HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Minghui, Wang, Yuanhang, Guo, Peijin, Wan, Wei, Hu, Shengshan, Hu, Shengqing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908622590574592
author Li, Minghui
Wang, Yuanhang
Guo, Peijin
Wan, Wei
Hu, Shengshan
Hu, Shengqing
author_facet Li, Minghui
Wang, Yuanhang
Guo, Peijin
Wan, Wei
Hu, Shengshan
Hu, Shengqing
contents Accurate prediction of Drug-Target Affinity (DTA) is crucial for reducing experimental costs and accelerating early screening in computational drug discovery. While sequence-based deep learning methods avoid reliance on costly 3D structures, they still overlook simultaneous modeling of global sequence semantic features and local topological structural features within drugs and proteins, and represent drugs as flat sequences without atomic-level, substructural-level, and molecular-level multi-scale features. We propose HiF-DTA, a hierarchical network that adopts a dual-pathway strategy to extract both global sequence semantic and local topological features from drug and protein sequences, and models drugs multi-scale to learn atomic, substructural, and molecular representations fused via a multi-scale bilinear attention module. Experiments on Davis, KIBA, and Metz datasets show HiF-DTA outperforms state-of-the-art baselines, with ablations confirming the importance of global-local extraction and multi-scale fusion.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27281
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction
Li, Minghui
Wang, Yuanhang
Guo, Peijin
Wan, Wei
Hu, Shengshan
Hu, Shengqing
Machine Learning
Artificial Intelligence
Accurate prediction of Drug-Target Affinity (DTA) is crucial for reducing experimental costs and accelerating early screening in computational drug discovery. While sequence-based deep learning methods avoid reliance on costly 3D structures, they still overlook simultaneous modeling of global sequence semantic features and local topological structural features within drugs and proteins, and represent drugs as flat sequences without atomic-level, substructural-level, and molecular-level multi-scale features. We propose HiF-DTA, a hierarchical network that adopts a dual-pathway strategy to extract both global sequence semantic and local topological features from drug and protein sequences, and models drugs multi-scale to learn atomic, substructural, and molecular representations fused via a multi-scale bilinear attention module. Experiments on Davis, KIBA, and Metz datasets show HiF-DTA outperforms state-of-the-art baselines, with ablations confirming the importance of global-local extraction and multi-scale fusion.
title HiF-DTA: Hierarchical Feature Learning Network for Drug-Target Affinity Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.27281