Seal
Troyanskaya lab's sequence-to-expression transfer-learning model: predicts gene expression and variant effects across 802 developing-brain contexts (26 regions, 30 cell types, 7 stages).
| Category | Genomics & DNA models |
|---|---|
| GitHub | FunctionLab/Seal |
| First public | 2024-08-27 (source) |
| Paper | https://doi.org/10.1038/s41593-026-02470-2 · Nature Neuroscience (2026) |
| License | Princeton/Simons license: academic and research use only; model weights on Zenodo CC BY 4.0 |
| Weights license | model weights on Zenodo CC BY 4.0 |
| What this allows | Non-commercial No commercial use. What do these mean? |
| License source | github.com/FunctionLab/Seal/blob/main/LICENSE.md · checked 2026-10-18 |
| Pricing | Open source (non-commercial) |
| Tags | #variant-effect#regulatory#transfer-learning |
| Last checked | · links verified |
Specs
| Input length / context | 40 kb around each gene's TSS |
|---|---|
| Resolution | — |
| Species | Human |
| Tasks | Expression and variant-effect prediction in 802 brain contexts (122 region states, 680 cell states); feature attribution |
| GitHub stars | 2 |
| Interface | CLI (Python) |
Specs come from each project's README, paper or official page · Seal README · Seal paper · Seal source 3. “—” means we couldn't verify it.
Compare with…
Pick 1–3 other Genomics & DNA models tools to compare side by side with Seal.
Related
Predicts gene expression from sequence with long-range interactions.
Genomics & DNA modelsOpen sourcePermissive (commercial OK)#expression
Genome language model across all domains of life with 1M-token context.
Genomics & DNA modelsOpen sourcePermissive (commercial OK)#dna-lm
DeepMind model predicting regulatory effects of DNA variants at base resolution.
Genomics & DNA modelsFree (research)Mixed (code vs weights differ)#regulatory