ttd

Name: ttd
Author: QSong-github

132stars4forks

How to install ttd?

qsong-github/drugclaw/ttd

$npx -y skills add QSong-github/DrugClaw --skill ttd

Installs into the current project.

Summary

Query the Therapeutic Target Database (TTD) for drug-target-disease interaction data. Use this skill when the user asks about therapeutic targets, drugs, diseases, or their relationships — including target-drug mappings, clinical status of drugs, disease indications, UniProt/gene

Files · 1

View on GitHub

SKILL.md

1	# TTD — Therapeutic Target Database
2
3	Source: https://ttd.idrblab.cn/
4	Paper: https://academic.oup.com/nar/article/52/D1/D1465/7275004
5	Data dir: `resources_metadata/dti/TTD`
6
7	## Data files (4 required)
8
9	\| File \| Content \|
10	\|------\|---------\|
11	\| `P1-01-TTD_target_download.txt` \| Target info: name, UniProt, gene, type, function, disease indication, pathway \|
12	\| `P2-01-TTD_target_drug.txt` \| Target ↔ Drug links with clinical status (Approved / Phase I–III / Experimental) \|
13	\| `P1-06-Target_disease.txt` \| Target ↔ Disease associations \|
14	\| `P1-07-Drug_disease.txt` \| Drug ↔ Disease associations \|
15
16	File formats:
17	- `P1-01`, `P2-01` — block format: blank-line separated records, each line `<ID>\t<KEY>\t<VALUE>`
18	- `P1-06`, `P1-07` — TSV with header row
19
20	---
21
22	## Query API
23
24	### `query(entities, entity_type="auto", data_dir=DATA_DIR)`
25
26	Returns a list of dicts, one per queried entity.
27
28	\| Parameter \| Type \| Description \|
29	\|-----------\|------\|-------------\|
30	\| `entities` \| `str` or `list[str]` \| One or more entity names / IDs \|
31	\| `entity_type` \| `"auto"` / `"target"` / `"drug"` / `"disease"` \| Restrict search; `"auto"` tries target → drug → disease \|
32	\| `data_dir` \| `str` \| Path to TTD data directory \|
33
34	### `query_json(entities, ...)` → `str`
35
36	Same as `query()` but returns a JSON string. Use for LLM consumption.
37
38	---
39
40	## Input formats accepted
41
42	\| Input \| Examples \|
43	\|-------\|---------\|
44	\| Gene / protein name \| `"EGFR"`, `"TP53"`, `"BCR-ABL"` \|
45	\| Drug name \| `"Imatinib"`, `"Gefitinib"`, `"Osimertinib"` \|
46	\| Disease name \| `"Lung cancer"`, `"Diabetes mellitus"` (partial match supported) \|
47	\| TTD Target ID \| `"TTDTARGET00001"` \|
48	\| TTD Drug ID \| `"D0Y4GH"` \|
49
50	Matching is case-insensitive; disease names support partial matching.
51
52	---
53
54	## Output structure
55
56	### Target result
57	```json
58	{
59	"query": "EGFR",
60	"entity_type": "target",
61	"ttd_id": "TTDTARGET00001",
62	"name": "Epidermal growth factor receptor",
63	"uniprot": "P00533",
64	"gene": "EGFR",
65	"target_type": "Successful target",
66	"function": "Receptor tyrosine kinase...",
67	"disease": "Non-small-cell lung cancer [ICD-11: 2C25]",
68	"pathway": "EGFR signaling pathway",
69	"drugs": [
70	{"drug_id": "D0Y4GH", "drug_name": "Gefitinib", "clinical_status": "Approved"},
71	{"drug_id": "D08VGC", "drug_name": "Erlotinib", "clinical_status": "Approved"}
72	]
73	}
74	```
75
76	### Drug result
77	```json
78	{
79	"query": "Imatinib",
80	"entity_type": "drug",
81	"drug_id": "D0IQX1",
82	"drug_name": "Imatinib",
83	"targets": [
84	{"ttd_target_id": "TTDTARGET00002", "target_name": "BCR-ABL",
85	"clinical_status": "Approved", "drug_id": "D0IQX1"}
86	],
87	"diseases": ["Chronic myelogenous leukemia", "Gastrointestinal stromal tumor"]
88	}
89	```
90
91	### Disease result
92	```json
93	{
94	"query": "Lung cancer",
95	"entity_type": "disease",
96	"disease_name": "non-small-cell lung cancer",
97	"targets": [
98	{"ttd_target_id": "TTDTARGET00001", "target_name": "EGFR"}
99	],
100	"drugs": ["Gefitinib", "Osimertinib", "Erlotinib"]
101	}
102	```
103
104	### Not found
105	```json
106	{"query": "XYZ123", "entity_type": "not_found", "message": "No match found in TTD."}
107	```
108
109	---
110
111	## Usage examples
112
113	```python
114	from 17_TTD import query, query_json
115
116	# Single entity
117	results = query("EGFR")
118
119	# Multiple entities (mixed types — auto-detected)
120	results = query(["EGFR", "Imatinib", "Lung cancer"])
121
122	# Restrict to drug search only
123	results = query(["Gefitinib", "Osimertinib"], entity_type="drug")
124
125	# JSON string output (for LLM)
126	print(query_json("TP53"))
127	```
128
129	CLI (demo runs with EGFR / Imatinib / Lung cancer if no args):
130	```bash
131	python 17_TTD.py EGFR Imatinib "Lung cancer"
132	python 17_TTD.py TTDTARGET00001
133	```
134
135	---
136
137	## Notes
138
139	- `entity_type="auto"` stops at the first match type per entity (target → drug → disease). Use explicit type to resolve ambiguity.
140	- `drugs` in target results lists all TTD-linked drugs; filter `clinical_status == "Approved"` for marketed drugs.
141	- Disease partial matching — `"lung cancer"` will match `"non-small-cell lung cancer"`. The first candidate is returned; use `entity_type="disease"` with a more specific name if needed.
142	- Multi-value fields (e.g. multiple pathways for one target) are returned as lists.

People who liked this also viewed

6 picks

Type

ttd

132stars4forks

View on GitHub

How to install ttd?

qsong-github/drugclaw/ttd

$npx -y skills add QSong-github/DrugClaw --skill ttd

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# TTD — Therapeutic Target Database
2
3	Source: https://ttd.idrblab.cn/
4	Paper: https://academic.oup.com/nar/article/52/D1/D1465/7275004
5	Data dir: `resources_metadata/dti/TTD`
6
7	## Data files (4 required)
8
9	\| File \| Content \|
10	\|------\|---------\|
11	\| `P1-01-TTD_target_download.txt` \| Target info: name, UniProt, gene, type, function, disease indication, pathway \|
12	\| `P2-01-TTD_target_drug.txt` \| Target ↔ Drug links with clinical status (Approved / Phase I–III / Experimental) \|
13	\| `P1-06-Target_disease.txt` \| Target ↔ Disease associations \|
14	\| `P1-07-Drug_disease.txt` \| Drug ↔ Disease associations \|
15
16	File formats:
17	- `P1-01`, `P2-01` — block format: blank-line separated records, each line `<ID>\t<KEY>\t<VALUE>`
18	- `P1-06`, `P1-07` — TSV with header row
19
20	---
21
22	## Query API
23
24	### `query(entities, entity_type="auto", data_dir=DATA_DIR)`
25
26	Returns a list of dicts, one per queried entity.
27
28	\| Parameter \| Type \| Description \|
29	\|-----------\|------\|-------------\|
30	\| `entities` \| `str` or `list[str]` \| One or more entity names / IDs \|
31	\| `entity_type` \| `"auto"` / `"target"` / `"drug"` / `"disease"` \| Restrict search; `"auto"` tries target → drug → disease \|
32	\| `data_dir` \| `str` \| Path to TTD data directory \|
33
34	### `query_json(entities, ...)` → `str`
35
36	Same as `query()` but returns a JSON string. Use for LLM consumption.
37
38	---
39
40	## Input formats accepted
41
42	\| Input \| Examples \|
43	\|-------\|---------\|
44	\| Gene / protein name \| `"EGFR"`, `"TP53"`, `"BCR-ABL"` \|
45	\| Drug name \| `"Imatinib"`, `"Gefitinib"`, `"Osimertinib"` \|
46	\| Disease name \| `"Lung cancer"`, `"Diabetes mellitus"` (partial match supported) \|
47	\| TTD Target ID \| `"TTDTARGET00001"` \|
48	\| TTD Drug ID \| `"D0Y4GH"` \|
49
50	Matching is case-insensitive; disease names support partial matching.
51
52	---
53
54	## Output structure
55
56	### Target result
57	```json
58	{
59	"query": "EGFR",
60	"entity_type": "target",
61	"ttd_id": "TTDTARGET00001",
62	"name": "Epidermal growth factor receptor",
63	"uniprot": "P00533",
64	"gene": "EGFR",
65	"target_type": "Successful target",
66	"function": "Receptor tyrosine kinase...",
67	"disease": "Non-small-cell lung cancer [ICD-11: 2C25]",
68	"pathway": "EGFR signaling pathway",
69	"drugs": [
70	{"drug_id": "D0Y4GH", "drug_name": "Gefitinib", "clinical_status": "Approved"},
71	{"drug_id": "D08VGC", "drug_name": "Erlotinib", "clinical_status": "Approved"}
72	]
73	}
74	```
75
76	### Drug result
77	```json
78	{
79	"query": "Imatinib",
80	"entity_type": "drug",
81	"drug_id": "D0IQX1",
82	"drug_name": "Imatinib",
83	"targets": [
84	{"ttd_target_id": "TTDTARGET00002", "target_name": "BCR-ABL",
85	"clinical_status": "Approved", "drug_id": "D0IQX1"}
86	],
87	"diseases": ["Chronic myelogenous leukemia", "Gastrointestinal stromal tumor"]
88	}
89	```
90
91	### Disease result
92	```json
93	{
94	"query": "Lung cancer",
95	"entity_type": "disease",
96	"disease_name": "non-small-cell lung cancer",
97	"targets": [
98	{"ttd_target_id": "TTDTARGET00001", "target_name": "EGFR"}
99	],
100	"drugs": ["Gefitinib", "Osimertinib", "Erlotinib"]
101	}
102	```
103
104	### Not found
105	```json
106	{"query": "XYZ123", "entity_type": "not_found", "message": "No match found in TTD."}
107	```
108
109	---
110
111	## Usage examples
112
113	```python
114	from 17_TTD import query, query_json
115
116	# Single entity
117	results = query("EGFR")
118
119	# Multiple entities (mixed types — auto-detected)
120	results = query(["EGFR", "Imatinib", "Lung cancer"])
121
122	# Restrict to drug search only
123	results = query(["Gefitinib", "Osimertinib"], entity_type="drug")
124
125	# JSON string output (for LLM)
126	print(query_json("TP53"))
127	```
128
129	CLI (demo runs with EGFR / Imatinib / Lung cancer if no args):
130	```bash
131	python 17_TTD.py EGFR Imatinib "Lung cancer"
132	python 17_TTD.py TTDTARGET00001
133	```
134
135	---
136
137	## Notes
138
139	- `entity_type="auto"` stops at the first match type per entity (target → drug → disease). Use explicit type to resolve ambiguity.
140	- `drugs` in target results lists all TTD-linked drugs; filter `clinical_status == "Approved"` for marketed drugs.
141	- Disease partial matching — `"lung cancer"` will match `"non-small-cell lung cancer"`. The first candidate is returned; use `entity_type="disease"` with a more specific name if needed.
142	- Multi-value fields (e.g. multiple pathways for one target) are returned as lists.

People who liked this also viewed

6 picks

Type