Loading BioAtlas...
Loading BioAtlas...
Vergleichen Sie biologische Modelle, Docking-Engines und Berechnungs-Workflows Seite an Seite. Filtern Sie nach Zugangsmodell, Rechenbedarf und Kategorie, um in unter einer Minute zu einer verwertbaren Entscheidungstabelle zu gelangen.
| Attribut | Biological Foundation Models RFdiffusion All-Atom (RFdiffusionAA)Institute for Protein Design (Baker Lab)Quelloffen⚡ A100/H100 | ＋ Werkzeug hinzufügen | ||||
|---|---|---|---|---|---|---|
| Category | Biological Foundation Models | Biological AI Models | Biological AI Models | Biological AI Models | Biological AI Models | — |
| Subcategory | De Novo Protein Design | Protein Design | Protein Design | Protein Design | Protein Design | — |
| Company | Institute for Protein Design (Baker Lab) | Pacesa Lab | Boltz Team | Baker Lab | Google DeepMind | — |
| Access mode | Academic Open Source | Research code or publication | Research code or publication | Research code or publication | Research Preview | — |
| Licence conditions | Open Source for academic research; commercial license required for for-profit use | Check code and model weights separately | Check code and model weights separately | Check code and model weights separately | Research Publication / DeepMind Research | — |
| Compute requirements | 1x NVIDIA A100 or RTX 4090 GPU (>= 24GB VRAM) | 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 | Enzyme active site design, small molecule sensor engineering, and drug receptor design | Nicht erfasst | Nicht erfasst | Nicht erfasst | De novo binder design, targeted cancer therapeutics, viral inhibitors, and biosensors | — |
| Research workflow | Diffusion of protein backbone and sidechains around explicit ligand coordinates | Nicht erfasst | Nicht erfasst | Nicht erfasst | Specify target protein structure and epitope binding site -> generate de novo binder sequences and 3D backbones | — |
| Evidence level | Peer-reviewed research (Science 2024) | Peer-reviewed primary method | Primary research preprint | Primary research preprint | DeepMind Research Whitepaper & arXiv preprint (2024) | — |
| Commercial eligibility | Commercial licensing available through University of Washington CoMotion | Unknown, requires audit | Unknown, requires audit | Unknown, requires audit | Research publication & early academic collaboration | — |
| Price | Free for academic research / Paid commercial license | Check selected model licence | Check selected model licence | Check selected model licence | Research Preview | — |
| Availability ⓘ | Available on GitHub | Public research method/code | Public research method/code | Public research method/code | DeepMind research publication and ongoing academic collaboration | — |
| Features | De novo design of protein binding pockets around specified small molecules, Co-generation of protein binders with coordinated catalytic ions and cofactors, Full atomic coordinate representation during the reverse diffusion trajectory, Seamless integration with LigandMPNN for sequence design | 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 | AI Model / Software | Research AI model / method | Research AI model / method | Research AI model / method | AI Model | — |
| AI role | De Novo Molecular Diffusion | Published biomedical AI method | Published biomedical AI method | Published biomedical AI method | De Novo Binder Design | — |
| Input data | Nicht erfasst | Target protein 3D coordinates; AF2/MPNN workflow and target interface constraints | Target context; design constraints | Target atomic geometry; designed region and constraints | Nicht erfasst | — |
| Output data | Nicht erfasst | Candidate binder sequences; modeled protein complexes | Binder sequence and structure candidates | Generated protein all-atom structures | Nicht erfasst | — |
| Validation | Nicht erfasst | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | Nicht erfasst | — |
| Type | Generative all-atom diffusion model | Nicht erfasst | Nicht erfasst | Nicht erfasst | Generative protein binder design model | — |
| Intended use | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Compatibility | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Manufacturer | Institute for Protein Design | Nicht erfasst | Nicht erfasst | Nicht erfasst | Google DeepMind | — |
| Integration evidence | https://github.com/baker-laboratory/rf_diffusion_all_atom | Nicht erfasst | Nicht erfasst | Nicht erfasst | https://deepmind.google/discover/blog/alphaproteo-generates-novel-proteins-for-biology-and-health-research/ | — |
| Laboratory handoff | Designs validated via yeast surface display and biolayer interferometry (BLI) | Nicht erfasst | Nicht erfasst | Nicht erfasst | Designed binder sequences are ordered as synthetic DNA for yeast surface display and SPR/BLI affinity validation | — |