Biology subjects

Rackauckas, C. V.

Publications and source records attributed to Rackauckas, C. V..

5 recordsLinked to original sources

bioRxiv2023

Uncertainty quantified discovery of chemical reaction systems via Bayesian scientific machine learning

1The recently proposed Chemical Reaction Neural Network (CRNN) discovers chemical reaction pathways from time resolved species concentration data in a deterministic manner. Since the weights and biases of a CRNN are physically interpretable, the CRNN acts as a digital twin of a classical chemical reaction network. In this study, we employ a Bayesian inference analysis coupled with neural ordinary differential equations (ODEs) on this digital twin to discover chemical reaction pathways in a probabilistic manner. This allows for estimation of the uncertainty surrounding the learned reaction network. To achieve this, we propose an algorithm which combines neural ODEs with a preconditioned stochastic gradient langevin descent (pSGLD) Bayesian framework, and ultimately performs posterior sampling on the neural network weights. We demonstrate the successful implementation of this algorithm on several reaction systems by not only recovering the chemical reaction pathways but also estimating the uncertainty in our predictions. We compare the results of the pSGLD with that of the standard SGLD and show that this optimizer more efficiently and accurately estimates the posterior of the reaction network parameters. Additionally, we demonstrate how the embedding of scientific knowledge improves extrapolation accuracy by comparing results to purely data-driven machine learning methods. Together, this provides a new framework for robust, autonomous Bayesian inference on unknown or complex chemical and biological reaction systems.

systems biology↗

bioRxiv2022

Catalyst: Fast Biochemical Modeling with Julia

We introduce Catalyst.jl, a flexible and feature-filled Julia library for modeling and high-performance simulation of chemical reaction networks (CRNs). Catalyst supports simulating stochastic chemical kinetics (jump process), chemical Langevin equation (stochastic differential equation), and reaction rate equation (ordinary differential equation) representations for CRNs. Through comprehensive benchmarks, we demonstrate that Catalyst simulation runtimes are often one to two orders of magnitude faster than other popular tools. More broadly, Catalyst acts as both a domain-specific language and an intermediate representation for symbolically encoding CRN models as Julia-native objects. This enables a pipeline of symbolically specifying, analyzing, and modifying CRNs; converting Catalyst models to symbolic representations of concrete mathematical models; and generating compiled code for numerical solvers. Leveraging ModelingToolkit.jl and Symbolics.jl, Catalyst models can be analyzed, simplified, and compiled into optimized representations for use in numerical solvers. Finally, we demonstrate Catalysts broad extensibility and composability by highlighting how it can compose with a variety of Julia libraries, and how existing open-source biological modeling projects have extended its intermediate representation.

systems biology↗

bioRxiv2021

Stably Accelerating Stiff Quantitative Systems Pharmacology Models: Continuous-Time Echo State Networks as Implicit Machine Learning

Quantitative systems pharmacology (QsP) may need to change in order to accommodate machine learning (ML), but ML may need to change to work for QsP. Here we investigate the use of neural network surrogates of stiff QsP models. This technique reduces and accelerates QsP models by training ML approximations on simulations. We describe how common neural network methodologies, such as residual neural networks, recurrent neural networks, and physics/biologically-informed neural networks, are fundamentally related to explicit solvers of ordinary differential equations (ODEs). Similar to how explicit ODE solvers are unstable on stiff QsP models, we demonstrate how these ML architectures see similar training instabilities. To address this issue, we showcase methods from scientific machine learning (SciML) which combine techniques from mechanistic modeling with traditional deep learning. We describe the continuous-time echo state network (CTESN) as the implicit analogue of ML architectures and showcase its ability to accurately train and predict on these stiff models where other methods fail. We demonstrate the CTESNs ability to surrogatize a production QsP model, a >1,000 ODE chemical reaction system from the SBML Biomodels repository, and a reaction-diffusion partial differential equation. We showcase the ability to accelerate QsP simulations by up to 56x against the optimized DifferentialEquations.jl solvers while achieving <5% relative error in all of the examples. This shows how incorporating the numerical properties of QsP methods into ML can improve the intersection, and thus presents a potential method for accelerating repeated calculations such as global sensitivity analysis and virtual populations.

pharmacology and toxicology↗

bioRxiv2021

Efficient Precision Dosing Under Estimated Uncertainties via Koopman Expectations of Bayesian Posteriors with Pumas

Personalized precision dosing is about mathematically determining effective dosing strategies that optimize the probability of containing a patients outcome within a therapeutic window. However, the common Monte Carlo approach for generating patient statistics is computationally expensive because thousands of simulations need to be computed. In this manuscript we describe a new method which utilizes the Koopman operator to perform a direct computation of expected patient outcomes with respect to quantified uncertainties of Bayesian posteriors in a nonlinear mixed effect model framework. We detail how quantities such as the probability of being within the therapeutic window can be calculated with a choice of loss function on the Koopman expectation. We demonstrate a high performance parallelized implementation of this methodology in Pumas(R) and showcase the ability to accelerate the computation of these expectations by 50x-200x over Monte Carlo. We showcase how dosing can be optimized with respect to probabilistic statements respecting variable uncertainties using the Koopman operator. We end by demonstrating an end-to-end workflow, from estimating variable uncertainties via Bayesian estimation to optimizing a dose with respect to parametric uncertainty.

pharmacology and toxicology↗

bioRxiv2020

Accelerated Predictive Healthcare Analytics with Pumas, A High Performance Pharmaceutical Modeling and Simulation Platform

Pharmacometric modeling establishes causal quantitative relationships between administered dose, tissue exposures, desired and undesired effects and patients risk factors. These models are employed to de-risk drug development and guide precision medicine decisions. However, pharmacometric tools have not been designed to handle todays heterogeneous big data and complex models. We set out to design a platform that facilitates domain-specific modeling and its integration with modern analytics to foster innovation and readiness in healthcare. Pumas demonstrates estimation methodologies with dramatic performance advances. New ODE solver algorithms, such as coeficient-optimized higher order integrators and new automatic stiffness detecting algorithms which are robust to frequent discontinuities, give rise to a median 4x performance improvement across a wide range of stiff and non-stiff systems seen in pharmacometric applications. These methods combine with JIT compiler techniques, such as statically-sized optimizations and discrete sensitivity analysis via forward-mode automatic differentiation, to further enhance the accuracy and performance of the solving and parameter estimation process. We demonstrate that when all of these techniques are combined with a validated clinical trial dosing mechanism and non-compartmental analysis (NCA) suite, real applications like NLME fitting see a median 81x acceleration while retaining the same accuracy. Meanwhile in areas with less prior software optimization, like optimal experimental design, we see orders of magnitude performance enhancements over competitors. Further, Pumas combines these technical advances with several workflows that are automated and designed to boost productivity of the day-to-day user activity. Together we show a fast pharmacometric modeling framework for next-generation precision analytics.

pharmacology and toxicology↗