A novel framework for single-cell Hi-C clustering based on graph-convolution-based imputation and two-phase-based feature extraction
Zhen, C.; Wang, Y.; Han, L.; Li, J.; Peng, J.; Wang, T.; Hao, J.; Shang, X.; Wei, Z.; Peng, J.
Show abstract
The three-dimensional genome structure plays a key role in cellular function and gene regulation. Singlecell Hi-C technology can capture genome structure information at the cell level, which provides the opportunity to study how genome structure varies among different cell types. However, few methods are well designed for single-cell Hi-C clustering, because of high sparsity, noise and heterogeneity of single-cell Hi-C data. In this manuscript, we propose a novel framework, named ScHiC-Rep, for singlecell Hi-C data representation and clustering. ScHiC-Rep mainly contains two parts: data imputation and feature extraction. In the imputation part, a novel imputation workflow is proposed, including graph convolution-based, random walk with restart-based and genomic neighbor-based imputation. In the feature extraction part, a two-phase feature extraction method is proposed, including linear phase for chromosome level and non-linear phase for cell level feature extraction. The evaluation results show that the proposed framework outperforms existing state-of-the-art approaches on both human and mouse datasets.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Predicting cell types with supervised contrastive learning on cells and their types 96%
- Novel cancer subtyping method based on patient-specific gene regulatory network 94%
- DeepInsight-3D for precision oncology: an improved anti-cancer drug response prediction from high-dimensional multi-omics data with convolutional neural networks 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.