Pharmacovigilance Safety Analyzer

Systematic drug safety analysis using FAERS adverse event data, FDA labeling, PharmGKB pharmacogenomics, and clinical trial safety signals.

KEY PRINCIPLES:

Report-first approach - Create report file FIRST, update progressively
Signal quantification - Use disproportionality measures (PRR, ROR)
Severity stratification - Prioritize serious/fatal events
Multi-source triangulation - FAERS, labels, trials, literature
Pharmacogenomic context - Include genetic risk factors
Actionable output - Risk-benefit summary with recommendations
English-first queries - Always use English drug names in tool calls

When to Use

Apply when user asks:

"What are the safety concerns for [drug]?"
"What adverse events are associated with [drug]?"
"Is [drug] safe? What are the risks?"
"Compare safety profiles of [drug A] vs [drug B]"
"Pharmacovigilance analysis for [drug]"

Critical Workflow Requirements

Report-First Approach (MANDATORY)

Create [DRUG]_safety_report.md FIRST with all section headers and [Researching...] placeholders
Progressively update as data is gathered
Output separate data files: [DRUG]_adverse_events.csv and [DRUG]_pharmacogenomics.csv

Citation Requirements (MANDATORY)

Every safety signal MUST include source tool, data period, PRR, case counts, and serious/fatal breakdown.

Tool Parameter Reference (CRITICAL)

Tool	WRONG Parameter	CORRECT Parameter
`FAERS_count_reactions_by_drug_event`	`drug`	`drug_name`
`DailyMed_search_spls`	`name`	`drug_name`
`PharmGKB_search_drug`	`drug`	`query`
`OpenFDA_get_drug_events`	`drug_name`	`search`

Workflow Overview

Phase 1: Drug Disambiguation
  -> Resolve drug name, get identifiers (ChEMBL, DrugBank)

Phase 2: Adverse Event Profiling (FAERS)
  -> Query FAERS, calculate PRR, stratify by seriousness

Phase 3: Label Warning Extraction
  -> DailyMed boxed warnings, contraindications, precautions

Phase 4: Pharmacogenomic Risk
  -> PharmGKB clinical annotations, high-risk genotypes

Phase 5: Clinical Trial Safety
  -> ClinicalTrials.gov Phase 3/4 safety data

Phase 5.5: Pathway & Mechanism Context
  -> KEGG drug metabolism, target pathway analysis

Phase 5.6: Literature Intelligence
  -> PubMed, BioRxiv/MedRxiv, OpenAlex citation analysis

Phase 6: Signal Prioritization
  -> Rank by PRR x severity x frequency

Phase 7: Report Synthesis

Phase 1: Drug Disambiguation

Search DailyMed via DailyMed_search_spls(drug_name=...) for NDC, SPL setid, generic name
Search ChEMBL via ChEMBL_search_drugs(query=...) for molecule ID, max phase
Document: generic name, brand names, drug class, mechanism, approval date

Phase 2: Adverse Event Profiling (FAERS)

Query FAERS_count_reactions_by_drug_event(drug_name=..., limit=50) for top events
For each event, get detailed breakdown (serious, fatal, hospitalization counts)
Calculate PRR: (A/B) / (C/D) where A=drug+event, B=drug+any, C=event+any_other, D=total_other
Apply signal thresholds: PRR > 2.0 (signal), > 3.0 (strong signal), case count >= 3

Severity classification:

Fatal (highest priority), Life-threatening, Hospitalization, Disability, Other serious, Non-serious

See SIGNAL_DETECTION.md for detailed disproportionality formulas and example output tables.

Phase 3: Label Warning Extraction

Get label via DailyMed_get_spl_by_set_id(setid=...)
Extract: boxed warnings, contraindications, warnings/precautions, drug interactions
Categorize severity: Boxed Warning > Contraindication > Warning > Precaution

Phase 4: Pharmacogenomic Risk

Search PharmGKB_search_drug(query=...) for clinical annotations
Document actionable variants with evidence levels (1A/1B/2A/2B/3)
Note CPIC/DPWG guideline status

PGx Evidence Levels:

Level	Description	Action
1A	CPIC/DPWG guideline, implementable	Follow guideline
1B	CPIC/DPWG guideline, annotation	Consider testing
2A	VIP annotation, moderate evidence	May inform
2B	VIP annotation, weaker evidence	Research
3	Low-level annotation	Not actionable

Phase 5: Clinical Trial Safety

Search search_clinical_trials(intervention=..., phase="Phase 3", status="Completed")
Extract serious AE rates, discontinuation rates, deaths
Compare drug vs placebo rates

Phase 5.5: Pathway & Mechanism Context

Query KEGG for drug metabolism pathways
Analyze target pathways for mechanistic basis of AEs
Document pathway-AE relationships

Phase 5.6: Literature Intelligence

PubMed: PubMed_search_articles(query='"[drug]" AND (safety OR adverse OR toxicity)')
BioRxiv/MedRxiv: Search for recent preprints (flag as not peer-reviewed)
OpenAlex: Citation analysis for key safety papers

Phase 6: Signal Prioritization

Signal Score = PRR x Severity_Weight x log10(Case_Count + 1)

Severity weights: Fatal=10, Life-threatening=8, Hospitalization=5, Disability=5, Other serious=3, Non-serious=1

Categorize signals:

Critical (immediate attention): High PRR + fatal outcomes
Moderate (monitor): Moderate PRR + serious outcomes
Known/Expected (manage clinically): Low PRR, in label

Output Report

Save as [DRUG]_safety_report.md. See REPORT_TEMPLATES.md for the full report structure and example outputs.

Evidence Grading

Tier	Criteria	Example
T1	PRR >10, fatal outcomes, boxed warning	Lactic acidosis
T2	PRR 3-10, serious outcomes	Hepatotoxicity
T3	PRR 2-3, moderate concern	Hypoglycemia
T4	PRR <2, known/expected	GI side effects

Fallback Chains

Primary Tool	Fallback 1	Fallback 2
`FAERS_count_reactions_by_drug_event`	`OpenFDA_get_drug_events`	Literature search
`DailyMed_get_spl_by_set_id`	`FDA_drug_label_search`	DailyMed website
`PharmGKB_search_drug`	`CPIC_get_guidelines`	Literature search
`search_clinical_trials`	`ClinicalTrials.gov` API	PubMed for trial results

Completeness Checklist

See CHECKLIST.md for the full phase-by-phase verification checklist.

References

FAERS: https://www.fda.gov/drugs/questions-and-answers-fdas-adverse-event-reporting-system-faers
DailyMed: https://dailymed.nlm.nih.gov
PharmGKB: https://www.pharmgkb.org
ClinicalTrials.gov: https://clinicaltrials.gov
OpenFDA: https://open.fda.gov
KEGG Drug: https://www.genome.jp/kegg/drug
Tool documentation: TOOLS_REFERENCE.md

tooluniverse-pharmacovigilance