Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.16776 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908975799205888 |
|---|---|
| author | Li, Jiahao Dong, Jiayi Ye, Peng Zhou, Xiaochi Lu, Haohai Wang, Fei |
| author_facet | Li, Jiahao Dong, Jiayi Ye, Peng Zhou, Xiaochi Lu, Haohai Wang, Fei |
| contents | Modeling single-cell gene expression across diverse biological and technical conditions is crucial for characterizing cellular states and simulating unseen scenarios. Existing methods often treat genes as independent tokens, overlooking their high-level biological relationships and leading to poor performance. We introduce SAVE, a unified generative framework based on conditional Transformers for multi-condition single-cell modeling. SAVE leverages a coarse-grained representation by grouping semantically related genes into blocks, capturing higher-order dependencies among gene modules. A Flow Matching mechanism and condition-masking strategy further enhance flexible simulation and enable generalization to unseen condition combinations. We evaluate SAVE on a range of benchmarks, including conditional generation, batch effect correction, and perturbation prediction. SAVE consistently outperforms state-of-the-art methods in generation fidelity and extrapolative generalization, especially in low-resource or combinatorially held-out settings. Overall, SAVE offers a scalable and generalizable solution for modeling complex single-cell data, with broad utility in virtual cell synthesis and biological interpretation. Our code is publicly available at https://github.com/fdu-wangfeilab/sc-save |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16776 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention Li, Jiahao Dong, Jiayi Ye, Peng Zhou, Xiaochi Lu, Haohai Wang, Fei Artificial Intelligence Modeling single-cell gene expression across diverse biological and technical conditions is crucial for characterizing cellular states and simulating unseen scenarios. Existing methods often treat genes as independent tokens, overlooking their high-level biological relationships and leading to poor performance. We introduce SAVE, a unified generative framework based on conditional Transformers for multi-condition single-cell modeling. SAVE leverages a coarse-grained representation by grouping semantically related genes into blocks, capturing higher-order dependencies among gene modules. A Flow Matching mechanism and condition-masking strategy further enhance flexible simulation and enable generalization to unseen condition combinations. We evaluate SAVE on a range of benchmarks, including conditional generation, batch effect correction, and perturbation prediction. SAVE consistently outperforms state-of-the-art methods in generation fidelity and extrapolative generalization, especially in low-resource or combinatorially held-out settings. Overall, SAVE offers a scalable and generalizable solution for modeling complex single-cell data, with broad utility in virtual cell synthesis and biological interpretation. Our code is publicly available at https://github.com/fdu-wangfeilab/sc-save |
| title | SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.16776 |