#nlmixr2 — Public Fediverse posts

New from the nlmixr2 Working Group: nlmixr2 7.0's covariance step, all grown up.

Request nearly any covariance method from nearly any estimation method, switch methods without refitting, and get SEs for every estimated parameter - including residual error.

https://r-consortium.org/posts/nlmixr2-7-0-covariance-step/

#RStats #OpenSource #RConsortium #nlmixr2

The R Consortium #nlmixr2 Working Group on admixr2: fit PK/PD models to published aggregate data when patient-level data aren't available.

Supports digitized mean±SD profiles, published NLME models (MBMA), and joint multi-study fits via nlmixr2/rxode2.

Cross-post: https://r-consortium.org/posts/fitting-pk-pd-models-to-published-data-with-admixr2/

Explore Working Groups: https://r-consortium.org/all-projects/isc-working-groups.html

#RStats #OpenSource #Pharmacometrics #RConsortium #nlmixr2

New nlmixr2 blog post: Fitting PK/PD models to published data with admixr2

admixr2 lets you fit PK/PD models to aggregate & published data — digitized mean±SD fits, model-based data generation via datagen(), and joint MBMA across studies.

By H. van de Beek

https://blog.nlmixr2.org/blog/2026-07-02-admixr2-mbma/

#pharmacometrics #nlmixr2 #RStats

One of the things I often get asked is if you can use #nlmixr2 in submissions. We were invited to meet with some of the FDA reviewers, and they confirmed they have received submissions in nlmixr2 and no issues were raised about its use

https://blog.nlmixr2.org/blog/2026-04-29-fda/

We are excited to announce a new feature in nlmixr2: mceta for FOCEi. This is a hybrid approach combines Monte-Carlo sampling with the classical FOCEi algorithm bringing flexibility & robustness to nonlinear mixed-effects modeling in pharmacometrics. #nlmixr2 #rstats

New features in #nlmixr2 4.0, a #rstats package include a vere-style loading, importing models from older versions of nlmixr2 and Rstudio bug fixes. See https://blog.nlmixr2.org/blog/2025-08-29-nlmixr2-verse/

In this month's Blog, I discuss a new feature in the nlmixr2 ecosystem (in babelmixr2) -- translating and using nlmixr2 models in optimal design. They are fast and easy to use making this my go to tool when doing optimal design. #nlmixr2 #rstats

https://blog.nlmixr2.org/blog/2024-11-06-poped/

nlmixr2 and rxode2 3.0 is out. It is a major release since there are some backward-incompatible changes. #nlmixr2 #rxode2 #rstats

https://blog.nlmixr2.org/blog/2024-09-18-nlmixr2-3.0.0-release/

We have a new nlmixr2 blog entry courtesy of Hitesh Mistry and Nicola Melillo (@NicolaMelillo) detailing how to upscale nlmixr2 using AWS. This is helpful for long running SAEM models. In the future it may be even more interesting with other methods parallelized. (#nlmixr2 #rstats)

https://blog.nlmixr2.org/blog/2024-03-05-aws/

A new version of #nlmixr2 was released on CRAN today. I will talk about a few features in the future:

- More flexible mu referencing

- User defined functions can now be used with nlmixr2 and rxode2

- Event handling changes

- Many new estimation methods for population only fitting
I am very grateful for both the nlmixr2 team and the nlmixr2 users who have helped me get to this point in nlmixr2's development.

See the blog for more details about the release.

https://blog.nlmixr2.org/blog/2024-01-09-nlmixr2-2.1.0-release/

Our colleagues at LAP&P are hosting a target-mediated drug disposition #TMDD course using #nlmixr2 at #PAGE2023 in A Coruña, Spain!

This is your chance to see nlmixr2 put through its paces in real-world #pharmacometrics by a world-class consulting team.

https://lapp.nl/lapp-page-course/

@justinwilkins @damiacer

That's what I was thinking. I think #nlmixr2 would fit right in there. Do you know folks at Roche? We should approach them.

- It is also validated against the #nlmixr2 / #rxode2 model so you know if it is working immediately

Want a single language for a few pharmcometric applications? How about giving #babelmixr2, an extension of #nlmixr2 a try?

I would like to mention a new release of #nlmixr2. I haven't posted about it but I would like to mention my favorite new features:

Hi everyone! This is the official home of #nlmixr2 on Mastodon. We are a constellation of #rstats packages aimed at supporting easy and robust nonlinear mixed-effects models in R. We are free and #OpenSource and will be forever.

Stay tuned for announcements of blog postings, chat, trivia, and whatever you all want to talk about!

#Pharmacometrics

https://www.nlmixr2.org

Modeling tools in our area are largely closed-source and massively expensive, and are a gigantic entry barrier for new people, especially in low and middle-income countries (and borderline unaffordable even for CROs like mine). #nlmixr2 is intended to be a solution to this problem. I also maintain the #pmxTools package, which provides a handy set of general #PMx functions.

@nlmixr2

https://www.nlmixr2.org

I'm on fosstodon.org because I do a lot of #rstats development, most notably as a member of the #nlmixr2 development team. nlmixr2 is a set of packages - let's call it the #mixrverse - for R that provides an #OpenSource alternative for nonlinear mixed-effects (#NLME) model development, which are the core of most #Pharmacometrics workflows (amongst others).

#introduction time! I’m Justin Wilkins, a #pharmacometrics consultant living in Germany. I work for a small CRO called Occams and I post occasionally about #healthscience, modeling and simulation, #rstats and the current wretched state of British politics. I’m a co-developer of the nonlinear mixed-effects model fitting package #nlmixr2 in R, as well as the #pmxTools package.