GFETM: Genome foundation-based embedded topic model for scATAC-seq modeling
Clinical Snapshot
PICO Framework
| P — Population | Single-cell ATAC-seq datasets from various cell types and tissues, including kidney diabetes samples |
| I — Intervention | Genome Foundation Embedded Topic Model (GFETM) - a deep learning framework combining genome foundation models with embedded topic modeling |
| C — Comparator | Standard scATAC-seq analysis methods and existing embedded topic models without genome foundation model integration |
| O — Outcomes | Modeling accuracy, generalizability, transcription factor activity prediction, cell-state identification, and biological interpretation of epigenomic signatures |
Bottom Line
GFETM represents a novel computational approach that combines genome foundation models with topic modeling to address the significant analytical challenges in single-cell chromatin accessibility sequencing. While the method shows promise for improving accuracy and biological interpretation of scATAC-seq data, the abstract lacks crucial quantitative validation metrics and statistical comparisons. The approach's ability to capture transcription factor activity and reveal epigenomic signatures in disease contexts like kidney diabetes suggests potential clinical utility. However, clinicians should await peer-reviewed validation studies with comprehensive performance benchmarks before considering this tool for diagnostic or therapeutic decision-making. The method's computational requirements may limit accessibility outside specialized research institutions.
Key Findings
P Value: Not reported
Effect Size: Not specified in abstract
Primary Outcome: Superior accuracy and generalizability in scATAC-seq modeling compared to existing methods
Nnt Or Sensitivity: Captures cell-state-specific transcription factor activity with zero-shot inference capability
Confidence Interval: Not reported
Clinical Application
Requires computational expertise and access to high-performance computing resources for genome foundation model implementation Relevant for Australian genomics research institutions and clinical genomics laboratories; aligns with NHMRC precision medicine initiatives and could support TGA-regulated genomic testing development Researchers and clinicians analyzing single-cell chromatin accessibility data, particularly in epigenomic studies
Abstract
Single-cell assay for transposase-accessible chromatin with sequencing (scATAC-seq) enables investigation of open chromatin landscapes at single-cell resolution. However, analyzing scATAC-seq data remains challenging due to inherent sparsity and noise. Genome foundation models (GFMs), pre-trained on extensive DNA sequence datasets, have demonstrated effectiveness in genome analysis. Because open chromatin regions (OCRs) harbor salient sequence features, we hypothesized that leveraging GFMs' sequence embeddings could enhance scATAC-seq modeling accuracy and generalizability. We introduce the genome foundation embedded topic model (GFETM), an interpretable deep learning framework combining GFMs with the embedded topic model (ETM) for scATAC-seq analysis. By integrating DNA sequence embeddings extracted by a GFM from OCRs, GFETM demonstrates superior accuracy and generalizability and captures cell-state-specific transcription factor (TF) activity with both zero-shot inference and attention-mechanism analysis. Finally, the topic mixtures inferred by GFETM reveal biologically meaningful epigenomic signatures of kidney diabetes. A record of this paper's transparent peer review process is included in the supplemental information.
References
- 1.Fan, Y., Osakwe, A., Han, S., Li, Y., Ding, J., & Li, Y. (2026). GFETM: Genome foundation-based embedded topic model for scATAC-seq modeling. Cell Systems. https://doi.org/10.1016/j.cels.2026.101563
Related Research
Biological psychiatry
Systematic Review and Mega-Analysis of the Peripheral Blood Transcriptome in Depression Implicates Dysregulation of Lymphoid Cells and Histones
16 June 2026
Cell systems
Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states
22 May 2026
Molecular genetics and genomics : MGG
Comparison between a conventional tool and deep learning models for RNA velocity analysis of scRNA-Seq data
14 May 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service