@inproceedings{zhang-etal-2024-prompt-based,
title = "Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery",
author = "Zhang, Ke and
Feng, Yimiao and
Zheng, Jie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1150",
pages = "13131--13142",
abstract = "Synthetic lethality (SL) offers a promising approach for targeted anti-cancer therapy. Deeply understanding SL gene pair mechanisms is vital for anti-cancer drug discovery. However, current wet-lab and machine learning-based SL prediction methods lack user-friendly and quantitatively evaluable explanations. To address these problems, we propose a prompt-based pipeline for generating natural language explanations. We first construct a natural language dataset named NexLeth. This dataset is derived from New Bing through prompt-based queries and expert annotations and contains 707 instances. NexLeth enhances the understanding of SL mechanisms and it is a benchmark for evaluating SL explanation methods. For the task of natural language generation for SL explanations, we combine subgraph explanations from an SL knowledge graph (KG) with instructions to construct novel personalized prompts, so as to inject the domain knowledge into the generation process. We then leverage the prompts to fine-tune pre-trained biomedical language models on our dataset. Experimental results show that the fine-tuned model equipped with designed prompts performs better than existing biomedical language models in terms of text quality and explainability, suggesting the potential of our dataset and the fine-tuned model for generating understandable and reliable explanations of SL mechanisms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-prompt-based">
<titleInfo>
<title>Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yimiao</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Synthetic lethality (SL) offers a promising approach for targeted anti-cancer therapy. Deeply understanding SL gene pair mechanisms is vital for anti-cancer drug discovery. However, current wet-lab and machine learning-based SL prediction methods lack user-friendly and quantitatively evaluable explanations. To address these problems, we propose a prompt-based pipeline for generating natural language explanations. We first construct a natural language dataset named NexLeth. This dataset is derived from New Bing through prompt-based queries and expert annotations and contains 707 instances. NexLeth enhances the understanding of SL mechanisms and it is a benchmark for evaluating SL explanation methods. For the task of natural language generation for SL explanations, we combine subgraph explanations from an SL knowledge graph (KG) with instructions to construct novel personalized prompts, so as to inject the domain knowledge into the generation process. We then leverage the prompts to fine-tune pre-trained biomedical language models on our dataset. Experimental results show that the fine-tuned model equipped with designed prompts performs better than existing biomedical language models in terms of text quality and explainability, suggesting the potential of our dataset and the fine-tuned model for generating understandable and reliable explanations of SL mechanisms.</abstract>
<identifier type="citekey">zhang-etal-2024-prompt-based</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1150</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13131</start>
<end>13142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery
%A Zhang, Ke
%A Feng, Yimiao
%A Zheng, Jie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-prompt-based
%X Synthetic lethality (SL) offers a promising approach for targeted anti-cancer therapy. Deeply understanding SL gene pair mechanisms is vital for anti-cancer drug discovery. However, current wet-lab and machine learning-based SL prediction methods lack user-friendly and quantitatively evaluable explanations. To address these problems, we propose a prompt-based pipeline for generating natural language explanations. We first construct a natural language dataset named NexLeth. This dataset is derived from New Bing through prompt-based queries and expert annotations and contains 707 instances. NexLeth enhances the understanding of SL mechanisms and it is a benchmark for evaluating SL explanation methods. For the task of natural language generation for SL explanations, we combine subgraph explanations from an SL knowledge graph (KG) with instructions to construct novel personalized prompts, so as to inject the domain knowledge into the generation process. We then leverage the prompts to fine-tune pre-trained biomedical language models on our dataset. Experimental results show that the fine-tuned model equipped with designed prompts performs better than existing biomedical language models in terms of text quality and explainability, suggesting the potential of our dataset and the fine-tuned model for generating understandable and reliable explanations of SL mechanisms.
%U https://aclanthology.org/2024.lrec-main.1150
%P 13131-13142
Markdown (Informal)
[Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery](https://aclanthology.org/2024.lrec-main.1150) (Zhang et al., LREC-COLING 2024)
ACL