@inproceedings{zeinalipour-etal-2024-design,
title = "Design Proteins Using Large Language Models: Enhancements and Comparative Analyses",
author = "Zeinalipour, Kamyar and
Jamshidi, Neda and
Bianchini, Monica and
Maggini, Marco and
Gori, Marco",
editor = "Edwards, Carl and
Wang, Qingyun and
Li, Manling and
Zhao, Lawrence and
Hope, Tom and
Ji, Heng",
booktitle = "Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.langmol-1.5",
doi = "10.18653/v1/2024.langmol-1.5",
pages = "34--47",
abstract = "Pre-trained LLMs have demonstrated substantial capabilities across a range of conventional natural language processing (NLP) tasks, such as summarization and entity recognition. In this paper, we explore the application of LLMs in the generation of high-quality protein sequences. Specifically, we adopt a suite of pre-trained LLMs, including Mistral-7B, Llama-2-7B, Llama-3-8B, and gemma-7B, to produce valid protein sequences. All of these models are publicly available (https://github.com/KamyarZeinalipour/protein-design-LLMs).Unlike previous work in this field, our approach utilizes a relatively small dataset comprising 42,000 distinct human protein sequences. We retrain these models to process protein-related data, ensuring the generation of biologically feasible protein structures. Our findings demonstrate that even with limited data, the adapted models exhibit efficiency comparable to established protein-focused models such as ProGen varieties, ProtGPT2, and ProLLaMA, which were trained on millions of protein sequences. To validate and quantify the performance of our models, we conduct comparative analyses employing standard metrics such as pLDDT, RMSD, TM-score, and REU. Furthermore, we commit to making the trained versions of all four models publicly available, fostering greater transparency and collaboration in the field of computational biology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeinalipour-etal-2024-design">
<titleInfo>
<title>Design Proteins Using Large Language Models: Enhancements and Comparative Analyses</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamyar</namePart>
<namePart type="family">Zeinalipour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neda</namePart>
<namePart type="family">Jamshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Bianchini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Maggini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carl</namePart>
<namePart type="family">Edwards</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Hope</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained LLMs have demonstrated substantial capabilities across a range of conventional natural language processing (NLP) tasks, such as summarization and entity recognition. In this paper, we explore the application of LLMs in the generation of high-quality protein sequences. Specifically, we adopt a suite of pre-trained LLMs, including Mistral-7B, Llama-2-7B, Llama-3-8B, and gemma-7B, to produce valid protein sequences. All of these models are publicly available (https://github.com/KamyarZeinalipour/protein-design-LLMs).Unlike previous work in this field, our approach utilizes a relatively small dataset comprising 42,000 distinct human protein sequences. We retrain these models to process protein-related data, ensuring the generation of biologically feasible protein structures. Our findings demonstrate that even with limited data, the adapted models exhibit efficiency comparable to established protein-focused models such as ProGen varieties, ProtGPT2, and ProLLaMA, which were trained on millions of protein sequences. To validate and quantify the performance of our models, we conduct comparative analyses employing standard metrics such as pLDDT, RMSD, TM-score, and REU. Furthermore, we commit to making the trained versions of all four models publicly available, fostering greater transparency and collaboration in the field of computational biology.</abstract>
<identifier type="citekey">zeinalipour-etal-2024-design</identifier>
<identifier type="doi">10.18653/v1/2024.langmol-1.5</identifier>
<location>
<url>https://aclanthology.org/2024.langmol-1.5</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>34</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Design Proteins Using Large Language Models: Enhancements and Comparative Analyses
%A Zeinalipour, Kamyar
%A Jamshidi, Neda
%A Bianchini, Monica
%A Maggini, Marco
%A Gori, Marco
%Y Edwards, Carl
%Y Wang, Qingyun
%Y Li, Manling
%Y Zhao, Lawrence
%Y Hope, Tom
%Y Ji, Heng
%S Proceedings of the 1st Workshop on Language + Molecules (L+M 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zeinalipour-etal-2024-design
%X Pre-trained LLMs have demonstrated substantial capabilities across a range of conventional natural language processing (NLP) tasks, such as summarization and entity recognition. In this paper, we explore the application of LLMs in the generation of high-quality protein sequences. Specifically, we adopt a suite of pre-trained LLMs, including Mistral-7B, Llama-2-7B, Llama-3-8B, and gemma-7B, to produce valid protein sequences. All of these models are publicly available (https://github.com/KamyarZeinalipour/protein-design-LLMs).Unlike previous work in this field, our approach utilizes a relatively small dataset comprising 42,000 distinct human protein sequences. We retrain these models to process protein-related data, ensuring the generation of biologically feasible protein structures. Our findings demonstrate that even with limited data, the adapted models exhibit efficiency comparable to established protein-focused models such as ProGen varieties, ProtGPT2, and ProLLaMA, which were trained on millions of protein sequences. To validate and quantify the performance of our models, we conduct comparative analyses employing standard metrics such as pLDDT, RMSD, TM-score, and REU. Furthermore, we commit to making the trained versions of all four models publicly available, fostering greater transparency and collaboration in the field of computational biology.
%R 10.18653/v1/2024.langmol-1.5
%U https://aclanthology.org/2024.langmol-1.5
%U https://doi.org/10.18653/v1/2024.langmol-1.5
%P 34-47
Markdown (Informal)
[Design Proteins Using Large Language Models: Enhancements and Comparative Analyses](https://aclanthology.org/2024.langmol-1.5) (Zeinalipour et al., LangMol-WS 2024)
ACL