arXiv subjects

Dilan Pathirana

Publications and source records attributed to Dilan Pathirana.

9 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

Scalable branch-and-bound model selection with non-monotonic criteria including AIC, BIC and Mallows's $\mathit{C_p}$

Model selection is a pivotal process in the quantitative sciences, where researchers must navigate between numerous candidate models of varying complexity. Traditional information criteria, such as the corrected Akaike Information Criterion (AICc), Bayesian Information Criterion (BIC), and Mallows's $\mathit{C_p}$, are valuable tools for identifying optimal models. However, the exponential increase in candidate models with each additional model parameter renders the evaluation of these criteria for all models -- a strategy known as exhaustive, or brute-force, searches -- computationally prohibitive. Consequently, heuristic approaches like stepwise regression are commonly employed, albeit without guarantees of finding the globally-optimal model. In this study, we challenge the prevailing notion that non-monotonicity in information criteria precludes bounds on the search space. We introduce a simple but novel bound that enables the development of branch-and-bound algorithms tailored for these non-monotonic functions. We demonstrate that our approach guarantees identification of the optimal model(s) across diverse model classes, sizes, and applications, often with orders of magnitude computational speedups. For instance, in one previously-published model selection task involving $2^{32}$ (approximately 4 billion) candidate models, our method achieves a computational speedup exceeding 6,000. These findings have broad implications for the scalability and effectiveness of model selection in complex scientific domains.

q-bio.QM↗

arXiv2024

EFECT: A Method to Quantify the Reproducibility of Stochastic Simulations

Reproducibility is a fundamental requirement for validating scientific claims in computational research. Stochastic computational models are widely used in fields such as systems biology, financial modeling and environmental sciences. However, achieving reproducibility in stochastic simulations remains challenging, as each run can produce different outcomes. Existing infrastructure and software tools do not address independent reproduction of simulation results. Without independent reproducibility, results and conclusions lack credibility, as it remains unclear whether observed findings reflect model behavior or are artifacts of stochastic variation or an underpowered study. To bridge this gap, we introduce the Empirical Characteristic Function Equality Convergence Test (EFECT), a data-driven method to quantify the reproducibility of stochastic simulation results. EFECT employs empirical characteristic functions to compare reported results with those independently generated by assessing distributional inequality, termed EFECT error. Additionally, we establish the EFECT convergence point, a quantitative metric for determining the required number of simulation runs to achieve an EFECT error value of a priori significance. EFECT is applicable to all bounded, real-valued outputs, regardless of the model type or simulation method that produced them. We tested EFECT with over 40 use cases to demonstrate its broad applicability and effectiveness. EFECT standardizes stochastic simulation reproducibility, establishing a workflow that guarantees reliable results, supporting a wide range of stakeholders, and thereby enhancing validation of stochastic simulation studies, across a model's lifecycle. To promote standardization, we are developing the open-source software library libSSR in multiple programming languages for easy integration of EFECT.

stat.ME↗

arXiv2024

Non-Negative Universal Differential Equations With Applications in Systems Biology

Universal differential equations (UDEs) leverage the respective advantages of mechanistic models and artificial neural networks and combine them into one dynamic model. However, these hybrid models can suffer from unrealistic solutions, such as negative values for biochemical quantities. We present non-negative UDE (nUDEs), a constrained UDE variant that guarantees non-negative values. Furthermore, we explore regularisation techniques to improve generalisation and interpretability of UDEs.

q-bio.QM↗

arXiv2024

Exploration of methods for computing sensitivities in ODE models at dynamic and steady states

Estimating parameters of dynamic models from experimental data is a challenging, and often computationally-demanding task. It requires a large number of model simulations and objective function gradient computations, if gradient-based optimization is used. The gradient depends on derivatives of the state variables with respect to parameters, also called state sensitivities, which are expensive to compute. In many cases, steady-state computation is a part of model simulation, either due to steady-state data or an assumption that the system is at steady state at the initial time point. Various methods are available for steady-state and gradient computation. Yet, the most efficient pair of methods (one for steady states, one for gradients) for a particular model is often not clear. Moreover, depending on the model and the available data, some methods may not be applicable or sufficiently robust. In order to facilitate the selection of methods, we explore six method pairs for computing the steady state and sensitivities at steady state using six real-world problems. The method pairs involve numerical integration or Newton's method to compute the steady-state, and -- for both forward and adjoint sensitivity analysis -- numerical integration or a tailored method to compute the sensitivities at steady-state. Our evaluation shows that the two method pairs that combine numerical integration for the steady-state with a tailored method for the sensitivities at steady-state were the most robust, and amongst the most computationally-efficient. We also observed that while Newton's method for steady-state computation yields a substantial speedup compared to numerical integration, it may lead to a large number of simulation failures. Overall, our study provides a concise overview across current methods for computing sensitivities at steady state, guiding modelers to choose the right methods.

q-bio.QM↗

arXiv2023

pyPESTO: A modular and scalable tool for parameter estimation for dynamic models

Mechanistic models are important tools to describe and understand biological processes. However, they typically rely on unknown parameters, the estimation of which can be challenging for large and complex systems. We present pyPESTO, a modular framework for systematic parameter estimation, with scalable algorithms for optimization and uncertainty quantification. While tailored to ordinary differential equation problems, pyPESTO is broadly applicable to black-box parameter estimation problems. Besides own implementations, it provides a unified interface to various popular simulation and inference methods. pyPESTO is implemented in Python, open-source under a 3-Clause BSD license. Code and documentation are available on GitHub (https://github.com/icb-dcm/pypesto).

q-bio.QM↗

arXiv2021

A protocol for dynamic model calibration

Ordinary differential equation models are nowadays widely used for the mechanistic description of biological processes and their temporal evolution. These models typically have many unknown and non-measurable parameters, which have to be determined by fitting the model to experimental data. In order to perform this task, known as parameter estimation or model calibration, the modeller faces challenges such as poor parameter identifiability, lack of sufficiently informative experimental data, and the existence of local minima in the objective function landscape. These issues tend to worsen with larger model sizes, increasing the computational complexity and the number of unknown parameters. An incorrectly calibrated model is problematic because it may result in inaccurate predictions and misleading conclusions. For non-expert users, there are a large number of potential pitfalls. Here, we provide a protocol that guides the user through all the steps involved in the calibration of dynamic models. We illustrate the methodology with two models, and provide all the code required to reproduce the results and perform the same analysis on new models. Our protocol provides practitioners and researchers in biological modelling with a one-stop guide that is at the same time compact and sufficiently comprehensive to cover all aspects of the problem.

q-bio.QM↗

arXiv2020

AMICI: High-Performance Sensitivity Analysis for Large Ordinary Differential Equation Models

Ordinary differential equation models facilitate the understanding of cellular signal transduction and other biological processes. However, for large and comprehensive models, the computational cost of simulating or calibrating can be limiting. AMICI is a modular toolbox implemented in C++/Python/MATLAB that provides efficient simulation and sensitivity analysis routines tailored for scalable, gradient-based parameter estimation and uncertainty quantification. AMICI is published under the permissive BSD-3-Clause license with source code publicly available on https://github.com/AMICI-dev/AMICI. Citeable releases are archived on Zenodo.

q-bio.QM↗

arXiv2020

PEtab -- interoperable specification of parameter estimation problems in systems biology

Reproducibility and reusability of the results of data-based modeling studies are essential. Yet, there has been -- so far -- no broadly supported format for the specification of parameter estimation problems in systems biology. Here, we introduce PEtab, a format which facilitates the specification of parameter estimation problems using Systems Biology Markup Language (SBML) models and a set of tab-separated value files describing the observation model and experimental data as well as parameters to be estimated. We already implemented PEtab support into eight well-established model simulation and parameter estimation toolboxes with hundreds of users in total. We provide a Python library for validation and modification of a PEtab problem and currently 20 example parameter estimation problems based on recent studies. Specifications of PEtab, the PEtab Python library, as well as links to examples, and all supporting software tools are available at https://github.com/PEtab-dev/PEtab, a snapshot is available at https://doi.org/10.5281/zenodo.3732958. All original content is available under permissive licenses.

q-bio.QM↗