Scholarlink

<p>Rapid advancements in single-cell RNA sequencing (scRNA-seq) technology have significantly propelled research on cellular heterogeneity. However, the accurate identification and classification of cell types from large-scale single-cell datasets remains challenging. Graph convolutional networks (GCN) have gained popularity in single-cell analysis by effectively extracting features and annotating data using expression similarities and cell network structures, but the black-box nature hampers the interpretation of results, limiting their broader application. This study proposes scIMGCN, an innovative method for automated cell type annotation in single-cell datasets. This method incorporates advanced techniques to alleviate the constraints imposed by GCNs in practical contexts. First, graph structure representation is enhanced through network augmentation techniques, resulting in a 4.7% improvement in annotation accuracy. Second, an enhanced Transformer module addresses the issue of long-range dependencies in GCNs by dynamically modeling global relationships via its self-attention mechanism. This method removes the need for predefined graph structures, mitigates noise amplification, and achieves a 7.1% improvement in accuracy. Third, a GCN variant, based on the Kolmogorov-Arnold network (KAN), yielded improved feature representation and nonlinearity, achieving a 5.6% accuracy gain. Additionally, the model’s decision transparency is enhanced by an interpretability masking mechanism. Experiments indicate scIMGCN attains accuracy between 94.8% and 100% across ten real datasets, exceeding traditional methods by more than 15%. Moreover, scIMGCN demonstrated a 4.8% improvement over existing state-of-the-art graph-based methods, thus highlighting its enhanced accuracy and scalability. Overall, scIMGCN demonstrated enhanced performance in cell-type annotation by effectively modeling complex long-range intercellular relationships, thus improving model interpretability and generalizability. The self-complied codes are available at <a href="https://github.com/gladex/scIMGCN">https://github.com/gladex/scIMGCN</a>.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

scIMGCN: an Automatic Single-Cell Type Annotation Method Based on Interpretable Graph Convolutional Network

  • 期刊论文

  • 发表日期：

    2025年7月19日

查看全文
  • Binhua Tang,
  • Guowei Cheng,
  • Xinyu Gao

摘要

Rapid advancements in single-cell RNA sequencing (scRNA-seq) technology have significantly propelled research on cellular heterogeneity. However, the accurate identification and classification of cell types from large-scale single-cell datasets remains challenging. Graph convolutional networks (GCN) have gained popularity in single-cell analysis by effectively extracting features and annotating data using expression similarities and cell network structures, but the black-box nature hampers the interpretation of results, limiting their broader application. This study proposes scIMGCN, an innovative method for automated cell type annotation in single-cell datasets. This method incorporates advanced techniques to alleviate the constraints imposed by GCNs in practical contexts. First, graph structure representation is enhanced through network augmentation techniques, resulting in a 4.7% improvement in annotation accuracy. Second, an enhanced Transformer module addresses the issue of long-range dependencies in GCNs by dynamically modeling global relationships via its self-attention mechanism. This method removes the need for predefined graph structures, mitigates noise amplification, and achieves a 7.1% improvement in accuracy. Third, a GCN variant, based on the Kolmogorov-Arnold network (KAN), yielded improved feature representation and nonlinearity, achieving a 5.6% accuracy gain. Additionally, the model’s decision transparency is enhanced by an interpretability masking mechanism. Experiments indicate scIMGCN attains accuracy between 94.8% and 100% across ten real datasets, exceeding traditional methods by more than 15%. Moreover, scIMGCN demonstrated a 4.8% improvement over existing state-of-the-art graph-based methods, thus highlighting its enhanced accuracy and scalability. Overall, scIMGCN demonstrated enhanced performance in cell-type annotation by effectively modeling complex long-range intercellular relationships, thus improving model interpretability and generalizability. The self-complied codes are available at https://github.com/gladex/scIMGCN.

Graphical Abstract