# 生物医疗

AIはこれまで生物学や医療分野で広く活用されてきました。かつて注目を集めたIBM Watsonによる医療画像解析が代表例です。最近のAIの急速な進化により、バイオテクノロジーと医療分野での応用はかつてないレベルに到達しています。

## Biotechnology

### Nvidia Evo 2 Protein Design

<https://blogs.nvidia.com/blog/evo-2-biomolecular-ai/>

NVIDIAは、創薬を加速し、タンパク質最適化や生成デザインを活用して生物学研究を前進させる最先端のバイオ分子AIモデル「Evo 2」を発表しました。

{% embed url="<https://blogs.nvidia.com/wp-content/uploads/2025/02/hc-corp-blog-evo2-blueprint-25-1280x680-1.jpg>" %}

### AlphaFold 3

<https://blog.google/technology/ai/google-deepmind-isomorphic-alphafold-3-ai-model/>

AlphaFold 3, developed by Isomorphic Labs and Google DeepMind, predicts the structure and interactions of all life’s molecules with unprecedented accuracy. It models large biomolecules like proteins, DNA, and RNA, as well as small molecules (ligands), enabling insights into biological processes and accelerating drug discovery. The new AlphaFold Server, free for non-commercial research, allows scientists to use these capabilities. This model significantly improves upon previous methods, with potential applications in genomics, drug design, and more resilient crops.

For more information, visit [Isomorphic Labs](https://www.isomorphiclabs.com/articles/alphafold-3-predicts-the-structure-and-interactions-of-all-of-lifes-molecules).

#### Updates:

Google DeepMind releases code behind its most advanced protein prediction program

Link: <https://github.com/google-deepmind/alphafold3>

{% embed url="<https://www.science.org/content/article/google-deepmind-releases-code-behind-its-most-advanced-protein-prediction-program>" %}

{% embed url="<https://www.nature.com/articles/d41586-024-03320-6>" %}

***

## Medical

### FDA Elsa

{% embed url="<https://www.fiercebiotech.com/cro/fda-launces-new-generative-ai-tool-elsa-month-ahead-schedule>" %}

### Google Med Gemini

<https://www.forbes.com/sites/talpatalon/2024/05/01/med-geminis-lions-roar/?sh=10e5238e3d72>

### Google Rad Explain

<https://huggingface.co/spaces/google/rad_explain>

Googleは、MedGemmaモデルを活用し、複雑な放射線レポートを明確で患者に優しい言葉に翻訳するHugging Face Space「Rad Explain」をリリースしました。これにより、医療コミュニケーションとアクセシビリティが向上します。

### Agent Hospital&#x20;

Check the paper here: <https://arxiv.org/pdf/2405.02957>

The paper introduces "Agent Hospital," a simulated hospital environment where autonomous agents, powered by large language models, interact to emulate the complete medical treatment process, enabling doctor agents to learn and improve their medical decision-making through experience.

### Toward robust mammography-based models for breast cancer risk

<https://www.science.org/doi/10.1126/scitranslmed.aba4373>

### Generative AI in healthcare: Adoption trends and what’s next

<https://www.mckinsey.com/industries/healthcare/our-insights/generative-ai-in-healthcare-adoption-trends-and-whats-next?stcr=E799236F2D7C484E910351C388FE9666&cid=other-eml-alt-mip-mck&hlkid=f759c8cfc8fa41c6b99c4ea7516838cc&hctky=14836052&hdpid=283e3e66-d07b-44c4-8536-778c820af02f>

{% embed url="<https://x.com/NVIDIAHealth/status/1902101464454934772>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aiandbusiness.com/ja/to/sheng-wu-yi-liao.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.