AlphaFold 3
Mdexa 已核实 · 依据公开的判定规则,逐条对照来源原文核实。了解核查方法结构共折叠 · Google DeepMind 可放置于代码仓库或数据集页面;状态与日期随核实结果更新。 说明徽章
[](https://mdexa.com/models/alphafold3/)<a href="https://mdexa.com/models/alphafold3/"><img src="https://mcp.mdexa.com/v1/badge/models/alphafold3.svg" alt="Mdexa verified · code: Permissive; weights: Restricted · 2026-11" height="20"></a>
AlphaFold 3 代码与权重许可
代码
- 商用
- 可以
- 改编
- 可以
- 再分发
- 可以
raw.githubusercontent.com ·
Apache License
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/LICENSE · 仓库许可证文件 · 核实于 2026-11-13
权重
- 商用
- 不可以
- 改编
- 未写明
- 再分发
- 不可以
raw.githubusercontent.com ·
The AlphaFold 3 model parameters and output are **only** available for
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/WEIGHTS_TERMS_OF_USE.md · 使用条款页 · 核实于 2026-11-13
raw.githubusercontent.com ·
You ***must not* publish or share AlphaFold 3 model parameters**
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/WEIGHTS_TERMS_OF_USE.md · 使用条款页 · 核实于 2026-11-13
raw.githubusercontent.com ·
The AlphaFold 3 model parameters and output are **only** available for non-commercial use by, or on behalf of, non-commercial organizations (*i.e.*, universities, non-profit organizations and research institutes, educational, journalism and government bodies).
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/WEIGHTS_TERMS_OF_USE.md · 使用条款页 · 核实于 2026-11-13
AlphaFold 3 是否允许商业使用
- 代码
- 可以 · 宽松
- 权重
- 不可以 · 有限制
代码与权重的许可分别成立,一方的结论不外推到另一方。原文与出处见上方许可一节。
结论仅记录来源所述,不构成法律意见。
对输出的限制
- 不得使用输出结果训练或构建与 AlphaFold 3 类似的生物分子结构预测机器学习模型或相关技术。
raw.githubusercontent.com ·
Use Output to train or create machine learning models or related technology for biomolecular structure prediction similar to AlphaFold 3
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/WEIGHTS_PROHIBITED_USE_POLICY.md · 使用条款页 · 核实于 2026-11-13
- 模型参数及其输出仅限大学、非营利组织、研究机构、教育机构、新闻机构和政府机构等非商业组织自身或代表其进行非商业使用。
raw.githubusercontent.com ·
The AlphaFold 3 model parameters and output are **only** available for non-commercial use by, or on behalf of, non-commercial organizations (*i.e.*, universities, non-profit organizations and research institutes, educational, journalism and government bodies).
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/WEIGHTS_TERMS_OF_USE.md · 使用条款页 · 核实于 2026-11-13
- AlphaFold 3 及其输出仅用于理论建模,并非为临床用途设计、验证或批准。
raw.githubusercontent.com ·
AlphaFold 3 and its output are for theoretical modeling only. They are not intended, validated, or approved for clinical use.
https://raw.githubusercontent.com/google-deepmind/alphafold3/HEAD/README.md · README · 核实于 2026-11-13
- 《输出使用条款》(最后修改 2024-11-09)禁止代表商业机构或在商业活动中使用 AF3 输出,包括为其开展的研究。
github.com ·
Output are made available free of charge, for non-commercial use
https://github.com/google-deepmind/alphafold3/blob/main/OUTPUT_TERMS_OF_USE.md · 数据集页面 · 核实于 2026-11-13
- 不得用 AF3 输出训练或构建与 AF3 类似的生物分子结构预测模型,包括通过蒸馏。
github.com ·
biomolecular structure prediction similar to AlphaFold 3 as made available
https://github.com/google-deepmind/alphafold3/blob/main/OUTPUT_TERMS_OF_USE.md · 数据集页面 · 核实于 2026-11-13
- 来源原句:You must not share Output with any commercial organization.
raw.githubusercontent.com ·
You must not share Output with any commercial organization.
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/OUTPUT_TERMS_OF_USE.md · model-card-page · 核实于 2026-11-13
- 来源原句:Distribute Output, or disclose findings arising from using AlphaFold 3 without citing our paper:
raw.githubusercontent.com ·
Distribute Output, or disclose findings arising from using AlphaFold 3 without citing our paper:
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/WEIGHTS_PROHIBITED_USE_POLICY.md · model-card-page · 核实于 2026-11-13
- 来源原句:making decisions in domains that affect material or individual rights or
raw.githubusercontent.com ·
making decisions in domains that affect material or individual rights or
https://raw.githubusercontent.com/google-deepmind/alphafold3/main/OUTPUT_TERMS_OF_USE.md · model-card-page · 核实于 2026-11-13
训练数据
- training data 训练所用结构数据均不晚于 2021-09-30 发布。
pmc.ncbi.nlm.nih.gov ·
No structural data used during training were released after 30 September 2021
https://pmc.ncbi.nlm.nih.gov/articles/PMC11168924/ · peer-reviewed-paper · 核实于 2026-11-13
- training data 训练数据中加入了 AlphaFold-Multimer v2.3 的预测结构(交叉蒸馏)。
pmc.ncbi.nlm.nih.gov ·
we use a cross-distillation method in which we enrich the training data with structures predicted by AlphaFold-Multimer (v.2.3)
https://pmc.ncbi.nlm.nih.gov/articles/PMC11168924/ · peer-reviewed-paper · 核实于 2026-11-13
AlphaFold 3 运行方式
- 权重下载storage.googleapis.com
- 托管接口alphafoldserver.com
- 第三方托管github.com
AlphaFold 3 各版本
- unspecified(2026-06-09):代码 —,权重 —
github.com ·
Only the code is re-licensed, the weights license and terms of use stay the same.
https://github.com/google-deepmind/alphafold3/commit/7b197fe859 · official-change-notice · 核实于 2026-11-13
- AlphaFold 3(2026-07-23):代码 —,权重 —
github.com ·
request access to the AlphaFold 3 model parameters, please complete
https://github.com/google-deepmind/alphafold3/commit/dd1a7badb6 · official-change-notice · 核实于 2026-11-13
与基准的重叠
AlphaFold 3 官方下载地址
尚无有出处的说明
已知缺陷与常见误用