Bolero
Bolero is a genomics & dna models tool whose code is published by liuhlab on GitHub, first public in 2026, described in bioRxiv (2026). Arc Institute cell-state-conditioned sequence-to-function model that predicts cell-state-specific chromatin accessibility and transcript abundance from DNA, using a frozen Borzoi/Flashzoi backbone with LoRA adapters generated from a cell-state embedding.
| Category | Genomics & DNA models |
|---|---|
| Developer (GitHub) | liuhlab |
| Task | Cell-state-specific chromatin accessibility and transcript abundance, variant scoring, enhancer design |
| Interface | Package (pixi), Hugging Face weights |
| Website | liuhlab.github.io/bolero |
| GitHub | liuhlab/bolero |
| Released | 2026-10-20 (source) |
| Paper | https://doi.org/10.64898/2026.10.19.760026 · bioRxiv (2026) |
| Code license | MIT |
| Weights license | model weights MIT (Hugging Face model card metadata) |
| What this allows | Permissive (commercial OK) Use, modify and ship it inside closed-source commercial products; keep the license text and copyright notices. What do these mean? |
| License source | github.com/liuhlab/bolero/blob/main/LICENSE · checked 2026-11-09 |
| Pricing | Open source |
| Tags | #sequence-to-function#chromatin-accessibility#borzoi#cell-state#enhancer-design |
| Last checked | · links verified |
Can I use Bolero commercially?
Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.
- Code: MIT
- Weights: model weights MIT (Hugging Face model card metadata)
- Source: github.com/liuhlab/bolero/blob/main/LICENSE · license checked 2026-11-09
What the license types mean · not legal advice.
Specs
| Input length / context | 524 kb |
|---|---|
| Resolution | 32 bp |
| Species | 6 mammals incl. human, mouse |
| Tasks | Cell-state-specific chromatin accessibility and transcript abundance, variant scoring, enhancer design |
| GitHub stars | 17 |
| Interface | Package (pixi), Hugging Face weights |
Compare with…
Pick 1–3 other Genomics & DNA models tools to compare side by side with Bolero.
Related
Predicts gene expression from sequence with long-range interactions.
Genome language model across all domains of life with 1M-token context.
DeepMind model predicting regulatory effects of DNA variants at base resolution.