Low-N Protein Activity Optimization with FolDE
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912673846788096 |
|---|---|
| author | Roberts, Jacob B. Ji, Catherine R. Donnell, Isaac Young, Thomas D. Pearson, Allison N. Hudson, Graham A. Keiser, Leah S. Wesselkamper, Mia Winegar, Peter H. Ludwig, Janik Klass, Sarah H. Sheth, Isha V. Ukabiala, Ezechinyere C. Astolfi, Maria C. T. Eysenbach, Benjamin Keasling, Jay D. |
| author_facet | Roberts, Jacob B. Ji, Catherine R. Donnell, Isaac Young, Thomas D. Pearson, Allison N. Hudson, Graham A. Keiser, Leah S. Wesselkamper, Mia Winegar, Peter H. Ludwig, Janik Klass, Sarah H. Sheth, Isha V. Ukabiala, Ezechinyere C. Astolfi, Maria C. T. Eysenbach, Benjamin Keasling, Jay D. |
| contents | Proteins are traditionally optimized through the costly construction and measurement of many mutants. Active Learning-assisted Directed Evolution (ALDE) alleviates that cost by predicting the best improvements and iteratively testing mutants to inform predictions. However, existing ALDE methods face a critical limitation: selecting the highest-predicted mutants in each round yields homogeneous training data insufficient for accurate prediction models in subsequent rounds. Here we present FolDE, an ALDE method designed to maximize end-of-campaign success. In simulations across 20 protein targets, FolDE discovers 23% more top 10% mutants than the best baseline ALDE method (p=0.005) and is 55% more likely to find top 1% mutants. FolDE achieves this primarily through naturalness-based warm-starting, which augments limited activity measurements with protein language model outputs to improve activity prediction. We also introduce a constant-liar batch selector, which improves batch diversity; this is important in multi-mutation campaigns but had limited effect in our benchmarks. The complete workflow is freely available as open-source software, making efficient protein optimization accessible to any laboratory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24053 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Low-N Protein Activity Optimization with FolDE Roberts, Jacob B. Ji, Catherine R. Donnell, Isaac Young, Thomas D. Pearson, Allison N. Hudson, Graham A. Keiser, Leah S. Wesselkamper, Mia Winegar, Peter H. Ludwig, Janik Klass, Sarah H. Sheth, Isha V. Ukabiala, Ezechinyere C. Astolfi, Maria C. T. Eysenbach, Benjamin Keasling, Jay D. Machine Learning Quantitative Methods Proteins are traditionally optimized through the costly construction and measurement of many mutants. Active Learning-assisted Directed Evolution (ALDE) alleviates that cost by predicting the best improvements and iteratively testing mutants to inform predictions. However, existing ALDE methods face a critical limitation: selecting the highest-predicted mutants in each round yields homogeneous training data insufficient for accurate prediction models in subsequent rounds. Here we present FolDE, an ALDE method designed to maximize end-of-campaign success. In simulations across 20 protein targets, FolDE discovers 23% more top 10% mutants than the best baseline ALDE method (p=0.005) and is 55% more likely to find top 1% mutants. FolDE achieves this primarily through naturalness-based warm-starting, which augments limited activity measurements with protein language model outputs to improve activity prediction. We also introduce a constant-liar batch selector, which improves batch diversity; this is important in multi-mutation campaigns but had limited effect in our benchmarks. The complete workflow is freely available as open-source software, making efficient protein optimization accessible to any laboratory. |
| title | Low-N Protein Activity Optimization with FolDE |
| topic | Machine Learning Quantitative Methods |
| url | https://arxiv.org/abs/2510.24053 |