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

arXiv: https://arxiv.org/abs/2510.27281 · HTML: https://mlsanity.com/paper/2510.27281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [DeepDTA: Deep Drug-Target Binding Affinity Prediction](https://mlsanity.com/paper/1801.10193/) (2018)
- [FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction](https://mlsanity.com/paper/2406.01651/) (2024)
- [ViDTA: Enhanced Drug-Target Affinity Prediction via Virtual Graph Nodes and Attention-based Feature Fusion](https://mlsanity.com/paper/2412.19589/) (2024)
- [Multi-Modality Representation Learning for Antibody-Antigen Interactions Prediction](https://mlsanity.com/paper/2503.17666/) (2025)
- [HCAF-DTA: drug-target binding affinity prediction with cross-attention fused hypergraph neural networks](https://mlsanity.com/paper/2504.02014/) (2025)
- [Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning](https://mlsanity.com/paper/2506.00936/) (2025)

## Abstract (arXiv)

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.