@nahisaho/satori 0.12.0 → 0.13.0

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

@@ -0,0 +1,245 @@
+---
+name: scientific-compound-screening
+description: |
+  化合物スクリーニングスキル。ZINC データベースを活用した購入可能化合物検索、
+  SMILES/名前ベースの類似性検索、カタログフィルタリング、
+  バーチャルスクリーニング前処理パイプライン。
+---
+
+# Scientific Compound Screening
+
+ZINC データベースを活用した化合物ライブラリ検索・
+バーチャルスクリーニング前処理パイプラインを提供する。
+
+## When to Use
+
+- 購入可能な化合物ライブラリを検索するとき
+- SMILES 構造式から類似化合物を探すとき
+- 化合物名からデータベースレコードを取得するとき
+- ベンダーカタログの絞り込みを行うとき
+- バーチャルスクリーニング用の化合物セットを準備するとき
+
+---
+
+## Quick Start
+
+## 1. ZINC 化合物名検索
+
+```python
+import requests
+import pandas as pd
+
+ZINC_API = "https://zinc15.docking.org"
+
+
+def zinc_search_by_name(name, max_results=20):
+    """
+    ZINC データベースで化合物名による検索。
+
+    Parameters:
+        name: str — compound name (e.g., "aspirin")
+        max_results: int — maximum results
+
+    ToolUniverse:
+        ZINC_search_by_name(name=name)
+    """
+    url = f"{ZINC_API}/substances/search"
+    params = {"q": name, "count": max_results}
+    resp = requests.get(url, params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data:
+        results.append({
+            "zinc_id": item.get("zinc_id", ""),
+            "name": item.get("name", ""),
+            "smiles": item.get("smiles", ""),
+            "mwt": item.get("mwt", ""),
+            "logp": item.get("logp", ""),
+            "purchasable": item.get("purchasability", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"ZINC search '{name}': {len(df)} compounds")
+    return df
+```
+
+## 2. ZINC SMILES 類似性検索
+
+```python
+def zinc_search_by_smiles(smiles, similarity=0.7, max_results=20):
+    """
+    ZINC で SMILES 構造式による類似性検索。
+
+    Parameters:
+        smiles: str — SMILES string
+        similarity: float — Tanimoto similarity threshold (0-1)
+
+    ToolUniverse:
+        ZINC_search_by_smiles(smiles=smiles)
+    """
+    url = f"{ZINC_API}/substances/search"
+    params = {
+        "smiles": smiles,
+        "similarity": similarity,
+        "count": max_results,
+    }
+    resp = requests.get(url, params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for item in data:
+        results.append({
+            "zinc_id": item.get("zinc_id", ""),
+            "smiles": item.get("smiles", ""),
+            "similarity": item.get("similarity", ""),
+            "mwt": item.get("mwt", ""),
+            "logp": item.get("logp", ""),
+            "purchasable": item.get("purchasability", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"ZINC SMILES search: {len(df)} similar compounds "
+          f"(threshold={similarity})")
+    return df
+```
+
+## 3. ZINC 化合物詳細取得
+
+```python
+def zinc_get_substance(zinc_id):
+    """
+    ZINC ID から化合物の完全情報を取得。
+
+    Parameters:
+        zinc_id: str — ZINC ID (e.g., "ZINC000000000001")
+
+    ToolUniverse:
+        ZINC_get_substance(zinc_id=zinc_id)
+    """
+    url = f"{ZINC_API}/substances/{zinc_id}.json"
+    resp = requests.get(url)
+    resp.raise_for_status()
+    data = resp.json()
+
+    info = {
+        "zinc_id": data.get("zinc_id", ""),
+        "name": data.get("name", ""),
+        "smiles": data.get("smiles", ""),
+        "inchikey": data.get("inchikey", ""),
+        "mwt": data.get("mwt", ""),
+        "logp": data.get("logp", ""),
+        "num_rotatable_bonds": data.get("num_rotatable_bonds", ""),
+        "num_hba": data.get("num_hba", ""),
+        "num_hbd": data.get("num_hbd", ""),
+        "tpsa": data.get("tpsa", ""),
+        "purchasable": data.get("purchasability", ""),
+    }
+
+    print(f"ZINC {zinc_id}: {info['name']} (MW={info['mwt']})")
+    return info, data
+```
+
+## 4. ZINC カタログ一覧
+
+```python
+def zinc_get_catalogs():
+    """
+    ZINC の利用可能カタログ (ベンダー) 一覧を取得。
+
+    ToolUniverse:
+        ZINC_get_catalogs()
+    """
+    url = f"{ZINC_API}/catalogs.json"
+    resp = requests.get(url)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for cat in data:
+        results.append({
+            "catalog_name": cat.get("name", ""),
+            "short_name": cat.get("short_name", ""),
+            "num_substances": cat.get("num_substances", 0),
+            "url": cat.get("url", ""),
+        })
+
+    df = pd.DataFrame(results)
+    print(f"ZINC catalogs: {len(df)} vendors")
+    return df
+```
+
+## 5. バーチャルスクリーニング前処理パイプライン
+
+```python
+def virtual_screening_prep(query_smiles, lipinski=True, max_compounds=100):
+    """
+    バーチャルスクリーニング用の化合物セット準備。
+    Lipinski's Rule of Five フィルタリング含む。
+
+    ToolUniverse (横断):
+        ZINC_search_by_smiles(smiles=query_smiles) → ZINC_get_substance(zinc_id)
+    """
+    # Step 1: Similar compound search
+    df = zinc_search_by_smiles(query_smiles, similarity=0.6,
+                               max_results=max_compounds)
+
+    if df.empty:
+        print("No similar compounds found")
+        return df
+
+    # Step 2: Lipinski filter
+    if lipinski:
+        df["mwt"] = pd.to_numeric(df["mwt"], errors="coerce")
+        df["logp"] = pd.to_numeric(df["logp"], errors="coerce")
+        before = len(df)
+        df = df[
+            (df["mwt"] <= 500)
+            & (df["logp"] <= 5)
+        ]
+        print(f"Lipinski filter: {before} → {len(df)} compounds")
+
+    # Step 3: Sort by similarity
+    df["similarity"] = pd.to_numeric(df["similarity"], errors="coerce")
+    df = df.sort_values("similarity", ascending=False)
+
+    print(f"VS prep: {len(df)} compounds ready for screening")
+    return df
+```
+
+## References
+
+### Output Files
+
+| ファイル | 形式 |
+|---|---|
+| `results/zinc_search.csv` | CSV |
+| `results/zinc_similar.csv` | CSV |
+| `results/zinc_substance.json` | JSON |
+| `results/zinc_catalogs.csv` | CSV |
+| `results/vs_library.csv` | CSV |
+
+### 利用可能ツール
+
+| カテゴリ | 主要ツール | 用途 |
+|---|---|---|
+| ZINC | `ZINC_search_by_name` | 化合物名検索 |
+| ZINC | `ZINC_search_by_smiles` | SMILES 類似性検索 |
+| ZINC | `ZINC_get_substance` | 化合物詳細 |
+| ZINC | `ZINC_get_catalogs` | カタログ一覧 |
+
+### 参照スキル
+
+| スキル | 関連 |
+|---|---|
+| `scientific-compound-similarity` | 化合物類似性 |
+| `scientific-pharmacology-targets` | 薬理学ターゲット |
+| `scientific-molecular-docking` | 分子ドッキング |
+| `scientific-drug-target-interaction` | DTI 解析 |
+| `scientific-admet-toxicity` | ADMET 毒性 |
+
+### 依存パッケージ
+
+`requests`, `pandas`

package/src/.github/skills/scientific-genome-sequence-tools/SKILL.md

@@ -0,0 +1,304 @@
+---
+name: scientific-genome-sequence-tools
+description: |
+  ゲノム配列解析総合スキル。Ensembl ゲノムブラウザ、dbSNP 変異データ、
+  BLAST 相同性検索、NCBI Nucleotide 配列取得、GDC がんゲノミクスデータの
+  統合パイプライン。
+---
+
+# Scientific Genome Sequence Tools
+
+公的ゲノムデータベース (Ensembl, dbSNP, BLAST, NCBI, GDC) を横断した
+配列検索・変異アノテーション・がんゲノミクスパイプラインを提供する。
+
+## When to Use
+
+- ゲノム配列・エクソン構造を Ensembl から取得するとき
+- rsID から変異のアレル頻度を調べるとき
+- BLAST で塩基/アミノ酸配列の相同性検索を行うとき
+- NCBI Nucleotide から配列をフェッチするとき
+- GDC がんゲノミクスデータ (体細胞変異, CNV, 発現) を取得するとき
+
+---
+
+## Quick Start
+
+## 1. dbSNP 変異情報取得
+
+```python
+import requests
+import pandas as pd
+
+
+def get_dbsnp_variant(rsid):
+    """
+    dbSNP から rsID ベースの変異情報 (アレル頻度含む) を取得。
+
+    Parameters:
+        rsid: str — e.g. "rs7412"
+
+    ToolUniverse:
+        dbsnp_get_variant_by_rsid(rsid=rsid)
+        dbsnp_get_frequencies(rsid=rsid)
+        dbsnp_search_by_gene(gene_symbol=gene_symbol)
+    """
+    url = f"https://api.ncbi.nlm.nih.gov/variation/v0/refsnp/{rsid.lstrip('rs')}"
+    resp = requests.get(url)
+    resp.raise_for_status()
+    data = resp.json()
+
+    # Extract primary info
+    info = {
+        "rsid": f"rs{data.get('refsnp_id', '')}",
+        "create_date": data.get("create_date", ""),
+        "update_date": data.get("update_date", ""),
+    }
+
+    # Allele frequencies
+    alleles = data.get("primary_snapshot_data", {}).get(
+        "allele_annotations", []
+    )
+    freq_data = []
+    for allele in alleles:
+        for freq_entry in allele.get("frequency", []):
+            freq_data.append({
+                "study": freq_entry.get("study_name", ""),
+                "allele": freq_entry.get("allele", ""),
+                "count": freq_entry.get("allele_count", 0),
+                "total": freq_entry.get("total_count", 0),
+            })
+
+    df_freq = pd.DataFrame(freq_data)
+    print(f"dbSNP {info['rsid']}: {len(df_freq)} frequency entries")
+    return info, df_freq
+```
+
+## 2. BLAST 相同性検索
+
+```python
+import time
+
+
+def blast_search(sequence, program="blastn", database="nt", max_hits=10):
+    """
+    NCBI BLAST REST API で相同性検索。
+
+    Parameters:
+        sequence: str — query sequence (nucleotide or protein)
+        program: str — "blastn", "blastp", "blastx", "tblastn"
+        database: str — "nt", "nr", "refseq_rna", etc.
+
+    ToolUniverse:
+        BLAST_nucleotide_search(sequence=sequence, database=database)
+        BLAST_protein_search(sequence=sequence, database=database)
+    """
+    put_url = "https://blast.ncbi.nlm.nih.gov/blast/Blast.cgi"
+    params = {
+        "CMD": "Put",
+        "PROGRAM": program,
+        "DATABASE": database,
+        "QUERY": sequence,
+        "FORMAT_TYPE": "JSON2",
+        "HITLIST_SIZE": max_hits,
+    }
+    resp = requests.post(put_url, data=params)
+    resp.raise_for_status()
+
+    # Extract RID
+    import re
+    rid_match = re.search(r"RID = (\S+)", resp.text)
+    if not rid_match:
+        raise ValueError("BLAST RID not found")
+    rid = rid_match.group(1)
+    print(f"BLAST submitted: RID={rid}")
+
+    # Poll for results
+    for _ in range(60):
+        time.sleep(10)
+        check = requests.get(put_url, params={
+            "CMD": "Get", "RID": rid, "FORMAT_TYPE": "JSON2"
+        })
+        if "Status=WAITING" not in check.text:
+            break
+
+    return check.json() if check.headers.get(
+        "Content-Type", ""
+    ).startswith("application/json") else check.text
+```
+
+## 3. NCBI Nucleotide 配列フェッチ
+
+```python
+def fetch_ncbi_sequence(accession, rettype="fasta"):
+    """
+    NCBI Nucleotide (E-utilities) から配列を取得。
+
+    Parameters:
+        accession: str — NCBI accession (e.g., "NM_000546.6")
+        rettype: str — "fasta", "gb", "gbwithparts"
+
+    ToolUniverse:
+        NCBI_search_nucleotide(query=query)
+        NCBI_fetch_accessions(accessions=accessions)
+        NCBI_get_sequence(accession=accession)
+    """
+    url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi"
+    params = {
+        "db": "nucleotide",
+        "id": accession,
+        "rettype": rettype,
+        "retmode": "text",
+    }
+    resp = requests.get(url, params=params)
+    resp.raise_for_status()
+
+    print(f"NCBI Nucleotide '{accession}': {len(resp.text)} chars ({rettype})")
+    return resp.text
+```
+
+## 4. GDC がんゲノミクスデータ
+
+```python
+def get_gdc_mutations(gene_symbol, project_id=None):
+    """
+    NCI GDC (Genomic Data Commons) から体細胞変異データを取得。
+
+    Parameters:
+        gene_symbol: str — e.g. "TP53"
+        project_id: str | None — e.g. "TCGA-BRCA"
+
+    ToolUniverse:
+        GDC_get_ssm_by_gene(gene_symbol=gene_symbol)
+        GDC_get_mutation_frequency(project_id=project_id)
+        GDC_get_gene_expression(gene_id=gene_id, project_id=project_id)
+        GDC_get_cnv_data(gene_id=gene_id)
+        GDC_list_projects()
+        GDC_search_cases(filters=filters)
+        GDC_list_files(filters=filters)
+    """
+    url = "https://api.gdc.cancer.gov/ssms"
+    filters = {
+        "op": "and",
+        "content": [
+            {"op": "in", "content": {
+                "field": "consequence.transcript.gene.symbol",
+                "value": [gene_symbol],
+            }},
+        ],
+    }
+    if project_id:
+        filters["content"].append({
+            "op": "in",
+            "content": {
+                "field": "cases.project.project_id",
+                "value": [project_id],
+            },
+        })
+
+    import json
+    params = {
+        "filters": json.dumps(filters),
+        "fields": ("ssm_id,consequence.transcript.gene.symbol,"
+                    "consequence.transcript.aa_change,"
+                    "consequence.transcript.consequence_type,"
+                    "genomic_dna_change"),
+        "size": 100,
+        "format": "json",
+    }
+    resp = requests.get(url, params=params)
+    resp.raise_for_status()
+    hits = resp.json().get("data", {}).get("hits", [])
+
+    results = []
+    for hit in hits:
+        for csq in hit.get("consequence", []):
+            tx = csq.get("transcript", {})
+            results.append({
+                "ssm_id": hit.get("ssm_id", ""),
+                "gene": tx.get("gene", {}).get("symbol", ""),
+                "aa_change": tx.get("aa_change", ""),
+                "consequence_type": tx.get("consequence_type", ""),
+                "genomic_dna_change": hit.get("genomic_dna_change", ""),
+            })
+
+    df = pd.DataFrame(results)
+    print(f"GDC SSMs '{gene_symbol}'"
+          f"{f' ({project_id})' if project_id else ''}: {len(df)} mutations")
+    return df
+```
+
+## 5. 統合ゲノム変異パイプライン
+
+```python
+def integrated_variant_pipeline(rsid, gene_symbol=None):
+    """
+    dbSNP + GDC を統合したゲノム変異解析パイプライン。
+
+    ToolUniverse (横断):
+        dbsnp_get_variant_by_rsid(rsid) → GDC_get_ssm_by_gene(gene_symbol)
+    """
+    pipeline_result = {"rsid": rsid}
+
+    # Step 1: dbSNP
+    info, freq_df = get_dbsnp_variant(rsid)
+    pipeline_result["dbsnp"] = info
+
+    # Step 2: GDC somatic mutations (if gene provided)
+    if gene_symbol:
+        gdc_df = get_gdc_mutations(gene_symbol)
+        pipeline_result["gdc_mutation_count"] = len(gdc_df)
+        pipeline_result["gdc_top_consequences"] = (
+            gdc_df["consequence_type"].value_counts().head(5).to_dict()
+            if not gdc_df.empty else {}
+        )
+
+    print(f"Integrated variant: {rsid}"
+          f" | GDC={pipeline_result.get('gdc_mutation_count', 'N/A')}")
+    return pipeline_result
+```
+
+## References
+
+### Output Files
+
+| ファイル | 形式 |
+|---|---|
+| `results/dbsnp_variant.json` | JSON |
+| `results/dbsnp_frequencies.csv` | CSV |
+| `results/blast_results.json` | JSON |
+| `results/ncbi_sequence.fasta` | FASTA |
+| `results/gdc_mutations.csv` | CSV |
+
+### 利用可能ツール
+
+| カテゴリ | 主要ツール | 用途 |
+|---|---|---|
+| dbSNP | `dbsnp_get_variant_by_rsid` | rsID 変異情報 |
+| dbSNP | `dbsnp_get_frequencies` | アレル頻度 |
+| dbSNP | `dbsnp_search_by_gene` | 遺伝子→変異 |
+| BLAST | `BLAST_nucleotide_search` | 核酸相同性検索 |
+| BLAST | `BLAST_protein_search` | タンパク質相同性検索 |
+| NCBI | `NCBI_search_nucleotide` | 配列検索 |
+| NCBI | `NCBI_fetch_accessions` | アクセッション取得 |
+| NCBI | `NCBI_get_sequence` | 配列フェッチ |
+| GDC | `GDC_get_ssm_by_gene` | 体細胞変異 |
+| GDC | `GDC_get_mutation_frequency` | 変異頻度 |
+| GDC | `GDC_get_gene_expression` | 発現データ |
+| GDC | `GDC_get_cnv_data` | CNV データ |
+| GDC | `GDC_list_projects` | プロジェクト一覧 |
+| GDC | `GDC_search_cases` | 症例検索 |
+| GDC | `GDC_list_files` | ファイル一覧 |
+
+### 参照スキル
+
+| スキル | 関連 |
+|---|---|
+| `scientific-variant-interpretation` | 変異アノテーション |
+| `scientific-population-genetics` | 集団遺伝学 |
+| `scientific-cancer-genomics` | がんゲノミクス |
+| `scientific-rare-disease-genetics` | 希少疾患遺伝学 |
+| `scientific-biothings-idmapping` | ID マッピング |
+
+### 依存パッケージ
+
+`requests`, `pandas`