Loading BioAtlas...
Loading BioAtlas...
Compare biological models, docking engines, and computational workflows side-by-side. Filter by access model, compute footprint, and category to reach an actionable decision table in under a minute.
| Attribute | ＋ Add tool | |||
|---|---|---|---|---|
| Category | Biological Foundation Models | Biological AI Models | Biological AI Models | — |
| Subcategory | Antibody Design | Protein Design | Protein Design | — |
| Company | Tsinghua University (AIR) | Pacesa Lab | Boltz Team | — |
| Access mode | Open Source | Research code or publication | Research code or publication | — |
| Licence conditions | MIT License | Check code and model weights separately | Check code and model weights separately | — |
| Compute requirements | 1x GPU (>= 16GB VRAM) | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | — |
| Biological application | Antibody CDR design, therapeutic optimization, and paratope engineering | Not recorded | Not recorded | — |
| Research workflow | Target antigen PDB -> generate complementary CDR conformations and sequences | Not recorded | Not recorded | — |
| Evidence level | Peer-reviewed research (ICLR 2023) | Peer-reviewed primary method | Primary research preprint | — |
| Commercial eligibility | Open source release | Unknown, requires audit | Unknown, requires audit | — |
| Price | Free Open Source | Check selected model licence | Check selected model licence | — |
| Availability ⓘ | Available on GitHub | Public research method/code | Public research method/code | — |
| Features | Joint structure-sequence diffusion on antibody CDR-H3 and light chain loops, Antigen-conditioned generation with physical clash penalties, Benchmark evaluations showing higher affinity and diversity than RosettaAntibody, Open source codebase with PyTorch and PyG implementations | AF2-guided optimization pipeline proposes protein binder designs for target structures., Candidate binder sequences, modeled protein complexes | Target-conditioned protein and peptide binder generation model as reported in its preprint., Binder sequence and structure candidates | — |
| Entry type | AI Model | Research AI model / method | Research AI model / method | — |
| AI role | Equivariant Generative Diffusion | Published biomedical AI method | Published biomedical AI method | — |
| Input data | Not recorded | Target protein 3D coordinates; AF2/MPNN workflow and target interface constraints | Target context; design constraints | — |
| Output data | Not recorded | Candidate binder sequences; modeled protein complexes | Binder sequence and structure candidates | — |
| Validation | Not recorded | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | — |
| Type | Equivariant diffusion model | Not recorded | Not recorded | — |
| Intended use | Not recorded | Not recorded | Not recorded | — |
| Compatibility | Not recorded | Not recorded | Not recorded | — |
| Manufacturer | Tsinghua University | Not recorded | Not recorded | — |
| Integration evidence | https://github.com/luost26/diffab | Not recorded | Not recorded | — |
| Laboratory handoff | Compatible with phage display and high-throughput antibody expression | Not recorded | Not recorded | — |