Package: EDISON 1.1.1

Frank Dondelinger

EDISON: Network Reconstruction and Changepoint Detection

Package EDISON (Estimation of Directed Interactions from Sequences Of Non-homogeneous gene expression) runs an MCMC simulation to reconstruct networks from time series data, using a non-homogeneous, time-varying dynamic Bayesian network. Networks segments and changepoints are inferred concurrently, and information sharing priors provide a reduction of the inference uncertainty.

Authors:Frank Dondelinger, Sophie Lebre

EDISON_1.1.1.tar.gz
EDISON_1.1.1.tar.gz(r-4.5-noble)EDISON_1.1.1.tar.gz(r-4.4-noble)
EDISON_1.1.1.tgz(r-4.4-emscripten)EDISON_1.1.1.tgz(r-4.3-emscripten)
EDISON.pdf |EDISON.html✨
EDISON/json (API)
NEWS

# Install 'EDISON' in R:
install.packages('EDISON', repos = 'https://cloud.r-project.org')

On CRAN:

Conda:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

2.62 score 2 stars 1 packages 223 downloads 7 mentions 58 exports 2 dependencies

Last updated 9 years agofrom:9d3d366062. Checks:3 OK. Indexed: yes.

TargetResultLatest binary
Doc / VignettesOKMar 10 2025
R-4.5-linuxOKMar 10 2025
R-4.4-linuxOKMar 10 2025

Exports:AcceptableMoveaddProposalNetworkInfoBinoHyperMoveBinoHyperRatiobp.computeAlphabuildXYCalculateChangescalculateCPPGlobalcalculateCPProbabilitiescalculateEdgeProbabilitiescalculateEdgeProbabilitiesSegscalculateEdgeProbabilitiesTimePointsCalculateLikelihoodRatioCalculatePriorRatioCollectNetworkInfocomputePxcomputeRho4convert_netscp.birthcp.deathcp.shiftdefaultOptionsdinvgammaEDISON.runExpHyperMoveExpHyperRatioTargetfix_eigenvaluesgenerateNetworkHyperparameterMoveHyperParmsinitmainmake_structure_moveNetworkProbBinoNetworkProbExpNetworkRatioBinoNetworkRatioExpoutputphase.updatePriorRatioPoissonproposalTuningproposeContinuousProposeDiscretepsrfpsrf_checkpsrf_check_hyperreadDataTSrinvgammarunDBNsampleBinitsampleBxysampleDelta2sampleKsampleParmssampleSig2simulateNetworkupdateSigMultiupdateSigSolo

Dependencies:corpcorMASS

Citation

To cite package EDISON in publications use:

Dondelinger F, Lèbre S, Husmeier D (2013). “Non-homogeneous dynamic Bayesian networks with Bayesian regularization for inferring gene regulatory networks with gradually time-varying structure.” Machine Learning, 90, 191-230.

Corresponding BibTeX entry: 

  @Article{,
    title = {Non-homogeneous dynamic Bayesian networks with Bayesian
      regularization for inferring gene regulatory networks with
      gradually time-varying structure},
    author = {F. Dondelinger and S. L\`{e}bre and D. Husmeier},
    year = {2013},
    journal = {Machine Learning},
    volume = {90},
    issue = {2},
    pages = {191-230},
  }

Readme and manuals

Help Manual

Help pageTopics
Allows for network reconstruction and changepoint detection.EDISON-package EDISON
Check if move is acceptable.AcceptableMove
Add the proposed new network to the new.nets list.addProposalNetworkInfo
Makes a binomial hyperparameter move.BinoHyperMove
Calculates the MH ratio of the binomial prior.BinoHyperRatio
Computes the acceptance ratio of two changepoint configurations.bp.computeAlpha
Builds response Y and predictor X.buildXY
Function to calculate the number of differences between adjaccent network segments.CalculateChanges
Calculated the global changepoint probabilities.calculateCPPGlobal
Calculate the changepoint probabilities.calculateCPProbabilities
Calculate the edge probabilities.calculateEdgeProbabilities
Calculate edge probabilities for fixed segments.calculateEdgeProbabilitiesSegs
Calculate the edge posterior probabilities for each timepoint.calculateEdgeProbabilitiesTimePoints
Calculates the ratio of two likelihoods in a structure move.CalculateLikelihoodRatio
Calculates the network prior ratio.CalculatePriorRatio
Collects all the network information in one list.CollectNetworkInfo
Compute projection matrix.computePx
Calculate proposal frequencies for changepoint moves.computeRho4
Convert internal representation of networks.convert_nets
Make changepoint birth move.cp.birth
Make changepoint death move.cp.death
Makes a changepoint shift move.cp.shift
Set the default options for the MCMC simulation.defaultOptions
Calculate inverse gamma distribution.dinvgamma
Wrapper function for starting an MCMC simulationEDISON.run
Makes an exponential hyperparameter move.ExpHyperMove
Calculates the ratio of an exponential hyperparameter move.ExpHyperRatioTarget
Modify network to ensure stationarity.fix_eigenvalues
Generate a random network.generateNetwork
Make a hyperparameter move.HyperparameterMove
Sets up initial values of hyperparameters.HyperParms
Initialise the MCMC simulation.init
Main function of the MCMC simulation.main
Makes a structure move.make_structure_move
Calculates the prior probability of the network segments under the binomial prior.NetworkProbBino
Calculates the prior probability of the network using the exponential prior.NetworkProbExp
Calculates the ratio of binomial prior probabilites.NetworkRatioBino
Calculates the ratio of exponential network prior probabilities.NetworkRatioExp
Collects and saves output.output
Make a network structure or hyperparameter move.phase.update
Calculate network prior ratio with Poisson prior.PriorRatioPoisson
Tune the proposal width for betas.proposalTuning
Propose a new real hyperparameter value.proposeContinuous
Propose a new discrete value.ProposeDiscrete
Calculates the potential scale reduction factor.psrf
Check the potential scale reduction factors for all parameters (edges).psrf_check
Checks the potential scale reduction factor for the hyperparameters.psrf_check_hyper
Read target data.readDataTS
Samples from the inverse gamma distribution.rinvgamma
Setup and run the MCMC simulation.runDBN
Sample initial regression coefficients.sampleBinit
Sample regression coefficients.sampleBxy
Sample delta squared.sampleDelta2
Sample initial number of changepoints.sampleK
Sample initial parameters for the MCMC simulation.sampleParms
Sample initial sigma squared.sampleSig2
Generate network and simulate data.simulateNetwork
Update sigma squared variances.updateSigMulti
Sample new values for sigma squared.updateSigSolo