Leveraging large language models for literature-driven prioritization of protein binding pockets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15310%2F25%3A73635235" target="_blank" >RIV/61989592:15310/25:73635235 - isvavai.cz</a>

Výsledek na webu

<a href="https://academic.oup.com/bioinformatics/article/41/8/btaf449/8225722" target="_blank" >https://academic.oup.com/bioinformatics/article/41/8/btaf449/8225722</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1093/bioinformatics/btaf449" target="_blank" >10.1093/bioinformatics/btaf449</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Leveraging large language models for literature-driven prioritization of protein binding pockets

Popis výsledku v původním jazyce

Motivation Accurately identifying and prioritizing protein binding pockets is a foundational element of small-molecule drug discovery. Defining these known pockets currently relies on a laborious manual process of extracting key residue data from selected publications, reconciling inconsistent terminology, and independently computing volumetric representations. This manual curation to ensure biological relevance is time-consuming, error-prone, and represents a major bottleneck for efficient, high-throughput drug discovery. Results We present a novel approach for the identification and prioritization of protein binding pockets for small molecules by combining geometric pocket detection with large language models (LLMs). Our method leverages Fpocket to generate candidate pockets, which are then validated against published experimental data extracted from research articles using LLM with a series of prompts fine-tuned to identify and extract residue-level information associated with experimentally confirmed binding sites. We developed a curated benchmark dataset of diverse proteins and associated literature to train and evaluate the LLM&apos;s performance in paper relevance assessment and pocket extraction. Availability and implementation The developed benchmark dataset and methodology are freely available at the GitHub repository (https://github.com/receptor-ai/LLM-benchmark-dataset) and Zenodo (DOI: 10.5281/zenodo.15798647).

Název v anglickém jazyce

Leveraging large language models for literature-driven prioritization of protein binding pockets

Popis výsledku anglicky

Motivation Accurately identifying and prioritizing protein binding pockets is a foundational element of small-molecule drug discovery. Defining these known pockets currently relies on a laborious manual process of extracting key residue data from selected publications, reconciling inconsistent terminology, and independently computing volumetric representations. This manual curation to ensure biological relevance is time-consuming, error-prone, and represents a major bottleneck for efficient, high-throughput drug discovery. Results We present a novel approach for the identification and prioritization of protein binding pockets for small molecules by combining geometric pocket detection with large language models (LLMs). Our method leverages Fpocket to generate candidate pockets, which are then validated against published experimental data extracted from research articles using LLM with a series of prompts fine-tuned to identify and extract residue-level information associated with experimentally confirmed binding sites. We developed a curated benchmark dataset of diverse proteins and associated literature to train and evaluate the LLM&apos;s performance in paper relevance assessment and pocket extraction. Availability and implementation The developed benchmark dataset and methodology are freely available at the GitHub repository (https://github.com/receptor-ai/LLM-benchmark-dataset) and Zenodo (DOI: 10.5281/zenodo.15798647).

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10403 - Physical chemistry

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

BIOINFORMATICS

ISSN

—

e-ISSN

1367-4811

Svazek periodika

41

Číslo periodika v rámci svazku

8

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

11

Strana od-do

"btaf449-1"-"btaf449-11"

Kód UT WoS článku

001554701100001

EID výsledku v databázi Scopus

2-s2.0-105013893294