BMCST: Balanced multi-view clustering for spatially resolved transcriptomics with Mamba-driven dynamic feature refinement

Open Webpage

Yanran Zhu, Xiao Zheng, Xiao He, Xin Zou, Peihong Wang, Chang Tang, Xinwang Liu, Kunlun He

Published: 2025, Last Modified: 15 Oct 2025Inf. Fusion 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A novel deep multi-view clustering network for SRT data termed as BMCST is proposed in this paper.•A Mamba-driven Dynamic Feature Refinement (MDFR) module is employed to optimize feature selection.•The unsupervised dominant view mining mechanism is utilized to tackle the view imbalance inherent in SRT data.•Extensive experiments demonstrate the outstanding performance of the proposed network.