VIGAT: VLM-guided gene activity quantification from single-cell ATAC-seq
- 1Duke University School of Medicine
Abstract
Gene activity quantification from single-cell ATAC-seq is challenging because genomic regions informative of cell identity can vary across genes and tissues, while broadly accessible regions may provide limited cell-type-discriminative information. We developed VIGAT, a vision-language model (VLM)-guided tool that automates visual interpretation of ATAC coverage plots for adaptive gene activity quantification. VIGAT jointly examines accessibility patterns across multiple marker genes, integrating genomic annotations and biological context to select gene-specific regions enriched for cluster-discriminative signals. Selected regions are used to generate a gene-by-cell activity matrix. Across 196 paired single-cell RNA-seq and ATAC-seq datasets, VIGAT outperformed five existing methods in recovering marker-associated accessibility enriched in the corresponding cell populations, demonstrating the utility of VLM-guided visual reasoning for scalable gene activity quantification. Availability and implementation: VIGAT is implemented as an open-source R package and is freely available at https://github.com/beijie02/VIGAT.
Related
- Rapid, accurate, and memory-frugal sub-gene-level quantification of probe-based, multiplexed single-cell data
- Alpha Spatial: Language-guided prediction of single-cell spatial gene expression from histology
- Advancing long-read metagenomic binning via single-copy-gene guided contrastive learning
- Model-guided design of single-cargo, dual-attractor gene circuits
- Uncertainty Quantification in Stochastic Dynamical Gene Regulatory Networks
BibTeX
@misc{ji2026vigat,
title = {{VIGAT: VLM-guided gene activity quantification from single-cell ATAC-seq}},
author = {B. Ji and Z. Ji},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.16.759698},
url = {https://www.biorxiv.org/content/10.64898/2026.10.16.759698v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - VIGAT: VLM-guided gene activity quantification from single-cell ATAC-seq
AU - B. Ji
AU - Z. Ji
PY - 2026
DA - 2026/10/16
PB - bioRxiv
DO - 10.64898/2026.10.16.759698
UR - https://www.biorxiv.org/content/10.64898/2026.10.16.759698v1
AB - Gene activity quantification from single-cell ATAC-seq is challenging because genomic regions informative of cell identity can vary across genes and tissues, while broadly accessible regions may provide limited cell-type-discriminative information. We developed VIGAT, a vision-language model (VLM)-guided tool that automates visual interpretation of ATAC coverage plots for adaptive gene activity quantification. VIGAT jointly examines accessibility patterns across multiple marker genes, integrating genomic annotations and biological context to select gene-specific regions enriched for cluster-discriminative signals. Selected regions are used to generate a gene-by-cell activity matrix. Across 196 paired single-cell RNA-seq and ATAC-seq datasets, VIGAT outperformed five existing methods in recovering marker-associated accessibility enriched in the corresponding cell populations, demonstrating the utility of VLM-guided visual reasoning for scalable gene activity quantification. Availability and implementation: VIGAT is implemented as an open-source R package and is freely available at https://github.com/beijie02/VIGAT.
ER -