菜单
Multimodal reasoning LLM for protein function prediction integrating protein embeddings with biological context to generate structured reasoning traces and functional annotations.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/lamm-mit/scienceclaw --skill bioreason-pro命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | bioreason_pro |
| description | Multimodal reasoning LLM for protein function prediction integrating protein embeddings with biological context to generate structured reasoning traces and functional annotations. |
| source_type | github |
| auth_required | false |
| repository_url | https://github.com/bowang-lab/BioReason-Pro |
| reference_url | https://www.biorxiv.org/content/10.64898/2026.03.19.712954v1 |
Multimodal reasoning LLM for protein function prediction integrating protein embeddings with biological context to generate structured reasoning traces and functional annotations.
https://github.com/bowang-lab/BioReason-Pro
Use this as the implementation source: clone the repo and follow its README for install, dependencies, and how to run code or experiments. The generated client prints JSON with a suggested git clone command.
https://www.biorxiv.org/content/10.64898/2026.03.19.712954v1
This is the paper or artifact home from DOI/registry metadata — not a JSON API. If this URL is arXiv, the generated client can still fetch live Atom metadata (title, abstract, authors) without a BASE_URL. For other hosts, the client uses stub mode until you set a real BASE_URL for a REST service.
The *_client.py script prints JSON that combines a GitHub repository (clone URL + suggested git clone) with optional paper context from arXiv (live Atom metadata when reference_url is arXiv). Run the real code by cloning the repo and following its README — the skill is your agent-facing entrypoint, not a substitute for the repo’s install steps.
To call a REST API instead, set BASE_URL in scripts/bioreason_pro_client.py or wrap the upstream CLI with subprocess after clone.
Extracted for operators and agents. Confirm against the upstream repository or paper before relying on it in production.
# Clone the repository
git clone https://github.com/bowang-lab/BioReason-Pro.git
cd BioReason-Pro
# Install package
pip install -e .
The README does not document specific CLI commands for running inference or training. However, the project provides:
Web Interface: Try BioReason-Pro directly at bioreason.net
Precomputed Predictions: Access 240,000+ precomputed protein predictions at bioreason.net/atlas
Model Checkpoints: Available on HuggingFace collection (wanglab/bioreason-pro)
Datasets: Training and evaluation datasets available at HuggingFace collection with detailed download and usage instructions
The README does not document specific environment variables, API keys, or configuration parameters. For detailed usage instructions on running inference or training, refer to the repository's code or documentation at https://github.com/bowang-lab/BioReason-Pro or the project website at https://bioreason.net.
The same text lives in scripts/USAGE.md for tools that prefer reading files under scripts/.
python3 scripts/bioreason_pro_client.py