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 | Multimodal Generative Models | — |
| Company | EvolutionaryScale | — |
| Access mode | Open weights & Cloud API | — |
| Licence conditions | EvolutionaryScale Open Model License (1.4B) / Commercial Cloud API | — |
| Compute requirements | 1x A100 GPU (1.4B open model) to multi-node H100 clusters (98B model) | — |
| Biological application | De novo protein generation, motif scaffolding, and functional sequence design | — |
| Research workflow | Structure & function generation from biological prompts | — |
| Evidence level | Peer-reviewed research and experimental wet-lab validation (Science 2024) | — |
| Commercial eligibility | Commercial API & enterprise licenses available; non-commercial for open weights | — |
| Price | Free open weights (1.4B) / Paid enterprise API | — |
| Availability ⓘ | Globally available via AWS Bedrock and EvolutionaryScale API | — |
| Features | Simultaneous multimodal generation across sequence, coordinates, and secondary structure, Promptable with structural motifs, active site geometries, or sequence fragments, Demonstrated de novo generation of fluorescent proteins with 500M years of divergent evolution, Available in 1.4B open weights, 7B, and 98B parameter frontier configurations | — |
| Entry type | AI Model | — |
| AI role | Multimodal Generative AI | — |
| Input data | 未明确记录 | — |
| Output data | 未明确记录 | — |
| Validation | 未明确记录 | — |
| Type | Generative protein language & structure model | — |
| Intended use | 未明确记录 | — |
| Compatibility | 未明确记录 | — |
| Manufacturer | EvolutionaryScale | — |
| Integration evidence | https://www.evolutionaryscale.ai/blog/esm-3-release | — |
| Laboratory handoff | Output FASTA sequences can be sent directly to gene synthesis vendors (Twist, IDT) | — |