Neural network aided approximation and parameter inference of non-Markovian models of gene expression

Qingchao Jiang, Xiaoming Fu, Shifu Yan, Runlai Li, Wenli Du, Zhixing Cao, Qian Feng, Ramon Grima

Research output: Contribution to journalArticlepeer-review

Abstract

Non-Markovian models of stochastic biochemical kinetics often incorporate explicit time delays to effectively model large numbers of intermediate biochemical processes. Analysis and simulation of these models, as well as the inference of their parameters from data, are fraught with difficulties because the dynamics depends on the system’s history. Here we use an artificial neural network to approximate the time-dependent distributions of non-Markovian models by the solutions of much simpler time in homogeneous Markovian models; the approximation does not increase the dimensionality of the model and simultaneously leads to inference of the kinetic parameters. The training of the neural network uses a relatively small set of noisy measurements generated by experimental data or stochastic simulations of the non-Markovian model. We show using a variety of models, where the delays stem from transcriptional processes and feedback control, that the Markovian models learnt by the neural network accurately reflect the stochastic dynamics across parameter space.
Original languageEnglish
Article number2618
Number of pages12
JournalNature Communications
Volume12
DOIs
Publication statusPublished - 11 May 2021

Fingerprint Dive into the research topics of 'Neural network aided approximation and parameter inference of non-Markovian models of gene expression'. Together they form a unique fingerprint.

Cite this