Loading BioAtlas...
Loading BioAtlas...
Compare modelos biológicos, motores de docking y flujos computacionales lado a lado. Filtre por modelo de acceso, huella de cómputo y categoría para obtener una tabla de decisiones útil en menos de un minuto.
| Atributo | ＋ Añadir herramienta | |||
|---|---|---|---|---|
| Category | Biological AI Models | Biological AI Models | Biological AI Models | — |
| Subcategory | Protein Structure | Protein Design | Protein Design | — |
| Company | AlQuraishi Laboratory / OpenFold contributors | Pacesa Lab | Boltz Team | — |
| Access mode | Public code / project terms | Research code or publication | Research code or publication | — |
| Licence conditions | Review the linked release, model weights, datasets and service terms separately | Check code and model weights separately | Check code and model weights separately | — |
| Compute requirements | Consult linked installation guidance; workload dependent | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | — |
| Biological application | No registrado | No registrado | No registrado | — |
| Research workflow | No registrado | No registrado | No registrado | — |
| Evidence level | Project or provider documentation; no local performance benchmark | Peer-reviewed primary method | Primary research preprint | — |
| Commercial eligibility | Not independently confirmed | Unknown, requires audit | Unknown, requires audit | — |
| Price | See project terms; compute costs may apply | Check selected model licence | Check selected model licence | — |
| Availability ⓘ | See project access and maintenance status | Public research method/code | Public research method/code | — |
| Features | Trainable PyTorch implementation of the AlphaFold 2 approach, Input: Protein sequences, alignments and training or inference configuration, Output: Protein structures or trained folding models | 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 | Research software / model | Research AI model / method | Research AI model / method | — |
| AI role | Scientific machine learning | Published biomedical AI method | Published biomedical AI method | — |
| Input data | Protein sequences, alignments and training or inference configuration | Target protein 3D coordinates; AF2/MPNN workflow and target interface constraints | Target context; design constraints | — |
| Output data | Protein structures or trained folding models | Candidate binder sequences; modeled protein complexes | Binder sequence and structure candidates | — |
| Validation | Evaluate on representative data; no clinical suitability established | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | — |
| Type | No registrado | No registrado | No registrado | — |
| Intended use | Biological and pharmaceutical research | No registrado | No registrado | — |
| Compatibility | No registrado | No registrado | No registrado | — |
| Limitations | Training and inference have different resource needs; code and downloaded parameters have separate terms. | No registrado | No registrado | — |