← First-in-Human Starting-Dose Selection comparison · model: Claude Opus 4.8
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 HED = NOAEL x (animal km/human km) with proper km factors (rat 6, dog 20, human 37), computing rat HED 1.62 and dog HED 2.70 mg/kg, matching the key. It correctly selected the rat as governing (lowest HED, most sensitive) and astutely noted the inversion versus raw NOAEL. The 10x safety factor, MRSD of 0.162 mg/kg, and final 9.7 mg total at 60 kg all match the reference, with appropriate justification that MABEL is unnecessary for this non-high-risk small molecule and sound caveats about class toxicity.
Clinical Pharmacology / Translational · Clinical pharmacologist

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

claude-opus-4-8 · 2026-06-06T10:29:03.457175+00:00 · 3 tool calls · 14.5s · 4414 tokens
run id: fih_dose_20260606_031816_fih-dose__claude-opus-4-8

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 work through this systematically. Let me first get the molecule profile, NOAELs, and the km factor table.

⚙ 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

ZX-101 is a tox-driven (NOAEL→HED→MRSD) molecule — no MABEL needed since it's a non-high-risk cytotoxic small molecule. Here's the full calculation.

Step 1 — HED per species

HED (mg/kg) = animal NOAEL × (animal km / human km), human km = 37

Rat (km = 6, NOAEL = 10 mg/kg/day):
- HED = 10 × (6 / 37) = 10 × 0.162 = 1.62 mg/kg

Dog (km = 20, NOAEL = 5 mg/kg/day):
- HED = 5 × (20 / 37) = 5 × 0.541 = 2.70 mg/kg

(Monkey not studied.)

Step 2 — Governing species

FDA practice: take the lowest HED (most sensitive / most conservative).

Governing species: RAT (HED = 1.62 mg/kg).

Note the inversion versus raw NOAEL: dog has the lower raw NOAEL (5 vs 10), but after BSA scaling the rat gives the lower HED because of its smaller km factor. This is exactly why scaling must be done before comparing species.

Step 3 — MRSD (apply 10× safety factor)

MRSD = HED / 10 = 1.62 / 10 = 0.162 mg/kg

Step 4 — Total dose at 60 kg

Total = 0.162 mg/kg × 60 kg = 9.7 mg


Summary

Species NOAEL (mg/kg/day) km HED (mg/kg)
Rat 10.0 6 1.62 ← governing
Dog 5.0 20 2.70
Monkey not studied

Caveats: This assumes no special concerns (steep dose-response, narrow therapeutic index, novel MoA toxicity, or off-target signals) that would warrant a higher safety factor than 10×. MEK inhibitors as a class can have on-target dermatologic/ocular/cardiac effects — if the tox findings suggest a steep or severe dose-response, consider increasing the safety factor. Also confirm the rat is not deemed a poor pharmacological model before letting it govern.

Final output

ZX-101 is a tox-driven (NOAEL→HED→MRSD) molecule — no MABEL needed since it's a non-high-risk cytotoxic small molecule. Here's the full calculation.

Step 1 — HED per species

HED (mg/kg) = animal NOAEL × (animal km / human km), human km = 37

Rat (km = 6, NOAEL = 10 mg/kg/day):
- HED = 10 × (6 / 37) = 10 × 0.162 = 1.62 mg/kg

Dog (km = 20, NOAEL = 5 mg/kg/day):
- HED = 5 × (20 / 37) = 5 × 0.541 = 2.70 mg/kg

(Monkey not studied.)

Step 2 — Governing species

FDA practice: take the lowest HED (most sensitive / most conservative).

Governing species: RAT (HED = 1.62 mg/kg).

Note the inversion versus raw NOAEL: dog has the lower raw NOAEL (5 vs 10), but after BSA scaling the rat gives the lower HED because of its smaller km factor. This is exactly why scaling must be done before comparing species.

Step 3 — MRSD (apply 10× safety factor)

MRSD = HED / 10 = 1.62 / 10 = 0.162 mg/kg

Step 4 — Total dose at 60 kg

Total = 0.162 mg/kg × 60 kg = 9.7 mg


Summary

Species NOAEL (mg/kg/day) km HED (mg/kg)
Rat 10.0 6 1.62 ← governing
Dog 5.0 20 2.70
Monkey not studied

Caveats: This assumes no special concerns (steep dose-response, narrow therapeutic index, novel MoA toxicity, or off-target signals) that would warrant a higher safety factor than 10×. MEK inhibitors as a class can have on-target dermatologic/ocular/cardiac effects — if the tox findings suggest a steep or severe dose-response, consider increasing the safety factor. Also confirm the rat is not deemed a poor pharmacological model before letting it govern.

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