AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913573237686272 |
|---|---|
| author | Liu, Yungeng Chen, Zan Wang, Yu Guang Shen, Yiqing |
| author_facet | Liu, Yungeng Chen, Zan Wang, Yu Guang Shen, Yiqing |
| contents | Protein engineering is important for biomedical applications, but conventional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their training or implementation into protein engineering remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) for protein engineering. AutoPE innovatively allows biologists without DL backgrounds to interact with DL models using natural language, lowering the entry barrier for protein engineering tasks. Our AutoPE uniquely integrates LLMs with AutoML to handle model selection for both protein sequence and graph modalities, automatic hyperparameter optimization, and automated data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial performance improvements compared to traditional zero-shot and manual fine-tuning approaches. By bridging the gap between DL and biologists' domain expertise, AutoPE empowers researchers to leverage DL without extensive programming knowledge. Our code is available at https://github.com/tsynbio/AutoPE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_04440 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering Liu, Yungeng Chen, Zan Wang, Yu Guang Shen, Yiqing Quantitative Methods Protein engineering is important for biomedical applications, but conventional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their training or implementation into protein engineering remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) for protein engineering. AutoPE innovatively allows biologists without DL backgrounds to interact with DL models using natural language, lowering the entry barrier for protein engineering tasks. Our AutoPE uniquely integrates LLMs with AutoML to handle model selection for both protein sequence and graph modalities, automatic hyperparameter optimization, and automated data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial performance improvements compared to traditional zero-shot and manual fine-tuning approaches. By bridging the gap between DL and biologists' domain expertise, AutoPE empowers researchers to leverage DL without extensive programming knowledge. Our code is available at https://github.com/tsynbio/AutoPE. |
| title | AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2411.04440 |