Loading BioAtlas...
Loading BioAtlas...
Confronta modelli biologici, motori di docking e flussi di calcolo affiancati. Filtra per modello di accesso, impronta di calcolo e categoria per ottenere una tabella decisionale attuabile in meno di un minuto.
| Attributo | ＋ Aggiungi strumento | |||||
|---|---|---|---|---|---|---|
| Category | Biological AI Models | Biological AI Models | Biological AI Models | Biological AI Models | Biological AI Models | — |
| Subcategory | Protein Design | Protein Design | Protein Design | Protein Design | Protein Design | — |
| Company | Microsoft Research / EvoDiff authors | Pacesa Lab | Boltz Team | Baker Lab | Google DeepMind | — |
| Access mode | Public code / project terms | Research code or publication | Research code or publication | Research code or publication | Research Preview | — |
| Licence conditions | Review code, weights, data and service terms separately | Check code and model weights separately | Check code and model weights separately | Check code and model weights separately | Research Publication / DeepMind Research | — |
| Compute requirements | See source requirements for selected configuration | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | GPU cluster for generative diffusion sampling and candidate filtering | — |
| Biological application | Non registrato | Non registrato | Non registrato | Non registrato | De novo binder design, targeted cancer therapeutics, viral inhibitors, and biosensors | — |
| Research workflow | Non registrato | Non registrato | Non registrato | Non registrato | Specify target protein structure and epitope binding site -> generate de novo binder sequences and 3D backbones | — |
| Evidence level | Project/provider documentation; no local benchmark | Peer-reviewed primary method | Primary research preprint | Primary research preprint | DeepMind Research Whitepaper & arXiv preprint (2024) | — |
| Commercial eligibility | Not independently confirmed | Unknown, requires audit | Unknown, requires audit | Unknown, requires audit | Research publication & early academic collaboration | — |
| Price | See project terms; compute costs may apply | Check selected model licence | Check selected model licence | Check selected model licence | Research Preview | — |
| Availability ⓘ | See project release and maintenance status | Public research method/code | Public research method/code | Public research method/code | DeepMind research publication and ongoing academic collaboration | — |
| Features | Protein sequence generation using discrete diffusion, Input: Sequence or alignment context and generation settings, Output: Candidate protein sequences | 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 | All-atom protein structure diffusion conditioned on specific ligand or nucleic acid atomic context., Generated protein all-atom structures | Generates high-affinity protein binders for diverse target proteins without initial starting fragments, Trained on large macromolecular structure repositories and AlphaFold predictions, Demonstrates up to 300-fold higher binding affinities than prior computational design methods, Experimental success rates ranging from 9% to 88% across diverse target proteins in wet-lab biophysical assays | — |
| Entry type | Research software / framework | Research AI model / method | Research AI model / method | Research AI model / method | AI Model | — |
| AI role | Scientific machine learning | Published biomedical AI method | Published biomedical AI method | Published biomedical AI method | De Novo Binder Design | — |
| Input data | Sequence or alignment context and generation settings | Target protein 3D coordinates; AF2/MPNN workflow and target interface constraints | Target context; design constraints | Target atomic geometry; designed region and constraints | Non registrato | — |
| Output data | Candidate protein sequences | Candidate binder sequences; modeled protein complexes | Binder sequence and structure candidates | Generated protein all-atom structures | Non registrato | — |
| Validation | Non registrato | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | Non registrato | — |
| Type | Non registrato | Non registrato | Non registrato | Non registrato | Generative protein binder design model | — |
| Intended use | Biological and pharmaceutical research | Non registrato | Non registrato | Non registrato | Non registrato | — |
| Compatibility | Non registrato | Non registrato | Non registrato | Non registrato | Non registrato | — |
| Limitations | Generated sequences need functional and expression testing; no biological performance guarantee. | Non registrato | Non registrato | Non registrato | Non registrato | — |
| Manufacturer | Non registrato | Non registrato | Non registrato | Non registrato | Google DeepMind | — |
| Integration evidence | Non registrato | Non registrato | Non registrato | Non registrato | https://deepmind.google/discover/blog/alphaproteo-generates-novel-proteins-for-biology-and-health-research/ | — |
| Laboratory handoff | Non registrato | Non registrato | Non registrato | Non registrato | Designed binder sequences are ordered as synthetic DNA for yeast surface display and SPR/BLI affinity validation | — |