undefined

undefined

---
**Data Sources for this section:**
- PubChem: `PubChem_get_compound_properties_by_CID` (CID: 4091)
- ChEMBL: `ChEMBL_get_bioactivity_by_chemblid` (CHEMBL1431)
- DGIdb: `DGIdb_get_drug_info` (metformin)
---

Step 1: Create report file with all section headers
        ↓
Step 2: Resolve compound identifiers → Update Section 1
        ↓
Step 3: Query PubChem/ADMET-AI/DailyMed SPL → Update Section 2 (Chemistry)
        ↓
Step 4: Query FDA Label MOA + ChEMBL activities + DGIdb → Update Section 3 (Mechanism & Targets)
        ↓
Step 5: Query ADMET-AI tools → Update Section 4 (ADMET)
        ↓
Step 6: Query ClinicalTrials.gov → Update Section 5 (Clinical Development)
        ↓
Step 7: Query FAERS/DailyMed → Update Section 6 (Safety)
        ↓
Step 8: Query PharmGKB → Update Section 7 (Pharmacogenomics)
        ↓
Step 9: Query DailyMed → Update Section 8 (Regulatory)
        ↓
Step 10: Query PubMed/literature → Update Section 9 (Literature)
        ↓
Step 11: Synthesize findings → Update Executive Summary & Section 10
        ↓
Step 12: Document all sources → Update Section 11 (Data Sources)

undefined

**GOOD** (detailed with sources):
```markdown

---

undefined

Then progressively replace `[Researching...]` with actual findings as you query each tool.

---

1. Get set_id: DailyMed_search_spls(drug_name)
   
2. Batch call for all core sections (or 3-4 calls with 4-5 sections each):
   DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["mechanism_of_action", "pharmacodynamics", ...])
   
3. Extract and populate report sections as you retrieve data

1. PubChem_get_CID_by_compound_name(compound_name)
   └─ Extract: CID, canonical SMILES, formula
   
2. ChEMBL_search_compounds(query=drug_name)
   └─ Extract: ChEMBL ID, pref_name
   
3. DailyMed_search_spls(drug_name)
   └─ Extract: Set ID, NDC codes (if approved)
   
4. PharmGKB_search_drugs(query=drug_name)
   └─ Extract: PharmGKB ID (PA...)

1. PubChem_get_compound_properties_by_CID(cid)
   └─ Extract: MW, formula, XLogP, TPSA, HBD, HBA, rotatable bonds
   
2. ADMETAI_predict_physicochemical_properties(smiles=[smiles])
   └─ Extract: MW, logP, HBD, HBA, Lipinski, QED, stereo_centers, TPSA
   
3. ADMETAI_predict_solubility_lipophilicity_hydration(smiles=[smiles])
   └─ Extract: Solubility_AqSolDB, Lipophilicity_AstraZeneca

4. DailyMed_search_spls(drug_name)
   └─ Extract SPL set_id, then:
   
5. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["chemistry"])
   └─ Extract: Salt forms, polymorphs, molecular formula, structure diagram
   
6. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["description", "inactive_ingredients"])
   └─ Extract: Formulation details, excipients, dosage forms

7. FORMULATION COMPARISON (if multiple formulations exist):
   a. DailyMed_search_spls(drug_name) → identify all formulations (IR, ER, XR, etc.)
   b. For each formulation:
      - DailyMed_parse_clinical_pharmacology(setid) → extract PK parameters
      - Parse: Tmax, Cmax, AUC, half-life
   c. Create comparison table showing bioavailability differences

undefined

undefined

1. DailyMed_search_spls(drug_name) → get set_id
   
2. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["mechanism_of_action", "pharmacodynamics"])
   └─ Extract: Official FDA MOA description [★★★]
   
3. ChEMBL_search_activities(molecule_chembl_id=chembl_id, limit=100)
   └─ Extract: Activity records with target_chembl_id, pChEMBL, standard_type
   └─ Parse unique target_chembl_id values (convert to strings)
   
4. ChEMBL_get_target(target_chembl_id) for each unique target
   └─ Extract: Target name, UniProt ID, organism [★★★]
   
5. DGIdb_get_drug_info(drugs=[drug_name])
   └─ Extract: Target genes, interaction types, sources [★★☆]
   
6. PubChem_get_bioactivity_summary_by_CID(cid)
   └─ Extract: Assay summary, active/inactive counts [★★☆]

undefined

undefined

1. ADMETAI_predict_bioavailability(smiles=[smiles])
   └─ Extract: Bioavailability_Ma, HIA_Hou, PAMPA_NCATS, Caco2_Wang, Pgp_Broccatelli
   
2. ADMETAI_predict_BBB_penetrance(smiles=[smiles])
   └─ Extract: BBB_Martins (0-1 probability)
   
3. ADMETAI_predict_CYP_interactions(smiles=[smiles])
   └─ Extract: CYP1A2, CYP2C9, CYP2C19, CYP2D6, CYP3A4 (inhibitor/substrate)
   
4. ADMETAI_predict_clearance_distribution(smiles=[smiles])
   └─ Extract: Clearance, Half_Life_Obach, VDss_Lombardo, PPBR_AZ
   
5. ADMETAI_predict_toxicity(smiles=[smiles])
   └─ Extract: AMES, hERG, DILI, ClinTox, LD50_Zhu, Carcinogens

6. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["clinical_pharmacology", "pharmacokinetics"])
   └─ Extract: Absorption, distribution, metabolism, excretion from label [★★★]
   
7. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["drug_interactions"])
   └─ Extract: CYP interactions, transporter interactions [★★★]
   
8. PubMed_search_articles(query="[drug] pharmacokinetics", max_results=10)
   └─ Extract: PK parameters from clinical studies [★★☆]

undefined

undefined

1. search_clinical_trials(intervention=drug_name, pageSize=100)
   └─ Extract: Full result set with NCT IDs, phases, statuses, conditions
   
2. COMPUTE PHASE COUNTS from results:
   └─ Count by phase: Phase 1, Phase 2, Phase 3, Phase 4
   └─ Count by status: Completed, Recruiting, Active not recruiting, Terminated
   └─ Group by condition/indication (top 5)
   └─ Generate summary table
   
3. SELECT REPRESENTATIVE TRIALS:
   └─ Top 5 Phase 3 completed trials (by enrollment or recency)
   └─ Top 5 Phase 4 post-marketing trials
   └─ Top 3 recruiting trials
   
4. get_clinical_trial_conditions_and_interventions(nct_ids=[selected_ids])
   └─ Extract: Detailed conditions, interventions, arm groups
   
5. extract_clinical_trial_outcomes(nct_ids=[completed_phase3])
   └─ Extract: Primary outcomes, efficacy measures, p-values (if available)
   
6. extract_clinical_trial_adverse_events(nct_ids=[completed_ids])
   └─ Extract: Serious AEs, common AEs by organ system (if available)

7. fda_pharmacogenomic_biomarkers(drug_name=drug_name)
   └─ Extract: FDA-required biomarker testing, approved companion diagnostics [★★★]

8. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["indications_and_usage"])
   └─ Parse for: "testing required", "biomarker", "companion diagnostic", "genetic testing" [★★★]

9. PharmGKB_search_drugs(query=drug_name)
   └─ Extract: PharmGKB drug ID for response predictors

10. PharmGKB_get_clinical_annotations(drug_id=pharmgkb_id)
    └─ Extract: Response/toxicity biomarkers with clinical evidence levels [★★☆]

undefined

undefined

1. FAERS_count_reactions_by_drug_event(medicinalproduct=drug_name)
   └─ Extract: Top 20 adverse reactions by MedDRA term [★★★]
   
2. FAERS_count_seriousness_by_drug_event(medicinalproduct=drug_name)
   └─ Extract: Serious vs non-serious counts & ratio [★★★]
   
3. FAERS_count_outcomes_by_drug_event(medicinalproduct=drug_name)
   └─ Extract: Recovered, recovering, fatal, unresolved counts [★★★]
   
4. FAERS_count_death_related_by_drug(medicinalproduct=drug_name)
   └─ Extract: Fatal outcome count [★★★]
   
5. FAERS_count_patient_age_distribution(medicinalproduct=drug_name)
   └─ Extract: Reports by age group [★★★]

6. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["drug_interactions"])
   └─ Extract: DDI table, CYP interactions, contraindicated combinations [★★★]
   
7. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["dosage_and_administration", "warnings_and_cautions"])
   └─ Extract: Dose modification triggers (ALT/AST thresholds, renal/hepatic impairment, CYP3A inhibitor/inducer adjustments) [★★★]

8. DailyMed_get_spl_by_setid(setid=set_id)
   └─ Parse full XML for drug-food interactions:
   └─ Search sections: "drug_and_or_food_interactions", "food_effect"
   └─ Keywords: grapefruit, alcohol, food, meal, dairy, high-fat, fasting
   └─ Extract: effect magnitude, mechanism, recommendations [★★★]

9. search_clinical_trials(intervention=f"{drug_name} AND combination", pageSize=50)
   └─ Extract: Approved combinations, regimens, co-administration studies [★★★]

10. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["indications_and_usage", "dosage_and_administration"])
    └─ Parse for: "in combination with", "administered with", regimen details [★★★]

undefined

undefined

1. PharmGKB_search_drugs(query=drug_name)
   └─ Extract: PharmGKB drug ID
   
2. PharmGKB_get_drug_details(drug_id)
   └─ Extract: Cross-references, related genes
   
3. PharmGKB_get_clinical_annotations(gene_id)  # For each related gene
   └─ Extract: Variant-drug associations, evidence levels
   
4. PharmGKB_get_dosing_guidelines(gene=gene_symbol)
   └─ Extract: CPIC/DPWG guideline recommendations

5. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["pharmacogenomics", "clinical_pharmacology"])
   └─ Extract: Label-based PGx information [★★★]
   
6. PubMed_search_articles(query="[drug] pharmacogenomics", max_results=5)
   └─ Extract: Published PGx associations [★★☆]

undefined

---

1. DailyMed_search_spls(drug_name=drug_name)
   └─ Extract: SetID for regulatory label data

2. FDA_OrangeBook_search_drug(brand_name=drug_name)
   └─ Extract: Application number, approval dates [★★★]

3. FDA_OrangeBook_get_approval_history(appl_no=app_number)
   └─ Extract: Original approval date, supplements, label changes [★★★]

4. FDA_OrangeBook_get_exclusivity(brand_name=drug_name)
   └─ Extract: Exclusivity types (NCE, Pediatric, Orphan), expiration dates [★★★]

5. FDA_OrangeBook_get_patent_info(brand_name=drug_name)
   └─ Extract: Patent numbers, substance/formulation claims [★★★]

6. FDA_OrangeBook_check_generic_availability(brand_name=drug_name)
   └─ Extract: Generic entries, TE codes (AB rating), first generic date [★★★]

7. DailyMed_get_spl_sections_by_setid(setid=set_id, sections=["indications_and_usage"])
   └─ Parse for: breakthrough designation, priority review, orphan status [★★★]

8. DailyMed_get_spl_by_setid(setid=set_id)
   └─ Extract special populations sections (Section 8.5):
   └─ pediatric_use (LOINC 34076-0): age groups, dosing, safety
   └─ geriatric_use (LOINC 34082-8): efficacy, safety in elderly
   └─ pregnancy (LOINC 42228-7): risk summary, animal data, recommendations
   └─ nursing_mothers (LOINC 34080-2): lactation risk, recommendations
   └─ Extract: renal/hepatic dosing from dosage section [★★★]

9. Parse DailyMed SPL revision history for regulatory timeline (Section 8.6):
   └─ Initial approval date
   └─ Major label changes (safety updates, indication expansions)
   └─ PMR/PMC commitments from label [★★★]

10. Combine FDA_OrangeBook_get_approval_history + label data:
    └─ Create regulatory timeline table
    └─ Document approval pathway (priority, breakthrough, orphan)
    └─ Note limitation: US-only data [★★★]

undefined

---

1. search_clinical_trials(study_type="OBSERVATIONAL", intervention=drug_name, pageSize=50)
   └─ Extract: RWE studies, registry trials, observational cohorts [★★★]

2. PubMed_search_articles(query=f"{drug_name} (real-world OR observational OR effectiveness)", max_results=20)
   └─ Extract: RWE publications, adherence studies, off-label use [★★☆]

3. PubMed_search_articles(query=f"{drug_name} (registry OR post-marketing OR surveillance)", max_results=10)
   └─ Extract: Post-marketing surveillance, long-term outcomes [★★☆]

4. Compare efficacy vs effectiveness:
   └─ Clinical trial primary outcomes vs real-world outcomes
   └─ Trial inclusion criteria vs real-world patient demographics
   └─ Adherence rates in trials vs clinical practice

undefined

---

1. Identify comparator drugs:
   └─ User provides OR infer from indication + mechanism
   └─ Example: For elacestrant (ER degrader), comparators = fulvestrant, other SERDs

2. For each comparator, run abbreviated tool chain:
   a. PubChem_get_CID_by_compound_name(compound=comparator)
   b. ChEMBL_search_activities(chemblid=comparator_chemblid, target="ESR1", max_results=20)
      └─ Extract: Potency vs primary target
   c. search_clinical_trials(intervention=comparator, condition=indication, pageSize=20)
      └─ Extract: Phase 3 trial counts, approval status
   d. FAERS_count_reactions_by_drug_event(medicinalproduct=comparator)
      └─ Extract: Top 5 adverse events, seriousness ratio

3. Search for head-to-head trials:
   search_clinical_trials(intervention=f"{drug_name} AND {comparator}")
   └─ Extract: Direct comparison trials [★★★]

4. PubMed_search_articles(query=f"{drug_name} vs {comparator}", max_results=10)
   └─ Extract: Network meta-analyses, indirect comparisons [★★☆]

5. Create comparison tables across dimensions:
   └─ Potency, selectivity, ADMET, efficacy, safety, cost (if available)

undefined

---

undefined

undefined

Metformin reduces hepatic glucose output via AMPK activation [★★★: FDA Label].
Phase 3 trials demonstrated HbA1c reduction of 1.0-1.5% [★★★: NCT00123456].
Preclinical studies suggest anti-cancer properties [★☆☆: PMID:23456789].
ADMET-AI predicts low hERG liability (0.12) [☆☆☆: computational].

undefined

---

undefined

---

---

---