Ghulam Murtaza

scWeave translates between gene expression and chromatin structure at single-cell resolution using deep learning, improving cross-modality inference across multiple datasets.

This paper presents near-complete, haplotype-resolved assemblies of a pancreatic cancer genome and normal tissue, identifying extensive somatic variants and epigenetic changes in previously excluded regions.

Puget predicts gene expression across cell types using sequence and Hi-C data, improving generalization to new biosamples and species.

Evo2HiC improves prediction of 3D genome architecture and epigenomic signals by integrating DNA sequences and Hi-C data, achieving better accuracy and computational efficiency.

scContrast is a contrastive learning method for embedding scRNA-seq data into a universal space, outperforming existing methods in integrating data from different sequencing protocols.

GrapHiC improves Hi-C read imputation by integrating Hi-C and ChIP-seq data in a graph framework, enhancing performance on sparse and cross-cell-type inputs.

scGrapHiC uses deep learning to predict cell-type-specific scHi-C contact maps from scRNA-seq data, improving recovery of Topologically Associating Domains by 23.2% over baselines.

This paper evaluates deep-learning methods for improving Hi-C resolution using experimentally generated datasets and finds they perform poorly on sparse data, with retraining offering limited improvement.