training set (protein sequences and fitness) and proposes candidates to explore next. These methods are challenged by sparsity of high-fitness samples in the training set, a problem that has been in the literature. A less recognized but equally important problem stems from the distribution of training samples in the design space: leading methods are not designed for scenarios where the desired optimum is in a region that is not only poorly represented in training data, but also relatively far from the highly represented low-fitness regions. We show that this problem of "separation" in the design space is a significant bottleneck in existing model-based optimization tools and propose a new approach that uses a novel VAE as its search model to overcome the problem. We demonstrate its advantage over prior methods in robustly finding improved samples, regardless of the imbalance and separation between low- and high-fitness samples. Our comprehensive benchmark on real and semi-synthetic protein datasets as well as solution design for physics-informed neural networks, showcases the generality of our approach in discrete and continuous design spaces. Our implementation is available at https://github.com/sabagh1994/PGVAE. |
| title | Robust Model-Based Optimization for Challenging Fitness Landscapes |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2305.13650 |