KANPM-DTA: improving drug–target affinity prediction with Kolmogorov–Arnold networks and pretrained models

TL;DR

KANPM-DTA is a new deep learning framework that improves drug–target affinity predictions by combining advanced modeling techniques and pretrained models, leading to better performance on benchmark datasets.

Contribution

The novel integration of Kolmogorov–Arnold networks and ESM-guided protein graphs enhances prediction accuracy and interpretability for drug–target affinity.

Findings

KANPM-DTA outperforms existing methods on Davis, KIBA, Metz, and BindingDB datasets with significant MSE reductions and CI increases.

The model achieves improved performance through a gated fusion mechanism and linear attention for capturing cross-modal dependencies.

A case study on the epidermal growth factor receptor demonstrates its effectiveness in predicting affinities for unknown drug–target pairs.

Abstract

Accurate drug–target affinity (DTA) prediction is critical for drug discovery and repurposing. However, existing models often struggle with generalizing to unseen drug–target pairs, lack interpretability, and fail to integrate heterogeneous biological features effectively. To overcome these challenges, we introduce KANPM-DTA, a deep learning framework designed to capture richer biochemical interactions and improve prediction reliability. Specifically, an ESM-guided protein graph construction strategy incorporates evolutionary and structural information to overcome underexplored protein representations. A gated fusion mechanism was employed to integrate drug–protein graph features, while linear attention captures cross-modal dependencies that enhance discriminative power. For the final affinity prediction, a Kolmogorov–Arnold network was used, offering a stronger nonlinear approximation and improved interpretability. Comprehensive experiments on benchmark datasets demonstrate that KANPM-DTA significantly outperforms state-of-the-art methods. On the Davis, KIBA, Metz, and BindingDB datasets, we achieved significant performance improvements under warm setting, with MSE reductions of 6.42%, 4.86%, 4.44%, and 5.46%, CI increases of 0.45%, 0.34%, 0.48%, and 0.80%, and \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{upgreek}
\usepackage{mathrsfs}
\setlength{\oddsidemargin}{-69pt}
\begin{document}
$r_{m}^{2}$\end{document} gains of 1.85%, 0.90%, 0.84%, and 1.05%, respectively. Moreover, a case study on the epidermal growth factor receptor further highlights the effectiveness of KANPM-DTA in predicting DTAs for unknown drug–target pairs, emphasizing its potential for real-world applications in drug discovery. However, wet-lab validation is required to assess the applicability of the results.

Figures