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 | Genomics & Sequence Modeling | — |
| Subcategory | Clinical Variant Effect Prediction | — |
| Company | Google DeepMind | — |
| Access mode | Open Access (Research) | — |
| Licence conditions | Code: Apache 2.0; Predictions/Data: CC BY-NC 4.0 | — |
| Compute requirements | Pre-computed database lookup (trained weights for arbitrary novel sequences not published) | — |
| Biological application | Rare disease diagnosis, oncogenic driver mutation identification, and human genetics | — |
| Research workflow | Query missense variant (e.g. BRCA1 p.Cys61Gly) -> obtain pathogenicity score (0 to 1) | — |
| Evidence level | Peer-reviewed research (Science 2023) | — |
| Commercial eligibility | Research use only (non-commercial clinical evaluation) | — |
| Price | Free Open Access | — |
| Availability ⓘ | Available on GitHub and Ensembl / ClinVar cross-references | — |
| Features | Comprehensive predictions for all 71 million possible human missense variants, Trained on population frequency data and structural context without clinical label leakage, Classified 89% of missense variants as either likely pathogenic (32%) or likely benign (57%), Pre-computed database and downloadable BigWig/VCF files for integration into clinical pipelines | — |
| Entry type | AI Model & Database | — |
| AI role | Clinical Pathogenicity Classification | — |
| Input data | 未明确记录 | — |
| Output data | 未明确记录 | — |
| Validation | 未明确记录 | — |
| Type | Structural variant effect prediction model & database | — |
| Intended use | 未明确记录 | — |
| Compatibility | 未明确记录 | — |
| Manufacturer | Google DeepMind | — |
| Integration evidence | https://github.com/google-deepmind/alphamissense | — |
| Laboratory handoff | Informs targeted functional genomics assays (Deep Mutational Scanning) | — |