PMxAgent: An Agentic Platform for Pharmacometrics

Abstract

AI agents are transforming computational workflows, yet pharmacometric analyses remain manual, relying on significant data wrangling, custom scripts, and specialized software. We present PMxAgent, an open‐source agentic platform for developing and deploying specialized agent‐callable pharmacometric tools. The platform uses Docker to orchestrate an R‐based API server alongside a Python‐based model context protocol (MCP) server, which automatically generates agent‐callable tools from OpenAPI specifications, making pharmacometric functions discoverable and usable by AI agents. To exemplify pharmacometric applications, five tools were developed: non‐compartmental analysis (NCA) using PKNCA, exposure‐response (ER) modeling, pharmacokinetic (PK) simulation using mrgsolve, data standardization (DATA), and generation of population PK datasets from the nlmixr2lib model library (LIBRARY). As a proof‐of‐concept case study, PMxAgent orchestrated a multistep pharmacometric workflow, consisting of a PK simulation of 60 subjects across three dose groups, NCA to derive individual exposure metrics, and ER analysis. To evaluate analytical accuracy and reproducibility, the agentic NCA workflow was benchmarked against four frontier AI agents across 182 drugs and 1820 simulated subjects, using PKanalix as reference. PMxAgent's NCA accuracy (98.3%) matched or exceeded that of all frontier agents evaluated. PMxAgent produced deterministic, reproducible results in contrast to GPT and Claude agents that performed NCA by generating new code each run. PMxAgent was demonstrated using two MCP‐compatible AI agents (Cursor and Claude Code) and is designed to integrate with any AI agent supporting the MCP protocol. PMxAgent provides an extensible foundation for integrating pharmacometric tools into human‐supervised AI‐driven workflows while ensuring reproducibility, transparency, and detailed documentation required for model‐informed drug development.

MolecureAI: an agentic AI platform for autonomous drug discovery
Mohamed Amine Chadi, Asmaa Amzil, Hajar Ezzahoud +1
Frontiers in pharmacology16 Oct 2026Peer-reviewedCC BYFull textPharmacology & toxicologyEurope PMC
TrialCalibre1: An Agentic System for Trial Emulation, Benchmarking, and Calibration
A. Habibdoust, X. Song
medRxiv13 Oct 2026PreprintAll rights reservedFull textEpidemiology & public healthmedRxiv
Real-world evaluation of a multilingual agentic retrieval-augmented clinical AI framework for evidence-grounded medical decision support
Mohammad Hossein Imani, Mohammad Hasannejad, Amir Hossein Imani +1
Scientific Reports14 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textEpidemiology & public healthCrossref
Human-Guided Agentic AI for End-to-End EHR Research: Sequential Antibody-Drug Conjugate Pathways in Breast Cancer
A. Loaiza-Bonilla, C. Colovos, D. Kim +3
medRxiv13 Oct 2026PreprintAll rights reservedFull textOncologymedRxiv
Beyond Billing Codes: An Agentic Large Language Model Pipeline for Extracting Glaucoma Procedural Data from Free-Text Clinical Notes
Janet Kang, Nicholas Solages, Gustavo A. Samico +4
medRxiv29 Oct 2026PreprintAll rights reservedFull textGeneral medicinemedRxivPMC

Cite

BibTeX RIS

BibTeX

@article{bloomingdale2026pmxagent,
  title = {{PMxAgent: An Agentic Platform for Pharmacometrics}},
  author = {Peter Bloomingdale and Antari Khot},
  journal = {CPT: Pharmacometrics \& Systems Pharmacology},
  year = {2026},
  month = sep,
  doi = {10.1002/psp4.70325},
  url = {https://doi.org/10.1002/psp4.70325},
  note = {CC BY-NC 4.0},
}

RIS

TY  - JOUR
TI  - PMxAgent: An Agentic Platform for Pharmacometrics
AU  - Peter Bloomingdale
AU  - Antari Khot
PY  - 2026
DA  - 2026/09/24
JO  - CPT: Pharmacometrics & Systems Pharmacology
DO  - 10.1002/psp4.70325
UR  - https://doi.org/10.1002/psp4.70325
AB  - AI agents are transforming computational workflows, yet pharmacometric analyses remain manual, relying on significant data wrangling, custom scripts, and specialized software. We present PMxAgent, an open‐source agentic platform for developing and deploying specialized agent‐callable pharmacometric tools. The platform uses Docker to orchestrate an R‐based API server alongside a Python‐based model context protocol (MCP) server, which automatically generates agent‐callable tools from OpenAPI specifications, making pharmacometric functions discoverable and usable by AI agents. To exemplify pharmacometric applications, five tools were developed: non‐compartmental analysis (NCA) using PKNCA, exposure‐response (ER) modeling, pharmacokinetic (PK) simulation using mrgsolve, data standardization (DATA), and generation of population PK datasets from the nlmixr2lib model library (LIBRARY). As a proof‐of‐concept case study, PMxAgent orchestrated a multistep pharmacometric workflow, consisting of a PK simulation of 60 subjects across three dose groups, NCA to derive individual exposure metrics, and ER analysis. To evaluate analytical accuracy and reproducibility, the agentic NCA workflow was benchmarked against four frontier AI agents across 182 drugs and 1820 simulated subjects, using PKanalix as reference. PMxAgent's NCA accuracy (98.3%) matched or exceeded that of all frontier agents evaluated. PMxAgent produced deterministic, reproducible results in contrast to GPT and Claude agents that performed NCA by generating new code each run. PMxAgent was demonstrated using two MCP‐compatible AI agents (Cursor and Claude Code) and is designed to integrate with any AI agent supporting the MCP protocol. PMxAgent provides an extensible foundation for integrating pharmacometric tools into human‐supervised AI‐driven workflows while ensuring reproducibility, transparency, and detailed documentation required for model‐informed drug development.
SN  - 2163-8306
ER  -

Abstract

Related

Cite