AbLang-2 vs AntiBERTy
AbLang-2: Paired-chain antibody language model trained to reduce germline bias. AntiBERTy: BERT-style antibody language model trained on 558M OAS sequences.
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: antibody, language-model.
| Field | AbLang-2 | AntiBERTy |
|---|---|---|
| Task | Antibody language model (germline-bias aware) | Antibody language model (embeddings) |
| Modalities | Paired antibody sequences | Antibody variable-domain sequences |
| MSA required | No (sequence language model) | No (26M-param BERT LM) |
| Open weights | — | Yes (Hugging Face, ~100 MB) |
| GPU need | Runs on CPU (device='cpu') | CPU, CUDA or MPS |
| License | BSD-3-Clause | MIT |
| Pricing | Open source | Open source |
| Released | 2024-02-07 | 2021-12-14 |
| Paper | Link | Link |
| GitHub | GitHub | GitHub |
| GitHub stars | 46 | 83 |
| Interface | Package | Package |
License and commercial use
| Field | AbLang-2 | AntiBERTy |
|---|---|---|
| Code license | BSD-3-Clause | 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 Protein structure & design tools to this comparison →
More Protein structure & design comparisons
- AlphaFold Server (AlphaFold 3) vs Boltz
- RFdiffusion vs BindCraft
- Chai-1 vs Boltz
- AlphaFold Server (AlphaFold 3) vs Chai-1
- Protenix vs Boltz
- OpenFold3 vs Boltz
- AlphaFold 2 vs OpenFold
- AlphaFold 2 vs ColabFold
- AlphaFold 2 vs RoseTTAFold
- ESM-2 / ESMFold vs ProtTrans
- ESM3 / EvolutionaryScale vs ESM-2 / ESMFold
- SaProt vs ESM-2 / ESMFold
- RFdiffusion vs RFdiffusion2
- RFdiffusion2 vs RFdiffusion3
- LigandMPNN vs ProteinMPNN
- All comparisons