@inproceedings{liu-etal-2025-autoproteinengine,
title = "{A}uto{P}rotein{E}ngine: A Large Language Model Driven Agent Framework for Multimodal {A}uto{ML} in Protein Engineering",
author = "Liu, Yungeng and
Chen, Zan and
Wang, Yuguang and
Shen, Yiqing",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.36/",
pages = "422--430",
abstract = "Protein engineering is important for various biomedical applications, but traditional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their implementation remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an innovative agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) in protein engineering. AutoPE introduces a conversational interface that 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 both protein sequence and graph modalities, automate hyperparameter optimization, and facilitate data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial improvements in model performance 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 advanced computational tools without extensive programming knowledge."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-autoproteinengine">
<titleInfo>
<title>AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yungeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuguang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqing</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Protein engineering is important for various biomedical applications, but traditional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their implementation remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an innovative agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) in protein engineering. AutoPE introduces a conversational interface that 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 both protein sequence and graph modalities, automate hyperparameter optimization, and facilitate data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial improvements in model performance 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 advanced computational tools without extensive programming knowledge.</abstract>
<identifier type="citekey">liu-etal-2025-autoproteinengine</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.36/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>422</start>
<end>430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering
%A Liu, Yungeng
%A Chen, Zan
%A Wang, Yuguang
%A Shen, Yiqing
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F liu-etal-2025-autoproteinengine
%X Protein engineering is important for various biomedical applications, but traditional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their implementation remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an innovative agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) in protein engineering. AutoPE introduces a conversational interface that 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 both protein sequence and graph modalities, automate hyperparameter optimization, and facilitate data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial improvements in model performance 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 advanced computational tools without extensive programming knowledge.
%U https://aclanthology.org/2025.coling-industry.36/
%P 422-430
Markdown (Informal)
[AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering](https://aclanthology.org/2025.coling-industry.36/) (Liu et al., COLING 2025)
ACL