药物重定位工具：使用ToolUniverse进行系统性药物发现与评估

tooluniverse-drug-repurposing by mims-harvard/tooluniverse

166 周安装量

1,200 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-drug-repurposing

AI/机器学习科研工具生物信息学

🇨🇳中文介绍

使用 ToolUniverse 进行药物重定位

利用多种计算策略，系统性地识别和评估药物重定位候选药物。

重要提示：在工具调用中始终使用英文术语。使用用户的语言进行回复。

核心策略

基于靶点：疾病靶点 -> 寻找调节这些靶点的药物
基于化合物：已批准药物 -> 寻找新的疾病适应症
基于疾病驱动：疾病 -> 靶点 -> 匹配现有药物

工作流概述

Phase 1: Disease & Target Analysis
  Get disease info (OpenTargets), find associated targets, get target details

Phase 2: Drug Discovery
  Search DrugBank, DGIdb, ChEMBL for drugs targeting disease-associated genes
  Get drug details, indications, pharmacology

Phase 3: Safety & Feasibility Assessment
  FDA warnings, FAERS adverse events, drug interactions, ADMET predictions

Phase 4: Literature Evidence
  PubMed, Europe PMC, clinical trials for existing evidence

Phase 5: Scoring & Ranking
  Composite score: target association + safety + literature + drug properties

详见：PROCEDURES.md 获取详细的逐步操作流程和代码模式。

快速开始

from tooluniverse import ToolUniverse
tu = ToolUniverse(use_cache=True)
tu.load_tools()

# Step 1: Get disease targets
disease_info = tu.tools.OpenTargets_get_disease_id_description_by_name(diseaseName="rheumatoid arthritis")
targets = tu.tools.OpenTargets_get_associated_targets_by_disease_efoId(efoId=disease_info['data']['id'], limit=10)

# Step 2: Find drugs for each target
for target in targets['data'][:5]:
    drugs = tu.tools.DGIdb_get_drug_gene_interactions(gene_name=target['gene_symbol'])

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

关键 ToolUniverse 工具

疾病与靶点：

OpenTargets_get_disease_id_description_by_name - 疾病查询
OpenTargets_get_associated_targets_by_disease_efoId - 疾病靶点
UniProt_get_entry_by_accession - 蛋白质详情

drugbank_get_drug_name_and_description_by_target_name - 按靶点查找药物
drugbank_get_drug_name_and_description_by_indication - 按适应症查找药物
DGIdb_get_drug_gene_interactions - 药物-基因相互作用
ChEMBL_search_drugs / ChEMBL_get_drug_mechanisms - 药物搜索和作用机制

drugbank_get_drug_basic_info_by_drug_name_or_id - 基本信息
drugbank_get_indications_by_drug_name_or_drugbank_id - 已批准适应症
drugbank_get_pharmacology_by_drug_name_or_drugbank_id - 药理学
drugbank_get_targets_by_drug_name_or_drugbank_id - 药物靶点

FDA_get_warnings_and_cautions_by_drug_name - FDA 警告
FAERS_search_reports_by_drug_and_reaction - 不良事件
FAERS_count_death_related_by_drug - 严重结果
drugbank_get_drug_interactions_by_drug_name_or_id - 相互作用

ADMETAI_predict_admet / ADMETAI_predict_toxicity - ADMET 和毒性

PubMed_search_articles / EuropePMC_search_articles / ClinicalTrials_search

类别	分值	细分
靶点关联性	0-40	强遗传关联：40，中等关联：25，通路水平关联：15，弱关联：5
安全性概况	0-30	FDA 批准：20，III 期临床试验：15，II 期临床试验：10，无黑框警告：+10
文献证据	0-20	临床试验：每项 5 分（最高 15 分），临床前研究：每项 1 分（最高 10 分）
药物性质	0-10	高生物利用度：5，血脑屏障穿透（中枢神经系统）：5，低毒性：5

广泛开始：查询多个数据库（DrugBank、ChEMBL、DGIdb）
验证靶点：在 OpenTargets 中确认靶点-疾病关联
安全第一：优先考虑具有已知安全性概况的已批准药物
文献挖掘：搜索现有的临床/临床前证据
考虑机制：评估生物学合理性
批量操作：使用 tu.run_batch() 进行并行查询

问题	解决方案
未找到疾病	尝试同义词或 EFO ID 查询
靶点无对应药物	检查 HUGO 命名法，扩展到通路水平，尝试类似靶点
文献证据不足	搜索药物类别，检查临床前/动物研究
安全性数据不可用	药物可能未在美国获批，检查 EMA 或临床试验安全性数据

REFERENCE.md - 详细参考文档
EXAMPLES.md - 重定位分析示例
PROCEDURES.md - 带代码的逐步操作流程
REPORT_TEMPLATE.md - 输出报告模板
相关技能：disease-intelligence-gatherer, chemical-compound-retrieval, tooluniverse-sdk

🇺🇸English

Drug Repurposing with ToolUniverse

Systematically identify and evaluate drug repurposing candidates using multiple computational strategies.

IMPORTANT : Always use English terms in tool calls. Respond in the user's language.

Core Strategies

Target-Based : Disease targets -> Find drugs that modulate those targets
Compound-Based : Approved drugs -> Find new disease indications
Disease-Driven : Disease -> Targets -> Match to existing drugs

Workflow Overview

Phase 1: Disease & Target Analysis
  Get disease info (OpenTargets), find associated targets, get target details

Phase 2: Drug Discovery
  Search DrugBank, DGIdb, ChEMBL for drugs targeting disease-associated genes
  Get drug details, indications, pharmacology

Phase 3: Safety & Feasibility Assessment
  FDA warnings, FAERS adverse events, drug interactions, ADMET predictions

Phase 4: Literature Evidence
  PubMed, Europe PMC, clinical trials for existing evidence

Phase 5: Scoring & Ranking
  Composite score: target association + safety + literature + drug properties

See: PROCEDURES.md for detailed step-by-step procedures and code patterns.

Quick Start

from tooluniverse import ToolUniverse
tu = ToolUniverse(use_cache=True)
tu.load_tools()

# Step 1: Get disease targets
disease_info = tu.tools.OpenTargets_get_disease_id_description_by_name(diseaseName="rheumatoid arthritis")
targets = tu.tools.OpenTargets_get_associated_targets_by_disease_efoId(efoId=disease_info['data']['id'], limit=10)

# Step 2: Find drugs for each target
for target in targets['data'][:5]:
    drugs = tu.tools.DGIdb_get_drug_gene_interactions(gene_name=target['gene_symbol'])

Key ToolUniverse Tools

Disease & Target:

OpenTargets_get_disease_id_description_by_name - Disease lookup
OpenTargets_get_associated_targets_by_disease_efoId - Disease targets
UniProt_get_entry_by_accession - Protein details

Drug Discovery :

drugbank_get_drug_name_and_description_by_target_name - Drugs by target
drugbank_get_drug_name_and_description_by_indication - Drugs by indication
DGIdb_get_drug_gene_interactions - Drug-gene interactions
ChEMBL_search_drugs / ChEMBL_get_drug_mechanisms - Drug search and MOA

Drug Information :

drugbank_get_drug_basic_info_by_drug_name_or_id - Basic info
drugbank_get_indications_by_drug_name_or_drugbank_id - Approved indications
drugbank_get_pharmacology_by_drug_name_or_drugbank_id - Pharmacology
drugbank_get_targets_by_drug_name_or_drugbank_id - Drug targets

Safety :

FDA_get_warnings_and_cautions_by_drug_name - FDA warnings
FAERS_search_reports_by_drug_and_reaction - Adverse events
FAERS_count_death_related_by_drug - Serious outcomes
drugbank_get_drug_interactions_by_drug_name_or_id - Interactions

Property Prediction :

ADMETAI_predict_admet / ADMETAI_predict_toxicity - ADMET and toxicity

Literature :

PubMed_search_articles / EuropePMC_search_articles / ClinicalTrials_search

Scoring Criteria

Category	Points	Breakdown
Target Association	0-40	Strong genetic: 40, Moderate: 25, Pathway-level: 15, Weak: 5
Safety Profile	0-30	FDA approved: 20, Phase III: 15, Phase II: 10, No black box: +10
Literature Evidence	0-20	Clinical trials: 5 each (max 15), Preclinical: 1 each (max 10)
Drug Properties	0-10	High bioavailability: 5, BBB penetration (CNS): 5, Low toxicity: 5

Best Practices

Start broad : Query multiple databases (DrugBank, ChEMBL, DGIdb)
Validate targets : Confirm target-disease associations in OpenTargets
Safety first : Prioritize approved drugs with known safety profiles
Literature mining : Search for existing clinical/preclinical evidence
Consider mechanism : Evaluate biological plausibility
Batch operations : Use tu.run_batch() for parallel queries

Troubleshooting

Problem	Solution
Disease not found	Try synonyms or EFO ID lookup
No drugs for target	Check HUGO nomenclature, expand to pathway-level, try similar targets
Insufficient literature	Search drug class instead, check preclinical/animal studies
Safety data unavailable	Drug may not be US-approved, check EMA or clinical trial safety

Reference Files

REFERENCE.md - Detailed reference documentation
EXAMPLES.md - Sample repurposing analyses
PROCEDURES.md - Step-by-step procedures with code
REPORT_TEMPLATE.md - Output report template
Related skills: disease-intelligence-gatherer, chemical-compound-retrieval, tooluniverse-sdk

Weekly Installs

147

Repository

mims-harvard/to…universe

GitHub Stars

1.2K

First Seen

Feb 8, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

gemini-cli138

codex138

opencode138

github-copilot135

kimi-cli130

amp130

AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具

50,900 周安装