repurposing_hub

Name: repurposing_hub
Author: QSong-github

132stars4forks

How to install repurposing_hub?

qsong-github/drugclaw/repurposing_hub

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

Installs into the current project.

Summary

Query the Broad Institute Drug Repurposing Hub (~6,800 compounds). Look up drugs by name, gene target, MOA, disease area, Broad ID, or InChIKey. Returns clinical phase, mechanism of action, targets, disease area, indication, and chemical identifiers.

Files · 1

View on GitHub

SKILL.md

1	# Drug Repurposing Hub Query Skill
2
3	Search the Broad Institute Drug Repurposing Hub by any entity.
4	Auto-detects input type by pattern:
5
6	\| Input Pattern \| Detected As \| Match Logic \|
7	\|---\|---\|---\|
8	\| `BRD-A12345678` \| Broad compound ID \| prefix on `broad_id` \|
9	\| `ABCDEFGHIJKLMN-OPQRSTUVWX-Y` \| InChIKey \| exact on `InChIKey` \|
10	\| `EGFR`, `BRAF`, `TOP1` \| Gene / target \| exact token in `target` (pipe-separated) \|
11	\| anything else \| free text \| substring on `pert_iname`, `moa`, `indication`, `disease_area` \|
12
13	## API
14
15	\| Function \| Input \| Returns \|
16	\|---\|---\|---\|
17	\| `load_drugs(path)` \| drug TSV path \| list[dict] \|
18	\| `load_samples(path)` \| sample TSV path \| list[dict] \|
19	\| `load_merged()` \| — \| list[dict] (drugs + chemical IDs from samples) \|
20	\| `search(entity)` \| single entity string \| list[dict] \|
21	\| `search_batch(entities)` \| list of entity strings \| dict[str, list[dict]] \|
22	\| `summarize(hits, entity)` \| hits + label \| compact LLM-readable text \|
23	\| `to_json(hits)` \| list[dict] \| list[dict] (JSON-serialisable) \|
24
25	## Usage
26
27	See `if __name__ == "__main__"` block in `29_Drug_Repurposing_Hub.py` for
28	runnable examples covering: drug name, gene target, MOA keyword, disease
29	area, batch search, and JSON output.
30
31	```python
32	from importlib.machinery import SourceFileLoader
33	hub = SourceFileLoader("hub", "29_Drug_Repurposing_Hub.py").load_module()
34
35	# Single drug lookup
36	hits = hub.search("imatinib")
37	print(hub.summarize(hits, "imatinib"))
38
39	# Target-based search
40	hits = hub.search("EGFR")
41
42	# Batch
43	results = hub.search_batch(["metformin", "aspirin", "BRAF"])
44	```
45
46	## Data
47
48	- Source: Broad Institute Drug Repurposing Hub (https://repo-hub.broadinstitute.org/repurposing)
49	- Drug file: `repo-drug-annotation-20200324.txt` — tab-delimited, `!`-prefixed comment lines
50	- Columns: `pert_iname`, `clinical_phase`, `moa`, `target`, `disease_area`, `indication`
51	- Sample file: `repo-sample-annotation-20240610.txt` — tab-delimited, `!`-prefixed comment lines
52	- Columns include: `broad_id`, `pert_iname`, `InChIKey`, `pubchem_cid`, `smiles`, `vendor`, `purity`, etc.
53	- Merge: on `pert_iname`; first sample with non-empty `InChIKey` is kept per drug
54	- Path: `DATA_DIR` variable in `29_Drug_Repurposing_Hub.py`
55	- Citation: Corsello SM et al. Nature Medicine 23, 405–408 (2017). doi:10.1038/nm.4306

People who liked this also viewed

6 picks

Type

repurposing_hub

132stars4forks

View on GitHub

How to install repurposing_hub?

qsong-github/drugclaw/repurposing_hub

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Drug Repurposing Hub Query Skill
2
3	Search the Broad Institute Drug Repurposing Hub by any entity.
4	Auto-detects input type by pattern:
5
6	\| Input Pattern \| Detected As \| Match Logic \|
7	\|---\|---\|---\|
8	\| `BRD-A12345678` \| Broad compound ID \| prefix on `broad_id` \|
9	\| `ABCDEFGHIJKLMN-OPQRSTUVWX-Y` \| InChIKey \| exact on `InChIKey` \|
10	\| `EGFR`, `BRAF`, `TOP1` \| Gene / target \| exact token in `target` (pipe-separated) \|
11	\| anything else \| free text \| substring on `pert_iname`, `moa`, `indication`, `disease_area` \|
12
13	## API
14
15	\| Function \| Input \| Returns \|
16	\|---\|---\|---\|
17	\| `load_drugs(path)` \| drug TSV path \| list[dict] \|
18	\| `load_samples(path)` \| sample TSV path \| list[dict] \|
19	\| `load_merged()` \| — \| list[dict] (drugs + chemical IDs from samples) \|
20	\| `search(entity)` \| single entity string \| list[dict] \|
21	\| `search_batch(entities)` \| list of entity strings \| dict[str, list[dict]] \|
22	\| `summarize(hits, entity)` \| hits + label \| compact LLM-readable text \|
23	\| `to_json(hits)` \| list[dict] \| list[dict] (JSON-serialisable) \|
24
25	## Usage
26
27	See `if __name__ == "__main__"` block in `29_Drug_Repurposing_Hub.py` for
28	runnable examples covering: drug name, gene target, MOA keyword, disease
29	area, batch search, and JSON output.
30
31	```python
32	from importlib.machinery import SourceFileLoader
33	hub = SourceFileLoader("hub", "29_Drug_Repurposing_Hub.py").load_module()
34
35	# Single drug lookup
36	hits = hub.search("imatinib")
37	print(hub.summarize(hits, "imatinib"))
38
39	# Target-based search
40	hits = hub.search("EGFR")
41
42	# Batch
43	results = hub.search_batch(["metformin", "aspirin", "BRAF"])
44	```
45
46	## Data
47
48	- Source: Broad Institute Drug Repurposing Hub (https://repo-hub.broadinstitute.org/repurposing)
49	- Drug file: `repo-drug-annotation-20200324.txt` — tab-delimited, `!`-prefixed comment lines
50	- Columns: `pert_iname`, `clinical_phase`, `moa`, `target`, `disease_area`, `indication`
51	- Sample file: `repo-sample-annotation-20240610.txt` — tab-delimited, `!`-prefixed comment lines
52	- Columns include: `broad_id`, `pert_iname`, `InChIKey`, `pubchem_cid`, `smiles`, `vendor`, `purity`, etc.
53	- Merge: on `pert_iname`; first sample with non-empty `InChIKey` is kept per drug
54	- Path: `DATA_DIR` variable in `29_Drug_Repurposing_Hub.py`
55	- Citation: Corsello SM et al. Nature Medicine 23, 405–408 (2017). doi:10.1038/nm.4306

People who liked this also viewed

6 picks

Type