Large Language Model is Secretly a Protein Sequence Optimizer
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_ | 1866929680630677504 |
|---|---|
| author | Wang, Yinkai He, Jiaxing Du, Yuanqi Chen, Xiaohui Li, Jianan Canal Liu, Li-Ping Xu, Xiaolin Hassoun, Soha |
| author_facet | Wang, Yinkai He, Jiaxing Du, Yuanqi Chen, Xiaohui Li, Jianan Canal Liu, Li-Ping Xu, Xiaolin Hassoun, Soha |
| contents | We consider the protein sequence engineering problem, which aims to find protein sequences with high fitness levels, starting from a given wild-type sequence. Directed evolution has been a dominating paradigm in this field which has an iterative process to generate variants and select via experimental feedback. We demonstrate large language models (LLMs), despite being trained on massive texts, are secretly protein sequence optimizers. With a directed evolutionary method, LLM can perform protein engineering through Pareto and experiment-budget constrained optimization, demonstrating success on both synthetic and experimental fitness landscapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09274 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large Language Model is Secretly a Protein Sequence Optimizer Wang, Yinkai He, Jiaxing Du, Yuanqi Chen, Xiaohui Li, Jianan Canal Liu, Li-Ping Xu, Xiaolin Hassoun, Soha Machine Learning Artificial Intelligence Quantitative Methods We consider the protein sequence engineering problem, which aims to find protein sequences with high fitness levels, starting from a given wild-type sequence. Directed evolution has been a dominating paradigm in this field which has an iterative process to generate variants and select via experimental feedback. We demonstrate large language models (LLMs), despite being trained on massive texts, are secretly protein sequence optimizers. With a directed evolutionary method, LLM can perform protein engineering through Pareto and experiment-budget constrained optimization, demonstrating success on both synthetic and experimental fitness landscapes. |
| title | Large Language Model is Secretly a Protein Sequence Optimizer |
| topic | Machine Learning Artificial Intelligence Quantitative Methods |
| url | https://arxiv.org/abs/2501.09274 |