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 | ＋ Werkzeug hinzufügen | |||||
|---|---|---|---|---|---|---|
| Category | Drug Discovery & Chemistry | AI Drug Discovery | AI Drug Discovery | AI Drug Discovery | AI Drug Discovery | — |
| Subcategory | Molecular Foundation Models | Research AI Methods | Molecular Property Prediction | Molecular Design | Research AI Methods | — |
| Company | IBM Research | Research / method authors | Luo Lab | Sekijima Lab | Research / method authors | — |
| Access mode | Open Source | Confirm distribution and exact release | Research code or publication | Research code or publication | Confirm distribution and exact release | — |
| Licence conditions | MIT License | NOT_INDEPENDENTLY_AUDITED | Check code and model weights separately | Check code and model weights separately | NOT_INDEPENDENTLY_AUDITED | — |
| Compute requirements | 1x GPU or CPU for inference; multi-GPU for fine-tuning | Version and data dependent | Check selected checkpoint and runtime; no GPU catalog recommendation | Check selected checkpoint and runtime; no GPU catalog recommendation | Version and data dependent | — |
| Biological application | Solubility, toxicity (hERG, Ames), BBB permeability, and binding affinity prediction | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Research workflow | SMILES input -> high-dimensional latent molecular embeddings -> downstream property predictions | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Evidence level | Peer-reviewed research (Nature Machine Intelligence 2022) | PEER_REVIEWED_METHOD_OR_CONFERENCE | Peer-reviewed primary method | Peer-reviewed primary method | OFFICIAL_DOCUMENTATION | — |
| Commercial eligibility | Open source release | NOT_INDEPENDENTLY_AUDITED | Unknown, requires audit | Unknown, requires audit | NOT_INDEPENDENTLY_AUDITED | — |
| Price | Free Open Source | Verify access and licence | Check selected model licence | Check selected model licence | Verify access and licence | — |
| Availability ⓘ | Available on Hugging Face and GitHub | Method paper or official documentation | Public research method/code | Public research method/code | Method paper or official documentation | — |
| Features | Trained on 1.1 billion SMILES strings from PubChem and ZINC databases, Linear attention mechanism enabling efficient scaling to large molecular graphs, State-of-the-art benchmarks on MoleculeNet across physical chemistry and biophysics tasks, Fine-tuning support for custom pharmaceutical assay endpoints | ADMET-AI scientific method, Molecular SMILES with well-defined compound stereochemistry and relevant assay domain, Predicted absorption, distribution, metabolism, excretion and toxicity endpoints | Chemical foundation model for learned molecular representations, property prediction and conditional molecule generation., Molecular features, predicted properties or generated SMILES | Diffusion-based ligand molecule generation constrained by specified pocket and pharmacophore interactions., Generated 3D chemical candidate structures | DiffSBDD scientific method, Protein binding pocket coordinates and desired molecular design context, Diffusion-generated candidate ligands | — |
| Entry type | AI Model | Source-scoped research method | Research AI model / method | Research AI model / method | Source-scoped research method | — |
| AI role | Chemical Foundation Model | ENSEMBLE_ML | Published biomedical AI method | Published biomedical AI method | DEEP_LEARNING | — |
| Input data | Nicht erfasst | Molecular SMILES with well-defined compound stereochemistry and relevant assay domain | Valid SMILES; trained downstream endpoint or conditioned molecule task | Protein pocket coordinates; interaction constraints | Protein binding pocket coordinates and desired molecular design context | — |
| Output data | Nicht erfasst | Predicted absorption, distribution, metabolism, excretion and toxicity endpoints | Molecular features; predicted properties or generated SMILES | Generated 3D chemical candidate structures | Diffusion-generated candidate ligands | — |
| Validation | Nicht erfasst | Published method scope; no independent BioAtlas execution or benchmark | Requires independent dataset-specific evaluation | Requires independent dataset-specific evaluation | Published method scope; no independent BioAtlas execution or benchmark | — |
| Type | Chemical transformer foundation model | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Intended use | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Compatibility | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Manufacturer | IBM Research | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Integration evidence | https://github.com/IBM/molformer | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |
| Laboratory handoff | Filters high-risk toxic molecules before compound synthesis | Nicht erfasst | Nicht erfasst | Nicht erfasst | Nicht erfasst | — |