COMPUTE, DON'T DESCRIBE

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

Adverse Drug Event Signal Detection & Analysis

Automated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making.

KEY PRINCIPLES:

1. Signal quantification first - Every adverse event must have PRR/ROR/IC with confidence intervals
2. Serious events priority - Deaths, hospitalizations, life-threatening events always analyzed first
3. Multi-source triangulation - FAERS + FDA labels + OpenTargets + DrugBank + literature
4. Context-aware assessment - Distinguish drug-specific vs class-wide vs confounding signals
5. Report-first approach - Create report file FIRST, update progressively
6. Evidence grading mandatory - T1 (regulatory/boxed warning) through T4 (computational)
7. English-first queries - Always use English drug names in tool calls, respond in user's language

REASONING STRATEGY — Start Here: Start with the signal: What adverse event was reported more than expected? (PRR >= 2.0, N >= 3, lower CI > 1.0 is the threshold). Then ask three questions in order:

1. Biologically plausible? Given the drug's mechanism of action and targets, does this adverse event make sense? An off-target kinase inhibitor causing cardiac events is plausible; a topical agent causing systemic toxicity needs more scrutiny. LOOK UP DON'T GUESS — use OpenTargets_get_drug_mechanisms_of_action_by_chemblId and drugbank_get_targets_by_drug_name_or_drugbank_id to check targets before asserting plausibility.