LucaCell: a sequence-centric foundation model for cross-species single-cell analysis
- 1Token Foundry, Alibaba Token Hub, Alibaba Group, Hangzhou, China
Abstract
Single-cell foundation models have transformed transcriptomic analysis, yet most rely on fixed gene identifiers that limit transfer across species and data types. Here we present LucaCell, a sequence-centric foundation model that represents genes through pre-trained mRNA sequence embeddings rather than static gene annotations. Gene expression is discretized into bins and modeled with a Transformer encoder, enabling sequence-informed cell representation without a fixed gene-ID vocabulary. Pre-training on 85 million human and mouse single cells, LucaCell is evaluated on human, mouse and lemur gene expression profiles, human chromatin accessibility data, unaligned reads from more than 50 prokaryotic taxa, and five influenza A virus genomes. LucaCell enables manual-mapping-free cross-species cell type annotation and an alignment-free microbial embedding framework that simultaneously distinguishes bacterial species identity and intra-species physiological states. It also improves gene expression reconstruction by incorporating donor-specific exonic SNP information into mRNA sequence embeddings, and predicts cellular viral load across influenza A virus strains while highlighting infection-like transcriptional states in mock-infected cells. These results show that sequence-informed gene representation can improve the generalization of single-cell foundation models across species, data types, and predictive tasks.
Related
- EpiZoo: a DNA sequence-aware foundation model for cross-species single-cell epigenomics
- 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
- SedaDNA metabarcoding reveals hidden histories of within-species sequence variation
BibTeX
@misc{sun2026lucacell,
title = {{LucaCell: a sequence-centric foundation model for cross-species single-cell analysis}},
author = {Y. Sun and Y. He and M. Ren and Y. Wang and P. Xu and Y. Hou and Y. Kang and T. Hou and J. Ye and H. Yang and Z. Wang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.08.750024},
url = {https://www.biorxiv.org/content/10.64898/2026.09.08.750024v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - LucaCell: a sequence-centric foundation model for cross-species single-cell analysis
AU - Y. Sun
AU - Y. He
AU - M. Ren
AU - Y. Wang
AU - P. Xu
AU - Y. Hou
AU - Y. Kang
AU - T. Hou
AU - J. Ye
AU - H. Yang
AU - Z. Wang
PY - 2026
DA - 2026/09/08
PB - bioRxiv
DO - 10.64898/2026.09.08.750024
UR - https://www.biorxiv.org/content/10.64898/2026.09.08.750024v1
AB - Single-cell foundation models have transformed transcriptomic analysis, yet most rely on fixed gene identifiers that limit transfer across species and data types. Here we present LucaCell, a sequence-centric foundation model that represents genes through pre-trained mRNA sequence embeddings rather than static gene annotations. Gene expression is discretized into bins and modeled with a Transformer encoder, enabling sequence-informed cell representation without a fixed gene-ID vocabulary. Pre-training on 85 million human and mouse single cells, LucaCell is evaluated on human, mouse and lemur gene expression profiles, human chromatin accessibility data, unaligned reads from more than 50 prokaryotic taxa, and five influenza A virus genomes. LucaCell enables manual-mapping-free cross-species cell type annotation and an alignment-free microbial embedding framework that simultaneously distinguishes bacterial species identity and intra-species physiological states. It also improves gene expression reconstruction by incorporating donor-specific exonic SNP information into mRNA sequence embeddings, and predicts cellular viral load across influenza A virus strains while highlighting infection-like transcriptional states in mock-infected cells. These results show that sequence-informed gene representation can improve the generalization of single-cell foundation models across species, data types, and predictive tasks.
ER -