Preference optimization of protein language models as a multi-objective binder design paradigm
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911790539997184 |
|---|---|
| author | Mistani, Pouria Mysore, Venkatesh |
| author_facet | Mistani, Pouria Mysore, Venkatesh |
| contents | We present a multi-objective binder design paradigm based on instruction fine-tuning and direct preference optimization (DPO) of autoregressive protein language models (pLMs). Multiple design objectives are encoded in the language model through direct optimization on expert curated preference sequence datasets comprising preferred and dispreferred distributions. We show the proposed alignment strategy enables ProtGPT2 to effectively design binders conditioned on specified receptors and a drug developability criterion. Generated binder samples demonstrate median isoelectric point (pI) improvements by $17\%-60\%$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04187 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Preference optimization of protein language models as a multi-objective binder design paradigm Mistani, Pouria Mysore, Venkatesh Biological Physics Artificial Intelligence Computational Engineering, Finance, and Science Biomolecules We present a multi-objective binder design paradigm based on instruction fine-tuning and direct preference optimization (DPO) of autoregressive protein language models (pLMs). Multiple design objectives are encoded in the language model through direct optimization on expert curated preference sequence datasets comprising preferred and dispreferred distributions. We show the proposed alignment strategy enables ProtGPT2 to effectively design binders conditioned on specified receptors and a drug developability criterion. Generated binder samples demonstrate median isoelectric point (pI) improvements by $17\%-60\%$. |
| title | Preference optimization of protein language models as a multi-objective binder design paradigm |
| topic | Biological Physics Artificial Intelligence Computational Engineering, Finance, and Science Biomolecules |
| url | https://arxiv.org/abs/2403.04187 |