Forecasting Hi-C data at future time points

HiC4D: forecasting spatiotemporal Hi-C data with residual ConvLSTM. On the right: predicted (based on time points 1, 2, and 3) and true Hi-C heatmaps for time points 4, 5, and 6.

Single-Cell DNA Methylation Prediction

scHiMe: predicting single-cell DNA methylation levels based on single-cell Hi-C data.

Predicting ChIA-PET from Hi-C

DeepChIA-PET: Accurately predicting ChIA-PET from Hi-C and ChIP-seq with deep dilated networks.

Single-Cell 3D Genome

SCL: A lattice-based approach to infer three-dimensional chromosome structures from single-cell Hi-C data. On the right, SCL-inferred 3D structure of single-cell human (GM12878) inactivated X-chromosome.

Family Classification of TADs

TADKB: Family classification and a knowledge base of topologically associating domains. On the right, multiple TADs are highlighted in the 3D structure of human chromosome 10.

Enhance Hi-C Data Resolution

HiCNN: A very deep convolutional neural network to better enhance the resolution of Hi-C data. On the right, black circle indicates a chromatin interaction that is revealed after enhancement.

Protein Function Prediction

PANDA2: protein function prediction using graph neural networks

Protein Structure Prediction

Predicting residue-specific qualities of individual protein models using residual neural networks and graph neural networks