---
title: "scSiameseClu: A Siamese Clustering Framework for Interpreting Single-cell RNA Sequencing Data"
authors:
  - "Ping Xu"
  - "Zhiyuan Ning"
  - "Pengjiang Li"
  - "Wenhao Liu"
  - "Pengyang Wang"
  - "Jiaxu Cui"
  - "Yuanchun Zhou"
  - "Pengfei Wang"
doi: "10.24963/ijcai.2025/875"
url: "https://ijcai.org/proceedings/2025/875"
pdf: "https://ijcai.org/proceedings/2025/0875.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "7867-7875"
track: "Main Track"
keywords:
  - "Machine Learning: ML: Applications"
  - "Data Mining: DM: Applications"
  - "Multidisciplinary Topics and Applications: MTA: Bioinformatics"
---

# scSiameseClu: A Siamese Clustering Framework for Interpreting Single-cell RNA Sequencing Data

Ping Xu, Zhiyuan Ning, Pengjiang Li, Wenhao Liu, Pengyang Wang, Jiaxu Cui, Yuanchun Zhou, Pengfei Wang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 7867-7875. DOI: [10.24963/ijcai.2025/875](https://doi.org/10.24963/ijcai.2025/875)

## Abstract

Single-cell RNA sequencing (scRNA-seq) reveals cell heterogeneity, with cell clustering playing a key role in identifying cell types and marker genes. Recent advances, especially graph neural networks (GNNs)-based methods, have significantly improved clustering performance. However, the analysis of scRNA-seq data remains challenging due to noise, sparsity, and high dimensionality. Compounding these challenges, GNNs often suffer from over-smoothing, limiting their ability to capture complex biological information. In response, we propose scSiameseClu, a novel Siamese Clustering framework for interpreting single-cell RNA-seq data, comprising of 3 key steps: (1) Dual Augmentation Module, which applies biologically informed perturbations to the gene expression matrix and cell graph relationships to enhance representation robustness; (2) Siamese Fusion Module, which combines cross-correlation refinement and adaptive information fusion to capture complex cellular relationships while mitigating over-smoothing; and (3) Optimal Transport Clustering, which utilizes Sinkhorn distance to efficiently align cluster assignments with predefined proportions while maintaining balance. Comprehensive evaluations on seven real-world datasets demonstrate that scSiameseClu outperforms state-of-the-art methods in single-cell clustering, cell type annotation, and cell type classification, providing a powerful tool for scRNA-seq data interpretation.