@nahisaho/satori 0.15.0 → 0.16.0

package/src/.github/skills/scientific-nci60-screening/SKILL.md

@@ -0,0 +1,307 @@
+---
+name: scientific-nci60-screening
+description: |
+  NCI-60 がん細胞株薬剤応答スキル。CellMiner API 薬剤感受性・
+  NCI-60 GI50/LC50 データ・DepMap cancer dependency 統合・
+  薬剤-分子マーカー相関・細胞株パネル比較解析。
+---
+
+# Scientific NCI-60 Screening
+
+CellMiner / NCI-60 / DepMap を活用したがん細胞株薬剤応答
+パイプラインを提供する。高スループットスクリーニングデータの
+統合解析、薬剤感受性マーカー同定、パネル比較。
+
+## When to Use
+
+- NCI-60 細胞株パネルの薬剤応答 (GI50) を解析するとき
+- CellMiner から化合物活性データを取得するとき
+- 薬剤感受性と分子マーカー (変異/発現) の相関を調べるとき
+- DepMap CRISPR/RNAi 依存性データを併用するとき
+- 細胞株間の薬剤応答パターンを比較するとき
+- 新規化合物のスクリーニング結果を NCI-60 と比較するとき
+
+---
+
+## Quick Start
+
+## 1. CellMiner データ取得
+
+```python
+import requests
+import pandas as pd
+import numpy as np
+from io import StringIO
+
+CELLMINER_BASE = "https://discover.nci.nih.gov/cellminer/api"
+
+
+def cellminer_drug_activity(nsc_id=None, drug_name=None):
+    """
+    CellMiner — NCI-60 薬剤活性データ取得。
+
+    Parameters:
+        nsc_id: str — NSC ID (例: "740")
+        drug_name: str — 薬剤名 (例: "Paclitaxel")
+    """
+    if nsc_id:
+        url = f"{CELLMINER_BASE}/compound/{nsc_id}/activity"
+    elif drug_name:
+        url = f"{CELLMINER_BASE}/compound/search"
+        params = {"name": drug_name}
+        resp = requests.get(url, params=params, timeout=30)
+        resp.raise_for_status()
+        compounds = resp.json()
+        if not compounds:
+            print(f"Drug not found: {drug_name}")
+            return pd.DataFrame()
+        nsc_id = compounds[0].get("nsc", "")
+        url = f"{CELLMINER_BASE}/compound/{nsc_id}/activity"
+
+    resp = requests.get(url, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for cell_line, values in data.get("activity", {}).items():
+        results.append({
+            "cell_line": cell_line,
+            "tissue": values.get("tissue", ""),
+            "gi50_log": values.get("gi50", None),
+            "tgi_log": values.get("tgi", None),
+            "lc50_log": values.get("lc50", None),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"CellMiner: NSC {nsc_id} → {len(df)} cell lines")
+    return df
+```
+
+## 2. NCI-60 バルクデータ取得
+
+```python
+def nci60_bulk_download(data_type="drug_activity"):
+    """
+    NCI-60 バルクデータセット取得。
+
+    Parameters:
+        data_type: str — "drug_activity", "gene_expression",
+                         "mutation", "copy_number"
+    """
+    urls = {
+        "drug_activity": "https://discover.nci.nih.gov/cellminer/download/DTP_NCI60_ZSCORE.csv",
+        "gene_expression": "https://discover.nci.nih.gov/cellminer/download/GeneExpr_RMA.csv",
+        "mutation": "https://discover.nci.nih.gov/cellminer/download/Exome_Mutation.csv",
+    }
+
+    url = urls.get(data_type)
+    if not url:
+        raise ValueError(f"Unknown data type: {data_type}")
+
+    resp = requests.get(url, timeout=120)
+    resp.raise_for_status()
+
+    df = pd.read_csv(StringIO(resp.text))
+    print(f"NCI-60 bulk: {data_type} → {df.shape}")
+    return df
+```
+
+## 3. 薬剤-分子マーカー相関
+
+```python
+from scipy import stats
+
+
+def drug_marker_correlation(drug_activity, molecular_data,
+                             marker_type="expression", top_n=50):
+    """
+    薬剤感受性と分子マーカーの相関解析。
+
+    Parameters:
+        drug_activity: pd.DataFrame — GI50 データ (cell_line, gi50)
+        molecular_data: pd.DataFrame — 分子データ (cell_line, gene, value)
+        marker_type: str — "expression", "mutation", "copy_number"
+        top_n: int — 上位相関遺伝子数
+    """
+    # 細胞株一致
+    common_lines = set(drug_activity["cell_line"]) & set(molecular_data["cell_line"])
+    drug_sub = drug_activity[drug_activity["cell_line"].isin(common_lines)]
+    mol_sub = molecular_data[molecular_data["cell_line"].isin(common_lines)]
+
+    # 遺伝子ごとの相関
+    correlations = []
+    genes = mol_sub["gene"].unique() if "gene" in mol_sub.columns else mol_sub.columns[1:]
+
+    drug_values = drug_sub.set_index("cell_line")["gi50_log"]
+
+    for gene in genes:
+        if "gene" in mol_sub.columns:
+            gene_data = mol_sub[mol_sub["gene"] == gene].set_index("cell_line")["value"]
+        else:
+            gene_data = mol_sub.set_index("cell_line")[gene]
+
+        common = drug_values.index.intersection(gene_data.index)
+        if len(common) < 10:
+            continue
+
+        r, p = stats.pearsonr(drug_values[common], gene_data[common])
+        correlations.append({
+            "gene": gene,
+            "pearson_r": r,
+            "p_value": p,
+            "n_samples": len(common),
+        })
+
+    corr_df = pd.DataFrame(correlations)
+    corr_df["adj_p"] = corr_df["p_value"] * len(corr_df)  # Bonferroni
+    corr_df = corr_df.sort_values("p_value")
+
+    print(f"Drug-marker correlation: {len(corr_df)} genes tested, "
+          f"top |r| = {corr_df['pearson_r'].abs().max():.3f}")
+    return corr_df.head(top_n)
+```
+
+## 4. 組織別薬剤応答パターン
+
+```python
+def tissue_response_pattern(drug_activity, min_lines=3):
+    """
+    組織別の薬剤応答パターン解析。
+
+    Parameters:
+        drug_activity: pd.DataFrame — GI50 データ
+        min_lines: int — 最小細胞株数
+    """
+    tissue_stats = drug_activity.groupby("tissue").agg(
+        n_lines=("gi50_log", "count"),
+        mean_gi50=("gi50_log", "mean"),
+        std_gi50=("gi50_log", "std"),
+        min_gi50=("gi50_log", "min"),
+        max_gi50=("gi50_log", "max"),
+    ).reset_index()
+
+    tissue_stats = tissue_stats[tissue_stats["n_lines"] >= min_lines]
+    tissue_stats = tissue_stats.sort_values("mean_gi50")
+
+    # 感受性/耐性スコア
+    overall_mean = drug_activity["gi50_log"].mean()
+    tissue_stats["sensitivity_z"] = (
+        (tissue_stats["mean_gi50"] - overall_mean)
+        / drug_activity["gi50_log"].std()
+    )
+
+    print(f"Tissue patterns: {len(tissue_stats)} tissues")
+    for _, row in tissue_stats.iterrows():
+        label = "Sensitive" if row["sensitivity_z"] < -0.5 else (
+            "Resistant" if row["sensitivity_z"] > 0.5 else "Neutral"
+        )
+        print(f"  {row['tissue']}: GI50={row['mean_gi50']:.2f} ({label})")
+    return tissue_stats
+```
+
+## 5. DepMap 統合スクリーニング
+
+```python
+DEPMAP_BASE = "https://depmap.org/portal/api"
+
+
+def depmap_gene_dependency(gene_symbol, dataset="Chronos_Combined"):
+    """
+    DepMap — CRISPR/RNAi 遺伝子依存性取得。
+
+    Parameters:
+        gene_symbol: str — 遺伝子シンボル
+        dataset: str — データセット名
+    """
+    url = f"{DEPMAP_BASE}/download/custom"
+    params = {
+        "gene": gene_symbol,
+        "dataset": dataset,
+    }
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for entry in data.get("data", []):
+        results.append({
+            "cell_line": entry.get("cell_line_name", ""),
+            "lineage": entry.get("lineage", ""),
+            "dependency_score": entry.get("score", None),
+        })
+
+    df = pd.DataFrame(results)
+    if len(df) > 0:
+        n_dependent = (df["dependency_score"] < -0.5).sum()
+        print(f"DepMap {gene_symbol}: {len(df)} lines, "
+              f"{n_dependent} dependent (score < -0.5)")
+    return df
+```
+
+## 6. NCI-60 統合スクリーニングパイプライン
+
+```python
+def nci60_screening_pipeline(drug_name=None, nsc_id=None,
+                              target_gene=None, output_dir="results"):
+    """
+    NCI-60 + DepMap 統合スクリーニングパイプライン。
+
+    Parameters:
+        drug_name: str — 薬剤名
+        nsc_id: str — NSC ID
+        target_gene: str — 標的遺伝子 (DepMap 連携)
+        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) NCI-60 薬剤活性
+    drug_data = cellminer_drug_activity(nsc_id=nsc_id, drug_name=drug_name)
+    drug_data.to_csv(output_dir / "drug_activity.csv", index=False)
+
+    # 2) 組織別パターン
+    tissue_patterns = tissue_response_pattern(drug_data)
+    tissue_patterns.to_csv(output_dir / "tissue_patterns.csv", index=False)
+
+    # 3) 発現相関
+    expr_data = nci60_bulk_download("gene_expression")
+    correlations = drug_marker_correlation(drug_data, expr_data)
+    correlations.to_csv(output_dir / "marker_correlations.csv", index=False)
+
+    # 4) DepMap 連携 (標的遺伝子あれば)
+    if target_gene:
+        depmap_data = depmap_gene_dependency(target_gene)
+        depmap_data.to_csv(output_dir / "depmap_dependency.csv", index=False)
+
+    print(f"Pipeline complete: {output_dir}")
+    return {
+        "drug_activity": drug_data,
+        "tissue_patterns": tissue_patterns,
+        "correlations": correlations,
+    }
+```
+
+---
+
+## パイプライン統合
+
+```
+compound-screening → nci60-screening → precision-oncology
+  (ZINC/VS)           (NCI-60/DepMap)    (MTB レポート)
+       │                     │                 ↓
+drug-target-profiling ──────┘          cancer-genomics
+  (ChEMBL/DGIdb)        │              (COSMIC/DepMap)
+                         ↓
+                   cell-line-resources
+                   (Cellosaurus)
+```
+
+## パイプライン出力
+
+| ファイル | 説明 | 次スキル |
+|---------|------|---------|
+| `results/drug_activity.csv` | NCI-60 GI50 データ | → precision-oncology |
+| `results/tissue_patterns.csv` | 組織別応答パターン | → cancer-genomics |
+| `results/marker_correlations.csv` | 薬剤-マーカー相関 | → drug-target-profiling |
+| `results/depmap_dependency.csv` | DepMap 依存性スコア | → cell-line-resources |

package/src/.github/skills/scientific-plant-biology/SKILL.md

@@ -0,0 +1,321 @@
+---
+name: scientific-plant-biology
+description: |
+  植物バイオロジー統合スキル。Plant Reactome 代謝パスウェイ・
+  TAIR Arabidopsis ゲノム情報・Phytozome 比較ゲノミクス・
+  Ensembl Plants 種間オーソログ解析。
+---
+
+# Scientific Plant Biology
+
+Plant Reactome / TAIR / Phytozome / Ensembl Plants を活用した
+植物ゲノム・代謝パスウェイ統合解析パイプラインを提供する。
+
+## When to Use
+
+- 植物代謝パスウェイ解析 (Plant Reactome) を実行するとき
+- Arabidopsis thaliana の遺伝子・タンパク質情報を取得するとき
+- 植物種間の比較ゲノミクス解析を行うとき
+- 植物オーソログ・パラログを同定するとき
+- 作物改良のための候補遺伝子を探索するとき
+- 植物表現型データと遺伝子型を統合するとき
+
+---
+
+## Quick Start
+
+## 1. Plant Reactome パスウェイ検索
+
+```python
+import requests
+import pandas as pd
+import json
+
+PLANT_REACTOME = "https://plantreactome.gramene.org/ContentService"
+
+
+def plant_reactome_search(query, species="Oryza sativa"):
+    """
+    Plant Reactome — 植物代謝/シグナルパスウェイ検索。
+
+    Parameters:
+        query: str — 検索クエリ (例: "photosynthesis")
+        species: str — 種名
+    """
+    url = f"{PLANT_REACTOME}/search/query"
+    params = {"query": query, "species": species, "cluster": True}
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for group in data.get("results", []):
+        for entry in group.get("entries", []):
+            results.append({
+                "stId": entry.get("stId", ""),
+                "name": entry.get("name", ""),
+                "species": entry.get("species", ""),
+                "type": entry.get("exactType", ""),
+                "compartment": entry.get("compartmentNames", []),
+            })
+
+    df = pd.DataFrame(results)
+    print(f"Plant Reactome: '{query}' → {len(df)} entries ({species})")
+    return df
+
+
+def plant_reactome_pathway_detail(pathway_id):
+    """
+    Plant Reactome パスウェイ詳細取得。
+
+    Parameters:
+        pathway_id: str — パスウェイ ID (例: "R-OSA-1119616")
+    """
+    url = f"{PLANT_REACTOME}/data/pathway/{pathway_id}/containedEvents"
+    resp = requests.get(url, timeout=30)
+    resp.raise_for_status()
+    events = resp.json()
+
+    steps = []
+    for event in events:
+        steps.append({
+            "stId": event.get("stId", ""),
+            "name": event.get("displayName", ""),
+            "type": event.get("className", ""),
+            "input_count": len(event.get("input", [])),
+            "output_count": len(event.get("output", [])),
+            "catalyst": event.get("catalystActivity", [{}])[0].get(
+                "displayName", "") if event.get("catalystActivity") else "",
+        })
+
+    df = pd.DataFrame(steps)
+    print(f"Pathway {pathway_id}: {len(df)} reaction steps")
+    return df
+```
+
+## 2. TAIR Arabidopsis 遺伝子情報
+
+```python
+TAIR_BASE = "https://www.arabidopsis.org/api"
+
+
+def tair_gene_search(gene_id=None, gene_name=None, keyword=None):
+    """
+    TAIR — Arabidopsis thaliana 遺伝子情報取得。
+
+    Parameters:
+        gene_id: str — AGI ID (例: "AT1G01010")
+        gene_name: str — 遺伝子名 (例: "FLC")
+        keyword: str — キーワード検索
+    """
+    if gene_id:
+        url = f"{TAIR_BASE}/gene/{gene_id}"
+        resp = requests.get(url, timeout=30)
+        resp.raise_for_status()
+        data = resp.json()
+        return pd.DataFrame([{
+            "agi_id": data.get("locus", ""),
+            "name": data.get("name", ""),
+            "description": data.get("description", ""),
+            "chromosome": data.get("chromosome", ""),
+            "start": data.get("start", ""),
+            "end": data.get("end", ""),
+            "strand": data.get("strand", ""),
+            "gene_model_type": data.get("gene_model_type", ""),
+        }])
+
+    # キーワード検索
+    search_term = gene_name or keyword or ""
+    url = f"{TAIR_BASE}/search/gene"
+    params = {"query": search_term, "limit": 50}
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for gene in data.get("results", []):
+        results.append({
+            "agi_id": gene.get("locus", ""),
+            "name": gene.get("name", ""),
+            "description": gene.get("description", ""),
+            "chromosome": gene.get("chromosome", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"TAIR: '{search_term}' → {len(df)} genes")
+    return df
+
+
+def tair_gene_expression(gene_id):
+    """
+    TAIR — 遺伝子発現パターン取得。
+
+    Parameters:
+        gene_id: str — AGI ID
+    """
+    url = f"{TAIR_BASE}/gene/{gene_id}/expression"
+    resp = requests.get(url, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    tissues = []
+    for expr in data.get("expression", []):
+        tissues.append({
+            "tissue": expr.get("tissue", ""),
+            "stage": expr.get("developmental_stage", ""),
+            "level": expr.get("expression_level", ""),
+            "source": expr.get("source", ""),
+        })
+
+    df = pd.DataFrame(tissues)
+    print(f"TAIR expression: {gene_id} → {len(df)} tissue records")
+    return df
+```
+
+## 3. Ensembl Plants 種間比較
+
+```python
+ENSEMBL_PLANTS = "https://rest.ensembl.org"
+
+
+def ensembl_plants_orthologs(gene_id, source_species="arabidopsis_thaliana",
+                              target_species=None):
+    """
+    Ensembl Plants — 植物種間オーソログ検索。
+
+    Parameters:
+        gene_id: str — Ensembl Gene ID or symbol
+        source_species: str — 起源種
+        target_species: str — ターゲット種 (None = 全種)
+    """
+    url = f"{ENSEMBL_PLANTS}/homology/id/{gene_id}"
+    params = {
+        "type": "orthologues",
+        "content-type": "application/json",
+        "compara": "plants",
+    }
+    if target_species:
+        params["target_species"] = target_species
+
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    orthologs = []
+    for homology in data.get("data", [{}])[0].get("homologies", []):
+        target = homology.get("target", {})
+        orthologs.append({
+            "source_gene": gene_id,
+            "source_species": source_species,
+            "target_gene": target.get("id", ""),
+            "target_species": target.get("species", ""),
+            "target_protein": target.get("protein_id", ""),
+            "identity": target.get("perc_id", 0),
+            "dn_ds": homology.get("dn_ds", None),
+            "type": homology.get("type", ""),
+        })
+
+    df = pd.DataFrame(orthologs)
+    print(f"Ensembl Plants orthologs: {gene_id} → {len(df)} homologs")
+    return df
+```
+
+## 4. Phytozome 比較ゲノミクス
+
+```python
+PHYTOZOME_BASE = "https://phytozome-next.jgi.doe.gov/api"
+
+
+def phytozome_gene_family(gene_id, species="Athaliana"):
+    """
+    Phytozome — 遺伝子ファミリー・比較ゲノミクス。
+
+    Parameters:
+        gene_id: str — 遺伝子 ID
+        species: str — 種略称
+    """
+    url = f"{PHYTOZOME_BASE}/search"
+    params = {"query": gene_id, "organism": species}
+    resp = requests.get(url, params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    families = []
+    for hit in data.get("hits", []):
+        families.append({
+            "gene_id": hit.get("gene_id", ""),
+            "family_id": hit.get("family_id", ""),
+            "family_name": hit.get("family_name", ""),
+            "species": hit.get("organism", ""),
+            "annotation": hit.get("annotation", ""),
+            "pfam_domains": hit.get("pfam", []),
+        })
+
+    df = pd.DataFrame(families)
+    print(f"Phytozome: {gene_id} → {len(df)} family members")
+    return df
+```
+
+## 5. 植物バイオロジー統合パイプライン
+
+```python
+def plant_biology_pipeline(gene_query, species="Oryza sativa",
+                            output_dir="results"):
+    """
+    植物バイオロジー統合パイプライン。
+
+    Parameters:
+        gene_query: str — 遺伝子/パスウェイクエリ
+        species: str — 対象種
+        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) Plant Reactome パスウェイ
+    pathways = plant_reactome_search(gene_query, species=species)
+    pathways.to_csv(output_dir / "plant_pathways.csv", index=False)
+
+    # 2) TAIR (Arabidopsis ならば)
+    tair_genes = tair_gene_search(keyword=gene_query)
+    tair_genes.to_csv(output_dir / "tair_genes.csv", index=False)
+
+    # 3) Ensembl Plants オーソログ
+    if len(tair_genes) > 0:
+        top_gene = tair_genes.iloc[0]["agi_id"]
+        orthologs = ensembl_plants_orthologs(top_gene)
+        orthologs.to_csv(output_dir / "orthologs.csv", index=False)
+    else:
+        orthologs = pd.DataFrame()
+
+    print(f"Plant biology pipeline: {output_dir}")
+    return {
+        "pathways": pathways,
+        "tair_genes": tair_genes,
+        "orthologs": orthologs,
+    }
+```
+
+---
+
+## パイプライン統合
+
+```
+pathway-enrichment → plant-biology → environmental-ecology
+  (KEGG/Reactome)   (PlantReactome)   (生態学/環境)
+       │                   │                ↓
+  gene-annotation ────────┘         marine-ecology
+  (GO/InterPro)      │              (OBIS/WoRMS)
+                      ↓
+               comparative-genomics
+               (Ensembl 比較)
+```
+
+## パイプライン出力
+
+| ファイル | 説明 | 次スキル |
+|---------|------|---------|
+| `results/plant_pathways.csv` | Plant Reactome パスウェイ | → pathway-enrichment |
+| `results/tair_genes.csv` | TAIR Arabidopsis 遺伝子 | → gene-annotation |
+| `results/orthologs.csv` | 種間オーソログ | → comparative-genomics |