MEGDTA: multi-modal drug-target affinity prediction based on protein three-dimensional structure and ensemble graph neural network

MEGDTA is validated on three publicly available benchmark datasets, Davis, KIBA and Metz. A comparative study is conducted with other existing models. The results show that MEGDTA performs strongly in terms of mean squared error (MSE) and concordance index (CI), and r<sup>2</sup><sub>m</sub>, which demonstrate the effectiveness of MEGDTA.

Authors

Haixia Zhai
Zhanwei Hou (ORCID: https://orcid.org/0000-0002-0111-9228)
Yulian Ding (ORCID: https://orcid.org/0000-0001-7435-7094)
Junwei Luo (ORCID: https://orcid.org/0000-0001-6841-9893)
Yijun Li (ORCID: https://orcid.org/0000-0002-7251-2000)
Yi Pan (ORCID: https://orcid.org/0009-0009-5417-6013)

Institutions

Henan Polytechnic University (CN)

Publication Details

Journal: BMC Genomics
Published: 2025-08-11
DOI: https://doi.org/10.1186/s12864-025-11943-w
Citations: 4
Primary Topic: Computational Drug Discovery Methods
Type: article
Field-Weighted Citation Impact: 6.02

Funders

Science and Technology Department of Henan Province

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

MEGDTA: multi-modal drug-target affinity prediction based on protein three-dimensional structure and ensemble graph neural network

Haixia Zhai, Zhanwei Hou, Yulian Ding, Junwei Luo et al.

Aug 11, 2025

4 citations

BMC Genomics

Computational Drug Discovery Methods

6.02

article

MEGDTA: multi-modal drug-target affinity prediction based on protein three-dimensional structure and ensemble graph neural network

Haixia Zhai, Zhanwei Hou, Yulian Ding, Junwei Luo, Yijun Li, Yi Pan

August 11, 2025article en

4 citations

Abstract

MEGDTA is validated on three publicly available benchmark datasets, Davis, KIBA and Metz. A comparative study is conducted with other existing models. The results show that MEGDTA performs strongly in terms of mean squared error (MSE) and concordance index (CI), and r<sup>2</sup><sub>m</sub>, which demonstrate the effectiveness of MEGDTA.

BMC GenomicsVol. 26(1)

Henan Polytechnic University (CN)

Science and Technology Department of Henan Province

Openalex Percentile: Top 4%

Computational Drug Discovery Methods

6.02

DOI Open Access PDF OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

MEGDTA: multi-modal drug-target affinity prediction based on protein three-dimensional structure and ensemble graph neural network — Haixia Zhai, Zhanwei Hou, et al. · BMC Genomics (2025) | TGRS Research Map | TGRS