{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T12:51:31Z","timestamp":1792068691435,"version":"4.4.0"},"reference-count":12,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CPT Pharmacom &amp;amp; Syst Pharma"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>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\u2010source agentic platform for developing and deploying specialized agent\u2010callable pharmacometric tools. The platform uses Docker to orchestrate an R\u2010based API server alongside a Python\u2010based model context protocol (MCP) server, which automatically generates agent\u2010callable tools from OpenAPI specifications, making pharmacometric functions discoverable and usable by AI agents. To exemplify pharmacometric applications, five tools were developed: non\u2010compartmental analysis (NCA) using PKNCA, exposure\u2010response (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\u2010of\u2010concept 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\u2010compatible 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\u2010supervised AI\u2010driven workflows while ensuring reproducibility, transparency, and detailed documentation required for model\u2010informed drug development.<\/jats:p>","DOI":"10.1002\/psp4.70325","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T09:27:53Z","timestamp":1790242073000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PMxAgent: An Agentic Platform for Pharmacometrics"],"prefix":"10.1002","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2860-6488","authenticated-orcid":false,"given":"Peter","family":"Bloomingdale","sequence":"first","affiliation":[{"name":"Translational and Quantitative PKPD Generate Biomedicines  Somerville Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antari","family":"Khot","sequence":"additional","affiliation":[{"name":"Clinical Pharmacology BeOne Medicine  Cambridge Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrd3681"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/psp4.12390"},{"key":"e_1_2_10_4_1","unstructured":"A.Vaswani N.Shazeer N.Parmar et\u00a0al. \u201cAttention Is All You Need\u201d(2017) arXiv [preprint] https:\/\/doi.org\/10.48550\/arXiv.1706.03762."},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/cts.70188"},{"key":"e_1_2_10_6_1","unstructured":"A. T.Kalai O.Nachum S. S.Vempala andE.Zhang \u201cWhy Language Models Hallucinate\u201d(2025) arXiv [preprint] arXiv:2509.04664."},{"issue":"1","key":"e_1_2_10_7_1","first-page":"S65","article-title":"Simple, Automatic Noncompartmental Analysis: The PKNCA R Package","volume":"42","author":"Denney W. S.","year":"2015","journal-title":"Journal of Pharmacokinetics and Pharmacodynamics"},{"key":"e_1_2_10_8_1","unstructured":"K. T.Baron \u201cmrgsolve: Simulate From ODE\u2010Based Models\u201d(2025) R Package https:\/\/CRAN.R\u2010project.org\/package=mrgsolve."},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"R.Hooijmaijers M.Fidler B.Denney andK.Vedantham \u201cnlmixr2lib: A Model Library for nlmixr2\u201d(2026) R package version 0.3.2 https:\/\/doi.org\/10.32614\/CRAN.package.nlmixr2lib.","DOI":"10.32614\/CRAN.package.nlmixr2lib"},{"key":"e_1_2_10_10_1","unstructured":"Anthropic \u201cModel Context Protocol Specification (Version 2025\u201011\u201005)\u201d(2025) https:\/\/modelcontextprotocol.io\/specification\/2025\u201011\u201005."},{"key":"e_1_2_10_11_1","unstructured":"Lixoft (A Simulations Plus company) \u201cPKanalix Version 2024R1 [Software]\u201d(2024) Antony France: Lixoft."},{"key":"e_1_2_10_12_1","unstructured":"International Council for Harmonisation \u201cICH M15: General Principles for Model\u2010Informed Drug Development\u201d(2026) Guidance for Industry. Silver Spring (MD): US Department of Health and Human Services Food and Drug Administration Center for Drug Evaluation and Research and Center for Biologics Evaluation and Research https:\/\/www.fda.gov\/media\/184747\/download."},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","unstructured":"Z.Shi Y.Wang L.Yan et\u00a0al. \u201cRetrieval Models Aren't Tool\u2010Savvy: Benchmarking Tool Retrieval for Large Language Models \u201d(2025) arXiv [Preprint] arXiv:2503.01763.","DOI":"10.18653\/v1\/2025.findings-acl.1258"}],"container-title":["CPT: Pharmacometrics &amp; Systems Pharmacology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/psp4.70325","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/psp4.70325","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/psp4.70325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T12:18:00Z","timestamp":1792066680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1002\/psp4.70325"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":12,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/psp4.70325"],"URL":"https:\/\/doi.org\/10.1002\/psp4.70325","archive":["Portico"],"relation":{},"ISSN":["2163-8306","2163-8306"],"issn-type":[{"value":"2163-8306","type":"print"},{"value":"2163-8306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]},"assertion":[{"value":"2026-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70325"}}