Back to Details

tooluniverse

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

ToolUniverse

ToolUniverse

Overview

概述

ToolUniverse is a unified ecosystem that enables AI agents to function as research scientists by providing standardized access to 600+ scientific resources. Use this skill to discover, execute, and compose scientific tools across multiple research domains including bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery.
Key Capabilities:
  • Access 600+ scientific tools, models, datasets, and APIs
  • Discover tools using natural language, semantic search, or keywords
  • Execute tools through standardized AI-Tool Interaction Protocol
  • Compose multi-step workflows for complex research problems
  • Integration with Claude Desktop/Code via Model Context Protocol (MCP)
ToolUniverse是一个统一的生态系统，它通过提供对600+科研资源的标准化访问，让AI Agent能够像科研人员一样开展工作。使用本Skill可在生物信息学、化学信息学、基因组学、结构生物学、蛋白质组学和药物发现等多个研究领域中发现、执行并组合科研工具。
核心功能：
  • 访问600+科研工具、模型、数据集和API
  • 支持通过自然语言、语义搜索或关键词发现工具
  • 通过标准化AI-Tool Interaction Protocol执行工具
  • 为复杂研究问题构建多步骤工作流
  • 通过Model Context Protocol (MCP)与Claude Desktop/Code集成

When to Use This Skill

适用场景

Use this skill when:
  • Searching for scientific tools by function or domain (e.g., "find protein structure prediction tools")
  • Executing computational biology workflows (e.g., disease target identification, drug discovery, genomics analysis)
  • Accessing scientific databases (OpenTargets, PubChem, UniProt, PDB, ChEMBL, KEGG, etc.)
  • Composing multi-step research pipelines (e.g., target discovery → structure prediction → virtual screening)
  • Working with bioinformatics, cheminformatics, or structural biology tasks
  • Analyzing gene expression, protein sequences, molecular structures, or clinical data
  • Performing literature searches, pathway enrichment, or variant annotation
  • Building automated scientific research workflows
当您遇到以下场景时可使用本Skill：
  • 按功能或领域搜索科研工具（例如："寻找蛋白质结构预测工具"）
  • 执行计算生物学工作流（例如：疾病靶点识别、药物发现、基因组学分析）
  • 访问科研数据库（OpenTargets、PubChem、UniProt、PDB、ChEMBL、KEGG等）
  • 构建多步骤研究管线（例如：靶点发现 → 结构预测 → 虚拟筛选）
  • 处理生物信息学、化学信息学或结构生物学相关任务
  • 分析基因表达、蛋白质序列、分子结构或临床数据
  • 进行文献检索、通路富集或变异注释
  • 构建自动化科研工作流

Quick Start

快速开始

Basic Setup

基础设置

python
from tooluniverse import ToolUniverse
python
from tooluniverse import ToolUniverse

Initialize and load tools

初始化并加载工具

tu = ToolUniverse() tu.load_tools() # Loads 600+ scientific tools
tu = ToolUniverse() tu.load_tools() # 加载600+科研工具

Discover tools

发现工具

tools = tu.run({ "name": "Tool_Finder_Keyword", "arguments": { "description": "disease target associations", "limit": 10 } })
tools = tu.run({ "name": "Tool_Finder_Keyword", "arguments": { "description": "disease target associations", "limit": 10 } })

Execute a tool

执行工具

result = tu.run({ "name": "OpenTargets_get_associated_targets_by_disease_efoId", "arguments": {"efoId": "EFO_0000537"} # Hypertension })
undefined
result = tu.run({ "name": "OpenTargets_get_associated_targets_by_disease_efoId", "arguments": {"efoId": "EFO_0000537"} # 高血压 })
undefined

Model Context Protocol (MCP)

Model Context Protocol (MCP)

For Claude Desktop/Code integration:
bash
tooluniverse-smcp
如需与Claude Desktop/Code集成：
bash
tooluniverse-smcp

Core Workflows

核心工作流

1. Tool Discovery

1. 工具发现

Find relevant tools for your research task:
Three discovery methods:
  • Tool_Finder
    - Embedding-based semantic search (requires GPU)
  • Tool_Finder_LLM
    - LLM-based semantic search (no GPU required)
  • Tool_Finder_Keyword
    - Fast keyword search
Example:
python
undefined
为您的研究任务寻找相关工具：
三种发现方式：
  • Tool_Finder
    - 基于嵌入的语义搜索（需要GPU）
  • Tool_Finder_LLM
    - 基于LLM的语义搜索（无需GPU）
  • Tool_Finder_Keyword
    - 快速关键词搜索
示例：
python
undefined

Search by natural language description

通过自然语言描述搜索工具

tools = tu.run({ "name": "Tool_Finder_LLM", "arguments": { "description": "Find tools for RNA sequencing differential expression analysis", "limit": 10 } })
tools = tu.run({ "name": "Tool_Finder_LLM", "arguments": { "description": "Find tools for RNA sequencing differential expression analysis", "limit": 10 } })

Review available tools

查看可用工具

for tool in tools: print(f"{tool['name']}: {tool['description']}")

**See `references/tool-discovery.md` for:**
- Detailed discovery methods and search strategies
- Domain-specific keyword suggestions
- Best practices for finding tools
for tool in tools: print(f"{tool['name']}: {tool['description']}")

**详见`references/tool-discovery.md`获取：**
- 详细的发现方法与搜索策略
- 领域特定关键词建议
- 工具查找最佳实践

2. Tool Execution

2. 工具执行

Execute individual tools through the standardized interface:
Example:
python
undefined
通过标准化接口执行单个工具：
示例：
python
undefined

Execute disease-target lookup

执行疾病-靶点查询

targets = tu.run({ "name": "OpenTargets_get_associated_targets_by_disease_efoId", "arguments": {"efoId": "EFO_0000616"} # Breast cancer })
targets = tu.run({ "name": "OpenTargets_get_associated_targets_by_disease_efoId", "arguments": {"efoId": "EFO_0000616"} # 乳腺癌 })

Get protein structure

获取蛋白质结构

structure = tu.run({ "name": "AlphaFold_get_structure", "arguments": {"uniprot_id": "P12345"} })
structure = tu.run({ "name": "AlphaFold_get_structure", "arguments": {"uniprot_id": "P12345"} })

Calculate molecular properties

计算分子属性

properties = tu.run({ "name": "RDKit_calculate_descriptors", "arguments": {"smiles": "CCO"} # Ethanol })

**See `references/tool-execution.md` for:**
- Real-world execution examples across domains
- Tool parameter handling and validation
- Result processing and error handling
- Best practices for production use
properties = tu.run({ "name": "RDKit_calculate_descriptors", "arguments": {"smiles": "CCO"} # 乙醇 })

**详见`references/tool-execution.md`获取：**
- 跨领域的真实执行示例
- 工具参数处理与验证
- 结果处理与错误处理
- 生产环境使用最佳实践

3. Tool Composition and Workflows

3. 工具组合与工作流

Compose multiple tools for complex research workflows:
Drug Discovery Example:
python
undefined
组合多个工具以完成复杂研究工作流：
药物发现示例：
python
undefined

1. Find disease targets

1. 查找疾病靶点

targets = tu.run({ "name": "OpenTargets_get_associated_targets_by_disease_efoId", "arguments": {"efoId": "EFO_0000616"} })
targets = tu.run({ "name": "OpenTargets_get_associated_targets_by_disease_efoId", "arguments": {"efoId": "EFO_0000616"} })

2. Get protein structures

2. 获取蛋白质结构

structures = [] for target in targets[:5]: structure = tu.run({ "name": "AlphaFold_get_structure", "arguments": {"uniprot_id": target['uniprot_id']} }) structures.append(structure)
structures = [] for target in targets[:5]: structure = tu.run({ "name": "AlphaFold_get_structure", "arguments": {"uniprot_id": target['uniprot_id']} }) structures.append(structure)

3. Screen compounds

3. 化合物筛选

hits = [] for structure in structures: compounds = tu.run({ "name": "ZINC_virtual_screening", "arguments": { "structure": structure, "library": "lead-like", "top_n": 100 } }) hits.extend(compounds)
hits = [] for structure in structures: compounds = tu.run({ "name": "ZINC_virtual_screening", "arguments": { "structure": structure, "library": "lead-like", "top_n": 100 } }) hits.extend(compounds)

4. Evaluate drug-likeness

4. 评估药物相似性

drug_candidates = [] for compound in hits: props = tu.run({ "name": "RDKit_calculate_drug_properties", "arguments": {"smiles": compound['smiles']} }) if props['lipinski_pass']: drug_candidates.append(compound)

**See `references/tool-composition.md` for:**
- Complete workflow examples (drug discovery, genomics, clinical)
- Sequential and parallel tool composition patterns
- Output processing hooks
- Workflow best practices
drug_candidates = [] for compound in hits: props = tu.run({ "name": "RDKit_calculate_drug_properties", "arguments": {"smiles": compound['smiles']} }) if props['lipinski_pass']: drug_candidates.append(compound)

**详见`references/tool-composition.md`获取：**
- 完整的工作流示例（药物发现、基因组学、临床研究）
- 顺序与并行工具组合模式
- 输出处理钩子
- 工作流最佳实践

Scientific Domains

科研领域

ToolUniverse supports 600+ tools across major scientific domains:
Bioinformatics:
  • Sequence analysis, alignment, BLAST
  • Gene expression (RNA-seq, DESeq2)
  • Pathway enrichment (KEGG, Reactome, GO)
  • Variant annotation (VEP, ClinVar)
Cheminformatics:
  • Molecular descriptors and fingerprints
  • Drug discovery and virtual screening
  • ADMET prediction and drug-likeness
  • Chemical databases (PubChem, ChEMBL, ZINC)
Structural Biology:
  • Protein structure prediction (AlphaFold)
  • Structure retrieval (PDB)
  • Binding site detection
  • Protein-protein interactions
Proteomics:
  • Mass spectrometry analysis
  • Protein databases (UniProt, STRING)
  • Post-translational modifications
Genomics:
  • Genome assembly and annotation
  • Copy number variation
  • Clinical genomics workflows
Medical/Clinical:
  • Disease databases (OpenTargets, OMIM)
  • Clinical trials and FDA data
  • Variant classification
See 
references/domains.md
for:
  • Complete domain categorization
  • Tool examples by discipline
  • Cross-domain applications
  • Search strategies by domain
ToolUniverse支持600+工具，覆盖主要科研领域：
生物信息学：
  • 序列分析、比对、BLAST
  • 基因表达（RNA-seq、DESeq2）
  • 通路富集（KEGG、Reactome、GO）
  • 变异注释（VEP、ClinVar）
化学信息学：
  • 分子描述符与指纹
  • 药物发现与虚拟筛选
  • ADMET预测与药物相似性
  • 化学数据库（PubChem、ChEMBL、ZINC）
结构生物学：
  • 蛋白质结构预测（AlphaFold）
  • 结构检索（PDB）
  • 结合位点检测
  • 蛋白质-蛋白质相互作用
蛋白质组学：
  • 质谱分析
  • 蛋白质数据库（UniProt、STRING）
  • 翻译后修饰
基因组学：
  • 基因组组装与注释
  • 拷贝数变异
  • 临床基因组学工作流
医学/临床：
  • 疾病数据库（OpenTargets、OMIM）
  • 临床试验与FDA数据
  • 变异分类
详见
references/domains.md
获取：
  • 完整的领域分类
  • 各学科工具示例
  • 跨领域应用
  • 分领域搜索策略

Reference Documentation

参考文档

This skill includes comprehensive reference files that provide detailed information for specific aspects:
  • references/installation.md
     - Installation, setup, MCP configuration, platform integration
  • references/tool-discovery.md
     - Discovery methods, search strategies, listing tools
  • references/tool-execution.md
     - Execution patterns, real-world examples, error handling
  • references/tool-composition.md
     - Workflow composition, complex pipelines, parallel execution
  • references/domains.md
     - Tool categorization by domain, use case examples
  • references/api_reference.md
     - Python API documentation, hooks, protocols
Workflow: When helping with specific tasks, reference the appropriate file for detailed instructions. For example, if searching for tools, consult 
references/tool-discovery.md
for search strategies.
本Skill包含全面的参考文件，提供各方面的详细信息：
  • references/installation.md
     - 安装、设置、MCP配置、平台集成
  • references/tool-discovery.md
     - 发现方法、搜索策略、工具列表
  • references/tool-execution.md
     - 执行模式、真实示例、错误处理
  • references/tool-composition.md
     - 工作流组合、复杂管线、并行执行
  • references/domains.md
     - 工具领域分类、用例示例
  • references/api_reference.md
     - Python API文档、钩子、协议
工作流建议： 当处理特定任务时，请查阅对应文件获取详细说明。例如，若您需要搜索工具，请参考
references/tool-discovery.md
中的搜索策略。

Example Scripts

示例脚本

Two executable example scripts demonstrate common use cases:
scripts/example_tool_search.py
 - Demonstrates all three discovery methods:
  • Keyword-based search
  • LLM-based search
  • Domain-specific searches
  • Getting detailed tool information
scripts/example_workflow.py
 - Complete workflow examples:
  • Drug discovery pipeline (disease → targets → structures → screening → candidates)
  • Genomics analysis (expression data → differential analysis → pathways)
Run examples to understand typical usage patterns and workflow composition.
两个可执行示例脚本展示了常见使用场景：
scripts/example_tool_search.py
 - 演示三种发现方式：
  • 基于关键词的搜索
  • 基于LLM的搜索
  • 领域特定搜索
  • 获取详细工具信息
scripts/example_workflow.py
 - 完整工作流示例：
  • 药物发现管线（疾病 → 靶点 → 结构 → 筛选 → 候选药物）
  • 基因组学分析（表达数据 → 差异分析 → 通路）
运行示例以了解典型使用模式与工作流组合方式。

Best Practices

最佳实践

  1. Tool Discovery:
    • Start with broad searches, then refine based on results
    • Use 
      Tool_Finder_Keyword
      for fast searches with known terms
    • Use 
      Tool_Finder_LLM
      for complex semantic queries
    • Set appropriate 
      limit
      parameter (default: 10)
  2. Tool Execution:
    • Always verify tool parameters before execution
    • Implement error handling for production workflows
    • Validate input data formats (SMILES, UniProt IDs, gene symbols)
    • Check result types and structures
  3. Workflow Composition:
    • Test each step individually before composing full workflows
    • Implement checkpointing for long workflows
    • Consider rate limits for remote APIs
    • Use parallel execution when tools are independent
  4. Integration:
    • Initialize ToolUniverse once and reuse the instance
    • Call 
      load_tools()
      once at startup
    • Cache frequently used tool information
    • Enable logging for debugging
  1. 工具发现：
    • 从宽泛搜索开始，再根据结果细化
    • 若已知术语，使用
      Tool_Finder_Keyword
      进行快速搜索
    • 针对复杂语义查询，使用
      Tool_Finder_LLM
    • 设置合适的
      limit
      参数（默认值：10）
  2. 工具执行：
    • 执行前务必验证工具参数
    • 为生产环境工作流实现错误处理
    • 验证输入数据格式（SMILES、UniProt ID、基因符号等）
    • 检查结果类型与结构
  3. 工作流组合：
    • 在组合完整工作流前，单独测试每个步骤
    • 为长工作流实现检查点机制
    • 考虑远程API的调用频率限制
    • 当工具相互独立时，使用并行执行
  4. 集成：
    • 初始化一次ToolUniverse并复用实例
    • 在启动时仅调用一次
      load_tools()
    • 缓存频繁使用的工具信息
    • 启用日志以方便调试

Key Terminology

关键术语

  • Tool: A scientific resource (model, dataset, API, package) accessible through ToolUniverse
  • Tool Discovery: Finding relevant tools using search methods (Finder, LLM, Keyword)
  • Tool Execution: Running a tool with specific arguments via 
    tu.run()
  • Tool Composition: Chaining multiple tools for multi-step workflows
  • MCP: Model Context Protocol for integration with Claude Desktop/Code
  • AI-Tool Interaction Protocol: Standardized interface for LLM-tool communication
  • Tool（工具）：可通过ToolUniverse访问的科研资源（模型、数据集、API、包）
  • Tool Discovery（工具发现）：使用搜索方法（Finder、LLM、关键词）寻找相关工具
  • Tool Execution（工具执行）：通过
    tu.run()
    运行带特定参数的工具
  • Tool Composition（工具组合）：将多个工具链接起来构建多步骤工作流
  • MCP：用于与Claude Desktop/Code集成的Model Context Protocol
  • AI-Tool Interaction Protocol：LLM与工具通信的标准化接口

Resources

资源