Seth Green, M.S.

Manager, Data Science Engineering

Seth joined the Technology Solutions team at Metrum in January 2020. He has expertise in a range of Data Science disciplines including machine learning, applied statistics, big data engineering, and data visualization as well as experience in software engineering from his work building tools and platforms in the digital advertising and scholarly publishing industries. Seth’s credentials include an MS in Data Science and a BA in Philosophy & History, both from the University of Virginia, plus almost a decade on the road as a professional musician.

Recent publications by this scientist

Explore MeRGE: the Metrum Research Group Ecosystem

July 12, 2024

Presented at PAGE 2024 – Hands-on Workshop. MeRGE is a suite of freely-available, open-source tools for scalable, reproducible pharmacometric workflows. MeRGE consists of individual but interconnected R packages that support scalability and reproducibility during: project setup, data assembly, data exploration, model development, execution, and evaluation, simulation, and reporting.

bbr.bayes: An Open-Source Tool to Facilitate an Efficient, Reproducible Bayesian Workflow Using NONMEM

July 8, 2024

Presented at PAGE 2024. The bbr.bayes package reduces much of the friction associated with a Bayesian pharmacometrics analysis in NONMEM® and promotes good practice applications.

simpar: an R Package for Parameter Uncertainty Simulations in Pharmacometric Modeling

November 15, 2023

Presented at ACoP14. This project is dedicated to integrating parameter uncertainty into pharmacometric simulations, which plays a crucial role in making informed decisions in drug development. Initially, the metrumrg package in R was instrumental for simulating both fixed and random effect parameters. However, this package has since been deprecated. Consequently, the primary objective was to create a new R package named simpar. This new package aimed to retain the essential functionalities of metrumrg while expanding its capabilities. The overarching goal was to significantly enhance the support for incorporating parameter uncertainty into pharmacometric simulations, thereby aiding more comprehensive and accurate decision-making processes in this field.

Download PDF