drugrepobank

Name: drugrepobank
Author: QSong-github

132stars4forks

How to install drugrepobank?

qsong-github/drugclaw/drugrepobank

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

Installs into the current project.

Summary

Query the DrugRepoBank drug repurposing evidence database. Use whenever the user asks about repurposing candidates, drug–disease–target repurposing evidence, or wants to look up any entity (drug name, DrugBank ID, ChEMBL ID, PubChem CID, TTD target ID, UniProt ID, disease name) i

Files · 1

View on GitHub

SKILL.md

1	# DrugRepoBank Query Skill
2
3	Search four linked tables (Drug, Target, DrugTargetInteraction, Literature)
4	for repurposing evidence. Auto-detects entity type by prefix:
5
6	\| Input Pattern \| Detected As \| Example \|
7	\|---\|---\|---\|
8	\| `DB00945` \| DrugBank ID \| exact on `DrugBank_ID` / `DrugID` \|
9	\| `T47101` \| TTD Target ID \| exact on `TargetID` \|
10	\| `FGFR1_HUMAN` \| UniProt ID \| exact on `UniprotID` \|
11	\| `CHEMBL2103749` \| ChEMBL ID \| exact on `ChEMBL ID` in Drug table \|
12	\| `16129704` (digits) \| PubChem CID \| exact on `PubChem_Compound_ID` / `PubChemID` \|
13	\| anything else \| free text \| substring on drug Name, TargetName, Disease, NewDisease \|
14
15	## API
16
17	\| Function \| Input \| Returns \|
18	\|---\|---\|---\|
19	\| `load_all()` \| — \| `dict` with keys `drug`, `dti`, `lit`, `target` (lists of row-dicts) \|
20	\| `search(tables, entity)` \| tables dict + single entity string \| `dict` with keys `entity`, `entity_type`, `drug`, `target`, `dti`, `literature` \|
21	\| `search_batch(tables, entities)` \| tables dict + list of entity strings \| `dict[str, search_result]` \|
22	\| `summarize(result)` \| single `search()` result \| compact one-line LLM-readable text \|
23	\| `to_json(result)` \| single `search()` result \| JSON string (trimmed heavy fields) \|
24
25	## Usage
26
27	See `if __name__ == "__main__"` block in `42_DrugRepoBank.py` for runnable
28	examples covering: drug name, DrugBank ID, TTD target ID, UniProt ID, ChEMBL
29	ID, disease free-text, batch search, and JSON output.
30
31	## Data
32
33	Four CSV tables in `DATA_DIR`:
34
35	\| File \| Key Columns \| Description \|
36	\|---\|---\|---\|
37	\| `Drug.csv` \| DrugBank_ID, Name, Drug Groups, PubChem_Compound_ID, ChEMBL ID, SMILES \| Drug identifiers & structures \|
38	\| `DrugTargetInteraction.csv` \| UniprotID, PubchemID, TargetID, DrugID, Highest_status, MOA \| Drug–target links with mechanism of action \|
39	\| `Literature.csv` \| DrugName, DrugID, Target, Disease, NewDisease, Evidence, Insilico, Invitro, Invivo, Clinicaltrial, PMID \| Repurposing evidence & literature references \|
40	\| `Targets.csv` \| TargetID, UniprotID, TargetName, TargetGeneName, TargetType, Function \| Target annotations & pathway memberships \|
41
42	- Path: `DATA_DIR` variable in `42_DrugRepoBank.py`
43	(`resources_metadata/drug_repurposing/DrugRepoBank`)
44	- Source: https://awi.cuhk.edu.cn/DrugRepoBank/php/index.php
45	- Paper: Huang et al., Database 2024, baae051. DOI:10.1093/database/baae051

People who liked this also viewed

6 picks

Type

drugrepobank

132stars4forks

View on GitHub

How to install drugrepobank?

qsong-github/drugclaw/drugrepobank

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DrugRepoBank Query Skill
2
3	Search four linked tables (Drug, Target, DrugTargetInteraction, Literature)
4	for repurposing evidence. Auto-detects entity type by prefix:
5
6	\| Input Pattern \| Detected As \| Example \|
7	\|---\|---\|---\|
8	\| `DB00945` \| DrugBank ID \| exact on `DrugBank_ID` / `DrugID` \|
9	\| `T47101` \| TTD Target ID \| exact on `TargetID` \|
10	\| `FGFR1_HUMAN` \| UniProt ID \| exact on `UniprotID` \|
11	\| `CHEMBL2103749` \| ChEMBL ID \| exact on `ChEMBL ID` in Drug table \|
12	\| `16129704` (digits) \| PubChem CID \| exact on `PubChem_Compound_ID` / `PubChemID` \|
13	\| anything else \| free text \| substring on drug Name, TargetName, Disease, NewDisease \|
14
15	## API
16
17	\| Function \| Input \| Returns \|
18	\|---\|---\|---\|
19	\| `load_all()` \| — \| `dict` with keys `drug`, `dti`, `lit`, `target` (lists of row-dicts) \|
20	\| `search(tables, entity)` \| tables dict + single entity string \| `dict` with keys `entity`, `entity_type`, `drug`, `target`, `dti`, `literature` \|
21	\| `search_batch(tables, entities)` \| tables dict + list of entity strings \| `dict[str, search_result]` \|
22	\| `summarize(result)` \| single `search()` result \| compact one-line LLM-readable text \|
23	\| `to_json(result)` \| single `search()` result \| JSON string (trimmed heavy fields) \|
24
25	## Usage
26
27	See `if __name__ == "__main__"` block in `42_DrugRepoBank.py` for runnable
28	examples covering: drug name, DrugBank ID, TTD target ID, UniProt ID, ChEMBL
29	ID, disease free-text, batch search, and JSON output.
30
31	## Data
32
33	Four CSV tables in `DATA_DIR`:
34
35	\| File \| Key Columns \| Description \|
36	\|---\|---\|---\|
37	\| `Drug.csv` \| DrugBank_ID, Name, Drug Groups, PubChem_Compound_ID, ChEMBL ID, SMILES \| Drug identifiers & structures \|
38	\| `DrugTargetInteraction.csv` \| UniprotID, PubchemID, TargetID, DrugID, Highest_status, MOA \| Drug–target links with mechanism of action \|
39	\| `Literature.csv` \| DrugName, DrugID, Target, Disease, NewDisease, Evidence, Insilico, Invitro, Invivo, Clinicaltrial, PMID \| Repurposing evidence & literature references \|
40	\| `Targets.csv` \| TargetID, UniprotID, TargetName, TargetGeneName, TargetType, Function \| Target annotations & pathway memberships \|
41
42	- Path: `DATA_DIR` variable in `42_DrugRepoBank.py`
43	(`resources_metadata/drug_repurposing/DrugRepoBank`)
44	- Source: https://awi.cuhk.edu.cn/DrugRepoBank/php/index.php
45	- Paper: Huang et al., Database 2024, baae051. DOI:10.1093/database/baae051

People who liked this also viewed

6 picks

Type