Modeling the vertebrate regulatory sequence landscape by UUATAC-seq and deep learning

Xiaoping Han; Hanyu Wu; Xueyi Wang; Daiyuan Liu; Yuting Fu; Lei Yang; Renying Wang; Peijing Zhang; Jingjing Wang; Lifeng Ma; Jizhong Mao; Lina Zhou; Siqi Wang; Xinlian Zhang; Mengmeng Jiang; Xinru Wang; Guoxia Wen; Danmei Jia; Guoji Guo

doi:10.1016/j.cell.2025.06.020

Modeling the vertebrate regulatory sequence landscape by UUATAC-seq and deep learning

Cell. 2025 Jul 1:S0092-8674(25)00686-5. doi: 10.1016/j.cell.2025.06.020. Online ahead of print.

Authors

Xiaoping Han¹, Hanyu Wu², Xueyi Wang², Daiyuan Liu², Yuting Fu², Lei Yang², Renying Wang², Peijing Zhang³, Jingjing Wang⁴, Lifeng Ma², Jizhong Mao⁴, Lina Zhou⁴, Siqi Wang², Xinlian Zhang², Mengmeng Jiang⁴, Xinru Wang², Guoxia Wen⁴, Danmei Jia², Guoji Guo⁵

Affiliations

¹ Bone Marrow Transplantation Center of the First Affiliated Hospital, and Center for Stem Cell and Regenerative Medicine, Zhejiang University School of Medicine, Hangzhou 310000, China. Electronic address: xhan@zju.edu.cn.
² Bone Marrow Transplantation Center of the First Affiliated Hospital, and Center for Stem Cell and Regenerative Medicine, Zhejiang University School of Medicine, Hangzhou 310000, China.
³ Bone Marrow Transplantation Center of the First Affiliated Hospital, and Center for Stem Cell and Regenerative Medicine, Zhejiang University School of Medicine, Hangzhou 310000, China; Liangzhu Laboratory, Zhejiang University, Hangzhou 311121, China.
⁴ Liangzhu Laboratory, Zhejiang University, Hangzhou 311121, China.
⁵ Bone Marrow Transplantation Center of the First Affiliated Hospital, and Center for Stem Cell and Regenerative Medicine, Zhejiang University School of Medicine, Hangzhou 310000, China; Liangzhu Laboratory, Zhejiang University, Hangzhou 311121, China; Zhejiang Provincial Key Laboratory for Tissue Engineering and Regenerative Medicine, Dr. Li Dak Sum & Yip Yio Chin Center for Stem Cell and Regenerative Medicine, Hangzhou 310058, China; Institute of Hematology, Zhejiang University, Hangzhou 310006, China. Electronic address: ggj@zju.edu.cn.

PMID: 40633538
DOI: 10.1016/j.cell.2025.06.020

Abstract

The regulatory sequences of vertebrate genomes remain incompletely understood. To address this, we developed an ultra-throughput, ultra-sensitive single-nucleus assay for transposase-accessible chromatin using sequencing (UUATAC-seq) protocol that enables the construction of chromatin accessibility landscapes for one species in a 1-day experiment. Using UUATAC-seq, we mapped candidate cis-regulatory elements (cCREs) across five representative vertebrate species. Our analysis revealed that genome size differences across species influence the number but not the size of cCREs. We introduced Nvwa cis-regulatory element (NvwaCE), a mega-task deep-learning model designed to interpret cis-regulatory grammar and predict cCRE landscapes directly from genomic sequences with high precision. NvwaCE demonstrated that regulatory grammar is more conserved than nucleotide sequences and that this grammar organizes cCREs into distinct functional modules. Moreover, NvwaCE accurately predicted the effects of synthetic mutations on lineage-specific cCRE function, aligning with causal quantitative trait loci (QTLs) and genome editing results. Together, our study provides a valuable resource for decoding the vertebrate regulatory language.

Keywords: NvwaCE; UUATAC-seq; cCRE; chromatin accessibility landscape; deep learning; genome editing; genomics; mutation effect; regulatory sequence; snATAC-seq.