Related Experiment Video
Updated: Jul 9, 2025
10:28
Reusable Single Cell for Iterative Epigenomic Analyses
Published on: February 11, 2022
1.3K
Subgraph extraction and graph representation learning for single cell Hi-C imputation and clustering
Jiahao Zheng1, Yuedong Yang1, Zhiming Dai1
1School of Computer Science and Engineering, Sun Yat-Sen University, 510006 Guangzhou, China.
Briefings in Bioinformatics
|December 1, 2023
Summary
Single-cell Hi-C (scHi-C) data analysis is improved by HiC-SGL, a new imputation model. This method enhances 3D chromatin structure analysis by accurately filling missing data and improving cell clustering.
Area of Science:
- Genomics and Bioinformatics
- Epigenetics and Chromatin Biology
Background:
- Single-cell Hi-C (scHi-C) technology reveals 3D chromatin structure heterogeneity.
- scHi-C data analysis faces significant challenges due to extensive missing values.
Purpose of the Study:
- To develop an advanced imputation model for scHi-C data.
- To improve the accuracy of 3D chromatin structure analysis at the single-cell level.
Main Methods:
- Introduced HiC-SGL, a novel imputation method utilizing Subgraph extraction and graph representation learning.
- HiC-SGL incorporates the ability to learn informative low-dimensional cell embeddings.
Main Results:
- HiC-SGL demonstrated superior imputation accuracy compared to existing methods.
- The model achieved enhanced cell clustering performance based on multiple evaluation metrics.
Conclusions:
- HiC-SGL effectively addresses the challenge of missing data in scHi-C.
- This method offers a significant advancement for analyzing 3D genome organization variability in single cells.
