Tooluniverse Drug Drug Interaction

Drug-Drug Interaction Prediction & Risk Assessment

Systematic analysis of drug-drug interactions with evidence-based risk scoring, mechanism identification, and clinical management recommendations.

KEY PRINCIPLES:

1. Report-first approach - Create DDI_risk_report.md FIRST, then populate progressively
2. Bidirectional analysis - Always analyze A→B and B→A interactions (effects may differ)
3. Evidence grading - Grade all DDI claims by evidence quality (★★★ FDA label, ★★☆ clinical study, ★☆☆ theoretical)
4. Risk scoring - Multi-dimensional scoring (0-100) combining mechanism + severity + clinical evidence
5. Patient safety focus - Provide actionable clinical guidance, not just theoretical interactions
6. Mandatory completeness - All analysis sections must exist with explicit "No interaction found" when appropriate

LOCAL PHARMACOLOGY REFERENCE (USE FIRST)

Before querying any external database, consult the local reference script for instant answers on CYP/UGT roles and known critical interactions:

scripts/pharmacology_ref.py   (no external dependencies, runs offline)

# Q927 pattern — valproate + lamotrigine:
python scripts/pharmacology_ref.py --type interaction --drug1 "valproate" --drug2 "lamotrigine"

# What does a drug do to UGT enzymes?
python scripts/pharmacology_ref.py --type ugt_inhibitor --drug "valproate"

# What enzymes metabolise a drug?
python scripts/pharmacology_ref.py --type ugt_substrate --drug "lamotrigine"
python scripts/pharmacology_ref.py --type cyp_substrate --drug "warfarin"

# Which drugs inhibit / induce a specific CYP?
python scripts/pharmacology_ref.py --type cyp_inhibitor --enzyme "CYP3A4"
python scripts/pharmacology_ref.py --type cyp_inducer  --enzyme "CYP2C9"

# Narrow therapeutic index checklist:
python scripts/pharmacology_ref.py --type narrow_ti

# All known interactions for one drug:
python scripts/pharmacology_ref.py --type all_interactions --drug "lamotrigine"

Covered interactions include (severity / mechanism): | Pair | Severity | Key mechanism | |------|----------|---------------| | valproate + lamotrigine | Major | UGT1A4 inhibition → 2× lamotrigine levels + SJS risk | | carbamazepine + lamotrigine | Major | UGT1A4 induction → 50% ↓ lamotrigine | | oral contraceptives + lamotrigine | Major | UGT1A4 induction → 50% ↓ lamotrigine | | valproate + phenytoin | Major | CYP2C9 inhibition + protein displacement | | carbamazepine + valproate | Moderate | Epoxide hydrolase inhibition → toxic metabolite ↑ | | simvastatin + ketoconazole | Contraindicated | CYP3A4 inhibition → rhabdomyolysis | | simvastatin + clarithromycin | Contraindicated | CYP3A4 inhibition → rhabdomyolysis | | rifampin + warfarin | Major | CYP2C9 induction → INR collapse | | amiodarone + warfarin | Major | CYP2C9 inhibition → INR rise | | clopidogrel + omeprazole | Moderate | CYP2C19 inhibition → reduced antiplatelet activation | | quinidine + digoxin | Major | P-gp inhibition → 2× digoxin levels | | lithium + NSAIDs | Major | Reduced renal clearance → lithium toxicity | | fluoxetine + MAOIs | Contraindicated | Serotonin syndrome |

The script also covers UGT2B7 substrates (morphine, zidovudine) inhibited by valproate, UGT1A1 induction by rifampin, and the complete narrow therapeutic index list with monitoring parameters.

LOOK UP, DON'T GUESS

When uncertain about any scientific fact, SEARCH databases first (PubMed, UniProt, ChEMBL, ClinVar, etc.) rather than reasoning from memory. A database-verified answer is always more reliable than a guess.

New Symptom After New Medication: First-Line Reasoning

When a patient develops NEW symptoms after starting a new medication, the FIRST question is: could the new drug be interacting with an existing medication? Specifically check: (1) Does the new drug inhibit metabolism of an existing drug? (2) Does the new drug have additive pharmacodynamic effects?

When to Use This Skill

Apply when users:

• Ask about interactions between 2+ specific drugs
• Need polypharmacy risk assessment (5+ medications)
• Request medication safety review for a patient
• Ask "can I take drug X with drug Y?"
• Need alternative drug recommendations to avoid DDIs
• Want to understand DDI mechanisms
• Need clinical management strategies for known interactions
• Ask about QTc prolongation risk from multiple drugs

Clinical Reasoning Framework

Before querying any database, apply this reasoning framework to predict interactions mechanistically.

The Perpetrator-Victim Model

In every drug interaction, identify two roles:

• PERPETRATOR: the drug causing the change (the inhibitor, inducer, or pharmacodynamic amplifier)
• VICTIM: the drug being affected (the one whose levels or effects change)

For each drug pair, ask these questions in order:

1. Does the perpetrator change how the victim is absorbed, distributed, metabolized, or eliminated? If yes, this is a pharmacokinetic interaction. Determine which enzyme or transporter is involved (CYP450, UGT, P-gp, OATP, etc.).
2. Is the perpetrator an inhibitor or an inducer of that pathway?

• Inhibitor → victim levels go UP → predict increased efficacy or toxicity
• Inducer → victim levels go DOWN → predict reduced efficacy or therapeutic failure

1. What happens clinically when the victim's level changes? Predict the downstream consequence: toxicity from supratherapeutic levels, or treatment failure from subtherapeutic levels.
2. Always check the reverse direction. Analyze B→A as well as A→B. The perpetrator-victim relationship may be asymmetric or bidirectional.

Special case -- Prodrugs: If the victim is a prodrug that requires metabolic activation, inhibiting its activating enzyme reduces efficacy (not toxicity). Inducing its activating enzyme may increase efficacy or toxicity of the active metabolite.

Phase II Metabolism: Glucuronidation Interactions (UGT Enzymes)

Most DDI reasoning focuses on CYP450 (Phase I metabolism), but Phase II conjugation reactions — especially glucuronidation via UGT enzymes — cause some of the most dangerous drug interactions. These are frequently missed because agents default to CYP-centric reasoning.

Core principle: UGT enzymes (UGT1A4, UGT2B7, UGT1A1, etc.) conjugate drugs with glucuronic acid for renal elimination. When a UGT inhibitor is co-administered with a UGT substrate, the substrate accumulates because its primary elimination pathway is blocked.

The valproate + lamotrigine paradigm (IDX 927 pattern):

1. Lamotrigine is primarily metabolized by UGT1A4 glucuronidation (>90% of elimination).
2. Valproate is a potent UGT1A4 inhibitor.
3. Co-administration doubles lamotrigine levels (t1/2 increases from ~25h to ~60h).
4. Clinical consequence: Stevens-Johnson syndrome (SJS) / toxic epidermal necrolysis (TEN) — a life-threatening dermatologic emergency.
5. Mechanism: inhibition of lamotrigine glucuronidation — NOT a CYP interaction.
6. Management: When adding valproate to lamotrigine, HALVE the lamotrigine dose. Titrate slowly.

Other critical UGT interactions:

• Valproate + morphine/zidovudine: Valproate inhibits UGT2B7 → increased morphine/zidovudine levels
• Valproate + phenytoin: Dual mechanism — CYP2C9 inhibition + protein binding displacement → unpredictable phenytoin levels
• Carbamazepine + lamotrigine: Carbamazepine INDUCES UGT1A4 → lamotrigine levels DROP by ~50% (opposite direction from valproate)
• Oral contraceptives + lamotrigine: Ethinylestradiol induces UGT1A4 → lamotrigine levels drop; when OCP stopped (pill-free week), lamotrigine rebounds
• Rifampin + many UGT substrates: Rifampin induces UGT1A1, UGT2B7 → decreased levels of morphine, bilirubin conjugation increased

Reasoning algorithm for UGT interactions:

1. Is the victim drug primarily cleared by glucuronidation? (Check: lamotrigine, morphine, lorazepam, zidovudine, bilirubin)