@nahisaho/satori 0.17.0 → 0.19.0

package/src/.github/skills/scientific-gtex-tissue-expression/SKILL.md

@@ -0,0 +1,271 @@
+---
+name: scientific-gtex-tissue-expression
+description: |
+  GTEx 組織発現スキル。GTEx Portal REST API v2 による
+  組織特異的遺伝子発現パターン解析・eQTL ルックアップ・
+  多組織比較。直接 API (ToolUniverse 非連携)。
+tu_tools: []
+---
+
+# Scientific GTEx Tissue Expression
+
+GTEx (Genotype-Tissue Expression) Portal REST API v2 を活用した
+組織特異的遺伝子発現解析・eQTL 検索・多組織比較パイプライン
+を提供する。
+
+## When to Use
+
+- 遺伝子の組織特異的発現パターンを調べるとき
+- 特定組織における eQTL (発現量的形質遺伝子座) を検索するとき
+- 複数組織間で遺伝子発現レベルを比較するとき
+- TPM (Transcripts Per Million) 発現データを取得するとき
+- バリアントが遺伝子発現に与える影響を評価するとき
+- 組織間の遺伝子共発現パターンを分析するとき
+
+---
+
+## Quick Start
+
+## 1. 組織特異的遺伝子発現取得
+
+```python
+import requests
+import pandas as pd
+
+GTEX_BASE = "https://gtexportal.org/api/v2"
+
+
+def gtex_gene_expression(gene_id, tissue=None):
+    """
+    GTEx — 組織別遺伝子発現 (中央値 TPM) 取得。
+
+    Parameters:
+        gene_id: str — 遺伝子シンボル or Ensembl ID
+            (例: "BRCA1", "ENSG00000012048")
+        tissue: str — 組織 ID (None で全組織)
+            (例: "Breast_Mammary_Tissue")
+    """
+    url = f"{GTEX_BASE}/expression/medianGeneExpression"
+    params = {
+        "gencodeId": gene_id,
+        "datasetId": "gtex_v8",
+    }
+    if tissue:
+        params["tissueSiteDetailId"] = tissue
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("data", []):
+        results.append({
+            "gene_symbol": item.get("geneSymbol", ""),
+            "gencode_id": item.get("gencodeId", ""),
+            "tissue": item.get("tissueSiteDetailId", ""),
+            "tissue_name": item.get("tissueSiteDetail", ""),
+            "median_tpm": item.get("median", 0),
+            "sample_count": item.get("numSamples", 0),
+        })
+
+    df = pd.DataFrame(results)
+    if not df.empty:
+        df = df.sort_values("median_tpm", ascending=False)
+
+    print(f"GTEx expression: {gene_id} → "
+          f"{len(df)} tissues")
+    return df
+
+
+def gtex_top_tissues(gene_id, top_n=10):
+    """
+    GTEx — 発現量上位組織。
+
+    Parameters:
+        gene_id: str — 遺伝子シンボル or Ensembl ID
+        top_n: int — 上位組織数
+    """
+    df = gtex_gene_expression(gene_id)
+    top = df.head(top_n) if not df.empty else df
+    print(f"GTEx top {top_n} tissues for {gene_id}:")
+    for _, row in top.iterrows():
+        print(f"  {row['tissue_name']}: "
+              f"{row['median_tpm']:.2f} TPM "
+              f"(n={row['sample_count']})")
+    return top
+```
+
+## 2. eQTL 検索
+
+```python
+def gtex_eqtl_lookup(gene_id, tissue, variant_id=None):
+    """
+    GTEx — eQTL ルックアップ。
+
+    Parameters:
+        gene_id: str — 遺伝子シンボル or Ensembl ID
+        tissue: str — 組織 ID
+            (例: "Liver", "Whole_Blood")
+        variant_id: str — バリアント ID (任意)
+            (例: "rs12345")
+    """
+    url = f"{GTEX_BASE}/association/singleTissueEqtl"
+    params = {
+        "gencodeId": gene_id,
+        "tissueSiteDetailId": tissue,
+        "datasetId": "gtex_v8",
+    }
+    if variant_id:
+        params["variantId"] = variant_id
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data.get("data", []):
+        results.append({
+            "gene_symbol": item.get("geneSymbol", ""),
+            "variant_id": item.get("variantId", ""),
+            "tissue": tissue,
+            "pvalue": item.get("pValue"),
+            "nes": item.get("nes"),  # normalized effect size
+            "maf": item.get("maf"),
+            "ref": item.get("ref", ""),
+            "alt": item.get("alt", ""),
+        })
+
+    df = pd.DataFrame(results)
+    if not df.empty:
+        df = df.sort_values("pvalue")
+
+    print(f"GTEx eQTL: {gene_id} in {tissue} → "
+          f"{len(df)} associations")
+    return df
+```
+
+## 3. 多組織比較
+
+```python
+def gtex_multi_gene_comparison(gene_ids, tissues=None):
+    """
+    GTEx — 複数遺伝子・複数組織の発現比較。
+
+    Parameters:
+        gene_ids: list[str] — 遺伝子リスト
+        tissues: list[str] — 組織リスト (None で全組織)
+    """
+    all_data = []
+    for gid in gene_ids:
+        try:
+            df = gtex_gene_expression(gid)
+            if tissues:
+                df = df[df["tissue"].isin(tissues)]
+            all_data.append(df)
+        except Exception as e:
+            print(f"  Warning: {gid} — {e}")
+            continue
+
+    if not all_data:
+        return pd.DataFrame()
+
+    combined = pd.concat(all_data, ignore_index=True)
+
+    # ピボットテーブル: 行=組織, 列=遺伝子, 値=TPM
+    if not combined.empty:
+        pivot = combined.pivot_table(
+            index="tissue_name",
+            columns="gene_symbol",
+            values="median_tpm",
+            aggfunc="first",
+        )
+        print(f"GTEx comparison: {len(gene_ids)} genes × "
+              f"{len(pivot)} tissues")
+        return pivot
+
+    return combined
+```
+
+## 4. GTEx 統合パイプライン
+
+```python
+def gtex_pipeline(gene_ids, tissues=None,
+                    output_dir="results"):
+    """
+    GTEx 統合パイプライン。
+
+    Parameters:
+        gene_ids: list[str] — 遺伝子リスト
+        tissues: list[str] — 組織リスト (None で全組織)
+        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) 全遺伝子の組織発現
+    all_expr = []
+    for gid in gene_ids:
+        try:
+            df = gtex_gene_expression(gid)
+            df.to_csv(output_dir / f"expression_{gid}.csv",
+                      index=False)
+            all_expr.append(df)
+        except Exception:
+            continue
+
+    # 2) 多組織比較マトリクス
+    pivot = gtex_multi_gene_comparison(gene_ids, tissues)
+    if isinstance(pivot, pd.DataFrame) and not pivot.empty:
+        pivot.to_csv(output_dir / "expression_matrix.csv")
+
+    # 3) eQTL 検索 (上位組織)
+    eqtl_results = []
+    for gid in gene_ids:
+        if all_expr:
+            top = all_expr[-1].head(3)
+            for _, row in top.iterrows():
+                try:
+                    eqtl = gtex_eqtl_lookup(gid,
+                                              row["tissue"])
+                    eqtl_results.append(eqtl)
+                except Exception:
+                    continue
+    if eqtl_results:
+        eqtl_combined = pd.concat(eqtl_results,
+                                    ignore_index=True)
+        eqtl_combined.to_csv(output_dir / "eqtl_results.csv",
+                              index=False)
+
+    print(f"GTEx pipeline: {output_dir}")
+    return {"expression": all_expr, "matrix": pivot}
+```
+
+---
+
+## ToolUniverse 連携
+
+| TU Key | ツール名 | 連携内容 |
+|--------|---------|---------|
+| (direct) | GTEx Portal API v2 | 直接 REST API — TU 非連携 |
+
+## パイプライン統合
+
+```
+gene-expression-transcriptomics → gtex-tissue-expression → variant-interpretation
+  (DESeq2/edgeR 差分発現)     (組織別 TPM + eQTL)       (臨床変異評価)
+          │                          │                        ↓
+  arrayexpress-expression ──────────┘              gwas-catalog
+  (ArrayExpress データ)          │               (GWAS 関連解析)
+                                 ↓
+                        disease-research
+                        (疾患関連遺伝子)
+```
+
+## パイプライン出力
+
+| ファイル | 説明 | 次スキル |
+|---------|------|---------|
+| `results/expression_*.csv` | 遺伝子別組織発現 | → disease-research |
+| `results/expression_matrix.csv` | 多遺伝子比較 | → pathway-enrichment |
+| `results/eqtl_results.csv` | eQTL 関連 | → variant-interpretation |

package/src/.github/skills/scientific-gwas-catalog/SKILL.md

@@ -0,0 +1,267 @@
+---
+name: scientific-gwas-catalog
+description: |
+  GWAS カタログスキル。NHGRI-EBI GWAS Catalog REST API によるゲノム
+  ワイド関連研究メタデータ・関連シグナル・形質・遺伝子座検索。
+  ToolUniverse 連携: gwas。
+tu_tools:
+  - key: gwas
+    name: GWAS Catalog
+    description: GWAS 関連シグナル・形質・遺伝子座検索
+---
+
+# Scientific GWAS Catalog
+
+NHGRI-EBI GWAS Catalog REST API を活用した GWAS メタデータ
+解析・遺伝子座レベル解釈パイプラインを提供する。
+
+## When to Use
+
+- GWAS Catalog から疾患/形質の関連バリアントを検索するとき
+- 遺伝的関連シグナルのエフェクトサイズ・P値を取得するとき
+- 特定遺伝子座の LD ブロック情報を解析するとき
+- 多形質 PheWAS-like 解析を実施するとき
+- GWAS サマリ統計量を下流解析に準備するとき
+- 公開 GWAS データから PRS ウェイトを抽出するとき
+
+---
+
+## Quick Start
+
+## 1. GWAS 関連シグナル検索
+
+```python
+import requests
+import pandas as pd
+import numpy as np
+
+GWAS_BASE = "https://www.ebi.ac.uk/gwas/rest/api"
+
+
+def gwas_search_associations(trait=None, gene=None, variant=None,
+                               p_upper=5e-8, limit=100):
+    """
+    GWAS Catalog — 関連シグナル検索。
+
+    Parameters:
+        trait: str — 形質/疾患 EFO ID or 名前 (例: "EFO_0001645")
+        gene: str — 遺伝子名 (例: "BRCA1")
+        variant: str — rsID (例: "rs1234567")
+        p_upper: float — P値上限
+        limit: int — 最大結果数
+    """
+    if trait:
+        url = f"{GWAS_BASE}/efoTraits/{trait}/associations"
+    elif gene:
+        url = f"{GWAS_BASE}/associations/search/findByGene"
+    elif variant:
+        url = f"{GWAS_BASE}/singleNucleotidePolymorphisms/{variant}/associations"
+    else:
+        url = f"{GWAS_BASE}/associations"
+
+    params = {"size": limit}
+    if gene:
+        params["geneName"] = gene
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    associations = data.get("_embedded", {}).get("associations", [])
+    results = []
+    for assoc in associations:
+        p_value = assoc.get("pvalue", 1.0)
+        if p_value and float(p_value) > p_upper:
+            continue
+
+        loci = assoc.get("loci", [{}])
+        genes = []
+        for locus in loci:
+            for gene_info in locus.get("authorReportedGenes", []):
+                genes.append(gene_info.get("geneName", ""))
+
+        snps = []
+        for snp_info in assoc.get("snps", []):
+            snps.append(snp_info.get("rsId", ""))
+
+        results.append({
+            "association_id": assoc.get("associationId", ""),
+            "p_value": float(p_value) if p_value else None,
+            "p_value_mlog": assoc.get("pvalueMantissa", 0),
+            "or_beta": assoc.get("orPerCopyNum", None),
+            "beta_num": assoc.get("betaNum", None),
+            "beta_direction": assoc.get("betaDirection", ""),
+            "ci": assoc.get("range", ""),
+            "risk_allele_freq": assoc.get("riskFrequency", ""),
+            "snps": "; ".join(snps),
+            "genes": "; ".join(genes),
+            "trait": assoc.get("efoTraits", [{}])[0].get("trait", "")
+                     if assoc.get("efoTraits") else "",
+            "study_accession": assoc.get("study", {}).get(
+                "accessionId", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"GWAS associations: {len(df)} results "
+          f"(trait={trait}, gene={gene}, p<{p_upper})")
+    return df.sort_values("p_value") if not df.empty else df
+```
+
+## 2. GWAS 研究メタデータ検索
+
+```python
+def gwas_search_studies(query=None, efo_trait=None, limit=50):
+    """
+    GWAS Catalog — 研究メタデータ検索。
+
+    Parameters:
+        query: str — フリーテキスト検索
+        efo_trait: str — EFO 形質 ID
+        limit: int — 最大結果数
+    """
+    if efo_trait:
+        url = f"{GWAS_BASE}/efoTraits/{efo_trait}/studies"
+    else:
+        url = f"{GWAS_BASE}/studies/search/findByDiseaseTrait"
+
+    params = {"size": limit}
+    if query:
+        params["diseaseTrait"] = query
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    studies = data.get("_embedded", {}).get("studies", [])
+    results = []
+    for s in studies:
+        results.append({
+            "accession": s.get("accessionId", ""),
+            "title": s.get("title", ""),
+            "pubmed_id": s.get("publicationInfo", {}).get(
+                "pubmedId", ""),
+            "author": s.get("publicationInfo", {}).get(
+                "author", {}).get("fullname", ""),
+            "journal": s.get("publicationInfo", {}).get(
+                "publication", ""),
+            "date": s.get("publicationInfo", {}).get(
+                "publicationDate", ""),
+            "initial_sample_size": s.get("initialSampleSize", ""),
+            "replication_sample_size": s.get(
+                "replicationSampleSize", ""),
+            "ancestry": s.get("ancestries", []),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"GWAS studies: {len(df)} results")
+    return df
+```
+
+## 3. GWAS 形質検索・PheWAS
+
+```python
+def gwas_phewas(variant_rsid, p_threshold=5e-8):
+    """
+    GWAS Catalog — バリアント PheWAS (形質横断検索)。
+
+    Parameters:
+        variant_rsid: str — rsID (例: "rs7903146")
+        p_threshold: float — P値閾値
+    """
+    url = (f"{GWAS_BASE}/singleNucleotidePolymorphisms/"
+           f"{variant_rsid}/associations")
+    resp = requests.get(url, params={"size": 500}, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    associations = data.get("_embedded", {}).get("associations", [])
+    results = []
+    for assoc in associations:
+        p_val = assoc.get("pvalue", 1.0)
+        if p_val and float(p_val) > p_threshold:
+            continue
+        for trait in assoc.get("efoTraits", []):
+            results.append({
+                "variant": variant_rsid,
+                "trait": trait.get("trait", ""),
+                "efo_uri": trait.get("shortForm", ""),
+                "p_value": float(p_val) if p_val else None,
+                "or_beta": assoc.get("orPerCopyNum", None),
+                "study": assoc.get("study", {}).get(
+                    "accessionId", ""),
+            })
+
+    df = pd.DataFrame(results)
+    if not df.empty:
+        df = df.sort_values("p_value")
+    print(f"PheWAS {variant_rsid}: {len(df)} trait associations")
+    return df
+```
+
+## 4. GWAS 統合パイプライン
+
+```python
+def gwas_catalog_pipeline(trait_query, output_dir="results"):
+    """
+    GWAS Catalog 統合パイプライン。
+
+    Parameters:
+        trait_query: str — 形質/疾患名
+        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) 研究検索
+    studies = gwas_search_studies(query=trait_query)
+    studies.to_csv(output_dir / "gwas_studies.csv", index=False)
+
+    # 2) 関連シグナル
+    assocs = gwas_search_associations(gene=None, trait=None)
+    assocs.to_csv(output_dir / "gwas_associations.csv", index=False)
+
+    # 3) トップバリアントの PheWAS
+    if not assocs.empty:
+        top_snps = assocs["snps"].str.split("; ").explode().unique()[:5]
+        phewas_all = []
+        for rsid in top_snps:
+            if rsid.startswith("rs"):
+                phewas = gwas_phewas(rsid)
+                phewas_all.append(phewas)
+        if phewas_all:
+            phewas_df = pd.concat(phewas_all, ignore_index=True)
+            phewas_df.to_csv(output_dir / "phewas.csv", index=False)
+
+    print(f"GWAS pipeline: {output_dir}")
+    return {"studies": studies, "associations": assocs}
+```
+
+---
+
+## ToolUniverse 連携
+
+| TU Key | ツール名 | 連携内容 |
+|--------|---------|---------|
+| `gwas` | GWAS Catalog | 関連シグナル・形質・研究メタデータ検索 |
+
+## パイプライン統合
+
+```
+disease-research → gwas-catalog → variant-interpretation
+  (DisGeNET/OMIM)  (GWAS Catalog)  (ACMG/AMP)
+       │                 │                ↓
+  population-genetics ──┘         variant-effect-prediction
+  (Fst/PCA)           │          (CADD/SpliceAI)
+                       ↓
+                  precision-oncology
+                  (臨床的意義判定)
+```
+
+## パイプライン出力
+
+| ファイル | 説明 | 次スキル |
+|---------|------|---------|
+| `results/gwas_studies.csv` | GWAS 研究メタデータ | → literature-search |
+| `results/gwas_associations.csv` | 関連シグナル | → variant-interpretation |
+| `results/phewas.csv` | PheWAS 結果 | → disease-research |