nsides
starsforks
How to install nsides?
qsong-github/drugclaw/nsides
$npx -y skills add QSong-github/DrugClaw --skill nsidesQuery the nSIDES drug side effect databases (OnSIDES, OffSIDES, KidSIDES). Use whenever the user asks about drug adverse reactions, side effects, off-label safety signals, or pediatric drug safety for a given drug name.
SKILL.md
| 1 | # nSIDES Query Skill |
| 2 | |
| 3 | Search drug adverse reactions across three complementary nSIDES sources by drug name. |
| 4 | |
| 5 | | Source | Content | Method | Scale | |
| 6 | |---|---|---|---| |
| 7 | | **OnSIDES** v3.1.0 | Label-extracted ADEs (US/EU/UK/JP) | PubMedBERT NLP on product labels | 1,955 ingredients, 5.5M drug-ADE pairs | |
| 8 | | **OffSIDES** | Off-label side effects | Propensity-score matching on FAERS | 3,300+ drugs | |
| 9 | | **KidSIDES** | Pediatric safety signals by developmental phase | Disproportionality analysis on FAERS | Age-stratified ADE signals | |
| 10 | |
| 11 | ## Entity Detection |
| 12 | |
| 13 | | Input | Routing | |
| 14 | |---|---| |
| 15 | | any free text | substring match on drug / ingredient name across all three sources | |
| 16 | |
| 17 | No ID-based routing — all queries are natural-language drug names. |
| 18 | |
| 19 | ## API |
| 20 | |
| 21 | | Function | Input | Returns | |
| 22 | |---|---|---| |
| 23 | | `search(entity, limit)` | drug name string | `dict` with keys: `entity`, `onsides`, `offsides`, `kidsides` | |
| 24 | | `search_batch(entities, limit)` | list of drug names | `list[dict]` | |
| 25 | | `search_onsides(drug_name, limit)` | drug name | `list[dict]` — ingredient, effect, meddra_id, source, label_count | |
| 26 | | `search_offsides(drug_name, limit)` | drug name | `list[dict]` — drug, condition, PRR, A/B/C/D | |
| 27 | | `search_kidsides(drug_name, limit)` | drug name | `list[dict]` — drug, event, nichd_phase, gam_score, ror | |
| 28 | | `summarize(result)` | single `search()` output | compact text | |
| 29 | | `to_json(result)` | single `search()` output | JSON string | |
| 30 | |
| 31 | ## Output Fields |
| 32 | |
| 33 | ### OnSIDES row |
| 34 | - `ingredient` — RxNorm ingredient name |
| 35 | - `effect` — MedDRA adverse effect term |
| 36 | - `meddra_id` — MedDRA concept ID |
| 37 | - `source` — label origin country (US / EU / UK / JP) |
| 38 | - `label_count` — number of labels reporting this ADE |
| 39 | |
| 40 | ### OffSIDES row |
| 41 | - `drug` — RxNorm drug name |
| 42 | - `condition` — MedDRA side effect name |
| 43 | - `PRR` — proportional reporting ratio (>1 = signal) |
| 44 | - `A/B/C/D` — 2×2 contingency counts |
| 45 | - `mean_reporting_frequency` — proportion of drug reports with this effect |
| 46 | |
| 47 | ### KidSIDES row |
| 48 | - `drug` — drug concept name |
| 49 | - `event` — adverse event name |
| 50 | - `nichd_phase` — NICHD developmental phase (e.g. "Neonatal", "Infancy", "Adolescence") |
| 51 | - `gam_score` — GAM model score |
| 52 | - `ror` / `ror_lower` / `ror_upper` — reporting odds ratio with 95% CI |
| 53 | |
| 54 | ## Usage |
| 55 | |
| 56 | See `if __name__ == "__main__"` block in `15_nSIDES.py` for runnable examples: |
| 57 | single-drug query, batch query, text summary, and JSON output. |
| 58 | |
| 59 | ## Data |
| 60 | |
| 61 | | File | Location | Size | |
| 62 | |---|---|---| |
| 63 | | `onsides.db` | `DATA_DIR/onsides.db` | SQLite, from OnSIDES v3.1.0 release | |
| 64 | | `OFFSIDES.csv.gz` | `DATA_DIR/OFFSIDES.csv.gz` | gzipped CSV | |
| 65 | | `ade_nichd.csv.gz` | `DATA_DIR/ade_nichd.csv.gz` | gzipped CSV (172 MB) | |
| 66 | | `drug.csv.gz` | `DATA_DIR/drug.csv.gz` | KidSIDES drug dictionary | |
| 67 | | `event.csv.gz` | `DATA_DIR/event.csv.gz` | KidSIDES event dictionary | |
| 68 | | `dictionary.csv.gz` | `DATA_DIR/dictionary.csv.gz` | NICHD phase dictionary | |
| 69 | |
| 70 | `DATA_DIR` default: `resources_metadata/adr/nSIDES` |
| 71 | |
| 72 | ## Citations |
| 73 | |
| 74 | - **OnSIDES**: Tanaka Y et al. OnSIDES database: Extracting adverse drug events from drug labels using NLP models. *Med*. 2025;100642. doi:10.1016/j.medj.2025.100642 |
| 75 | - **OffSIDES / TwoSIDES**: Tatonetti NP et al. Data-driven prediction of drug effects and interactions. *Sci Transl Med*. 2012;4(125):125ra31. doi:10.1126/scitranslmed.3003377 |
| 76 | - **KidSIDES**: Giangreco NP, Tatonetti NP. A database of pediatric drug effects to evaluate ontogenic mechanisms. *Med*. 2022. |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
