dilirank

Name: dilirank
Author: QSong-github

132stars4forks

How to install dilirank?

qsong-github/drugclaw/dilirank

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

Installs into the current project.

Summary

Query the DILIrank/FDA Liver Toxicity Knowledge Base (LTKB). Use whenever the user asks about drug-induced liver injury (DILI) risk, hepatotoxicity classification, or wants to look up any drug (by name, LTKB ID, or DILIst ID) in the DILIrank or DILIst datasets.

Files · 1

View on GitHub

SKILL.md

1	# LTKB Query Skill
2
3	Search FDA LTKB records (DILIrank 2.0 + DILIst) by any entity. Auto-detects type by pattern:
4
5	\| Input Pattern \| Detected As \| Searched In \|
6	\|---\|---\|---\|
7	\| `LT00040` \| LTKB ID \| DILIrank only \|
8	\| `2` (digits) \| DILIst ID \| DILIst only \|
9	\| anything else \| drug name \| both datasets (substring) \|
10
11	## Datasets
12
13	DILIrank 2.0 — 1,036 FDA-approved drugs ranked by DILI concern:
14
15	\| vDILI-Concern \| Meaning \|
16	\|---\|---\|
17	\| vMOST-DILI-concern \| Strong evidence of causing DILI \|
18	\| vLess-DILI-concern \| Some evidence of causing DILI \|
19	\| vNo-DILI-concern \| No credible evidence \|
20	\| vAmbiguous-DILI-concern \| Conflicting/insufficient evidence \|
21
22	Columns: `LTKBID`, `CompoundName`, `SeverityClass`, `LabelSection`, `vDILI-Concern`, `Comment`
23
24	DILIst — 1,279 drugs classified by DILI severity:
25
26	\| Classification \| Meaning \|
27	\|---\|---\|
28	\| 1 \| DILI-positive \|
29	\| 0 \| DILI-negative \|
30
31	Columns: `DILIST_ID`, `CompoundName`, `DILIst Classification`, `Routs of Administration`
32
33	## API
34
35	\| Function \| Input \| Returns \|
36	\|---\|---\|---\|
37	\| `load_all(rank_path, list_path)` \| Excel paths \| `{"dilirank": [...], "dilist": [...]}` \|
38	\| `search(data, entity)` \| data dict + entity string \| `{"entity", "type", "dilirank": [], "dilist": []}` \|
39	\| `search_batch(data, entities)` \| data dict + list of strings \| `{entity: search_result}` \|
40	\| `summarize(result, entity)` \| search result + label \| compact text \|
41	\| `to_json(result)` \| search result \| JSON string \|
42
43	## Usage
44
45	See `if __name__ == "__main__"` block in `48_LTKB.py` for runnable examples covering: drug name, LTKB ID, DILIst ID, batch search, and JSON output.
46
47	## Data
48
49	- Source: FDA LTKB — <https://www.fda.gov/science-research/bioinformatics-tools/liver-toxicity-knowledge-base-ltkb>
50	- Files: `Drug Induced Liver Injury Rank (DILIrank 2.0) Dataset FDA.xlsx`, `DILIst Supplementary Table.xlsx`
51	- Path: `DATA_DIR` variable in `48_LTKB.py`

People who liked this also viewed

6 picks

Type

dilirank

132stars4forks

View on GitHub

How to install dilirank?

qsong-github/drugclaw/dilirank

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# LTKB Query Skill
2
3	Search FDA LTKB records (DILIrank 2.0 + DILIst) by any entity. Auto-detects type by pattern:
4
5	\| Input Pattern \| Detected As \| Searched In \|
6	\|---\|---\|---\|
7	\| `LT00040` \| LTKB ID \| DILIrank only \|
8	\| `2` (digits) \| DILIst ID \| DILIst only \|
9	\| anything else \| drug name \| both datasets (substring) \|
10
11	## Datasets
12
13	DILIrank 2.0 — 1,036 FDA-approved drugs ranked by DILI concern:
14
15	\| vDILI-Concern \| Meaning \|
16	\|---\|---\|
17	\| vMOST-DILI-concern \| Strong evidence of causing DILI \|
18	\| vLess-DILI-concern \| Some evidence of causing DILI \|
19	\| vNo-DILI-concern \| No credible evidence \|
20	\| vAmbiguous-DILI-concern \| Conflicting/insufficient evidence \|
21
22	Columns: `LTKBID`, `CompoundName`, `SeverityClass`, `LabelSection`, `vDILI-Concern`, `Comment`
23
24	DILIst — 1,279 drugs classified by DILI severity:
25
26	\| Classification \| Meaning \|
27	\|---\|---\|
28	\| 1 \| DILI-positive \|
29	\| 0 \| DILI-negative \|
30
31	Columns: `DILIST_ID`, `CompoundName`, `DILIst Classification`, `Routs of Administration`
32
33	## API
34
35	\| Function \| Input \| Returns \|
36	\|---\|---\|---\|
37	\| `load_all(rank_path, list_path)` \| Excel paths \| `{"dilirank": [...], "dilist": [...]}` \|
38	\| `search(data, entity)` \| data dict + entity string \| `{"entity", "type", "dilirank": [], "dilist": []}` \|
39	\| `search_batch(data, entities)` \| data dict + list of strings \| `{entity: search_result}` \|
40	\| `summarize(result, entity)` \| search result + label \| compact text \|
41	\| `to_json(result)` \| search result \| JSON string \|
42
43	## Usage
44
45	See `if __name__ == "__main__"` block in `48_LTKB.py` for runnable examples covering: drug name, LTKB ID, DILIst ID, batch search, and JSON output.
46
47	## Data
48
49	- Source: FDA LTKB — <https://www.fda.gov/science-research/bioinformatics-tools/liver-toxicity-knowledge-base-ltkb>
50	- Files: `Drug Induced Liver Injury Rank (DILIrank 2.0) Dataset FDA.xlsx`, `DILIst Supplementary Table.xlsx`
51	- Path: `DATA_DIR` variable in `48_LTKB.py`

People who liked this also viewed

6 picks

Type