Computational Tools


MomentClosure.jl

MomentClosure.jl is a Julia package providing automated derivation of the time-evolution equations of the moments of molecule numbers for virtually any chemical reaction network using a wide range of moment closure approximations. Source code and documentation are available at https://github.com/augustinas1/MomentClosure.jl. Paper briefly discussing the package PDF

DelaySSAToolkit.jl

DelaySSAToolkit.jl is a Julia package for modelling reaction systems with non-Markovian dynamics, specifically those with deterministic or non-exponential time delays (in the example below this is shown by double right arrow). Source code and documentation are available at https://github.com/palmtree2013/DelaySSAToolkit.jl. Paper briefly discussing the package PDF

Neural Estimation of Stochastic Simulations for Inference and Exploration (NESSIE)

Nessie leverages the representational power of neural networks to approximate the solution of the chemical master equation (the stochastic description of biochemical systems dynamics). Source code and documentation are available at https://github.com/augustinas1/Nessie Paper introducing and showcasing NESSIE PDF
 

 
Neural network aided approximation and parameter inference of non-Markovian models of gene expression
 
We circumvent the challenges of analysing and inferring non-Markovian stochastic biochemical models with deterministic or stochastic time delays by using a neural network to approximate their dynamics with simpler time-inhomogeneous Markovian models. PDF
 

Efficient and scalable prediction of spatio-temporal stochastic gene expression in cells and tissues using graph neural networks
 
We introduce a graph neural network approach that learns an effective master equation for sub-cellular gene expression from limited spatial stochastic simulations, enabling accurate and scalable prediction of mRNA and protein distributions across tissues at a fraction of the usual computational cost. PDF
 
 
DART: Deep learning for the Analysis and Reconstruction of Transcriptional dynamics from live-cell imaging data
 
DART is a deep learning framework that infers promoter switching dynamics and kinetic parameters from live-cell fluorescence traces, outperforming existing methods and revealing non-trivial coupling between transcriptional activation and inactivation rates. PDF