A generalizable framework to comprehensively predict epigenome, chromatin organization, and transcriptome

Zhang, Zhenhao; Feng, Fan; Qiu, Yiyang; Liu, Jie

doi:10.1093/nar/gkad436

Cited by 12 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ablation experiments with ChromaFold demonstrated that co-accessibility from scATAC-seq gave a significant performance improvement over pseudobulk accessibility alone. While a number of models including EPCOT 40 and C.Origami have relied on bulk ATAC-seq as an input signal to help generalization across cell types, our results suggest that covariation in scATAC-seq provides additional information that can be leveraged for contact map prediction. ChromaFold prediction accuracy improved when cell-type-specific CTCF ChIP-seq data was provided as an input.…”

Section: Discussionmentioning

confidence: 89%

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

Gao¹,

Yang²,

Das

et al. 2023

Preprint

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 89%

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

Gao¹,

Yang²,

Das

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We used a deep learning framework that can predict epigenome, chromatin organization and transcription (EPCOT) (Z. Zhang et al, 2023) to impute high-resolution 3D chromatin contacts (Micro-C) using the endothelial ATAC profile. This approach predicted high contacts of the caSNP-caPeak region with the INHBB gene TSS, nominating the gene as a target ( Figure.…”

Section: Resultsmentioning

confidence: 99%

“…We used EPCOT (Z. Zhang et al, 2023) to impute the high-resolution 3D chromatin contact maps. EPCOT is a computational framework that predicts multiple genomic modalities using chromatin accessibility profiles and the reference genome sequence as input.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Population-scale skeletal muscle single-nucleus multi-omic profiling reveals extensive context specific genetic regulation

Varshney,

Manickam,

Orchard

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

SummarySkeletal muscle, the largest human organ by weight, is relevant to several polygenic metabolic traits and diseases including type 2 diabetes (T2D). Identifying genetic mechanisms underlying these traits requires pinpointing the relevant cell types, regulatory elements, target genes, and causal variants. Here, we used genetic multiplexing to generate population-scale single nucleus (sn) chromatin accessibility (snATAC-seq) and transcriptome (snRNA-seq) maps across 287 frozen human skeletal muscle biopsies representing 456,880 nuclei. We identified 13 cell types that collectively represented 983,155 ATAC summits. We integrated genetic variation to discover 6,866 expression quantitative trait loci (eQTL) and 100,928 chromatin accessibility QTL (caQTL) (5% FDR) across the five most abundant cell types, cataloging caQTL peaks that atlas-level snATAC maps often miss. We identified 1,973 eGenes colocalized with caQTL and used mediation analyses to construct causal directional maps for chromatin accessibility and gene expression. 3,378 genome-wide association study (GWAS) signals across 43 relevant traits colocalized with sn-e/caQTL, 52% in a cell-specific manner. 77% of GWAS signals colocalized with caQTL and not eQTL, highlighting the critical importance of population-scale chromatin profiling for GWAS functional studies. GWAS-caQTL colocalization showed distinct cell-specific regulatory paradigms. For example, aC2CD4A/BT2D GWAS signal colocalized with caQTL in muscle fibers and multiple chromatin loop models nominatedVPS13C, a glucose uptake gene. Sequence of the caQTL peak overlapping caSNP rs7163757 showed allelic regulatory activity differences in a human myocyte cell line massively parallel reporter assay. These results illuminate the genetic regulatory architecture of human skeletal muscle at high-resolution epigenomic, transcriptomic, and cell state scales and serve as a template for population-scale multiomic mapping in complex tissues and traits.

show abstract

“…By leveraging the knowledge encoded within the pre-trained Sei model, we were able to quickly train models with higher accuracy than our earlier models; furthermore, by directly using the predicted chromatin state variables predicted by Sei, we were able to use a simple logistic regression approach that yielded a highly interpretable model enabling us to make direct connections between transcription factors and their involvement in intron retention and discover a much larger set of transcription factors involved in this process. The methodology used here is similar to the one employed by the authors of the recent EPCOT model [32]. EPCOT is a chromatin state foundation model that has the added feature of using chromatin accessibility as part of its input which provides better generalization across cell-types.…”

Section: Introductionmentioning

confidence: 99%

The role of chromatin state in intron retention: a case study in leveraging large scale deep learning models

Daoud,

Ben-Hur

2024

Preprint

View full text Add to dashboard Cite

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA langauage model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

show abstract

A generalizable framework to comprehensively predict epigenome, chromatin organization, and transcriptome

Cited by 12 publications

References 49 publications

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

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

Population-scale skeletal muscle single-nucleus multi-omic profiling reveals extensive context specific genetic regulation

The role of chromatin state in intron retention: a case study in leveraging large scale deep learning models

Contact Info

Product

Resources

About