Loading BioAtlas...
Loading BioAtlas...
将生物大模型、对接计算引擎与组学管线并排横向对比。按获取方式、硬件开销及细分领域灵活筛选，在一分钟内得出客观可辩护的技术选型方案。
| 技术参数指标 | ＋ 添加工具 | |
|---|---|---|
| Category | Drug Discovery & Chemistry | — |
| Subcategory | Molecular Foundation Models | — |
| Company | IBM Research | — |
| Access mode | Open Source | — |
| Licence conditions | MIT License | — |
| Compute requirements | 1x GPU or CPU for inference; multi-GPU for fine-tuning | — |
| Biological application | Solubility, toxicity (hERG, Ames), BBB permeability, and binding affinity prediction | — |
| Research workflow | SMILES input -> high-dimensional latent molecular embeddings -> downstream property predictions | — |
| Evidence level | Peer-reviewed research (Nature Machine Intelligence 2022) | — |
| Commercial eligibility | Open source release | — |
| Price | Free Open Source | — |
| Availability ⓘ | Available on Hugging Face and GitHub | — |
| 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 | — |
| Entry type | AI Model | — |
| AI role | Chemical Foundation Model | — |
| Input data | 未明确记录 | — |
| Output data | 未明确记录 | — |
| Validation | 未明确记录 | — |
| Type | Chemical transformer foundation model | — |
| Intended use | 未明确记录 | — |
| Compatibility | 未明确记录 | — |
| Manufacturer | IBM Research | — |
| Integration evidence | https://github.com/IBM/molformer | — |
| Laboratory handoff | Filters high-risk toxic molecules before compound synthesis | — |