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 | Biological Foundation Models | — |
| Subcategory | Protein Language Models | — |
| Company | Salesforce AI Research | — |
| Access mode | Open Source | — |
| Licence conditions | BSD-3-Clause | — |
| Compute requirements | 1x GPU (>= 16GB VRAM) for inference | — |
| Biological application | Enzyme engineering, antibody optimization, and zero-shot fitness prediction | — |
| Research workflow | Generate sequence variants with high predicted stability and activity | — |
| Evidence level | Peer-reviewed publication (NeurIPS 2023) | — |
| Commercial eligibility | Permissive open source release | — |
| Price | Free Open Source | — |
| Availability ⓘ | Available on GitHub and Hugging Face | — |
| Features | Trained on over 1 billion sequences from UniParc, BFD, and metagenomic sources, Controllable sequence generation with tag-based conditioning, High accuracy zero-shot variant effect prediction, Model sizes ranging from 150M to 6.4B parameters | — |
| Entry type | AI Model | — |
| AI role | Generative Protein Modeling | — |
| Input data | 未明确记录 | — |
| Output data | 未明确记录 | — |
| Validation | 未明确记录 | — |
| Type | Autoregressive protein language model | — |
| Intended use | 未明确记录 | — |
| Compatibility | 未明确记录 | — |
| Manufacturer | Salesforce AI Research | — |
| Integration evidence | https://github.com/salesforce/progen | — |
| Laboratory handoff | Sequences ready for oligonucleotide synthesis and screening | — |