The event bus in brief | Events emitted by nlmixr2est | fitComplete | solveComplete | fitUpdate | The call field | What is not emitted | Listening | Full logging | For developers: nlmixrUpdateObject()

Abstract | Provenance of the R optim::L-BFGS-B and related solvers | Functions in package lbfgsb3c | Candlestick function | Extended Rosenbrock function (from funconstrain) | Using compiled function code | References

A first diagram | Drawing engines | The graph behind the diagram | How the equations are read | Pharmacodynamic models | Target-mediated drug disposition | Dosing compartments | Dosing properties and delays | linCmt() models | Limitations

The shape of it | Parse time: where the weights come from | Getting a value out of a UDF | The weight-block offset: the sharpest edge here | Cotangent capture | Which score is used, and why | Model augmentation | The training backend | Persistence | Things that look safe and are not | The weight penalty | Lambda is a fraction, not an amount | Extending | Where to look when something is wrong

What nn() is | Simulating a model you have not fitted | Learning a term you do not know (UDE) | Letting the network find a covariate relationship | A model with no between-subject variability | Saving, reloading and refitting | When you want to steer the training | Regularization, when a network learns too much | What is supported

How the methods differ | Steihaug truncated-CG trust region | What matches basin | BOBYQA and NEWUOA | The thread-safe C interfaces | References

Similarities: what carries over unchanged | Differences | Speed | When to use which interface | Using the C interface | Calling it from your own package: the registration pattern

The problem is not the same one | Sensitivities: forward, not adjoint | What that costs, and what follows from it | Regularization | The kinetic term | Augmentation, and a limit worth knowing | What is deliberately absent | References

General | Specific Drugs | DDMoRe

Introduction to nlmixr2targets | Initial conditions | Running one model with one dataset (tar_nlmixr()) | Running multiple models with one dataset (tar_nlmixr_multimodel()) | Model piping for multiple models estimated with one dataset | Continuing the pipeline when a model fails | What nlmixr2targets passes to nlmixr2est::nlmixr() -- and what it omits | table (passed, but only when you change it) | ... -- nothing to pass | save -- the targets store already does this | envir -- explicitly omitted

What same() is for | The rules | How it is stored: the condition column | Reading the column | Round trips | same() versus cnd(same = n)

Why priors are in lotri | The syntax | What a prior can be attached to | Population parameters | A single between subject variability term | A whole covariance block | Degrees of freedom for an omega block | A prior on the omega values themselves | One joint block over thetas and omega elements | One block at a time | The normal prior shorthand | More than one parameter | Transformations | Zero variance | Distribution names | Why dt() is not studentT() | The supported distributions | Bounds and truncated priors | What else is checked | Getting the priors back out | Using this downstream | A prior must never be silently ignored

What triggers a re-fit? | Examples of common edits | Inspecting and pruning the indirect cache | tar_outdated() is a quick way to preview what would rerun

Why a dedicated multimodel factory? | Minimal comparison plan | Extracting parameter estimates across models | Within-list piping for nested edits | Tips for large model libraries

1. Adding a new estimation method | 2. Intercepting an estimation | Passing options to your interceptor | 3. Contributing to the objective (compiled linkage) | See also

Setting up nonmem2rx for your model | Pointing nonmem2rx at the input data | General linear models (ADVAN5/ADVAN7) | Technical details about reading NONMEM to rxode2

Two forms accepted inside nlmixr2targets | What tar_nlmixr() does behind the scenes | Pipe forms | Known limitation: env functions never routed through tar_nlmixr() | Summary

Model library conventions within nlmixr2lib | Compartment naming | Estimated parameter naming | Parameter naming | Multi-component clearance | Parent drug + metabolite parameters | Parameter transforms | Random effects | Covariate effects | Drug effects | Model files

Introduction | Creating rxode2 models | Syntax | Note | Example model | Example | Interface and data handling between R and the generated C code

Overview | Population and units | Source trace | Typical-value simulations | Single-dose profiles (100 mg SC) | Target and complex trajectories (1-cmt models) | Repeated SC dosing — drug-concentration difference across structures | Regime-convergence check | Assumptions and deviations

Create your dataset | Create your model | Fit the model | Simulate your data | Summarize the simulations

Model and source | Population | Source trace | Virtual cohort | Simulation | Replicate published figures | Figure 1 / 3 — typical IV vs SC profiles | VPC-style percentile bands | PKNCA validation | Comparison against published NCA | Assumptions and deviations

Introduction | General workflow | The yaml report file structure | placeholders | parameters | covariates | options | Building figures & tables | figures | tables | pptx | docx | Customizing reports for your organization | PowerPoint | Word | Report configuration file report_fit.yaml

Introduction | Creating figures and tables | Using report objects in RMarkdown

Motivation | Creating lists of matrices with attached properties | Combining symmetric named matrices

Construct symbolic expressions | Create symbol x from a string. | Parse an expression from a string | Manipulating symbolic expressions | Expand an expression | Substitute variables | Compute derivatives | Solve a polynomial equation | Construct vector and matrix | Construct a vector with c | Construct a vector with Vector | Construct a symbolic matrix with Matrix | Construct a symbolic matrix with rbind | Numerically evaluate symbolic expressions | Print Latex in Rmarkdown document