Cherimoya
Cherimoya is a genomics & dna models tool whose code is published by jmschrei on GitHub, first public in 2026. Compact BPNet-family sequence-to-function model with an end-to-end CLI (peak calling, training, attribution, motif discovery); ships pretrained atlases CATv1 (accessibility) and BATv1 (17,145 TF-binding models).
| Category | Genomics & DNA models |
|---|---|
| Developer (GitHub) | jmschrei |
| Task | TF binding (ChIP-seq), chromatin accessibility (DNase/ATAC-seq) and other sequencing readouts from DNA sequence |
| GitHub | jmschrei/cherimoya |
| Released | 2026-10-30 (source) |
| Code license | MIT |
| Weights license | CATv1 and BATv1 weights CC-BY-4.0 |
| 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 | huggingface.co/programmable-genomics/BATv1 · checked 2026-11-01 |
| Pricing | Open source |
| Tags | #sequence-to-function#dna-model#tf-binding#chromatin-accessibility |
| Last checked | · links verified |
Can I use Cherimoya commercially?
Yes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices.
- Code: MIT
- Weights: CATv1 and BATv1 weights CC-BY-4.0
- Source: huggingface.co/programmable-genomics/BATv1 · license checked 2026-11-01
What the license types mean · not legal advice.
Specs
| Input length / context | 2,114 bp input |
|---|---|
| Resolution | Base-resolution 1,000 bp profile plus total count |
| Species | Human (GRCh38) for pretrained atlases |
| Tasks | TF binding (ChIP-seq), chromatin accessibility (DNase/ATAC-seq) and other sequencing readouts from DNA sequence |
| GitHub stars | 71 |
| Interface | — |
Compare with…
Pick 1–3 other Genomics & DNA models tools to compare side by side with Cherimoya.
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.