Sheng Ye ^1* Jue Wang ² Mingmin Zhu ¹ Sisi Yuan ³ Linlin Zhuo ⁴ Tiancong Chen ⁵ Jinjian Gao ¹

• ¹ Wenzhou Medical University, Wenzhou, China
• ² Shandong University, Jinan, Shandong Province, China
• ³ University of North Carolina at Charlotte, Charlotte, North Carolina, United States
• ⁴ Wenzhou University of Technology, Wenzhou, China
• ⁵ Wenzhou People’s Hospital, Wenzhou, Zhejiang Province, China

The growing microbial resistance to traditional medicines necessitates in-depth analysis of medicine-microbe interactions (MMIs) to develop new therapeutic strategies. Widely used artificial intelligence models are limited by sparse observational data and prevalent noise, leading to over-reliance on specific data for feature extraction and reduced generalization ability. To address these limitations, we integrate Kolmogorov-Arnold Networks (KANs), independent subspaces, and collaborative decoding techniques into the masked graph autoencoder (Mask GAE) framework, creating an innovative MMI prediction model with enhanced accuracy, generalization, and interpretability. First, we apply Bernoulli distribution to randomly mask parts of the medicinemicrobe graph, advancing self-supervised training and reducing noise impact. Additionally, the independent subspace technique enables graph neural networks (GNNs) to learn weights independently across different feature subspaces, enhancing feature expression. Fusing the multi-layer outputs of GNNs effectively reduces information loss caused by masking. Moreover, using KANs for advanced nonlinear mapping enhances the learnability and interpretability of weights, deepening the understanding of complex MMIs.These measures significantly enhanced the accuracy, generalization, and interpretability of our model in MMI prediction tasks. We validated our model on three public datasets with results showing that our model 1 Sample et al. outperformed existing leading models. The relevant data and code are publicly accessible at: https://github.com/zhuoninnin1992/MKAN-MMI.