@inproceedings{liu-etal-2024-prott3,
title = "{P}rot{T}3: Protein-to-Text Generation for Text-based Protein Understanding",
author = "Liu, Zhiyuan and
Zhang, An and
Fei, Hao and
Zhang, Enzhi and
Wang, Xiang and
Kawaguchi, Kenji and
Chua, Tat-Seng",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.324",
doi = "10.18653/v1/2024.acl-long.324",
pages = "5949--5966",
abstract = "Language Models (LMs) excel in understanding textual descriptions of proteins, as evident in biomedical question-answering tasks. However, their capability falters with raw protein data, such as amino acid sequences, due to a deficit in pretraining on such data. Conversely, Protein Language Models (PLMs) can understand and convert protein data into high-quality representations, but struggle to process texts. To address their limitations, we introduce ProtT3, a framework for Protein-to-Text Generation for Text-based Protein Understanding. ProtT3 empowers an LM to understand protein sequences of amino acids by incorporating a PLM as its protein understanding module, enabling effective protein-to-text generation. This collaboration between PLM and LM is facilitated by a cross-modal projector (i.e., Q-Former) that bridges the modality gap between the PLM{'}s representation space and the LM{'}s input space. Unlike previous studies focusing on protein property prediction and protein-text retrieval, we delve into the largely unexplored field of protein-to-text generation. To facilitate comprehensive benchmarks and promote future research, we establish quantitative evaluations for protein-text modeling tasks, including protein captioning, protein question-answering, and protein-text retrieval. Our experiments show that ProtT3 substantially surpasses current baselines, with ablation studies further highlighting the efficacy of its core components. Our code is available at https://github.com/acharkq/ProtT3.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2024-prott3">
<titleInfo>
<title>ProtT3: Protein-to-Text Generation for Text-based Protein Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enzhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Kawaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tat-Seng</namePart>
<namePart type="family">Chua</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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</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>Language Models (LMs) excel in understanding textual descriptions of proteins, as evident in biomedical question-answering tasks. However, their capability falters with raw protein data, such as amino acid sequences, due to a deficit in pretraining on such data. Conversely, Protein Language Models (PLMs) can understand and convert protein data into high-quality representations, but struggle to process texts. To address their limitations, we introduce ProtT3, a framework for Protein-to-Text Generation for Text-based Protein Understanding. ProtT3 empowers an LM to understand protein sequences of amino acids by incorporating a PLM as its protein understanding module, enabling effective protein-to-text generation. This collaboration between PLM and LM is facilitated by a cross-modal projector (i.e., Q-Former) that bridges the modality gap between the PLM’s representation space and the LM’s input space. Unlike previous studies focusing on protein property prediction and protein-text retrieval, we delve into the largely unexplored field of protein-to-text generation. To facilitate comprehensive benchmarks and promote future research, we establish quantitative evaluations for protein-text modeling tasks, including protein captioning, protein question-answering, and protein-text retrieval. Our experiments show that ProtT3 substantially surpasses current baselines, with ablation studies further highlighting the efficacy of its core components. Our code is available at https://github.com/acharkq/ProtT3.</abstract>
<identifier type="citekey">liu-etal-2024-prott3</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.324</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.324</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>5949</start>
<end>5966</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ProtT3: Protein-to-Text Generation for Text-based Protein Understanding
%A Liu, Zhiyuan
%A Zhang, An
%A Fei, Hao
%A Zhang, Enzhi
%A Wang, Xiang
%A Kawaguchi, Kenji
%A Chua, Tat-Seng
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F liu-etal-2024-prott3
%X Language Models (LMs) excel in understanding textual descriptions of proteins, as evident in biomedical question-answering tasks. However, their capability falters with raw protein data, such as amino acid sequences, due to a deficit in pretraining on such data. Conversely, Protein Language Models (PLMs) can understand and convert protein data into high-quality representations, but struggle to process texts. To address their limitations, we introduce ProtT3, a framework for Protein-to-Text Generation for Text-based Protein Understanding. ProtT3 empowers an LM to understand protein sequences of amino acids by incorporating a PLM as its protein understanding module, enabling effective protein-to-text generation. This collaboration between PLM and LM is facilitated by a cross-modal projector (i.e., Q-Former) that bridges the modality gap between the PLM’s representation space and the LM’s input space. Unlike previous studies focusing on protein property prediction and protein-text retrieval, we delve into the largely unexplored field of protein-to-text generation. To facilitate comprehensive benchmarks and promote future research, we establish quantitative evaluations for protein-text modeling tasks, including protein captioning, protein question-answering, and protein-text retrieval. Our experiments show that ProtT3 substantially surpasses current baselines, with ablation studies further highlighting the efficacy of its core components. Our code is available at https://github.com/acharkq/ProtT3.
%R 10.18653/v1/2024.acl-long.324
%U https://aclanthology.org/2024.acl-long.324
%U https://doi.org/10.18653/v1/2024.acl-long.324
%P 5949-5966
Markdown (Informal)
[ProtT3: Protein-to-Text Generation for Text-based Protein Understanding](https://aclanthology.org/2024.acl-long.324) (Liu et al., ACL 2024)
ACL
- Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, and Tat-Seng Chua. 2024. ProtT3: Protein-to-Text Generation for Text-based Protein Understanding. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5949–5966, Bangkok, Thailand. Association for Computational Linguistics.