arXiv subjects

Marija Cvijovic

Publications and source records attributed to Marija Cvijovic.

3 recordsLinked to original sources

arXiv2026

PEtab SciML: an exchange format for specifying and training dynamic scientific machine learning models

Summary: Dynamic scientific machine learning (SciML) models that combine mechanistic ordinary differential equations (ODEs) with machine learning (ML) components have applications ranging from learning unknown biological processes to integrating auxiliary data modalities into dynamic modelling. To enable reproducible and efficient SciML training, we introduce PEtab SciML, an interoperable data format for specifying parameter estimation problems in which mechanistic and ML model parameters are jointly estimated from time series data. PEtab SciML supports several ML ODE hybridization patterns in realistic problem setups. It is accompanied by a reference Python library and downstream modelling support in Python/JAX and Julia, provided by AMICI and PEtab$.$jl, respectively, and a collection of real data benchmarks. Availability and implementation: PEtab SciML is available on GitHub (https://github.com/PEtab-dev/petab_sciml). The reference Python package is installable from PyPI and is continuously tested and supported on Linux, macOS, and Windows.

q-bio.QM↗

arXiv2025

Simulation-based inference for stochastic nonlinear mixed-effects models with applications in systems biology

The analysis of data from multiple experiments, such as observations of several individuals, is commonly approached using mixed-effects models, which account for variation between individuals through hierarchical representations. This makes mixed-effects models widely applied in fields such as biology, pharmacokinetics, and sociology. In this work, we propose a novel methodology for scalable Bayesian inference in hierarchical mixed-effects models. Our framework first constructs amortized approximations of the likelihood and the posterior distribution, which are then rapidly refined for each individual dataset, to ultimately approximate the parameters posterior across many individuals. The framework is easily trainable, as it uses mixtures of experts but without neural networks, leading to parsimonious yet expressive surrogate models of the likelihood and the posterior. We demonstrate the effectiveness of our methodology using challenging stochastic models, such as mixed-effects stochastic differential equations emerging in systems biology-driven problems. However, the approach is broadly applicable and can accommodate both stochastic and deterministic models. We show that our approach can seamlessly handle inference for many parameters. Additionally, we applied our method to a real-data case study of mRNA transfection. When compared to exact pseudomarginal Bayesian inference, our approach proved to be both fast and competitive in terms of statistical accuracy.

stat.CO↗

arXiv2024

A multitype Galton-Watson model for rejuvenating cells

We employ the framework of multitype Galton-Watson processes to model a population of dividing cells. The cellular type is represented by its biological age, defined as the count of harmful proteins hosted by the cell. The stochastic evolution of the biological age of a cell is modeled as a discrete Markov chain with a finite state space $\{0,1,\ldots,n\}$, where $n$ signifies the absorbing state corresponding to the senescent state of the cell. Consequently, the set of individual types in the multitype Galton-Watson process becomes $\{0,\ldots,n-1\}$. In our setting, a dividing cell may undergo rejuvenation meaning that its biological ages reduces due to transfer of harmful proteins to the daughter cell. For the proposed model, we define and study several biologically meaningful features, such as rejuvenation states, expected replicative lifespan, population growth rate, stable biological age distribution, and the population average of the biological age.

math.PR↗