Hi-C data Resolution Enhancement using Deep Learning
Keywords: Hi-C; Deep Learning; Bioinformatics; Resolution Enhancement; 3D Genome; Super-Resolution
Fall 2019 - present
High throughput chromosome conformation capture (Hi-C) contact matrices are used to predict three-dimensional (3D) chromatin structures in eukaryotic cells.
High resolution Hi-C data are less available than low resolution Hi-C data due to sequencing costs, but provide greater insight into the intricate details of 3D chromatin structures such as enhancer-promoter interactions and sub-domains.
To provide a cost effective solution to high resolution Hi-C data collection,deep learning models are used to predict high resolution Hi-C matrices from existing low resolution matrices across multiple cell types.
- Hicks, P., & Oluwadare, O. (2022). HiCARN:Resolution Enhancement of Hi-C Data Using Cascading Residual Network. Bioinformatics. https://doi.org/10.1093/bioinformatics/btac156 [@ Bioinformatics][Funding: CRCW] [@ Parker's Video Presentation at a Conference at Concordia University Irvine]
[@ Won 2nd Place at 2022 President's Academic Showcase at Concordia University Irvine]
Abstract: Here, we present two Cascading Residual Networks called HiCARN-1 and HiCARN-2, a convolutional neural network and a generative adversarial network, that use a novel framework of cascading connections throughout the network for Hi-C contact matrix prediction from low-resolution data.
Shown by image evaluation and Hi-C reproducibility metrics, both HiCARN models, overall, outperform state-of-the-art Hi-C resolution enhancement algorithms in predictive accuracy for both human and mouse 1/16, 1/32, 1/64, and 1/100 downsampled high-resolution Hi-C data.
Also, validation by extracting topologically associating domains (TADs) and chromosome 3D structure predictions from the enhanced data shows that HiCARN can proficiently reconstruct biologically significant regions.
All our algorithms are made public, open-source, and freely accessible to all through our GitHub repository