Biology subjects

Karbalayghareh, A.

Publications and source records attributed to Karbalayghareh, A..

8 recordsLinked to original sources

bioRxiv2026

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

Single-cell atlases of the tumor-immune microenvironment have defined numerous fine-grained immune cell states, but each study uses its own nomenclature and procedure for annotating cell types. Transferring annotations from a reference atlas to a query dataset is complicated by both batch effects and by the presence of query populations that the reference does not contain. Here we present scDIVA, a semi-supervised deep generative model that adapts the Domain Invariant Variational Autoencoder to scRNA-seq for fine-grained tumor-immune label transfer. Three encoders disentangle each cells expression profile into separate latent subspaces for cell type, batch, and residual variation; a single decoder reconstructs the cells expression profile from all three latent embeddings, and auxiliary classifiers on the cell type and batch embeddings encourage each encoder to capture the respective source of variation; scDIVAs cell type embeddings are batch-invariant by construction rather than through explicit or adversarial correction. Benchmarked against four established reference-mapping approaches--Harmony/Symphony, scANVI with scArches, scPoli with scArches, and Seurat with label transfer--across six tumor-immune atlases spanning five cancer types, scDIVA achieved the highest mean macro-F1 in five of six atlases and the highest biological conservation scores. To detect query-enriched populations, we adapted the Milo differential abundance (DA) framework, added a directional test, corrected spatialFDR weighting, and parallelized neighborhood distances for atlas-scale data, and applied it to scDIVAs cell type embeddings with reference- versus-query membership as the condition. This design correctly identified cell types held out from the reference as OOR and flagged exhausted CD8 T cells from a tumor-immune atlas as OOR relative to a healthy pan-tissue immune reference; conversely, this procedure confirmed a conserved immune landscape between two independent colorectal cancer cohorts. scDIVA thus couples fine-grained annotation and integration with an FDR-controlled test for states the reference lacks, solving both tasks required for accurate label transfer in tumor-immune scRNA-seq atlases.

bioinformatics↗

bioRxiv2026

DoFormer: Causal Transformer for Gene Perturbation

Learning causal gene regulatory mechanisms from single-cell data, and thereby predicting the effects of unseen perturbations, remains challenging. Observational RNA-seq data alone is insufficient for causal modeling, whereas perturbational data is essential. Classical causal inference methods often rely on unrealistic directed acyclic graph (DAG) assumptions and are not well suited to integrating multimodal data. Current transcriptomic foundation models also typically treat observational and perturbational data identically, limiting their ability to model perturbations. We present DoFormer, a causal multimodal Transformer that makes no DAG assumptions and leverages rich perturbational data to accurately predict previously unseen perturbations. DoFormer enables principled in silico perturbations by adapting the causal do-operator within the attention mechanism: the perturbed gene is set to the intervention value and prevented from attending to other genes, allowing the model to fully distinguish observational from interventional regimes. We train DoFormer using biologically informed loss functions and evaluate it with comprehensive perturbation prediction metrics. DoFormer substantially improves perturbation prediction relative to baseline and prior foundation models, underscoring the importance of intervention-aware architectures and biologically grounded objectives for causal modeling in single-cell genomics.

bioinformatics↗

bioRxiv2025

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

We present DynaVelo, a generative neural ordinary differential equation model that learns the joint dynamics of gene expression and transcription factor (TF) motif activities in evolving cell systems using single-cell multiome with joint gene expression and chromatin accesibility readout. DynaVelo leverages partial RNA velocity information together with single-cell TF motif accessibility data to improve the modeling of cell state dynamics and identification of TF drivers. We show that DynaVelo recovers the complex and bifurcating in vivo dynamics of wildtype murine germinal center (GC) B cells and reveals how these cell dynamics change under loss-of-function mutations in epigenetic regulators Arid1a and Ctcf. DynaVelo resolves how TF motif activities evolve along latent time trajectories using analysis of training cells or through generated trajectories from the model. In silico perturbation analysis further enables DynaVelo to infer dynamic and cell-state-specific gene regulatory networks (GRNs), recovering many known TF-to-gene edges in the wildtype GC GRN and predicting those that are disrupted in mutants. Finally, in silico gene and TF perturbations allow both the prediction of cell dynamics under loss-of-function genetic mutations and the identification of TF perturbations to rescue loss-of-function dynamic and immunological phenotypes. This analysis predicted that Ctcf knockout would rescue Arid1a loss-of-function phenotype in the GC reaction and nominated Bcl6 and Stat3 as additional TFs whose knockout would rescue Arid1a loss. We validated these predictions in vivo using double heterozygous mutant mice, confirming rescue of the Arid1a dark zone phenotype in all cases and quantitatively assessing model predictions using multiome in Arid1aHet;CtcfHet double heterozygous mice. DynaVelo therefore provides a powerful new deep learning framework for modeling and perturbing dynamic cell systems by harnessing single-cell multiome data sets.

systems biology↗

bioRxiv2024

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

AO_SCPLOWBSTRACTC_SCPLOWHi-C is a chromosome conformation capture assay used to study 3D genome organization. The recent development of single-cell Hi-C technologies has further enabled the examination of 3D chromatin organization in individual cells, although these approaches often suffer from low-coverage libraries and data sparsity. Here we introduce HiC2Self, a self-supervised framework for denoising Hi-C contact maps that requires only low-coverage data as input. HiC2Self not only reconstructs key structures (such as TADs and significant loops) from bulk libraries, but its self-supervised training framework also allows it to easily reconstruct cell-type-specific Hi-C structures without the generalization challenges faced by supervised models. HiC2Self can also accurately reconstruct significant loops from Micro-C data at 1 kb resolution. Moreover, when applied to single-nucleus methyl-3C data, HiC2Self successfully reconstructs local TAD structures around specific genes at 10 kb resolution with as few as 50 cells. Finally, HiC2Self enables the examination of single-cell structures at 50 kb resolution in individual cells of the same cell type. HiC2Self thus provides a general tool for denoising bulk, pseudo-bulk, and single-cell 3D contact maps to enable downstream analyses.

genomics↗

bioRxiv2023

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

Identifying transcriptional enhancers and their target genes is essential for understanding gene regulation and the impact of human genetic variation on disease1-6. Here we create and evaluate a resource of >13 million enhancer-gene regulatory interactions across 352 cell types and tissues, by integrating predictive models, measurements of chromatin state and 3D contacts, and large-scale genetic perturbations generated by the ENCODE Consortium7. We first create a systematic benchmarking pipeline to compare predictive models, assembling a dataset of 10,411 element-gene pairs measured in CRISPR perturbation experiments, >30,000 fine-mapped eQTLs, and 569 fine-mapped GWAS variants linked to a likely causal gene. Using this framework, we develop a new predictive model, ENCODE-rE2G, that achieves state-of-the-art performance across multiple prediction tasks, demonstrating a strategy involving iterative perturbations and supervised machine learning to build increasingly accurate predictive models of enhancer regulation. Using the ENCODE-rE2G model, we build an encyclopedia of enhancer-gene regulatory interactions in the human genome, which reveals global properties of enhancer networks, identifies differences in the functions of genes that have more or less complex regulatory landscapes, and improves analyses to link noncoding variants to target genes and cell types for common, complex diseases. By interpreting the model, we find evidence that, beyond enhancer activity and 3D enhancer-promoter contacts, additional features guide enhancer-promoter communication including promoter class and enhancer-enhancer synergy. Altogether, these genome-wide maps of enhancer-gene regulatory interactions, benchmarking software, predictive models, and insights about enhancer function provide a valuable resource for future studies of gene regulation and human genetics.

genomics↗

bioRxiv2023

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

The identification of cell-type-specific 3D chromatin interactions between regulatory elements can help to decipher gene regulation and to interpret the function of disease-associated non-coding variants. However, current chromosome conformation capture (3C) technologies are unable to resolve interactions at this resolution when only small numbers of cells are available as input. We therefore present ChromaFold, a deep learning model that predicts 3D contact maps and regulatory interactions from single-cell ATAC sequencing (scATAC-seq) data alone. ChromaFold uses pseudobulk chromatin accessibility, co-accessibility profiles across metacells, and predicted CTCF motif tracks as input features and employs a lightweight architecture to enable training on standard GPUs. Once trained on paired scATAC-seq and Hi-C data in human cell lines and tissues, ChromaFold can accurately predict both the 3D contact map and peak-level interactions across diverse human and mouse test cell types. In benchmarking against a recent deep learning method that uses bulk ATAC-seq, DNA sequence, and CTCF ChIP-seq to make cell-type-specific predictions, ChromaFold yields superior prediction performance when including CTCF ChIP-seq data as an input and comparable performance without. Finally, fine-tuning ChromaFold on paired scATAC-seq and Hi-C in a complex tissue enables deconvolution of chromatin interactions across cell subpopulations. ChromaFold thus achieves state-of-the-art prediction of 3D contact maps and regulatory interactions using scATAC-seq alone as input data, enabling accurate inference of cell-type-specific interactions in settings where 3C-based assays are infeasible.

bioinformatics↗

bioRxiv2021

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

Recent deep learning models that predict the Hi-C contact map from DNA sequence achieve promising accuracy but cannot generalize to new cell types and indeed do not capture cell-type-specific differences among training cell types. We propose Epiphany, a neural network to predict cell-type-specific Hi-C contact maps from five epigenomic tracks that are already available in hundreds of cell types and tissues: DNase I hypersensitive sites and ChIP-seq for CTCF, H3K27ac, H3K27me3, and H3K4me3. Epiphany uses 1D convolutional layers to learn local representations from the input tracks, a bidirectional long short-term memory (Bi-LSTM) layers to capture long term dependencies along the epigenome, as well as a generative adversarial network (GAN) architecture to encourage contact map realism. To improve the usability of predicted contact matrices, we trained and evaluated models using multiple normalization and matrix balancing techniques including KR, ICE, and HiC-DC+ Z-score and observed-over-expected count ratio. Epiphany is trained with a combination of MSE and adversarial (i.a., a GAN) loss to enhance its ability to produce realistic Hi-C contact maps for downstream analysis. Epiphany shows robust performance and generalization to held-out chromosomes within and across cell types and species, and its predicted contact matrices yield accurate TAD and significant interaction calls. At inference time, Epiphany can be used to study the contribution of specific epigenomic peaks to 3D architecture and to predict the structural changes caused by perturbations of epigenomic signals.

genomics↗

bioRxiv2021

Chromatin interaction aware gene regulatory modeling with graph attention networks

Linking distal enhancers to genes and modeling their impact on target gene expression are longstanding unresolved problems in regulatory genomics and critical for interpreting non-coding genetic variation. Here we present a new deep learning approach called GraphReg that exploits 3D interactions from chromosome conformation capture assays in order to predict gene expression from 1D epigenomic data or genomic DNA sequence. By using graph attention networks to exploit the connectivity of distal elements up to 2Mb away in the genome, GraphReg more faithfully models gene regulation and more accurately predicts gene expression levels than state-of-the-art deep learning methods for this task. Feature attribution used with GraphReg accurately identifies functional enhancers of genes, as validated by CRISPRi-FlowFISH and TAP-seq assays, outperforming both CNNs and the recently proposed Activity-by-Contact model. Sequence-based GraphReg also accurately predicts direct transcription factor (TF) targets as validated by CRISPRi TF knockout experiments via in silico ablation of TF binding motifs. GraphReg therefore represents an important advance in modeling the regulatory impact of epigenomic and sequence elements.

genomics↗