@inproceedings{afnan-etal-2026-exploring,
title = "Exploring Novel Drug Research Area using Large Language Models Based on Research Trends in Biomedical Literature",
author = "Afnan, Afnan and
Van Supranes, Michael and
Nishiyama, Tomohiro and
Wakamiya, Shoko and
Aramaki, Eiji",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.81/",
pages = "997--1013",
ISBN = "979-8-89176-434-7",
abstract = "The rapid expansion of biomedical literature makes manual identification of novel drug-disease relationships increasingly difficult. Existing approaches have leveraged LLMs to mine abstracts or construct knowledge graphs for drug repurposing. There are two key limitations: finite context windows for capturing macro-level research trends, and single-pass black-box pipelines make it difficult to verify outputs. This paper proposes a pipeline for discovering new drug targets by combining disease and drug research trends using Large Language Models (LLMs). Our method extracts PICO components from PubMed abstracts, normalizing the Population and Intervention Component to ICD and ATC codes, respectively. A temporal frequency delta matrix is constructed to capture publication count shifts across 2013 to 2022, then used to discover novel drug areas. Compared with the abstract-based baseline, our approach showed qualitative signs of generating combinations that were more closely aligned with observed research trends and, in some cases, more clinically plausible. These findings suggest the potential usefulness of structured trend information for LLM-based exploration, although the differences between the two methods were limited and the results remain preliminary. Future work will focus on validating the consistency and reliability of these candidates."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afnan-etal-2026-exploring">
<titleInfo>
<title>Exploring Novel Drug Research Area using Large Language Models Based on Research Trends in Biomedical Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afnan</namePart>
<namePart type="family">Afnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Van Supranes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomohiro</namePart>
<namePart type="family">Nishiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shoko</namePart>
<namePart type="family">Wakamiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiji</namePart>
<namePart type="family">Aramaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>The rapid expansion of biomedical literature makes manual identification of novel drug-disease relationships increasingly difficult. Existing approaches have leveraged LLMs to mine abstracts or construct knowledge graphs for drug repurposing. There are two key limitations: finite context windows for capturing macro-level research trends, and single-pass black-box pipelines make it difficult to verify outputs. This paper proposes a pipeline for discovering new drug targets by combining disease and drug research trends using Large Language Models (LLMs). Our method extracts PICO components from PubMed abstracts, normalizing the Population and Intervention Component to ICD and ATC codes, respectively. A temporal frequency delta matrix is constructed to capture publication count shifts across 2013 to 2022, then used to discover novel drug areas. Compared with the abstract-based baseline, our approach showed qualitative signs of generating combinations that were more closely aligned with observed research trends and, in some cases, more clinically plausible. These findings suggest the potential usefulness of structured trend information for LLM-based exploration, although the differences between the two methods were limited and the results remain preliminary. Future work will focus on validating the consistency and reliability of these candidates.</abstract>
<identifier type="citekey">afnan-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.81/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>997</start>
<end>1013</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Novel Drug Research Area using Large Language Models Based on Research Trends in Biomedical Literature
%A Afnan, Afnan
%A Van Supranes, Michael
%A Nishiyama, Tomohiro
%A Wakamiya, Shoko
%A Aramaki, Eiji
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F afnan-etal-2026-exploring
%X The rapid expansion of biomedical literature makes manual identification of novel drug-disease relationships increasingly difficult. Existing approaches have leveraged LLMs to mine abstracts or construct knowledge graphs for drug repurposing. There are two key limitations: finite context windows for capturing macro-level research trends, and single-pass black-box pipelines make it difficult to verify outputs. This paper proposes a pipeline for discovering new drug targets by combining disease and drug research trends using Large Language Models (LLMs). Our method extracts PICO components from PubMed abstracts, normalizing the Population and Intervention Component to ICD and ATC codes, respectively. A temporal frequency delta matrix is constructed to capture publication count shifts across 2013 to 2022, then used to discover novel drug areas. Compared with the abstract-based baseline, our approach showed qualitative signs of generating combinations that were more closely aligned with observed research trends and, in some cases, more clinically plausible. These findings suggest the potential usefulness of structured trend information for LLM-based exploration, although the differences between the two methods were limited and the results remain preliminary. Future work will focus on validating the consistency and reliability of these candidates.
%U https://aclanthology.org/2026.bionlp-1.81/
%P 997-1013
Markdown (Informal)
[Exploring Novel Drug Research Area using Large Language Models Based on Research Trends in Biomedical Literature](https://aclanthology.org/2026.bionlp-1.81/) (Afnan et al., BioNLP 2026)
ACL