scGPT vs UCE (Universal Cell Embeddings)
scGPT: Generative pretrained transformer foundation model for single-cell multi-omics. UCE (Universal Cell Embeddings): Cross-species zero-shot universal cell embedding foundation model.
Facts below come from each project's own website, repository and paper. We don't publish benchmark claims here; see the papers for evaluations. Shared tags: foundation-model.
| Field | scGPT | UCE (Universal Cell Embeddings) |
|---|---|---|
| Pretraining corpus | 33M human cells (whole-human checkpoint) | Cell atlas data from human and other species (self-supervised) |
| Architecture | Generative transformer | Transformer |
| Tasks | Annotation, integration, reference mapping, perturbation | Zero-shot embeddings |
| Species | Human | Multi-species (species flag) |
| License | MIT | MIT |
| Pricing | Open source | Open source |
| Released | 2023-05-01 | 2023-11-29 |
| Paper | Link | Link |
| GitHub | GitHub | GitHub |
| GitHub stars | 1,654 | 349 |
| Interface | Package | Package |
License and commercial use
| Field | scGPT | UCE (Universal Cell Embeddings) |
|---|---|---|
| Code license | MIT | MIT |
| Weights license | — | — |
| Commercial use | Permissive (commercial OK) | Permissive (commercial OK) |
| Answer | Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. Details | Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. Details |
Add more Single-cell & foundation models tools to this comparison →