Alireza Karbalayghareh

scDIVA: semi-supervised integration and fine-grained annotation of tumor-immune single-cell atlases

scDIVA transfers fine-grained immune cell type annotations between tumor-immune scRNA-seq datasets by integrating batch correction and detecting novel cell states.

HiC2Self: self-supervised denoising for bulk and single-cell Hi-C contact maps

HiC2Self denoises Hi-C contact maps using self-supervised learning, reconstructing 3D chromatin structures from low-coverage data across bulk and single-cell samples.

DoFormer: Causal Transformer for Gene Perturbation

DoFormer improves perturbation prediction by using a causal Transformer that distinguishes observational from interventional regimes without DAG assumptions.

Deep dynamical models of single-cell multiomic velocities predict loss-of-function and rescue perturbations in B cells

ChromaFold predicts the 3D contact map from single-cell chromatin accessibility

ChromaFold predicts 3D chromatin contact maps from scATAC-seq data, outperforming bulk-based methods and enabling cell-type-specific interaction analysis.

An encyclopedia of enhancer-gene regulatory interactions in the human genome

ENCODE-rE2G, a classifier trained on K562 CRISPR perturbations, maps 13,455,443 enhancer-gene interactions across 352 biosamples, matching or exceeding prior models on CRISPR, eQTL, and GWAS benchmarks.

Epiphany: predicting Hi-C contact maps from 1D epigenomic signals

Epiphany predicts cell-type-specific Hi-C contact maps from epigenomic signals, showing robust performance across cell types and species.

Chromatin interaction aware gene regulatory modeling with graph attention networks

This paper introduces GraphReg, a deep learning model that uses graph attention networks to predict gene expression from epigenomic data and genomic sequences, outperforming existing methods in modeling gene regulation and identifying functional enhancers.