跳到正文
cccskills
免费在 GitHub 公开

query-reactome

Query Reactome for biological pathways and reactions. Use when user asks about signaling cascades, biological processes, pathway diagrams, or reaction details. Triggers on "reactome", "signaling cascade", "biological pathway", "pathway diagram", "reaction mechanism".

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md2.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Reactome Pathway Database

Query the Reactome ContentService and AnalysisService APIs.

When to Use

  • User asks about detailed biological pathways
  • User wants pathway diagrams
  • User asks about specific reactions in a pathway
  • User wants to do pathway enrichment with a gene list

How to Execute

import requests
import json

CONTENT_URL = "https://reactome.org/ContentService"
ANALYSIS_URL = "https://reactome.org/AnalysisService"

# 1. Search pathways by keyword
def search_pathways(keyword, species="Homo sapiens"):
    url = f"{CONTENT_URL}/search/query"
    params = {"query": keyword, "species": species, "types": "Pathway", "cluster": True}
    r = requests.get(url, params=params)
    r.raise_for_status()
    return r.json()

# 2. Get pathway details
def get_pathway(pathway_id):
    url = f"{CONTENT_URL}/data/query/{pathway_id}"
    r = requests.get(url, headers={"Accept": "application/json"})
    r.raise_for_status()
    return r.json()

# 3. Get genes/proteins in a pathway
def get_pathway_participants(pathway_id):
    url = f"{CONTENT_URL}/data/participants/{pathway_id}"
    r = requests.get(url, headers={"Accept": "application/json"})
    r.raise_for_status()
    return r.json()

# 4. Gene list pathway enrichment
def pathway_enrichment(gene_list):
    url = f"{ANALYSIS_URL}/identifiers/projection"
    genes_text = "\n".join(gene_list)
    headers = {"Content-Type": "text/plain"}
    r = requests.post(url, data=genes_text, headers=headers)
    r.raise_for_status()
    return r.json()

# 5. Look up a gene in Reactome
def query_gene(gene_symbol):
    url = f"{CONTENT_URL}/data/query/{gene_symbol}"
    r = requests.get(url, headers={"Accept": "application/json"})
    r.raise_for_status()
    return r.json()

# Example: DNA repair pathways
results = search_pathways("DNA repair")
entries = results.get("results", [])
for entry in entries[:5]:
    for e in entry.get("entries", []):
        print(f"{e.get('stId', 'N/A')}: {e.get('name', 'N/A')}")

# Pathway enrichment
enrichment = pathway_enrichment(["BRCA1", "BRCA2", "TP53", "ATM", "CHEK2"])
for p in enrichment.get("pathways", [])[:5]:
    name = p.get("name", "N/A")
    pval = p.get("entities", {}).get("pValue", "N/A")
    found = p.get("entities", {}).get("found", 0)
    print(f"{name} — p={pval:.2e}, {found} genes found")

Common Pathway IDs

  • DNA Repair: R-HSA-73894
  • Apoptosis: R-HSA-109581
  • Cell Cycle: R-HSA-1640170
  • Immune System: R-HSA-168256

Follow-up Suggestions

  • "Want me to do pathway enrichment with your gene list?"
  • "Should I compare with KEGG pathways?"
  • "Want me to find upstream regulators of this pathway?"

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

alphafold

免费

Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

AlphaFold2 / AlphaFold-Multimer structure prediction for validation and confidence scoring. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm2-sequence-scoring. For QC thresholds, use protein-design-qc.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

Workflow for event-level and isoform-level splicing analysis with sashimi-ready outputs and splice QC.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

atac-seq

免费

ATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

bindcraft

免费

End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

查看 BioTender-max 的全部技能

报告此技能的问题