EpiZoo: a DNA sequence-aware foundation model for cross-species single-cell epigenomics
- 1Tsinghua University
Abstract
Large-scale single-cell epigenomic atlases characterize chromatin regulatory landscapes across diverse biological contexts, spanning cell types, tissues, individuals and species. Foundation models provide an opportunity to capture the full spectrum of cellular diversity in these atlases, yet current models remain largely confined to individual species by genomic coordinate dependence and overlook regulatory information encoded in DNA sequences. Here we introduce EpiZoo, a DNA sequence-aware foundation model for cross-species single-cell epigenomics. EpiZoo converts million-dimensional single-cell epigenomic profiles from diverse species into compact cell sentences that integrate DNA-encoded regulatory information, sequence-independent epigenomic context and accessibility-based importance. Built around a mixture-of-experts transformer and containing 2.6 billion parameters in total, EpiZoo is pretrained on our manually curated multi-species Omni-scATAC corpus of approximately 20.9 million cells to learn regulatory programs across species. On external datasets excluded from pretraining, EpiZoo achieves state-of-the-art performance in fundamental single-cell analysis tasks, including feature extraction, cell type annotation and data imputation. Its sequence-aware architecture enables extension to evolutionarily diverse species, and supports comparative analysis of regulatory conservation and divergence during primate evolution. Benefiting from this modeling design, EpiZoo enables context-aware prioritization of somatic mutations in cancer and prediction of cell-type-specific chromatin accessibility from DNA sequences across genomic regions and species.
Related
- LucaCell: a sequence-centric foundation model for cross-species single-cell analysis
- A foundation model learns the sequence and functional grammar of fully human heavy-chain-only antibodies
- OmniTCR: a foundation model unifying T cell receptor recognition prediction and conditional sequence generation
- Bioactivity foundation model for hit identification and hit-to-lead optimization from sequence data
- Long‐Read Reference Transcriptomes for Five Species of Rosaceae Tribe Spiraeeae: A Resource for Investigating Sequence Divergence, Species‐Associated Expression Variation, and Leaf‐Developmental Candidate Genes
BibTeX
@misc{li2026epizoo,
title = {{EpiZoo: a DNA sequence-aware foundation model for cross-species single-cell epigenomics}},
author = {K. Li and X. Chen and Q. Jiang and Z. Wang and H. Lv and R. Jiang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.754017},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.754017v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - EpiZoo: a DNA sequence-aware foundation model for cross-species single-cell epigenomics
AU - K. Li
AU - X. Chen
AU - Q. Jiang
AU - Z. Wang
AU - H. Lv
AU - R. Jiang
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.754017
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.754017v1
AB - Large-scale single-cell epigenomic atlases characterize chromatin regulatory landscapes across diverse biological contexts, spanning cell types, tissues, individuals and species. Foundation models provide an opportunity to capture the full spectrum of cellular diversity in these atlases, yet current models remain largely confined to individual species by genomic coordinate dependence and overlook regulatory information encoded in DNA sequences. Here we introduce EpiZoo, a DNA sequence-aware foundation model for cross-species single-cell epigenomics. EpiZoo converts million-dimensional single-cell epigenomic profiles from diverse species into compact cell sentences that integrate DNA-encoded regulatory information, sequence-independent epigenomic context and accessibility-based importance. Built around a mixture-of-experts transformer and containing 2.6 billion parameters in total, EpiZoo is pretrained on our manually curated multi-species Omni-scATAC corpus of approximately 20.9 million cells to learn regulatory programs across species. On external datasets excluded from pretraining, EpiZoo achieves state-of-the-art performance in fundamental single-cell analysis tasks, including feature extraction, cell type annotation and data imputation. Its sequence-aware architecture enables extension to evolutionarily diverse species, and supports comparative analysis of regulatory conservation and divergence during primate evolution. Benefiting from this modeling design, EpiZoo enables context-aware prioritization of somatic mutations in cancer and prediction of cell-type-specific chromatin accessibility from DNA sequences across genomic regions and species.
ER -