@nahisaho/satori 0.18.0 → 0.20.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (34) hide show
  1. package/README.md +79 -39
  2. package/package.json +1 -1
  3. package/src/.github/skills/scientific-admet-pharmacokinetics/SKILL.md +4 -0
  4. package/src/.github/skills/scientific-biobank-cohort/SKILL.md +268 -0
  5. package/src/.github/skills/scientific-cancer-genomics/SKILL.md +7 -0
  6. package/src/.github/skills/scientific-cell-line-resources/SKILL.md +4 -0
  7. package/src/.github/skills/scientific-chembl-assay-mining/SKILL.md +4 -0
  8. package/src/.github/skills/scientific-civic-evidence/SKILL.md +292 -0
  9. package/src/.github/skills/scientific-compound-screening/SKILL.md +4 -0
  10. package/src/.github/skills/scientific-depmap-dependencies/SKILL.md +239 -0
  11. package/src/.github/skills/scientific-disease-research/SKILL.md +4 -0
  12. package/src/.github/skills/scientific-drug-target-profiling/SKILL.md +4 -0
  13. package/src/.github/skills/scientific-drugbank-resources/SKILL.md +269 -0
  14. package/src/.github/skills/scientific-gdc-portal/SKILL.md +280 -0
  15. package/src/.github/skills/scientific-gnomad-variants/SKILL.md +356 -0
  16. package/src/.github/skills/scientific-immunoinformatics/SKILL.md +4 -0
  17. package/src/.github/skills/scientific-metabolic-flux/SKILL.md +306 -0
  18. package/src/.github/skills/scientific-metabolic-modeling/SKILL.md +4 -0
  19. package/src/.github/skills/scientific-metabolomics/SKILL.md +4 -0
  20. package/src/.github/skills/scientific-metabolomics-databases/SKILL.md +4 -0
  21. package/src/.github/skills/scientific-microbiome-metagenomics/SKILL.md +4 -0
  22. package/src/.github/skills/scientific-monarch-ontology/SKILL.md +260 -0
  23. package/src/.github/skills/scientific-opentargets-genetics/SKILL.md +299 -0
  24. package/src/.github/skills/scientific-pharmacology-targets/SKILL.md +10 -0
  25. package/src/.github/skills/scientific-precision-oncology/SKILL.md +4 -0
  26. package/src/.github/skills/scientific-protein-interaction-network/SKILL.md +4 -0
  27. package/src/.github/skills/scientific-rare-disease-genetics/SKILL.md +4 -0
  28. package/src/.github/skills/scientific-rcsb-pdb-search/SKILL.md +280 -0
  29. package/src/.github/skills/scientific-reactome-pathways/SKILL.md +242 -0
  30. package/src/.github/skills/scientific-spatial-multiomics/SKILL.md +293 -0
  31. package/src/.github/skills/scientific-stitch-chemical-network/SKILL.md +318 -0
  32. package/src/.github/skills/scientific-string-network-api/SKILL.md +4 -0
  33. package/src/.github/skills/scientific-uniprot-proteome/SKILL.md +273 -0
  34. package/src/.github/skills/scientific-variant-interpretation/SKILL.md +4 -0
@@ -0,0 +1,292 @@
1
+ ---
2
+ name: scientific-civic-evidence
3
+ description: |
4
+ CIViC 臨床エビデンススキル。CIViC (Clinical Interpretation
5
+ of Variants in Cancer) REST API を用いたバリアント臨床解釈・
6
+ エビデンスアイテム・分子プロファイル・アサーション検索。
7
+ ToolUniverse 連携: civic。
8
+ tu_tools:
9
+ - key: civic
10
+ name: CIViC
11
+ description: がんバリアント臨床解釈データベース
12
+ ---
13
+
14
+ # Scientific CIViC Evidence
15
+
16
+ CIViC (Clinical Interpretation of Variants in Cancer) REST API
17
+ を活用したバリアント臨床解釈・エビデンスアイテム取得・
18
+ 分子プロファイル・アサーションパイプラインを提供する。
19
+
20
+ ## When to Use
21
+
22
+ - がんバリアントの臨床的解釈を検索するとき
23
+ - エビデンスアイテム (薬剤応答・予後・診断) を取得するとき
24
+ - 遺伝子ごとのバリアントサマリーを確認するとき
25
+ - 分子プロファイル (Molecular Profile) を検索するとき
26
+ - アサーション (ガイドライン推奨) を取得するとき
27
+
28
+ ---
29
+
30
+ ## Quick Start
31
+
32
+ ## 1. バリアント検索・臨床解釈
33
+
34
+ ```python
35
+ import requests
36
+ import pandas as pd
37
+
38
+ CIVIC_API = "https://civicdb.org/api"
39
+
40
+
41
+ def civic_variant_search(gene_name, variant_name=None,
42
+ limit=50):
43
+ """
44
+ CIViC — バリアント検索。
45
+
46
+ Parameters:
47
+ gene_name: str — 遺伝子名 (例: "BRAF")
48
+ variant_name: str — バリアント名
49
+ (例: "V600E")
50
+ limit: int — 最大結果数
51
+ """
52
+ url = f"{CIVIC_API}/variants"
53
+ params = {"count": limit}
54
+
55
+ # 遺伝子名で検索
56
+ gene_url = f"{CIVIC_API}/genes/{gene_name}"
57
+ try:
58
+ resp = requests.get(gene_url, timeout=30)
59
+ if resp.status_code == 200:
60
+ gene_data = resp.json()
61
+ else:
62
+ # 検索 API フォールバック
63
+ search_url = f"{CIVIC_API}/genes"
64
+ params_g = {"name": gene_name, "count": 5}
65
+ resp = requests.get(search_url,
66
+ params=params_g,
67
+ timeout=30)
68
+ resp.raise_for_status()
69
+ records = resp.json().get("records", [])
70
+ gene_data = records[0] if records else {}
71
+ except Exception as e:
72
+ print(f" CIViC gene lookup: {e}")
73
+ gene_data = {}
74
+
75
+ if not gene_data:
76
+ return pd.DataFrame()
77
+
78
+ variants = gene_data.get("variants", [])
79
+ rows = []
80
+ for v in variants[:limit]:
81
+ name = v.get("name", "")
82
+ if variant_name and variant_name.lower() \
83
+ not in name.lower():
84
+ continue
85
+ rows.append({
86
+ "variant_id": v.get("id", ""),
87
+ "gene": gene_name,
88
+ "variant_name": name,
89
+ "description": (v.get("description", "")
90
+ [:200]),
91
+ "evidence_count": len(
92
+ v.get("evidence_items", [])),
93
+ })
94
+
95
+ df = pd.DataFrame(rows)
96
+ print(f"CIViC variants: {gene_name} → {len(df)}")
97
+ return df
98
+
99
+
100
+ def civic_gene_summary(gene_name):
101
+ """
102
+ CIViC — 遺伝子サマリー取得。
103
+
104
+ Parameters:
105
+ gene_name: str — 遺伝子名 (例: "EGFR")
106
+ """
107
+ url = f"{CIVIC_API}/genes/{gene_name}"
108
+ resp = requests.get(url, timeout=30)
109
+ resp.raise_for_status()
110
+ data = resp.json()
111
+
112
+ result = {
113
+ "gene_id": data.get("id", ""),
114
+ "name": data.get("name", ""),
115
+ "description": data.get("description", ""),
116
+ "n_variants": len(data.get("variants", [])),
117
+ "aliases": "; ".join(
118
+ data.get("aliases", [])),
119
+ }
120
+ return result
121
+ ```
122
+
123
+ ## 2. エビデンスアイテム取得
124
+
125
+ ```python
126
+ def civic_evidence_items(variant_id, limit=50):
127
+ """
128
+ CIViC — エビデンスアイテム取得。
129
+
130
+ Parameters:
131
+ variant_id: int — バリアント ID
132
+ limit: int — 最大結果数
133
+ """
134
+ url = f"{CIVIC_API}/variants/{variant_id}"
135
+ resp = requests.get(url, timeout=30)
136
+ resp.raise_for_status()
137
+ data = resp.json()
138
+
139
+ rows = []
140
+ for ev in data.get("evidence_items", [])[:limit]:
141
+ drugs = [d.get("name", "")
142
+ for d in ev.get("drugs", [])]
143
+ rows.append({
144
+ "evidence_id": ev.get("id", ""),
145
+ "variant_id": variant_id,
146
+ "evidence_type": ev.get(
147
+ "evidence_type", ""),
148
+ "evidence_level": ev.get(
149
+ "evidence_level", ""),
150
+ "evidence_direction": ev.get(
151
+ "evidence_direction", ""),
152
+ "clinical_significance": ev.get(
153
+ "clinical_significance", ""),
154
+ "disease": ev.get("disease", {}).get(
155
+ "name", ""),
156
+ "drugs": "; ".join(drugs),
157
+ "rating": ev.get("rating", ""),
158
+ "status": ev.get("status", ""),
159
+ "source_citation": ev.get(
160
+ "source", {}).get("citation", ""),
161
+ })
162
+
163
+ df = pd.DataFrame(rows)
164
+ print(f"CIViC evidence: variant {variant_id} "
165
+ f"→ {len(df)} items")
166
+ return df
167
+ ```
168
+
169
+ ## 3. アサーション取得
170
+
171
+ ```python
172
+ def civic_assertions(gene_name=None, limit=50):
173
+ """
174
+ CIViC — アサーション (ガイドライン推奨) 取得。
175
+
176
+ Parameters:
177
+ gene_name: str — 遺伝子名フィルタ
178
+ limit: int — 最大結果数
179
+ """
180
+ url = f"{CIVIC_API}/assertions"
181
+ params = {"count": limit}
182
+
183
+ resp = requests.get(url, params=params, timeout=30)
184
+ resp.raise_for_status()
185
+ data = resp.json()
186
+
187
+ rows = []
188
+ for a in data.get("records", []):
189
+ genes = [g.get("name", "")
190
+ for g in a.get("genes", [])]
191
+ if gene_name and gene_name not in genes:
192
+ continue
193
+ drugs = [d.get("name", "")
194
+ for d in a.get("drugs", [])]
195
+ rows.append({
196
+ "assertion_id": a.get("id", ""),
197
+ "genes": "; ".join(genes),
198
+ "variant": a.get("variant", {}).get(
199
+ "name", ""),
200
+ "disease": a.get("disease", {}).get(
201
+ "name", ""),
202
+ "drugs": "; ".join(drugs),
203
+ "assertion_type": a.get(
204
+ "assertion_type", ""),
205
+ "assertion_direction": a.get(
206
+ "assertion_direction", ""),
207
+ "clinical_significance": a.get(
208
+ "clinical_significance", ""),
209
+ "amp_level": a.get("amp_level", ""),
210
+ "status": a.get("status", ""),
211
+ })
212
+
213
+ df = pd.DataFrame(rows)
214
+ print(f"CIViC assertions: {len(df)}")
215
+ return df
216
+ ```
217
+
218
+ ## 4. CIViC 統合パイプライン
219
+
220
+ ```python
221
+ def civic_pipeline(gene_name, variant_name=None,
222
+ output_dir="results"):
223
+ """
224
+ CIViC 統合パイプライン。
225
+
226
+ Parameters:
227
+ gene_name: str — 遺伝子名 (例: "BRAF")
228
+ variant_name: str — バリアント名 (例: "V600E")
229
+ output_dir: str — 出力ディレクトリ
230
+ """
231
+ from pathlib import Path
232
+ output_dir = Path(output_dir)
233
+ output_dir.mkdir(parents=True, exist_ok=True)
234
+
235
+ # 1) 遺伝子サマリー
236
+ summary = civic_gene_summary(gene_name)
237
+ pd.DataFrame([summary]).to_csv(
238
+ output_dir / "civic_gene.csv", index=False)
239
+
240
+ # 2) バリアント検索
241
+ variants = civic_variant_search(gene_name,
242
+ variant_name)
243
+ variants.to_csv(output_dir / "civic_variants.csv",
244
+ index=False)
245
+
246
+ # 3) トップバリアントのエビデンス
247
+ if not variants.empty:
248
+ top_vid = variants.iloc[0]["variant_id"]
249
+ evidence = civic_evidence_items(top_vid)
250
+ evidence.to_csv(
251
+ output_dir / "civic_evidence.csv",
252
+ index=False)
253
+
254
+ # 4) アサーション
255
+ assertions = civic_assertions(gene_name)
256
+ assertions.to_csv(
257
+ output_dir / "civic_assertions.csv",
258
+ index=False)
259
+
260
+ print(f"CIViC pipeline: {gene_name} → {output_dir}")
261
+ return {"variants": variants}
262
+ ```
263
+
264
+ ---
265
+
266
+ ## ToolUniverse 連携
267
+
268
+ | TU Key | ツール名 | 連携内容 |
269
+ |--------|---------|---------|
270
+ | `civic` | CIViC | がんバリアント臨床解釈 (~12 tools) |
271
+
272
+ ## パイプライン統合
273
+
274
+ ```
275
+ variant-interpretation → civic-evidence → precision-oncology
276
+ (ClinVar バリアント) (CIViC REST) (精密腫瘍学)
277
+ │ │ ↓
278
+ gnomad-variants ────────────┘ drug-target-profiling
279
+ (集団頻度) │ (標的プロファイリング)
280
+
281
+ opentargets-genetics
282
+ (OT 標的-疾患)
283
+ ```
284
+
285
+ ## パイプライン出力
286
+
287
+ | ファイル | 説明 | 次スキル |
288
+ |---------|------|---------|
289
+ | `results/civic_gene.csv` | 遺伝子サマリー | → cancer-genomics |
290
+ | `results/civic_variants.csv` | バリアント一覧 | → variant-interpretation |
291
+ | `results/civic_evidence.csv` | エビデンス | → precision-oncology |
292
+ | `results/civic_assertions.csv` | アサーション | → pharmacogenomics |
@@ -4,6 +4,10 @@ description: |
4
4
  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、
5
5
  SMILES/名前ベースの類似性検索、カタログフィルタリング、
6
6
  バーチャルスクリーニング前処理パイプライン。
7
+ tu_tools:
8
+ - key: zinc
9
+ name: ZINC
10
+ description: 購入可能化合物データベース
7
11
  ---
8
12
 
9
13
  # Scientific Compound Screening
@@ -0,0 +1,239 @@
1
+ ---
2
+ name: scientific-depmap-dependencies
3
+ description: |
4
+ DepMap 依存性スキル。Cancer Dependency Map (DepMap) Portal
5
+ API によるがん細胞株 CRISPR/RNAi 依存性スコア・薬剤
6
+ 感受性データ・遺伝子効果取得。ToolUniverse 連携: depmap。
7
+ tu_tools:
8
+ - key: depmap
9
+ name: DepMap
10
+ description: がん細胞株依存性マップ API
11
+ ---
12
+
13
+ # Scientific DepMap Dependencies
14
+
15
+ Cancer Dependency Map (DepMap) Portal API を活用した
16
+ がん細胞株の CRISPR/RNAi 遺伝子依存性スコア取得・
17
+ 薬剤感受性データ・遺伝子効果パイプラインを提供する。
18
+
19
+ ## When to Use
20
+
21
+ - がん細胞株の遺伝子依存性 (CRISPR/RNAi) を調べるとき
22
+ - 遺伝子のがん選択的必須性を評価するとき
23
+ - 薬剤感受性データと遺伝子発現の相関を調べるとき
24
+ - 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
25
+ - Cell Model Passports データを参照するとき
26
+
27
+ ---
28
+
29
+ ## Quick Start
30
+
31
+ ## 1. DepMap 細胞株検索・メタデータ
32
+
33
+ ```python
34
+ import requests
35
+ import pandas as pd
36
+
37
+ DEPMAP_API = "https://api.cellmodelpassports.sanger.ac.uk/v1"
38
+
39
+
40
+ def depmap_cell_lines(tissue=None, cancer_type=None,
41
+ limit=50):
42
+ """
43
+ DepMap / Cell Model Passports — 細胞株検索。
44
+
45
+ Parameters:
46
+ tissue: str — 組織型フィルタ (例: "Breast")
47
+ cancer_type: str — がん種フィルタ
48
+ (例: "Breast Carcinoma")
49
+ limit: int — 最大結果数
50
+ """
51
+ url = f"{DEPMAP_API}/models"
52
+ params = {"page_size": limit}
53
+ if tissue:
54
+ params["tissue"] = tissue
55
+ if cancer_type:
56
+ params["cancer_type"] = cancer_type
57
+
58
+ resp = requests.get(url, params=params, timeout=30)
59
+ resp.raise_for_status()
60
+ data = resp.json()
61
+
62
+ rows = []
63
+ for model in data.get("data", data
64
+ if isinstance(data, list)
65
+ else []):
66
+ if isinstance(model, dict):
67
+ rows.append({
68
+ "model_id": model.get("model_id", ""),
69
+ "model_name": model.get("model_name", ""),
70
+ "tissue": model.get("tissue", ""),
71
+ "cancer_type": model.get(
72
+ "cancer_type", ""),
73
+ "sample_site": model.get(
74
+ "sample_site", ""),
75
+ "gender": model.get("gender", ""),
76
+ })
77
+
78
+ df = pd.DataFrame(rows[:limit])
79
+ print(f"DepMap cell lines: {len(df)} models")
80
+ return df
81
+ ```
82
+
83
+ ## 2. CRISPR 遺伝子依存性スコア
84
+
85
+ ```python
86
+ def depmap_gene_dependency(gene_symbol,
87
+ dataset="Chronos_Combined"):
88
+ """
89
+ DepMap — 遺伝子依存性スコア取得。
90
+
91
+ Parameters:
92
+ gene_symbol: str — 遺伝子シンボル (例: "KRAS")
93
+ dataset: str — データセット名
94
+ (例: "Chronos_Combined", "RNAi_merged")
95
+ """
96
+ # DepMap Public Portal download URL
97
+ DEPMAP_PORTAL = "https://depmap.org/portal/api"
98
+
99
+ url = f"{DEPMAP_PORTAL}/dataset/search"
100
+ params = {"gene": gene_symbol,
101
+ "dataset": dataset}
102
+
103
+ try:
104
+ resp = requests.get(url, params=params,
105
+ timeout=30)
106
+ resp.raise_for_status()
107
+ data = resp.json()
108
+ except Exception:
109
+ # Fallback: alternative DepMap API
110
+ print(f" DepMap portal fallback for "
111
+ f"{gene_symbol}")
112
+ data = []
113
+
114
+ rows = []
115
+ if isinstance(data, list):
116
+ for entry in data:
117
+ if isinstance(entry, dict):
118
+ rows.append({
119
+ "gene": gene_symbol,
120
+ "cell_line": entry.get(
121
+ "cell_line_name", ""),
122
+ "depmap_id": entry.get(
123
+ "depmap_id", ""),
124
+ "dependency_score": entry.get(
125
+ "dependency", 0),
126
+ "dataset": dataset,
127
+ })
128
+
129
+ df = pd.DataFrame(rows)
130
+ if not df.empty:
131
+ df = df.sort_values("dependency_score")
132
+ print(f"DepMap dependency: {gene_symbol} "
133
+ f"→ {len(df)} cell lines")
134
+ return df
135
+ ```
136
+
137
+ ## 3. 薬剤感受性データ
138
+
139
+ ```python
140
+ def depmap_drug_sensitivity(compound_name=None,
141
+ limit=100):
142
+ """
143
+ DepMap — 薬剤感受性データ取得。
144
+
145
+ Parameters:
146
+ compound_name: str — 化合物名フィルタ
147
+ (例: "Paclitaxel")
148
+ limit: int — 最大結果数
149
+ """
150
+ url = f"{DEPMAP_API}/drugs"
151
+ params = {"page_size": limit}
152
+ if compound_name:
153
+ params["name"] = compound_name
154
+
155
+ resp = requests.get(url, params=params, timeout=30)
156
+ resp.raise_for_status()
157
+ data = resp.json()
158
+
159
+ rows = []
160
+ for drug in data.get("data", data
161
+ if isinstance(data, list)
162
+ else []):
163
+ if isinstance(drug, dict):
164
+ rows.append({
165
+ "drug_id": drug.get("drug_id", ""),
166
+ "drug_name": drug.get("drug_name", ""),
167
+ "target": drug.get("target", ""),
168
+ "pathway": drug.get("pathway", ""),
169
+ "n_cell_lines": drug.get(
170
+ "n_cell_lines_tested", 0),
171
+ })
172
+
173
+ df = pd.DataFrame(rows[:limit])
174
+ print(f"DepMap drugs: {len(df)} compounds")
175
+ return df
176
+ ```
177
+
178
+ ## 4. DepMap 統合パイプライン
179
+
180
+ ```python
181
+ def depmap_pipeline(gene_symbol,
182
+ output_dir="results"):
183
+ """
184
+ DepMap 統合パイプライン。
185
+
186
+ Parameters:
187
+ gene_symbol: str — 遺伝子シンボル
188
+ output_dir: str — 出力ディレクトリ
189
+ """
190
+ from pathlib import Path
191
+ output_dir = Path(output_dir)
192
+ output_dir.mkdir(parents=True, exist_ok=True)
193
+
194
+ # 1) 遺伝子依存性
195
+ deps = depmap_gene_dependency(gene_symbol)
196
+ deps.to_csv(output_dir / "depmap_dependency.csv",
197
+ index=False)
198
+
199
+ # 2) 関連薬剤
200
+ drugs = depmap_drug_sensitivity()
201
+ drugs.to_csv(output_dir / "depmap_drugs.csv",
202
+ index=False)
203
+
204
+ # 3) 依存性の高い細胞株
205
+ if not deps.empty:
206
+ top_dependent = deps.head(10)
207
+ top_dependent.to_csv(
208
+ output_dir / "depmap_top_dependent.csv",
209
+ index=False)
210
+
211
+ print(f"DepMap pipeline: {gene_symbol} → {output_dir}")
212
+ return {"dependency": deps, "drugs": drugs}
213
+ ```
214
+
215
+ ---
216
+
217
+ ## ToolUniverse 連携
218
+
219
+ | TU Key | ツール名 | 連携内容 |
220
+ |--------|---------|---------|
221
+ | `depmap` | DepMap | がん細胞株依存性マップ API |
222
+
223
+ ## パイプライン統合
224
+
225
+ ```
226
+ cancer-genomics → depmap-dependencies → precision-oncology
227
+ (がんゲノム) (DepMap Portal) (精密腫瘍学)
228
+ │ │ ↓
229
+ expression-analysis ──────┘ drug-target-profiling
230
+ (発現リスト) (標的プロファイリング)
231
+ ```
232
+
233
+ ## パイプライン出力
234
+
235
+ | ファイル | 説明 | 次スキル |
236
+ |---------|------|---------|
237
+ | `results/depmap_dependency.csv` | 依存性スコア | → cancer-genomics |
238
+ | `results/depmap_drugs.csv` | 薬剤感受性 | → drug-target-profiling |
239
+ | `results/depmap_top_dependent.csv` | 依存細胞株 | → precision-oncology |
@@ -5,6 +5,10 @@ description: |
5
5
  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・
6
6
  疫学的特性評価を支援。
7
7
  「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。
8
+ tu_tools:
9
+ - key: disgenet
10
+ name: DisGeNET
11
+ description: 疾患-遺伝子関連スコア (GDA) データベース
8
12
  ---
9
13
 
10
14
  # Scientific Disease Research
@@ -5,6 +5,10 @@ description: |
5
5
  を活用したドラッグターゲットインテリジェンス。ドラッガビリティ評価、安全性プロファイリング、
6
6
  ターゲット-疾患アソシエーション、競合パイプライン分析を統合的に実行。
7
7
  「ターゲット評価して」「druggability 分析して」「標的タンパク質を調べて」で発火。
8
+ tu_tools:
9
+ - key: dgidb
10
+ name: DGIdb
11
+ description: 薬物-遺伝子相互作用データベース
8
12
  ---
9
13
 
10
14
  # Scientific Drug Target Profiling