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 | Biomolecular Complex Prediction | Protein Design | Protein Design | — |
| Company | Baidu PaddleHelix | Pacesa Lab | Boltz Team | — |
| Access mode | Open Source & Web Service | Research code or publication | Research code or publication | — |
| Licence conditions | Apache 2.0 (code) / Model License | Check code and model weights separately | Check code and model weights separately | — |
| Compute requirements | 1x NVIDIA A100 or Kunlunxin AI accelerators | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | — |
| Biological application | Target-ligand interaction modeling, RNA-protein complex prediction, and covalent drug discovery | Not recorded | Not recorded | — |
| Research workflow | Input biomolecular sequence and SMILES -> generate 3D complex coordinates and confidence scores | Not recorded | Not recorded | — |
| Evidence level | Preprint and blind benchmark evaluation (2024) | Peer-reviewed primary method | Primary research preprint | — |
| Commercial eligibility | Open research access with enterprise private deployment | Unknown, requires audit | Unknown, requires audit | — |
| Price | Free Open Source / Enterprise Support | Check selected model licence | Check selected model licence | — |
| Availability ⓘ | Available globally on GitHub | Public research method/code | Public research method/code | — |
| Features | Unified prediction of protein-ligand, protein-nucleic acid, and multi-chain assemblies, High-throughput distributed inference accelerated by PaddleHelix engine, Includes specialized chemical bond loss for precise covalent drug interactions, Openly accessible web server and downloadable weights for enterprise deployment | 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 / Web Server | Research AI model / method | Research AI model / method | — |
| AI role | Structural Complex Modeling | 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 | All-atom structure prediction model | Not recorded | Not recorded | — |
| Intended use | Not recorded | Not recorded | Not recorded | — |
| Compatibility | Not recorded | Not recorded | Not recorded | — |
| Manufacturer | Baidu Inc. | Not recorded | Not recorded | — |
| Integration evidence | https://github.com/PaddlePaddle/PaddleHelix | Not recorded | Not recorded | — |
| Laboratory handoff | Structures inform cryo-EM model fitting and crystallographic phasing | Not recorded | Not recorded | — |