@nahisaho/satori 0.12.0 → 0.14.0

package/src/.github/skills/scientific-public-health-data/SKILL.md

@@ -0,0 +1,322 @@
+---
+name: scientific-public-health-data
+description: |
+  公衆衛生データアクセススキル。NHANES 疫学調査データ、MedlinePlus 一般向け
+  健康情報、RxNorm 薬剤標準語彙、ODPHP 健康目標・ガイドライン、
+  Health Disparities 健康格差データ統合パイプライン。
+---
+
+# Scientific Public Health Data
+
+NHANES / MedlinePlus / RxNorm / ODPHP / Health Disparities /
+Guidelines を統合した公衆衛生データアクセスパイプラインを提供する。
+
+## When to Use
+
+- NHANES 疫学調査データ (検査値・アンケート) を取得するとき
+- MedlinePlus で一般向け健康情報を検索するとき
+- RxNorm で薬剤名の標準化・マッピングを行うとき
+- ODPHP Healthy People 目標や健康ガイドラインを参照するとき
+- 健康格差 (Health Disparities) データを分析するとき
+- 臨床ガイドライン (USPSTF/WHO) を検索するとき
+
+---
+
+## Quick Start
+
+## 1. NHANES 疫学調査データ取得
+
+```python
+import requests
+import pandas as pd
+import io
+
+NHANES_BASE = "https://wwwn.cdc.gov/nchs/nhanes"
+
+
+def get_nhanes_dataset(cycle, dataset_name):
+    """
+    NHANES データセット (XPT/SAS 形式) 取得。
+
+    Parameters:
+        cycle: str — 調査サイクル (e.g., "2017-2018", "2019-2020")
+        dataset_name: str — データセット名 (e.g., "DEMO_J", "BIOPRO_J")
+
+    ToolUniverse:
+        NHANES_get_dataset(cycle=cycle, dataset=dataset_name)
+        NHANES_list_datasets(cycle=cycle)
+    """
+    cycle_code = cycle.replace("-", "_")
+    url = f"{NHANES_BASE}/search/DataPage.aspx"
+
+    # XPT ファイルの直接ダウンロード
+    xpt_url = f"https://wwwn.cdc.gov/Nchs/Nhanes/{cycle}/{dataset_name}.XPT"
+    resp = requests.get(xpt_url)
+    resp.raise_for_status()
+
+    df = pd.read_sas(io.BytesIO(resp.content), format="xport")
+    print(f"NHANES {cycle} {dataset_name}: {df.shape[0]} rows × {df.shape[1]} columns")
+    return df
+
+
+def search_nhanes_variables(keyword):
+    """
+    NHANES 変数検索。
+
+    Parameters:
+        keyword: str — 変数名/説明の検索語
+
+    ToolUniverse:
+        NHANES_search_variables(keyword=keyword)
+    """
+    url = f"{NHANES_BASE}/search/variablelist.aspx"
+    params = {"SearchTarget": keyword}
+    resp = requests.get(url, params=params)
+    resp.raise_for_status()
+
+    print(f"NHANES variable search '{keyword}': response received")
+    return resp.text
+```
+
+## 2. MedlinePlus 健康情報検索
+
+```python
+MEDLINEPLUS_API = "https://connect.medlineplus.gov/service"
+MEDLINEPLUS_WS = "https://wsearch.nlm.nih.gov/ws/query"
+
+
+def search_medlineplus_health_topics(query, language="English"):
+    """
+    MedlinePlus 健康トピック検索。
+
+    ToolUniverse:
+        MedlinePlus_search_health_topics(query=query)
+        MedlinePlus_get_health_topic(topic_id=topic_id)
+        MedlinePlus_search_drugs(query=query)
+        MedlinePlus_search_labs(query=query)
+        MedlinePlus_connect(code=code, code_system=system)
+    """
+    params = {
+        "db": "healthTopics",
+        "term": query,
+    }
+    resp = requests.get(MEDLINEPLUS_WS, params=params)
+    resp.raise_for_status()
+
+    # XML response parsing
+    import xml.etree.ElementTree as ET
+    root = ET.fromstring(resp.text)
+
+    results = []
+    for doc in root.findall(".//document"):
+        results.append({
+            "title": doc.find(".//content[@name='title']").text
+            if doc.find(".//content[@name='title']") is not None else "",
+            "url": doc.get("url", ""),
+            "summary": doc.find(".//content[@name='FullSummary']").text[:300]
+            if doc.find(".//content[@name='FullSummary']") is not None else "",
+            "rank": doc.get("rank", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"MedlinePlus search '{query}': {len(df)} health topics")
+    return df
+```
+
+## 3. RxNorm 薬剤標準語彙
+
+```python
+RXNORM_API = "https://rxnav.nlm.nih.gov/REST"
+
+
+def rxnorm_lookup(drug_name):
+    """
+    RxNorm 薬剤名正規化・コードマッピング。
+
+    Parameters:
+        drug_name: str — 薬剤名 (商品名 or 一般名)
+
+    ToolUniverse:
+        RxNorm_get_rxcui(name=drug_name)
+    """
+    resp = requests.get(
+        f"{RXNORM_API}/rxcui.json",
+        params={"name": drug_name}
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    rxcui = data.get("idGroup", {}).get("rxnormId", [None])[0]
+    if not rxcui:
+        print(f"RxNorm: '{drug_name}' not found")
+        return None
+
+    # Get properties
+    props_resp = requests.get(f"{RXNORM_API}/rxcui/{rxcui}/properties.json")
+    props_resp.raise_for_status()
+    props = props_resp.json().get("properties", {})
+
+    # Get related concepts
+    related_resp = requests.get(
+        f"{RXNORM_API}/rxcui/{rxcui}/related.json",
+        params={"tty": "IN+BN+SBD+SCD"}
+    )
+    related_resp.raise_for_status()
+    related = related_resp.json()
+
+    result = {
+        "rxcui": rxcui,
+        "name": props.get("name", ""),
+        "tty": props.get("tty", ""),
+        "synonym": props.get("synonym", ""),
+        "related_concepts": [
+            {
+                "rxcui": c.get("rxcui"),
+                "name": c.get("name"),
+                "tty": c.get("tty"),
+            }
+            for group in related.get("relatedGroup", {}).get("conceptGroup", [])
+            for c in group.get("conceptProperties", [])
+        ],
+    }
+    print(f"RxNorm '{drug_name}': RXCUI={rxcui}, TTY={result['tty']}")
+    return result
+```
+
+## 4. Health Disparities データ取得
+
+```python
+HD_API = "https://data.cdc.gov/resource"
+
+
+def get_health_disparities(indicator, dataset_id="pqnx-3xr5"):
+    """
+    CDC 健康格差データ取得。
+
+    Parameters:
+        indicator: str — 健康指標名
+        dataset_id: str — CDC Socrata データセット ID
+
+    ToolUniverse:
+        HealthDisparities_search(query=indicator)
+        HealthDisparities_get_indicators(category=category)
+    """
+    params = {
+        "$where": f"indicator LIKE '%{indicator}%'",
+        "$limit": 1000,
+    }
+    resp = requests.get(f"{HD_API}/{dataset_id}.json", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    df = pd.DataFrame(data)
+    print(f"Health Disparities '{indicator}': {len(df)} records")
+    return df
+```
+
+## 5. ODPHP 健康ガイドライン
+
+```python
+ODPHP_API = "https://health.gov/myhealthfinder/api/v3"
+
+
+def search_health_guidelines(keyword, category=None):
+    """
+    ODPHP MyHealthfinder ガイドライン検索。
+
+    ToolUniverse:
+        ODPHP_search_topics(keyword=keyword)
+        ODPHP_get_topic(topic_id=topic_id)
+    """
+    params = {"keyword": keyword}
+    if category:
+        params["categoryId"] = category
+    resp = requests.get(f"{ODPHP_API}/topicsearch.json", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for topic in data.get("Result", {}).get("Resources", {}).get("Resource", []):
+        results.append({
+            "title": topic.get("Title", ""),
+            "categories": topic.get("Categories", ""),
+            "url": topic.get("AccessibleVersion", ""),
+            "sections": [
+                s.get("Title", "") for s in topic.get("Sections", {}).get("section", [])
+            ],
+        })
+
+    df = pd.DataFrame(results)
+    print(f"ODPHP search '{keyword}': {len(df)} guidelines")
+    return df
+```
+
+## 6. 臨床ガイドライン検索 (USPSTF)
+
+```python
+def search_clinical_guidelines(query, source="uspstf"):
+    """
+    USPSTF/WHO 臨床ガイドライン検索。
+
+    ToolUniverse:
+        Guidelines_search(query=query, source=source)
+        Guidelines_get_recommendations(topic_id=topic_id)
+    """
+    sources = {
+        "uspstf": "https://www.uspreventiveservicestaskforce.org/uspstf/api",
+        "who": "https://app.magicapp.org/api",
+    }
+    base_url = sources.get(source, sources["uspstf"])
+
+    resp = requests.get(f"{base_url}/search", params={"q": query})
+    if resp.status_code == 200:
+        data = resp.json()
+        results = []
+        for item in data.get("results", []):
+            results.append({
+                "title": item.get("title", ""),
+                "grade": item.get("grade", ""),
+                "population": item.get("population", ""),
+                "date": item.get("date", ""),
+                "recommendation": item.get("recommendation", ""),
+            })
+        df = pd.DataFrame(results)
+    else:
+        df = pd.DataFrame()
+
+    print(f"Guidelines ({source}) search '{query}': {len(df)} recommendations")
+    return df
+```
+
+---
+
+## 利用可能ツール
+
+| ToolUniverse カテゴリ | 主なツール |
+|---|---|
+| `nhanes` | `NHANES_get_dataset`, `NHANES_list_datasets`, `NHANES_search_variables` |
+| `health_disparities` | `HealthDisparities_search`, `HealthDisparities_get_indicators` |
+| `medlineplus` | `MedlinePlus_search_health_topics`, `MedlinePlus_get_health_topic`, `MedlinePlus_search_drugs`, `MedlinePlus_search_labs`, `MedlinePlus_connect` |
+| `odphp` | `ODPHP_search_topics`, `ODPHP_get_topic` |
+| `rxnorm` | `RxNorm_get_rxcui` |
+| `guidelines_tools` | `Guidelines_search`, `Guidelines_get_recommendations` |
+
+## パイプライン出力
+
+| 出力ファイル | 説明 | 連携先スキル |
+|---|---|---|
+| `results/nhanes_data.csv` | NHANES 疫学データ | → epidemiology-public-health, survival-clinical |
+| `results/drug_mapping.json` | RxNorm 薬剤マッピング | → pharmacovigilance, pharmacogenomics |
+| `results/health_guidelines.json` | 臨床ガイドライン | → clinical-decision-support |
+| `results/health_disparities.csv` | 健康格差指標 | → epidemiology-public-health, causal-inference |
+
+## パイプライン統合
+
+```
+epidemiology-public-health ──→ public-health-data ──→ clinical-decision-support
+  (RR/OR/DAG)                  (NHANES/CDC/ODPHP)    (GRADE エビデンス)
+                                      │
+                                      ├──→ pharmacovigilance (RxNorm + 安全性)
+                                      ├──→ pharmacogenomics (RxNorm + PGx)
+                                      └──→ survival-clinical (NHANES コホート)
+```

package/src/.github/skills/scientific-rare-disease-genetics/SKILL.md

@@ -0,0 +1,327 @@
+---
+name: scientific-rare-disease-genetics
+description: |
+  希少疾患遺伝学スキル。OMIM 遺伝子-疾患マッピング、Orphanet 希少疾患
+  分類・遺伝子照会、DisGeNET 疾患-遺伝子関連スコア、IMPC マウス表現型
+  参照、遺伝子-表現型統合解析パイプライン。
+---
+
+# Scientific Rare Disease Genetics
+
+OMIM / Orphanet / DisGeNET / IMPC を統合した
+希少疾患遺伝学パイプラインを提供する。
+
+## When to Use
+
+- 希少疾患の原因遺伝子を同定するとき
+- OMIM で遺伝子-疾患の Mendelian 関連を調べるとき
+- Orphanet で希少疾患分類や有病率を検索するとき
+- DisGeNET で疾患-遺伝子関連スコア (GDA) を取得するとき
+- IMPC マウスノックアウト表現型と比較するとき
+
+---
+
+## Quick Start
+
+## 1. OMIM 遺伝子-疾患マッピング
+
+```python
+import requests
+import pandas as pd
+
+OMIM_API = "https://api.omim.org/api"
+
+
+def search_omim(query, api_key, include="geneMap"):
+    """
+    OMIM データベース検索。
+
+    Parameters:
+        query: str — 検索語 (遺伝子名、疾患名)
+        api_key: str — OMIM API キー
+        include: str — "geneMap", "clinicalSynopsis", "all"
+
+    ToolUniverse:
+        OMIM_search(query=query)
+        OMIM_get_entry(mim_number=mim_number)
+        OMIM_get_gene_map(gene_symbol=gene_symbol)
+        OMIM_get_clinical_synopsis(mim_number=mim_number)
+    """
+    params = {
+        "search": query,
+        "include": include,
+        "format": "json",
+        "apiKey": api_key,
+    }
+    resp = requests.get(f"{OMIM_API}/entry/search", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    entries = data.get("omim", {}).get("searchResponse", {}).get("entryList", [])
+    results = []
+    for entry in entries:
+        e = entry.get("entry", {})
+        gene_map = e.get("geneMap", {})
+        results.append({
+            "mim_number": e.get("mimNumber"),
+            "title": e.get("titles", {}).get("preferredTitle", ""),
+            "gene_symbols": gene_map.get("geneSymbols", ""),
+            "chromosome": gene_map.get("computedCytoLocation", ""),
+            "phenotypes": [
+                p.get("phenotype", "")
+                for p in gene_map.get("phenotypeMapList", [])
+            ],
+            "inheritance": [
+                p.get("phenotypeMappingKey", "")
+                for p in gene_map.get("phenotypeMapList", [])
+            ],
+        })
+
+    df = pd.DataFrame(results)
+    print(f"OMIM search '{query}': {len(df)} entries")
+    return df
+```
+
+## 2. Orphanet 希少疾患分類
+
+```python
+ORPHANET_API = "https://api.orphadata.com"
+
+
+def search_orphanet_diseases(query):
+    """
+    Orphanet 希少疾患検索。
+
+    ToolUniverse:
+        Orphanet_search_diseases(query=query)
+        Orphanet_search_by_name(name=query)
+        Orphanet_get_disease(orpha_code=code)
+        Orphanet_get_genes(orpha_code=code)
+        Orphanet_get_classification(orpha_code=code)
+    """
+    resp = requests.get(
+        f"{ORPHANET_API}/rd-cross-referencing",
+        params={"query": query}
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data if isinstance(data, list) else [data]:
+        results.append({
+            "orpha_code": item.get("ORPHAcode", ""),
+            "name": item.get("Preferred term", ""),
+            "prevalence_class": item.get("Prevalence", {}).get("PrevalenceClass", ""),
+            "inheritance": item.get("TypeOfInheritance", []),
+            "age_of_onset": item.get("AgeOfOnset", []),
+            "genes": item.get("DisorderGeneAssociationList", []),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"Orphanet search '{query}': {len(df)} diseases")
+    return df
+```
+
+## 3. DisGeNET 疾患-遺伝子関連スコア
+
+```python
+DISGENET_API = "https://www.disgenet.org/api"
+
+
+def get_disease_gene_associations(disease_id, api_key):
+    """
+    DisGeNET GDA スコアによる疾患-遺伝子関連取得。
+
+    Parameters:
+        disease_id: str — UMLS CUI (e.g., "C0023264") or disease name
+        api_key: str — DisGeNET API key
+
+    ToolUniverse:
+        DisGeNET_search_disease(query=disease_id)
+        DisGeNET_get_disease_genes(disease_id=disease_id)
+        DisGeNET_search_gene(query=gene)
+        DisGeNET_get_gene_diseases(gene_symbol=gene)
+        DisGeNET_get_variant_diseases(variant_id=variant)
+    """
+    headers = {"Authorization": f"Bearer {api_key}"}
+    resp = requests.get(
+        f"{DISGENET_API}/gda/disease/{disease_id}",
+        headers=headers
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for gda in data:
+        results.append({
+            "gene_symbol": gda.get("gene_symbol", ""),
+            "gene_id": gda.get("geneid", ""),
+            "gda_score": gda.get("score", 0),
+            "ei": gda.get("ei", 0),  # Evidence Index
+            "el": gda.get("el", ""),  # Evidence Level
+            "n_pmids": gda.get("pmid_count", 0),
+            "source": gda.get("source", ""),
+        })
+
+    df = pd.DataFrame(results)
+    if not df.empty:
+        df = df.sort_values("gda_score", ascending=False)
+
+    print(f"DisGeNET '{disease_id}': {len(df)} gene associations, "
+          f"top GDA score={df['gda_score'].max():.3f}" if len(df) > 0 else "")
+    return df
+```
+
+## 4. IMPC マウス表現型参照
+
+```python
+IMPC_API = "https://www.ebi.ac.uk/mi/impc/solr"
+
+
+def get_impc_mouse_phenotypes(gene_symbol):
+    """
+    IMPC マウスノックアウト表現型データ取得。
+
+    ToolUniverse:
+        IMPC_search_genes(query=gene_symbol)
+        IMPC_get_gene_summary(gene_symbol=gene_symbol)
+        IMPC_get_phenotypes_by_gene(gene_symbol=gene_symbol)
+        IMPC_get_gene_phenotype_hits(gene_symbol=gene_symbol)
+    """
+    params = {
+        "q": f"marker_symbol:{gene_symbol}",
+        "rows": 100,
+        "wt": "json",
+    }
+    resp = requests.get(f"{IMPC_API}/genotype-phenotype/select", params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for doc in data.get("response", {}).get("docs", []):
+        results.append({
+            "gene_symbol": doc.get("marker_symbol", ""),
+            "mp_term_id": doc.get("mp_term_id", ""),
+            "mp_term_name": doc.get("mp_term_name", ""),
+            "top_level_mp": doc.get("top_level_mp_term_name", []),
+            "p_value": doc.get("p_value", None),
+            "effect_size": doc.get("effect_size", None),
+            "zygosity": doc.get("zygosity", ""),
+            "procedure_name": doc.get("procedure_name", ""),
+        })
+
+    df = pd.DataFrame(results)
+    if not df.empty and "p_value" in df.columns:
+        df = df.sort_values("p_value")
+
+    print(f"IMPC '{gene_symbol}': {len(df)} phenotype associations")
+    return df
+```
+
+## 5. 遺伝子-表現型統合解析
+
+```python
+def rare_disease_gene_analysis(gene_symbol, omim_api_key=None,
+                                 disgenet_api_key=None):
+    """
+    全 DB 統合の希少疾患遺伝子プロファイリング。
+    """
+    profile = {"gene": gene_symbol, "sources": {}}
+
+    # 1. OMIM
+    if omim_api_key:
+        try:
+            omim_df = search_omim(gene_symbol, omim_api_key)
+            profile["sources"]["omim"] = {
+                "entries": len(omim_df),
+                "phenotypes": omim_df["phenotypes"].explode().dropna().unique().tolist()
+                    if not omim_df.empty else [],
+            }
+        except Exception as e:
+            profile["sources"]["omim"] = {"error": str(e)}
+
+    # 2. Orphanet
+    try:
+        orpha_df = search_orphanet_diseases(gene_symbol)
+        profile["sources"]["orphanet"] = {
+            "diseases": len(orpha_df),
+            "names": orpha_df["name"].tolist() if not orpha_df.empty else [],
+        }
+    except Exception as e:
+        profile["sources"]["orphanet"] = {"error": str(e)}
+
+    # 3. DisGeNET
+    if disgenet_api_key:
+        try:
+            dgn_df = get_disease_gene_associations(gene_symbol, disgenet_api_key)
+            profile["sources"]["disgenet"] = {
+                "associations": len(dgn_df),
+                "max_gda_score": float(dgn_df["gda_score"].max())
+                    if not dgn_df.empty else 0,
+            }
+        except Exception as e:
+            profile["sources"]["disgenet"] = {"error": str(e)}
+
+    # 4. IMPC
+    try:
+        impc_df = get_impc_mouse_phenotypes(gene_symbol)
+        profile["sources"]["impc"] = {
+            "phenotypes": len(impc_df),
+            "top_phenotypes": impc_df["mp_term_name"].head(5).tolist()
+                if not impc_df.empty else [],
+        }
+    except Exception as e:
+        profile["sources"]["impc"] = {"error": str(e)}
+
+    n_sources = sum(1 for v in profile["sources"].values() if "error" not in v)
+    print(f"Rare disease profile '{gene_symbol}': {n_sources}/4 sources OK")
+    return profile
+```
+
+## References
+
+### Output Files
+
+| ファイル | 形式 |
+|---|---|
+| `results/omim_search.csv` | CSV |
+| `results/orphanet_diseases.csv` | CSV |
+| `results/disgenet_gda.csv` | CSV |
+| `results/impc_phenotypes.csv` | CSV |
+| `results/rare_disease_profile.json` | JSON |
+
+### 利用可能ツール
+
+| カテゴリ | 主要ツール | 用途 |
+|---|---|---|
+| OMIM | `OMIM_search` | 遺伝子/疾患検索 |
+| OMIM | `OMIM_get_entry` | MIM エントリ取得 |
+| OMIM | `OMIM_get_gene_map` | 遺伝子マップ |
+| OMIM | `OMIM_get_clinical_synopsis` | 臨床概要 |
+| Orphanet | `Orphanet_search_diseases` | 希少疾患検索 |
+| Orphanet | `Orphanet_get_disease` | 疾患詳細 |
+| Orphanet | `Orphanet_get_genes` | 関連遺伝子 |
+| Orphanet | `Orphanet_get_classification` | 分類情報 |
+| Orphanet | `Orphanet_search_by_name` | 名前検索 |
+| DisGeNET | `DisGeNET_search_disease` | 疾患検索 |
+| DisGeNET | `DisGeNET_get_disease_genes` | 疾患遺伝子 |
+| DisGeNET | `DisGeNET_get_gene_diseases` | 遺伝子疾患 |
+| DisGeNET | `DisGeNET_get_variant_diseases` | バリアント疾患 |
+| IMPC | `IMPC_search_genes` | 遺伝子検索 |
+| IMPC | `IMPC_get_gene_summary` | 遺伝子サマリー |
+| IMPC | `IMPC_get_phenotypes_by_gene` | 表現型取得 |
+| IMPC | `IMPC_get_gene_phenotype_hits` | ヒット数 |
+
+### 参照スキル
+
+| スキル | 関連 |
+|---|---|
+| `scientific-disease-research` | GWAS/Orphanet 疾患研究 |
+| `scientific-variant-interpretation` | ACMG バリアント解釈 |
+| `scientific-variant-effect-prediction` | 病原性予測 |
+| `scientific-population-genetics` | 集団遺伝学 |
+| `scientific-human-protein-atlas` | タンパク質発現 |
+
+### 依存パッケージ
+
+`requests`, `pandas`