Massive computational acceleration by using neural networks to emulate mechanism-based biological models

Abstract

Mechanism-based mathematical models are the foundation for diverse applications. It is often critical to explore the massive parametric space for each model. However, for many applications, such as agent-based models, partial differential equations, and stochastic differential equations, this practice can impose a prohibitive computational demand. To overcome this limitation, we present a fundamentally new framework to improve computational efficiency by orders of magnitude. The key concept is to train an artificial neural network using a limited number of simulations generated by a mechanistic model. This number is small enough such that the simulations can be completed in a short time frame but large enough to enable reliable training of the neural network. The trained neural network can then be used to explore the system dynamics of a much larger parametric space. We demonstrate this notion by training neural networks to predict self-organized pattern formation and stochastic gene expression. With this framework, we can predict not only the 1-D distribution in space (for partial differential equation models) and probability density function (for stochastic differential equation models) of variables of interest with high accuracy, but also novel system dynamics not present in the training sets. We further demonstrate that using an ensemble of neural networks enables the self-contained evaluation of the quality of each prediction. Our work can potentially be a platform for faster parametric space screening of biological models with user defined objectives.

Predictive biology: modelling, understanding and harnessing microbial complexity

“…Rather, integrating these advances to establish a next-generation paradigm of predictive biology will undoubtedly yield the greatest return (Figure 2). Indeed, several recent studies demonstrate that non-canonical uses of machine learning that leverage the utility of computational modeling can yield powerful quantitative insights, including generating coarse-grained predictions for ecological interactions 133 , improving computational efficiency to accelerate model predictions 134 , and elucidating causal mechanistic relationships between drug perturbation and cellular response 129 . For example, recent work by Yang et al used a "white-box" machine learning approach that integrated genome-scale network modeling with antibiotic IC50 data; the authors utilized a perturbation response methodology to tie machine learning predictions to experimental data, which identified nucleotide biosynthesis as a key metabolic pathway contributing to antibiotic lethality 129 .…”

Research on Modeling and Dynamic Characteristics of Complex Biological Neural Network Model considering BP Neural Network Method

“…e sine wave signal in brain waves does not exist alone. e lower the frequency, the lower the amplitude, and vice versa [5][6][7]. Consider the brain.…”

Exploring the rules of chimeric antigen receptor phenotypic output using combinatorial signaling motif libraries and machine learning

“…Due to the stochastic nature of network initialization and dropout, as well as the availability of a limited training set, every neural network is unique in terms of the parameterization of the network connections( 27, 28 ). To mitigate the potential impact of this issue, we implemented an ensemble decision method to obtain consensus prediction from ten identical neural networks.…”