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

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

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

Original language description

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).

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10403 - Physical chemistry

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

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

Name of the periodical

BIOINFORMATICS

ISSN

—

e-ISSN

1367-4811

Volume of the periodical

41

Issue of the periodical within the volume

8

Country of publishing house

GB - UNITED KINGDOM

Number of pages

11

Pages from-to

"btaf449-1"-"btaf449-11"

UT code for WoS article

001554701100001

EID of the result in the Scopus database

2-s2.0-105013893294