A composable ecosystem for infectious disease modelling
Why we are building EpiAware, and where it is today.
Jul 8, 2026
EpiAware
Composable tools for infectious disease modelling in Julia.
Composable at every level
EpiAware gives you composable pieces at two levels: build the exact distributions your data need, and assemble whole models from interchangeable parts. Use either on its own, or together.
Compose distributions
using ComposedDistributions, Distributions
# A case's delays: infection → onset → admission → death
chain = Sequential([Gamma(2.0, 1.5),
LogNormal(1.0, 0.5), Gamma(2.0, 3.0)])
Build a joint model
using ComposableTuringIDModels, Distributions
# A random-walk-driven model, observed with Poisson error
model = IDModel(
DirectInfections(; Z = RandomWalk(),
initialisation_prior = Normal()),
PoissonError())
Composable
Small packages that each do one thing and combine into joint models, so you assemble the model a problem needs instead of rebuilding it.
Uncertainty-aware
Components propagate uncertainty correctly when combined, avoiding the error that creeps in when separate models are chained together.
Built for response
Designed for real-time infectious disease analysis under the time pressure and resource limits of a live outbreak.
Core packages
ComposableTuringIDModels.jl
Assemble infectious disease models from interchangeable parts as a single Turing model. Docs ↗
CensoredDistributions.jl
Handle the censoring and truncation biases common in epidemiological delay data. Docs ↗
ConvolvedDistributions.jl
Convolve distributions, with shared quadrature. Docs ↗
ComposedDistributions.jl
A grammar for composing distributions. Docs ↗
From the blog
Built on Julia
We build in Julia for its type system, multiple dispatch, and automatic differentiation, and on the scientific infrastructure already there:
SciML
Differential equations, sensitivity analysis, and scientific machine learning.
Turing.jl
Probabilistic programming and Bayesian inference.
Distributions.jl
The shared vocabulary of probability distributions our packages extend.
New to Julia? Start with the Using Julia guide.
Background
In R we built the epinowcast ecosystem and packages such as EpiNow2 and scoringutils, now used by academics and public health teams internationally. EpiAware is the Julia equivalent: a domain-focused ecosystem in the mould of SciML or Turing.jl, with community infrastructure like rOpenSci and the domain focus of SpeedyWeather.jl.
We are at an early stage and looking for collaborators — here is how to get involved.