@nahisaho/satori 0.13.0 → 0.14.0

package/src/.github/skills/scientific-ebi-databases/SKILL.md

@@ -0,0 +1,280 @@
+---
+name: scientific-ebi-databases
+description: |
+  EBI データベース群統合アクセススキル。EBI Search 横断検索、ENA Browser
+  ヌクレオチドアーカイブ、BioStudies 研究データ、dbfetch エントリ取得、
+  MetaboLights メタボロミクスリポジトリの統合パイプライン。
+---
+
+# Scientific EBI Databases
+
+EBI Search / ENA Browser / BioStudies / dbfetch / MetaboLights を統合した
+EBI データベース群アクセスパイプラインを提供する。
+
+## When to Use
+
+- EBI Search で複数データベースを横断検索するとき
+- ENA (European Nucleotide Archive) で配列データを検索するとき
+- BioStudies で研究プロジェクトデータを探すとき
+- dbfetch でエントリを一括取得するとき
+- MetaboLights でメタボロミクス実験データにアクセスするとき
+
+---
+
+## Quick Start
+
+## 1. EBI Search 横断検索
+
+```python
+import requests
+import pandas as pd
+
+EBI_SEARCH_API = "https://www.ebi.ac.uk/ebisearch/ws/rest"
+
+
+def search_ebi(query, domain="allebi", size=25, fields=None):
+    """
+    EBI Search 横断検索 — 複数 EBI データベースを一括検索。
+
+    Parameters:
+        query: str — 検索クエリ
+        domain: str — 検索ドメイン ("allebi", "uniprot", "pdb", "ena", etc.)
+        size: int — 最大取得数
+        fields: list — 返却フィールド
+
+    ToolUniverse:
+        EBI_Search_query(query=query, domain=domain)
+        EBI_Search_get_entry(domain=domain, entry_id=entry_id)
+    """
+    params = {
+        "query": query,
+        "size": size,
+        "format": "json",
+    }
+    if fields:
+        params["fields"] = ",".join(fields)
+
+    resp = requests.get(f"{EBI_SEARCH_API}/{domain}", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for entry in data.get("entries", []):
+        row = {"id": entry.get("id", ""), "source": entry.get("source", "")}
+        for field in entry.get("fields", {}):
+            row[field] = entry["fields"][field][0] if entry["fields"][field] else ""
+        results.append(row)
+
+    df = pd.DataFrame(results)
+    total = data.get("hitCount", 0)
+    print(f"EBI Search [{domain}] '{query}': {total} total hits, {len(df)} returned")
+    return df
+```
+
+## 2. ENA (European Nucleotide Archive) 配列検索
+
+```python
+ENA_API = "https://www.ebi.ac.uk/ena/browser/api"
+
+
+def search_ena(query, result_type="sequence", limit=100):
+    """
+    ENA ヌクレオチドアーカイブ検索。
+
+    Parameters:
+        query: str — 検索クエリ or Taxon ID
+        result_type: str — "sequence", "read_run", "analysis", "study"
+        limit: int — 最大取得数
+
+    ToolUniverse:
+        ENA_search(query=query, result=result_type)
+        ENA_get_entry(accession=accession)
+    """
+    params = {
+        "query": query,
+        "result": result_type,
+        "limit": limit,
+        "format": "json",
+    }
+    resp = requests.get(f"{ENA_API}/search", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    df = pd.DataFrame(data) if isinstance(data, list) else pd.DataFrame()
+    print(f"ENA search '{query}' [{result_type}]: {len(df)} entries")
+    return df
+
+
+def get_ena_entry(accession, display="json"):
+    """
+    ENA アクセッション番号によるエントリ取得。
+
+    Parameters:
+        accession: str — ENA accession (e.g., "ERS000001", "ERR000001")
+    """
+    resp = requests.get(
+        f"{ENA_API}/entry/{accession}",
+        params={"display": display}
+    )
+    resp.raise_for_status()
+    print(f"ENA entry {accession}: retrieved")
+    return resp.json() if display == "json" else resp.text
+```
+
+## 3. BioStudies 研究データ検索
+
+```python
+BIOSTUDIES_API = "https://www.ebi.ac.uk/biostudies/api/v1"
+
+
+def search_biostudies(query, page_size=25):
+    """
+    BioStudies 研究プロジェクトデータ検索。
+
+    Parameters:
+        query: str — 検索クエリ
+        page_size: int — ページサイズ
+
+    ToolUniverse:
+        BioStudies_search(query=query)
+        BioStudies_get_study(accession=accession)
+    """
+    params = {"query": query, "pageSize": page_size}
+    resp = requests.get(f"{BIOSTUDIES_API}/search", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for hit in data.get("hits", []):
+        results.append({
+            "accession": hit.get("accno", ""),
+            "title": hit.get("title", ""),
+            "author": hit.get("author", ""),
+            "release_date": hit.get("rtime", ""),
+            "type": hit.get("type", ""),
+            "files": hit.get("files", 0),
+            "links": hit.get("links", 0),
+        })
+
+    df = pd.DataFrame(results)
+    total = data.get("totalHits", 0)
+    print(f"BioStudies search '{query}': {total} total, {len(df)} returned")
+    return df
+```
+
+## 4. dbfetch エントリ一括取得
+
+```python
+DBFETCH_API = "https://www.ebi.ac.uk/Tools/dbfetch/dbfetch"
+
+
+def dbfetch(db, ids, format_type="json", style="raw"):
+    """
+    dbfetch — EBI データベースエントリ一括取得。
+
+    Parameters:
+        db: str — データベース名 (e.g., "uniprotkb", "embl", "pdb")
+        ids: list — ID リスト
+        format_type: str — 出力形式 ("json", "fasta", "xml")
+        style: str — スタイル ("raw", "html")
+
+    ToolUniverse:
+        dbfetch_get_entries(db=db, ids=ids, format=format_type)
+    """
+    ids_str = ",".join(ids) if isinstance(ids, list) else ids
+    params = {
+        "db": db,
+        "id": ids_str,
+        "format": format_type,
+        "style": style,
+    }
+    resp = requests.get(DBFETCH_API, params=params)
+    resp.raise_for_status()
+
+    print(f"dbfetch [{db}]: {len(ids) if isinstance(ids, list) else 1} entries, "
+          f"format={format_type}")
+    if format_type == "json":
+        return resp.json()
+    return resp.text
+```
+
+## 5. MetaboLights メタボロミクスリポジトリ
+
+```python
+METABOLIGHTS_API = "https://www.ebi.ac.uk/metabolights/ws"
+
+
+def search_metabolights(query):
+    """
+    MetaboLights メタボロミクス実験データ検索。
+
+    Parameters:
+        query: str — 検索クエリ (化合物名、疾患名、生物種)
+
+    ToolUniverse:
+        MetaboLights_search_studies(query=query)
+        MetaboLights_get_study(study_id=study_id)
+    """
+    resp = requests.get(
+        f"{METABOLIGHTS_API}/studies/search",
+        params={"query": query}
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for study in data.get("content", []):
+        results.append({
+            "study_id": study.get("studyIdentifier", ""),
+            "title": study.get("title", ""),
+            "organism": study.get("organism", ""),
+            "description": (study.get("description") or "")[:200],
+            "submission_date": study.get("submissionDate", ""),
+            "status": study.get("studyStatus", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"MetaboLights search '{query}': {len(df)} studies")
+    return df
+
+
+def get_metabolights_study(study_id):
+    """MetaboLights 個別研究取得。"""
+    resp = requests.get(f"{METABOLIGHTS_API}/studies/{study_id}")
+    resp.raise_for_status()
+    data = resp.json()
+    print(f"MetaboLights {study_id}: {data.get('title', '')[:80]}")
+    return data
+```
+
+---
+
+## 利用可能ツール
+
+| ToolUniverse カテゴリ | 主なツール |
+|---|---|
+| `ebi_search` | `EBI_Search_query`, `EBI_Search_get_entry` |
+| `ena_browser` | `ENA_search`, `ENA_get_entry` |
+| `biostudies` | `BioStudies_search`, `BioStudies_get_study` |
+| `dbfetch` | `dbfetch_get_entries` |
+| `metabolights` | `MetaboLights_search_studies`, `MetaboLights_get_study` |
+
+## パイプライン出力
+
+| 出力ファイル | 説明 | 連携先スキル |
+|---|---|---|
+| `results/ebi_search.csv` | EBI 横断検索結果 | → bioinformatics, literature-search |
+| `results/ena_sequences.fasta` | ENA 配列データ | → genome-sequence-tools, sequence-analysis |
+| `results/biostudies_metadata.json` | 研究プロジェクト情報 | → multi-omics, systematic-review |
+| `results/metabolights_study.json` | メタボロミクスデータ | → metabolomics, metabolomics-databases |
+
+## パイプライン統合
+
+```
+genome-sequence-tools ──→ ebi-databases ──→ metabolomics-databases
+  (NCBI/BLAST)           (ENA/EBI Search)   (HMDB/MetaCyc)
+                              │
+                              ├──→ bioinformatics (配列データ)
+                              ├──→ sequence-analysis (FASTA)
+                              └──→ structural-proteomics (PDBe cross-ref)
+```

package/src/.github/skills/scientific-ontology-enrichment/SKILL.md

@@ -0,0 +1,340 @@
+---
+name: scientific-ontology-enrichment
+description: |
+  オントロジー・エンリッチメント解析スキル。EFO 実験ファクターオントロジー、
+  OLS オントロジー検索サービス、Enrichr 遺伝子セット濃縮解析、
+  UMLS メタシソーラス統一医学言語体系の統合パイプライン。
+---
+
+# Scientific Ontology Enrichment
+
+EFO / OLS / Enrichr / UMLS を統合した
+オントロジー検索・エンリッチメント解析パイプラインを提供する。
+
+## When to Use
+
+- EFO で実験条件 (疾患・細胞型・組織) のオントロジー ID を取得するとき
+- OLS で複数オントロジー横断検索 (HP, MONDO, DOID, GO, CHEBI) するとき
+- Enrichr で遺伝子リストの濃縮解析を行うとき
+- UMLS CUI で異なる用語体系間のマッピングを行うとき
+- GWAS Catalog の trait を EFO 用語で標準化するとき
+
+---
+
+## Quick Start
+
+## 1. EFO 実験ファクターオントロジー
+
+```python
+import requests
+import pandas as pd
+
+OLS_API = "https://www.ebi.ac.uk/ols4/api"
+
+
+def search_efo(query, exact=False):
+    """
+    EFO (Experimental Factor Ontology) 検索。
+
+    Parameters:
+        query: str — 検索語 (疾患名、細胞型、組織名等)
+        exact: bool — 完全一致検索
+
+    ToolUniverse:
+        EFO_search(query=query, exact=exact)
+    """
+    params = {
+        "q": query,
+        "ontology": "efo",
+        "exact": str(exact).lower(),
+        "rows": 30,
+    }
+    resp = requests.get(f"{OLS_API}/search", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for doc in data.get("response", {}).get("docs", []):
+        results.append({
+            "efo_id": doc.get("obo_id", ""),
+            "label": doc.get("label", ""),
+            "description": (doc.get("description") or [""])[0][:200],
+            "iri": doc.get("iri", ""),
+            "ontology": doc.get("ontology_name", ""),
+            "is_defining_ontology": doc.get("is_defining_ontology", False),
+            "synonyms": doc.get("synonym", []),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"EFO search '{query}': {len(df)} terms")
+    return df
+```
+
+## 2. OLS マルチオントロジー検索
+
+```python
+def search_ols(query, ontologies=None, type_filter=None):
+    """
+    OLS (Ontology Lookup Service) マルチオントロジー横断検索。
+
+    Parameters:
+        query: str — 検索語
+        ontologies: list — オントロジー ID リスト (e.g., ["hp", "mondo", "go"])
+        type_filter: str — "class", "property", "individual"
+
+    ToolUniverse:
+        OLS_search(query=query, ontology=ontology)
+        OLS_get_term(ontology=ontology, iri=iri)
+        OLS_get_ancestors(ontology=ontology, iri=iri)
+    """
+    params = {"q": query, "rows": 50}
+    if ontologies:
+        params["ontology"] = ",".join(ontologies)
+    if type_filter:
+        params["type"] = type_filter
+
+    resp = requests.get(f"{OLS_API}/search", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for doc in data.get("response", {}).get("docs", []):
+        results.append({
+            "obo_id": doc.get("obo_id", ""),
+            "label": doc.get("label", ""),
+            "ontology": doc.get("ontology_name", ""),
+            "description": (doc.get("description") or [""])[0][:200],
+            "iri": doc.get("iri", ""),
+            "synonyms": doc.get("synonym", []),
+            "has_children": doc.get("has_children", False),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"OLS search '{query}' "
+          f"[{','.join(ontologies) if ontologies else 'all'}]: "
+          f"{len(df)} terms")
+    return df
+
+
+def get_ols_term_hierarchy(ontology, term_id):
+    """
+    OLS 用語の階層構造 (ancestors/descendants) 取得。
+
+    Parameters:
+        ontology: str — オントロジー ID (e.g., "hp", "go")
+        term_id: str — OBO ID (e.g., "HP:0001250")
+    """
+    iri = f"http://purl.obolibrary.org/obo/{term_id.replace(':', '_')}"
+    encoded_iri = requests.utils.quote(requests.utils.quote(iri, safe=""), safe="")
+
+    # Ancestors
+    anc_resp = requests.get(
+        f"{OLS_API}/ontologies/{ontology}/terms/{encoded_iri}/ancestors"
+    )
+
+    # Descendants
+    desc_resp = requests.get(
+        f"{OLS_API}/ontologies/{ontology}/terms/{encoded_iri}/descendants"
+    )
+
+    hierarchy = {"ancestors": [], "descendants": []}
+
+    if anc_resp.status_code == 200:
+        for t in anc_resp.json().get("_embedded", {}).get("terms", []):
+            hierarchy["ancestors"].append({
+                "id": t.get("obo_id", ""),
+                "label": t.get("label", ""),
+            })
+
+    if desc_resp.status_code == 200:
+        for t in desc_resp.json().get("_embedded", {}).get("terms", []):
+            hierarchy["descendants"].append({
+                "id": t.get("obo_id", ""),
+                "label": t.get("label", ""),
+            })
+
+    print(f"OLS hierarchy {term_id}: "
+          f"{len(hierarchy['ancestors'])} ancestors, "
+          f"{len(hierarchy['descendants'])} descendants")
+    return hierarchy
+```
+
+## 3. Enrichr 遺伝子セット濃縮解析
+
+```python
+ENRICHR_API = "https://maayanlab.cloud/Enrichr"
+
+
+def run_enrichr(gene_list, description="", gene_set_libraries=None):
+    """
+    Enrichr 遺伝子リスト濃縮解析。
+
+    Parameters:
+        gene_list: list — 遺伝子シンボルリスト (e.g., ["TP53", "BRCA1", "EGFR"])
+        description: str — 解析の説明
+        gene_set_libraries: list — 使用する遺伝子セットライブラリ
+
+    ToolUniverse:
+        Enrichr_submit_gene_list(genes=gene_list)
+        Enrichr_get_enrichment(user_list_id=id, library=library)
+    """
+    if gene_set_libraries is None:
+        gene_set_libraries = [
+            "GO_Biological_Process_2023",
+            "GO_Molecular_Function_2023",
+            "KEGG_2021_Human",
+            "Reactome_2022",
+            "WikiPathway_2023_Human",
+            "DisGeNET",
+        ]
+
+    # Submit gene list
+    genes_str = "\n".join(gene_list)
+    submit_resp = requests.post(
+        f"{ENRICHR_API}/addList",
+        files={"list": (None, genes_str), "description": (None, description)},
+    )
+    submit_resp.raise_for_status()
+    user_list_id = submit_resp.json().get("userListId")
+    print(f"Enrichr: submitted {len(gene_list)} genes (ID={user_list_id})")
+
+    # Get enrichment results per library
+    all_results = {}
+    for library in gene_set_libraries:
+        enrich_resp = requests.get(
+            f"{ENRICHR_API}/enrich",
+            params={"userListId": user_list_id, "backgroundType": library},
+        )
+        enrich_resp.raise_for_status()
+        data = enrich_resp.json()
+
+        results = []
+        for term_data in data.get(library, []):
+            results.append({
+                "rank": term_data[0],
+                "term": term_data[1],
+                "p_value": term_data[2],
+                "z_score": term_data[3],
+                "combined_score": term_data[4],
+                "overlap_genes": term_data[5],
+                "adjusted_p": term_data[6],
+            })
+
+        df = pd.DataFrame(results)
+        if not df.empty:
+            df = df.sort_values("adjusted_p")
+        all_results[library] = df
+        sig_count = (df["adjusted_p"] < 0.05).sum() if not df.empty else 0
+        print(f"  {library}: {sig_count} significant terms (FDR < 0.05)")
+
+    return all_results
+```
+
+## 4. UMLS メタシソーラスマッピング
+
+```python
+UMLS_API = "https://uts-ws.nlm.nih.gov/rest"
+
+
+def search_umls(query, api_key, search_type="words"):
+    """
+    UMLS メタシソーラス検索。
+
+    Parameters:
+        query: str — 検索語 (疾患名、症状、薬剤名)
+        api_key: str — UMLS API キー
+        search_type: str — "words", "exact", "leftTruncation"
+
+    ToolUniverse:
+        UMLS_search(query=query, search_type=search_type)
+        UMLS_get_concept(cui=cui)
+    """
+    params = {
+        "string": query,
+        "searchType": search_type,
+        "apiKey": api_key,
+        "pageSize": 25,
+    }
+    resp = requests.get(f"{UMLS_API}/search/current", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("result", {}).get("results", []):
+        results.append({
+            "cui": item.get("ui", ""),
+            "name": item.get("name", ""),
+            "root_source": item.get("rootSource", ""),
+            "uri": item.get("uri", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"UMLS search '{query}': {len(df)} concepts")
+    return df
+
+
+def get_umls_crosswalk(cui, api_key, target_source=None):
+    """
+    UMLS CUI からの用語体系間マッピング。
+
+    Parameters:
+        cui: str — UMLS CUI (e.g., "C0023264")
+        api_key: str — UMLS API キー
+        target_source: str — ターゲット用語体系 (e.g., "SNOMEDCT_US", "ICD10CM", "MeSH")
+    """
+    params = {"apiKey": api_key, "pageSize": 100}
+    if target_source:
+        params["sabs"] = target_source
+
+    resp = requests.get(f"{UMLS_API}/content/current/CUI/{cui}/atoms", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    mappings = []
+    for atom in data.get("result", []):
+        mappings.append({
+            "source": atom.get("rootSource", ""),
+            "code": atom.get("sourceConcept", ""),
+            "name": atom.get("name", ""),
+            "term_type": atom.get("termType", ""),
+        })
+
+    df = pd.DataFrame(mappings)
+    if target_source:
+        df = df[df["source"] == target_source]
+
+    print(f"UMLS crosswalk {cui}: {len(df)} mappings "
+          f"({target_source or 'all sources'})")
+    return df
+```
+
+---
+
+## 利用可能ツール
+
+| ToolUniverse カテゴリ | 主なツール |
+|---|---|
+| `efo` | `EFO_search` |
+| `ols` | `OLS_search`, `OLS_get_term`, `OLS_get_ancestors` |
+| `enrichr` | `Enrichr_submit_gene_list`, `Enrichr_get_enrichment` |
+| `umls` | `UMLS_search`, `UMLS_get_concept` |
+
+## パイプライン出力
+
+| 出力ファイル | 説明 | 連携先スキル |
+|---|---|---|
+| `results/efo_terms.csv` | EFO 標準化用語 | → disease-research, gene-expression |
+| `results/enrichr_results/` | 遺伝子セット濃縮結果 | → pathway-enrichment, multi-omics |
+| `results/umls_mapping.json` | UMLS 用語マッピング | → clinical-decision-support, public-health-data |
+| `results/ontology_hierarchy.json` | オントロジー階層 | → text-mining-nlp, knowledge-graph |
+
+## パイプライン統合
+
+```
+disease-research ──→ ontology-enrichment ──→ pathway-enrichment
+  (GWAS/DisGeNET)    (EFO/OLS/UMLS/Enrichr)   (KEGG/Reactome/GO)
+                              │
+                              ├──→ biothings-idmapping (CUI→Gene→Protein)
+                              ├──→ public-health-data (UMLS→RxNorm)
+                              └──→ clinical-reporting (SNOMED/ICD マッピング)
+```