← First-in-Human Starting-Dose Selection comparison · model: Claude Haiku 4.5
LLM-judge score: 5.0 / 5 · strong
allometric_scaling: 5 species_selection: 5 safety_mabel_judgment: 5 final_dose: 5 faithfulness: 5
The agent correctly applied the FDA BSA method with proper km factors (rat 6, dog 20, human 37), accurately computed HEDs (rat 1.62, dog 2.70 mg/kg), selected the most sensitive species (rat), applied the default 10x safety factor for MRSD, and reached the correct ~9.7 mg total dose at 60 kg. All values trace faithfully to the NOAEL and km data with no fabrication. MABEL is appropriately not invoked since this is a small-molecule inhibitor rather than a high-risk agonist biologic.
Clinical Pharmacology / Translational · Clinical pharmacologist

First-in-Human Starting-Dose Selection — agent trajectory for expert review

claude-haiku-4-5-20251001 · 2026-06-06T10:29:13.562901+00:00 · 3 tool calls · 5.6s · 3730 tokens
run id: fih_dose_20260606_031816_fih-dose__claude-haiku-4-5

Query

Recommend a first-in-human starting dose for ZX-101, an oral small-molecule MEK1/2 inhibitor. Use the GLP tox NOAELs and FDA body-surface-area scaling; show your HED per species, the governing species, the MRSD, and the total mg dose at 60 kg.

Trajectory

Agent · turn 1

I'll help you determine the first-in-human starting dose for ZX-101. Let me gather the necessary information.

⚙ calls get_molecule(molecule=ZX-101)
⚙ calls get_tox_noael(molecule=ZX-101)
⚙ calls get_km_factors()
↳ get_molecule result
show data
{
  "id": "ZX-101",
  "name": "ZX-101",
  "modality": "Small molecule (oral kinase inhibitor)",
  "target": "MEK1/2",
  "high_risk": false,
  "high_risk_reason": null,
  "human_weight_kg": 60.0,
  "notes": "Direct cytotoxic/anti-proliferative MoA; tox-driven dose selection is appropriate. No immune-agonist risk, so NOAEL->HED->MRSD with a 10x safety factor governs.",
  "most_appropriate_species_note": "Standard FDA practice: convert each species, then take the lowest HED (most sensitive) unless a species is known to be a poor model."
}
↳ get_tox_noael result
show data
{
  "id": "ZX-101",
  "name": "ZX-101",
  "units": "mg/kg/day (GLP repeat-dose NOAEL)",
  "species_noael_mg_kg": {
    "rat": 10.0,
    "dog": 5.0
  },
  "species_not_studied": [
    "monkey"
  ],
  "human_weight_kg": 60.0,
  "most_appropriate_species_note": "Standard FDA practice: convert each species, then take the lowest HED (most sensitive) unless a species is known to be a poor model."
}
↳ get_km_factors result
show data
{
  "description": "FDA 2005 body-surface-area (km) conversion factors. HED (mg/kg) = animal NOAEL (mg/kg) x (animal km / human km). Human adult km = 37.",
  "human_km": 37,
  "default_safety_factor": 10,
  "default_human_weight_kg": 60.0,
  "km_factors": {
    "human_adult": {
      "km": 37,
      "ref_weight_kg": 60.0
    },
    "human_child": {
      "km": 25,
      "ref_weight_kg": 20.0
    },
    "mouse": {
      "km": 3,
      "ref_weight_kg": 0.02
    },
    "hamster": {
      "km": 5,
      "ref_weight_kg": 0.08
    },
    "rat": {
      "km": 6,
      "ref_weight_kg": 0.15
    },
    "ferret": {
      "km": 7,
      "ref_weight_kg": 0.3
    },
    "guinea_pig": {
      "km": 8,
      "ref_weight_kg": 0.4
    },
    "rabbit": {
      "km": 12,
      "ref_weight_kg": 1.8
    },
    "dog": {
      "km": 20,
      "ref_weight_kg": 10.0
    },
    "monkey": {
      "km": 12,
      "ref_weight_kg": 3.0
    },
    "marmoset": {
      "km": 6,
      "ref_weight_kg": 0.35
    },
    "squirrel_monkey": {
      "km": 12,
      "ref_weight_kg": 0.6
    },
    "baboon": {
      "km": 20,
      "ref_weight_kg": 12.0
    },
    "micro_pig": {
      "km": 27,
      "ref_weight_kg": 20.0
    },
    "mini_pig": {
      "km": 35,
      "ref_weight_kg": 40.0
    }
  }
}
Agent · turn 2

Perfect! Now I'll calculate the HED for each species and determine the first-in-human starting dose.

ZX-101 First-in-Human Starting Dose Recommendation

GLP Repeat-Dose NOAELs

HED Calculations (FDA BSA Method)

Using the formula: HED (mg/kg) = Animal NOAEL (mg/kg) × (Animal km / Human km)

Human km = 37

Species NOAEL (mg/kg) km HED (mg/kg)
Rat 10.0 6 10.0 × (6/37) = 1.62 mg/kg
Dog 5.0 20 5.0 × (20/37) = 2.70 mg/kg

Governing Species & MRSD

Rat is the most sensitive species with an HED of 1.62 mg/kg.

Maximum Recommended Starting Dose (MRSD):
- NOAEL HED: 1.62 mg/kg
- Safety factor: 10×
- MRSD = 1.62 ÷ 10 = 0.162 mg/kg

Total Dose at 60 kg Body Weight

First-in-Human Starting Dose = 0.162 mg/kg × 60 kg = 9.72 mg

Recommendation: Start at ~10 mg (or 9.7 mg) as a single oral dose for the first cohort.


Summary

This represents a 10-fold safety margin from the most sensitive animal model, consistent with FDA guidance for conventional small-molecule kinase inhibitors with cytotoxic activity.

Final output

Perfect! Now I'll calculate the HED for each species and determine the first-in-human starting dose.

ZX-101 First-in-Human Starting Dose Recommendation

GLP Repeat-Dose NOAELs

HED Calculations (FDA BSA Method)

Using the formula: HED (mg/kg) = Animal NOAEL (mg/kg) × (Animal km / Human km)

Human km = 37

Species NOAEL (mg/kg) km HED (mg/kg)
Rat 10.0 6 10.0 × (6/37) = 1.62 mg/kg
Dog 5.0 20 5.0 × (20/37) = 2.70 mg/kg

Governing Species & MRSD

Rat is the most sensitive species with an HED of 1.62 mg/kg.

Maximum Recommended Starting Dose (MRSD):
- NOAEL HED: 1.62 mg/kg
- Safety factor: 10×
- MRSD = 1.62 ÷ 10 = 0.162 mg/kg

Total Dose at 60 kg Body Weight

First-in-Human Starting Dose = 0.162 mg/kg × 60 kg = 9.72 mg

Recommendation: Start at ~10 mg (or 9.7 mg) as a single oral dose for the first cohort.


Summary

This represents a 10-fold safety margin from the most sensitive animal model, consistent with FDA guidance for conventional small-molecule kinase inhibitors with cytotoxic activity.

Reference answer key (deterministic) — open after grading

Deterministic FDA-MRSD / MABEL calc over the curated nonclinical inputs. HED = NOAEL x (animal km / human km); most sensitive species governs; MRSD = HED / 10; total = MRSD x 60 kg. For high-risk agonists, MABEL is computed from in vitro potency / receptor occupancy and the LOWER dose is recommended (the TGN1412 lesson). A strong agent should reproduce these steps and units.

StepValueNote
MoleculeZX-101 (Small molecule (oral kinase inhibitor))target MEK1/2
HED from rat10.0 x 6/37 = 1.622 mg/kgNOAEL 10.0 mg/kg, km 6
HED from dog5.0 x 20/37 = 2.703 mg/kgNOAEL 5.0 mg/kg, km 20
Governing species (most sensitive)rat -> HED 1.622 mg/kglowest HED across studied species
MRSD (NOAEL path)1.622 / 10 = 0.162 mg/kgdefault 10x safety factor
NOAEL-based total dose0.162 mg/kg x 60.0 kg = 9.73 mg60.0 kg human
RECOMMENDED FIH starting dose9.73 mg (via NOAEL/HED)governed by NOAEL/HED

Expert grading

HED / allometric scaling correctness 1 (poor) 5 (excellent)
5: Applies HED = NOAEL x (animal km / human km) with the correct km factors (rat 6, dog 20, monkey 12, human 37) and computes each species' HED accurately.
1: Uses wrong km values, inverts the ratio, scales by simple mg/kg without BSA correction, or makes arithmetic errors in the HED.
Most-sensitive-species selection 1 (poor) 5 (excellent)
5: Selects the governing species correctly — the lowest HED (most sensitive) for the small molecule, and the pharmacologically relevant species (NHP) for the antibodies — and justifies it.
1: Picks the highest HED, ignores a more sensitive species, or uses a non-binding rodent species for a human-specific antibody.
Safety factor & MABEL judgment 1 (poor) 5 (excellent)
5: Applies the default 10x safety factor, and for immunostimulatory/agonist biologics computes a MABEL from potency/receptor occupancy and takes the LOWER of MABEL vs NOAEL — explicitly invoking the TGN1412 rationale.
1: Omits the safety factor, dosing a high-risk agonist off the NOAEL alone, or fails to compute/compare MABEL when it clearly governs.
Final dose reasonableness & units 1 (poor) 5 (excellent)
5: States a single recommended starting dose with correct units (mg or ug total at 60 kg), in a plausible range — mg-range for the small molecule/mAb, microgram-range for the high-risk biologics.
1: Reports a dose with wrong/missing units, off by orders of magnitude, or recommends a dangerously high dose for an agonist (e.g. a TGN1412-style 0.1 mg/kg).
Evidence faithfulness 1 (poor) 5 (excellent)
5: Every number traces to the returned NOAELs, km table, and pharmacology; no fabricated NOAELs, potencies, or species.
1: Invents NOAEL or potency values, uses km factors not in the table, or contradicts the returned tool data.
Overall verdict
Your name / ID