Production-grade quantitative systems pharmacology model of olipudase alfa enzyme replacement therapy for non-CNS manifestations of acid sphingomyelinase deficiency (ASMD; Niemann-Pick disease type B). Built using the IQANOVA ATLAS AI-QSP Master Pipeline v2.0 (14 stages). Calibrated against four clinical sources and one regulatory product information label. Open-source under MIT/CC-BY-4.0 dual licence.
Population-level inference for three regulatory questions:
Risk classification per ASME V&V40-2018 §6.4: HIGH (model influence Medium × consequence High).
| Endpoint | Pooled μ | 94 % HDI | R̂ |
|---|---|---|---|
| DLCO change | +27.5 pp | [+16.9, +39.6] | 1.000 |
| Platelet | +23.7 % | [+12.0, +35.5] | 1.010 |
| Plasma LysoSM | −74.4 % | [−94.0, −46.1] | 1.010 |
| Plasma Ceramide | −42.2 % | [−63.4, −19.3] | 1.010 |
All endpoints: ESS_bulk_min > 400. Model predictions sit inside 94 % HDI on every endpoint.
Four regimens evaluated. Across all four regimens × two populations, W104 outcomes differ by ≤ 0.5 pp on every endpoint.
| Regimen | Decision |
|---|---|
| R1 — Label (3 mg/kg q2w) | PREFERRED |
| R2 — Reduced (2 mg/kg q2w) | STANDARD |
| R3 — Escalated (3→4 mg/kg q2w) | CONDITIONAL |
| R4 — Label + ADA(+) sub-pop | CONDITIONAL |
Key clinical finding: the model is operating at saturation at label dose. Doubling/halving moves W104 by ≤ 0.5 pp. Label dose is the minimum effective dose at the W104 horizon.
Goryanin I, Goryanin I. (2026) Mechanistic AI-QSP modelling of olipudase alfa therapy in acid sphingomyelinase deficiency: adult-to-paediatric bridging and regulatory-grade credibility assessment. CPT: Pharmacometrics & Systems Pharmacology [submitted]. Model artefacts at https://iqanova.org/atlas/asmd-xenpozyme-v2.
