@nahisaho/satori 0.18.0 → 0.19.0

package/src/.github/skills/scientific-depmap-dependencies/SKILL.md

@@ -0,0 +1,239 @@
+---
+name: scientific-depmap-dependencies
+description: |
+  DepMap 依存性スキル。Cancer Dependency Map (DepMap) Portal
+  API によるがん細胞株 CRISPR/RNAi 依存性スコア・薬剤
+  感受性データ・遺伝子効果取得。ToolUniverse 連携: depmap。
+tu_tools:
+  - key: depmap
+    name: DepMap
+    description: がん細胞株依存性マップ API
+---
+
+# Scientific DepMap Dependencies
+
+Cancer Dependency Map (DepMap) Portal API を活用した
+がん細胞株の CRISPR/RNAi 遺伝子依存性スコア取得・
+薬剤感受性データ・遺伝子効果パイプラインを提供する。
+
+## When to Use
+
+- がん細胞株の遺伝子依存性 (CRISPR/RNAi) を調べるとき
+- 遺伝子のがん選択的必須性を評価するとき
+- 薬剤感受性データと遺伝子発現の相関を調べるとき
+- 細胞株メタデータ (組織型・疾患サブタイプ) を取得するとき
+- Cell Model Passports データを参照するとき
+
+---
+
+## Quick Start
+
+## 1. DepMap 細胞株検索・メタデータ
+
+```python
+import requests
+import pandas as pd
+
+DEPMAP_API = "https://api.cellmodelpassports.sanger.ac.uk/v1"
+
+
+def depmap_cell_lines(tissue=None, cancer_type=None,
+                         limit=50):
+    """
+    DepMap / Cell Model Passports — 細胞株検索。
+
+    Parameters:
+        tissue: str — 組織型フィルタ (例: "Breast")
+        cancer_type: str — がん種フィルタ
+            (例: "Breast Carcinoma")
+        limit: int — 最大結果数
+    """
+    url = f"{DEPMAP_API}/models"
+    params = {"page_size": limit}
+    if tissue:
+        params["tissue"] = tissue
+    if cancer_type:
+        params["cancer_type"] = cancer_type
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    rows = []
+    for model in data.get("data", data
+                          if isinstance(data, list)
+                          else []):
+        if isinstance(model, dict):
+            rows.append({
+                "model_id": model.get("model_id", ""),
+                "model_name": model.get("model_name", ""),
+                "tissue": model.get("tissue", ""),
+                "cancer_type": model.get(
+                    "cancer_type", ""),
+                "sample_site": model.get(
+                    "sample_site", ""),
+                "gender": model.get("gender", ""),
+            })
+
+    df = pd.DataFrame(rows[:limit])
+    print(f"DepMap cell lines: {len(df)} models")
+    return df
+```
+
+## 2. CRISPR 遺伝子依存性スコア
+
+```python
+def depmap_gene_dependency(gene_symbol,
+                              dataset="Chronos_Combined"):
+    """
+    DepMap — 遺伝子依存性スコア取得。
+
+    Parameters:
+        gene_symbol: str — 遺伝子シンボル (例: "KRAS")
+        dataset: str — データセット名
+            (例: "Chronos_Combined", "RNAi_merged")
+    """
+    # DepMap Public Portal download URL
+    DEPMAP_PORTAL = "https://depmap.org/portal/api"
+
+    url = f"{DEPMAP_PORTAL}/dataset/search"
+    params = {"gene": gene_symbol,
+              "dataset": dataset}
+
+    try:
+        resp = requests.get(url, params=params,
+                            timeout=30)
+        resp.raise_for_status()
+        data = resp.json()
+    except Exception:
+        # Fallback: alternative DepMap API
+        print(f"  DepMap portal fallback for "
+              f"{gene_symbol}")
+        data = []
+
+    rows = []
+    if isinstance(data, list):
+        for entry in data:
+            if isinstance(entry, dict):
+                rows.append({
+                    "gene": gene_symbol,
+                    "cell_line": entry.get(
+                        "cell_line_name", ""),
+                    "depmap_id": entry.get(
+                        "depmap_id", ""),
+                    "dependency_score": entry.get(
+                        "dependency", 0),
+                    "dataset": dataset,
+                })
+
+    df = pd.DataFrame(rows)
+    if not df.empty:
+        df = df.sort_values("dependency_score")
+    print(f"DepMap dependency: {gene_symbol} "
+          f"→ {len(df)} cell lines")
+    return df
+```
+
+## 3. 薬剤感受性データ
+
+```python
+def depmap_drug_sensitivity(compound_name=None,
+                               limit=100):
+    """
+    DepMap — 薬剤感受性データ取得。
+
+    Parameters:
+        compound_name: str — 化合物名フィルタ
+            (例: "Paclitaxel")
+        limit: int — 最大結果数
+    """
+    url = f"{DEPMAP_API}/drugs"
+    params = {"page_size": limit}
+    if compound_name:
+        params["name"] = compound_name
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    rows = []
+    for drug in data.get("data", data
+                         if isinstance(data, list)
+                         else []):
+        if isinstance(drug, dict):
+            rows.append({
+                "drug_id": drug.get("drug_id", ""),
+                "drug_name": drug.get("drug_name", ""),
+                "target": drug.get("target", ""),
+                "pathway": drug.get("pathway", ""),
+                "n_cell_lines": drug.get(
+                    "n_cell_lines_tested", 0),
+            })
+
+    df = pd.DataFrame(rows[:limit])
+    print(f"DepMap drugs: {len(df)} compounds")
+    return df
+```
+
+## 4. DepMap 統合パイプライン
+
+```python
+def depmap_pipeline(gene_symbol,
+                       output_dir="results"):
+    """
+    DepMap 統合パイプライン。
+
+    Parameters:
+        gene_symbol: str — 遺伝子シンボル
+        output_dir: str — 出力ディレクトリ
+    """
+    from pathlib import Path
+    output_dir = Path(output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    # 1) 遺伝子依存性
+    deps = depmap_gene_dependency(gene_symbol)
+    deps.to_csv(output_dir / "depmap_dependency.csv",
+                index=False)
+
+    # 2) 関連薬剤
+    drugs = depmap_drug_sensitivity()
+    drugs.to_csv(output_dir / "depmap_drugs.csv",
+                 index=False)
+
+    # 3) 依存性の高い細胞株
+    if not deps.empty:
+        top_dependent = deps.head(10)
+        top_dependent.to_csv(
+            output_dir / "depmap_top_dependent.csv",
+            index=False)
+
+    print(f"DepMap pipeline: {gene_symbol} → {output_dir}")
+    return {"dependency": deps, "drugs": drugs}
+```
+
+---
+
+## ToolUniverse 連携
+
+| TU Key | ツール名 | 連携内容 |
+|--------|---------|---------|
+| `depmap` | DepMap | がん細胞株依存性マップ API |
+
+## パイプライン統合
+
+```
+cancer-genomics → depmap-dependencies → precision-oncology
+  (がんゲノム)       (DepMap Portal)     (精密腫瘍学)
+        │                  │                  ↓
+expression-analysis ──────┘       drug-target-profiling
+  (発現リスト)                    (標的プロファイリング)
+```
+
+## パイプライン出力
+
+| ファイル | 説明 | 次スキル |
+|---------|------|---------|
+| `results/depmap_dependency.csv` | 依存性スコア | → cancer-genomics |
+| `results/depmap_drugs.csv` | 薬剤感受性 | → drug-target-profiling |
+| `results/depmap_top_dependent.csv` | 依存細胞株 | → precision-oncology |

package/src/.github/skills/scientific-disease-research/SKILL.md

@@ -5,6 +5,10 @@ description: |
   疾患-遺伝子関連解析・希少疾患診断支援・表現型-遺伝型マッピング・
   疫学的特性評価を支援。
   「疾患と遺伝子の関連を調べて」「希少疾患を診断して」「GWAS 結果を解析して」で発火。
+tu_tools:
+  - key: disgenet
+    name: DisGeNET
+    description: 疾患-遺伝子関連スコア (GDA) データベース
 ---
 
 # Scientific Disease Research

package/src/.github/skills/scientific-drugbank-resources/SKILL.md

@@ -0,0 +1,269 @@
+---
+name: scientific-drugbank-resources
+description: |
+  DrugBank リソーススキル。DrugBank API を用いた薬剤記述・
+  薬理情報・標的タンパク質・薬物相互作用検索。
+  ToolUniverse 連携: drugbank。
+tu_tools:
+  - key: drugbank
+    name: DrugBank
+    description: 薬剤データベース API
+---
+
+# Scientific DrugBank Resources
+
+DrugBank API を活用した薬剤記述・薬理情報 (MOA)・標的タンパク質
+検索・薬物相互作用 (DDI) パイプラインを提供する。
+
+## When to Use
+
+- 薬剤の基本情報 (名前・分類・構造) を検索するとき
+- 薬理メカニズム (MOA) を調べるとき
+- 標的タンパク質から薬剤を逆引き検索するとき
+- 薬物相互作用 (DDI) を確認するとき
+- 薬剤の ADMET プロパティを取得するとき
+
+---
+
+## Quick Start
+
+## 1. 薬剤検索・基本情報
+
+```python
+import requests
+import pandas as pd
+
+DRUGBANK_API = "https://api.drugbank.com/v1"
+
+
+def drugbank_search(query, limit=25, api_key=None):
+    """
+    DrugBank — 薬剤テキスト検索。
+
+    Parameters:
+        query: str — 検索クエリ (例: "imatinib")
+        limit: int — 最大結果数
+        api_key: str — DrugBank API キー
+    """
+    headers = {}
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+
+    url = f"{DRUGBANK_API}/drugs"
+    params = {"q": query, "per_page": limit}
+    resp = requests.get(url, params=params,
+                        headers=headers, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    rows = []
+    for d in data:
+        rows.append({
+            "drugbank_id": d.get("drugbank_id", ""),
+            "name": d.get("name", ""),
+            "cas_number": d.get("cas_number", ""),
+            "drug_type": d.get("type", ""),
+            "state": d.get("state", ""),
+            "description": (d.get("description", "")
+                            [:200]),
+        })
+
+    df = pd.DataFrame(rows)
+    print(f"DrugBank search: '{query}' → {len(df)} drugs")
+    return df
+
+
+def drugbank_drug_detail(drugbank_id, api_key=None):
+    """
+    DrugBank — 薬剤詳細取得。
+
+    Parameters:
+        drugbank_id: str — DrugBank ID (例: "DB01254")
+        api_key: str — DrugBank API キー
+    """
+    headers = {}
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+
+    url = f"{DRUGBANK_API}/drugs/{drugbank_id}"
+    resp = requests.get(url, headers=headers, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    result = {
+        "drugbank_id": data.get("drugbank_id", ""),
+        "name": data.get("name", ""),
+        "description": data.get("description", ""),
+        "indication": data.get("indication", ""),
+        "pharmacodynamics": data.get(
+            "pharmacodynamics", ""),
+        "mechanism_of_action": data.get(
+            "mechanism_of_action", ""),
+        "absorption": data.get("absorption", ""),
+        "half_life": data.get("half_life", ""),
+        "protein_binding": data.get(
+            "protein_binding", ""),
+        "molecular_weight": data.get(
+            "average_molecular_weight", ""),
+    }
+    return result
+```
+
+## 2. 標的タンパク質検索
+
+```python
+def drugbank_targets(drugbank_id, api_key=None):
+    """
+    DrugBank — 薬剤の標的タンパク質取得。
+
+    Parameters:
+        drugbank_id: str — DrugBank ID
+        api_key: str — DrugBank API キー
+    """
+    headers = {}
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+
+    url = f"{DRUGBANK_API}/drugs/{drugbank_id}/targets"
+    resp = requests.get(url, headers=headers, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    rows = []
+    for t in data:
+        polypeptide = t.get("polypeptide", {}) or {}
+        rows.append({
+            "drugbank_id": drugbank_id,
+            "target_name": t.get("name", ""),
+            "organism": t.get("organism", ""),
+            "known_action": t.get("known_action", ""),
+            "gene_name": polypeptide.get(
+                "gene_name", ""),
+            "uniprot_id": polypeptide.get(
+                "external_identifiers", {}).get(
+                "UniProtKB", ""),
+        })
+
+    df = pd.DataFrame(rows)
+    print(f"DrugBank targets: {drugbank_id} "
+          f"→ {len(df)} targets")
+    return df
+```
+
+## 3. 薬物相互作用 (DDI)
+
+```python
+def drugbank_interactions(drugbank_id, api_key=None):
+    """
+    DrugBank — 薬物相互作用取得。
+
+    Parameters:
+        drugbank_id: str — DrugBank ID
+        api_key: str — DrugBank API キー
+    """
+    headers = {}
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+
+    url = (f"{DRUGBANK_API}/drugs/"
+           f"{drugbank_id}/drug_interactions")
+    resp = requests.get(url, headers=headers, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    rows = []
+    for inter in data:
+        rows.append({
+            "drug_a": drugbank_id,
+            "drug_b_id": inter.get(
+                "drugbank_id", ""),
+            "drug_b_name": inter.get("name", ""),
+            "description": inter.get(
+                "description", "")[:300],
+        })
+
+    df = pd.DataFrame(rows)
+    print(f"DrugBank DDI: {drugbank_id} "
+          f"→ {len(df)} interactions")
+    return df
+```
+
+## 4. DrugBank 統合パイプライン
+
+```python
+def drugbank_pipeline(drug_name, api_key=None,
+                         output_dir="results"):
+    """
+    DrugBank 統合パイプライン。
+
+    Parameters:
+        drug_name: str — 薬剤名 (例: "imatinib")
+        api_key: str — DrugBank API キー
+        output_dir: str — 出力ディレクトリ
+    """
+    from pathlib import Path
+    output_dir = Path(output_dir)
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    # 1) 検索
+    results = drugbank_search(drug_name,
+                              api_key=api_key)
+    results.to_csv(output_dir / "drugbank_search.csv",
+                   index=False)
+
+    if results.empty:
+        print(f"DrugBank: '{drug_name}' not found")
+        return {"search": results}
+
+    db_id = results.iloc[0]["drugbank_id"]
+
+    # 2) 詳細
+    detail = drugbank_drug_detail(db_id,
+                                  api_key=api_key)
+    pd.DataFrame([detail]).to_csv(
+        output_dir / "drugbank_detail.csv",
+        index=False)
+
+    # 3) 標的
+    targets = drugbank_targets(db_id,
+                               api_key=api_key)
+    targets.to_csv(output_dir / "drugbank_targets.csv",
+                   index=False)
+
+    # 4) DDI
+    ddi = drugbank_interactions(db_id,
+                                api_key=api_key)
+    ddi.to_csv(output_dir / "drugbank_ddi.csv",
+               index=False)
+
+    print(f"DrugBank pipeline: {drug_name} → {output_dir}")
+    return {"detail": detail, "targets": targets,
+            "ddi": ddi}
+```
+
+---
+
+## ToolUniverse 連携
+
+| TU Key | ツール名 | 連携内容 |
+|--------|---------|---------|
+| `drugbank` | DrugBank | 薬剤データベース API |
+
+## パイプライン統合
+
+```
+drug-target-profiling → drugbank-resources → admet-pharmacokinetics
+  (標的プロファイリング)   (DrugBank API)     (ADMET 予測)
+          │                     │                  ↓
+opentargets-genetics ──────────┘       compound-screening
+  (OT 薬剤エビデンス)                  (ZINC 化合物検索)
+```
+
+## パイプライン出力
+
+| ファイル | 説明 | 次スキル |
+|---------|------|---------|
+| `results/drugbank_search.csv` | 薬剤検索結果 | → drug-target-profiling |
+| `results/drugbank_detail.csv` | 薬剤詳細 | → admet-pharmacokinetics |
+| `results/drugbank_targets.csv` | 標的タンパク質 | → protein-interaction-network |
+| `results/drugbank_ddi.csv` | 薬物相互作用 | → pharmacogenomics |