Variational Graph Auto-encoder for Denoising Single-cell Hi-C Data

Neda Shokraneh Kenari, Maxwell Libbrecht
Proceedings of the 20th Machine Learning in Computational Biology meeting, PMLR 311:213-229, 2025.

Abstract

Single-cell Hi-C (scHi-C) enables the study of 3D genome organization at the resolution of individual cells and cell types that cannot be isolated for bulk profiling. However, the extreme sparsity of scHi-C data presents major challenges, particularly in recovering cell-type-specific 3D structures when only a small number of cells are available. We introduce contactVI, a method that combines the strengths of graph-based models and variational autoencoders (VAEs) to account for spatial dependencies in noisy chromatin interaction data and effectively denoise them. On simulated data, contactVI outperforms existing imputation methods in recovering Hi-C contact maps at both the single-cell and cell-type levels. On real datasets, contactVI performs comparably to or better than other graph-based methods across different resolutions. When applied to jointly profiled single-cell Hi-C and RNA-seq data, contactVI successfully recovers the expected association between genome compartmentalization and gene expression.

Cite this Paper

BibTeX
@InProceedings{pmlr-v311-shokraneh-kenari25a, title = {Variational Graph Auto-encoder for Denoising Single-cell Hi-C Data}, author = {Shokraneh Kenari, Neda and Libbrecht, Maxwell}, booktitle = {Proceedings of the 20th Machine Learning in Computational Biology meeting}, pages = {213--229}, year = {2025}, editor = {Knowles, David A and Koo, Peter K}, volume = {311}, series = {Proceedings of Machine Learning Research}, month = {10--11 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v311/main/assets/shokraneh-kenari25a/shokraneh-kenari25a.pdf}, url = {https://proceedings.mlr.press/v311/shokraneh-kenari25a.html}, abstract = {Single-cell Hi-C (scHi-C) enables the study of 3D genome organization at the resolution of individual cells and cell types that cannot be isolated for bulk profiling. However, the extreme sparsity of scHi-C data presents major challenges, particularly in recovering cell-type-specific 3D structures when only a small number of cells are available. We introduce contactVI, a method that combines the strengths of graph-based models and variational autoencoders (VAEs) to account for spatial dependencies in noisy chromatin interaction data and effectively denoise them. On simulated data, contactVI outperforms existing imputation methods in recovering Hi-C contact maps at both the single-cell and cell-type levels. On real datasets, contactVI performs comparably to or better than other graph-based methods across different resolutions. When applied to jointly profiled single-cell Hi-C and RNA-seq data, contactVI successfully recovers the expected association between genome compartmentalization and gene expression.} }
Endnote
%0 Conference Paper %T Variational Graph Auto-encoder for Denoising Single-cell Hi-C Data %A Neda Shokraneh Kenari %A Maxwell Libbrecht %B Proceedings of the 20th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2025 %E David A Knowles %E Peter K Koo %F pmlr-v311-shokraneh-kenari25a %I PMLR %P 213--229 %U https://proceedings.mlr.press/v311/shokraneh-kenari25a.html %V 311 %X Single-cell Hi-C (scHi-C) enables the study of 3D genome organization at the resolution of individual cells and cell types that cannot be isolated for bulk profiling. However, the extreme sparsity of scHi-C data presents major challenges, particularly in recovering cell-type-specific 3D structures when only a small number of cells are available. We introduce contactVI, a method that combines the strengths of graph-based models and variational autoencoders (VAEs) to account for spatial dependencies in noisy chromatin interaction data and effectively denoise them. On simulated data, contactVI outperforms existing imputation methods in recovering Hi-C contact maps at both the single-cell and cell-type levels. On real datasets, contactVI performs comparably to or better than other graph-based methods across different resolutions. When applied to jointly profiled single-cell Hi-C and RNA-seq data, contactVI successfully recovers the expected association between genome compartmentalization and gene expression.
APA
Shokraneh Kenari, N. & Libbrecht, M.. (2025). Variational Graph Auto-encoder for Denoising Single-cell Hi-C Data. Proceedings of the 20th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 311:213-229 Available from https://proceedings.mlr.press/v311/shokraneh-kenari25a.html.

Related Material