Miic v2 (tmiic) (#131)

Implementation of tMIIC

.gitignore

@@ -1,6 +1,7 @@
 # RStudio
 *.Rproj
 *.Rproj.user
+.Rproj.user
 # R
 .Rhistory
 .RData

DESCRIPTION

@@ -1,23 +1,39 @@
 Package: miic
 Title: Learning Causal or Non-Causal Graphical Models Using Information Theory
-Version: 1.9.0
+Version: 2.0.0
 Authors@R:
-    c(person(given = "Vincent",
-             family = "Cabeli",
+    c(person(given = "Franck",
+             family = "Simon",
              role = c("aut", "cre"),
-             email = "[email protected]"),
+             email = "[email protected]"),
+      person(given = "Tiziana",
+             family = "Tocci",
+             role = "aut",
+             email = "[email protected]"),
+      person(given = "Nikita",
+             family = "Lagrange",
+             role = "aut",
+             email = "[email protected]"),
+      person(given = "Orianne",
+             family = "Debeaupuis",
+             role = "aut",
+             email = "[email protected]"),
+      person(given = "Louise",
+             family = "Dupuis",
+             role = "aut",
+             email = "[email protected]"),
+      person(given = "Vincent",
+             family = "Cabeli",
+             role = "aut"),
       person(given = "Honghao",
              family = "Li",
-             role = "aut",
-             email = "[email protected]"),
+             role = "aut"),
       person(given = "Marcel",
              family = "Ribeiro Dantas",
-             role = "aut",
-             email = "[email protected]"),
+             role = "aut"),
       person(given = "Nadir",
              family = "Sella",
-             role = "aut",
-             email = "[email protected]"),
+             role = "aut"),
       person(given = "Louis",
              family = "Verny",
              role = "aut"),
@@ -27,7 +43,7 @@ Authors@R:
       person(given = "Hervé",
              family = "Isambert",
              role = "aut",
-             email = "Herve.Isambert@curie.fr"))
+             email = "herve.isambert@curie.fr"))
 Description: We report an information-theoretic method which learns a large
     class of causal or non-causal graphical models from purely observational
     data, while including the effects of unobserved latent variables, commonly
@@ -39,7 +55,10 @@ Description: We report an information-theoretic method which learns a large
     be applied on a wide range of datasets and provide new biological insights
     on regulatory networks from single cell expression data, genomic alterations
     during tumor development and co-evolving residues in protein structures.
-    For more information you can refer to:
+    Since the version 2.0, MIIC can in addition process stationary time series 
+    to unveil temporal causal graphs.
+    For more information, you can refer to:
+    Simon et al. eLife, reviewed preprint <doi:10.1101/2024.02.06.579177>, 
     Cabeli et al. PLoS Comp. Bio. 2020 <doi:10.1371/journal.pcbi.1007866>,
     Verny et al. PLoS Comp. Bio. 2017 <doi:10.1371/journal.pcbi.1005662>.
 License: GPL (>= 2)
@@ -60,4 +79,4 @@ LinkingTo:
 SystemRequirements: C++14
 LazyData: true
 Encoding: UTF-8
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1

NAMESPACE

@@ -1,14 +1,17 @@
 # Generated by roxygen2: do not edit by hand
 
 S3method(plot,miic)
+S3method(plot,tmiic)
 export(computeMutualInfo)
 export(computeThreePointInfo)
 export(discretizeMDL)
 export(discretizeMutual)
+export(estimateTemporalDynamic)
 export(miic)
 export(miic.export)
 export(miic.write.network.cytoscape)
 export(miic.write.style.cytoscape)
+export(tmiic.export)
 import(Rcpp)
 importFrom(stats,density)
 importFrom(stats,sd)

NEWS.md

@@ -1,13 +1,72 @@
 # Development version
 
+# v2.0.0
+
+## Features
+
+- tMIIC version for temporal causal discovery on stationary time series: 
+  new mode of MIIC to reconstruct networks from temporal stationary datasets.
+  [Simon et al., eLife, reviewed preprint]
+  (https://www.biorxiv.org/content/10.1101/2024.02.06.579177v1.abstract)
+
+## Known issues
+
+- A (very) large number of contributors can lead to a memory fault.
+  Initial fix has been reverted due to side effects.
+
+# v1.8.1
+
+## Fixes and improvements
+
+- The discretization of continuous variables has been modified when dealing 
+  with variables having a large number of identical values.
+
+- Fix for memory overflow on shared memory space.
+
+# v1.8.0
+
+## Features
+
+- Addition of the 'is consequence' prior knowledge. Consequence variables are 
+  excluded from the possible contributors, edges between consequences are 
+  ignored and edges between a non consequence and a consequence are pre-oriented 
+  toward the consequence.
+
+# v1.7.0
+
+## Features
+
+- iMIIC version introducing genuine vs putative causes, contextual variables
+  and multiple enhancements to deal with very large datasets.
+  [Ribeiro-Dantas et al., iScience 2024]
+  (https://arxiv.org/abs/2303.06423)
+
+# v1.6.0
+
+## Features
+
+- Enhancement of orientations using mutual information supremum principle for 
+  finite datasets.
+  [Cabeli et al., Why21 at NeurIPS 2021]
+  (http://kinefold.curie.fr/isambertlab/PAPERS/cabeli_Why21-NeurIPS2021.pdf)
+
+- By default, MIIC does not propagate orientations anymore
+  and allows latent variables discovery during orientation step. 
+
+# v1.5.3
+
+## Features
+
+- Release to CRAN
+
 # v1.5.2
 
 ## Fixes and improvements
-- Further refactoring of the C++ code for the computation of information
+- Further refactoring of the C++ code for the computation of information.
 
-- Fix minor bugs in the continuous computation
+- Fix minor bugs in the continuous computation.
 
-- Fix incompatibility with older versions of GCC (std::align)
+- Fix incompatibility with older versions of GCC (std::align).
 
 # v1.5.1
 
@@ -29,11 +88,11 @@
   edges.
 
 ## Fixes and improvements
-- Faster post processing in R
+- Faster post processing in R.
 
-- Rework plot functionality
+- Rework plot functionality.
 
-- Fix a bug in the orientation part about the log score
+- Fix a bug in the orientation part about the log score.
 
 - Refactor of the C++ code base (orientation).
 

R/data.R

@@ -101,3 +101,20 @@ NULL
 #'
 #' @keywords data
 NULL
+
+#' Covid cases
+#'
+#' Demo dataset of chronological series to be used in temporal mode of miic.
+#' Evolution of Covid cases on a subset of EU countries from 12/31/2019 to 06/18/2020.
+#' Source of the data : European Centre for Disease Prevention and Control.
+#'
+#' @docType data
+#' @usage data(covidCases)
+#' @format A data.frame object.
+#' @keywords datasets
+#' @name covidCases
+#' @references ECDC (\href{https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide}{ECDC link})
+#'
+#' @keywords data
+NULL
+

R/discretizeMutual.R

@@ -1,6 +1,6 @@
 #' Iterative dynamic programming for (conditional) mutual information through optimized discretization.
 #' @description This function chooses cutpoints in the input distributions by maximizing the mutual
-#' information minus a complexity cost (computed as BIC or with the Normalized Maximum Likelihood ). The
+#' information minus a complexity cost (computed as BIC or with the Normalized Maximum Likelihood). The
 #' (conditional) mutual information computed on the optimized discretized distributions effectively approaches
 #' the mutual information computed on the original continuous variables.
 #'
@@ -52,11 +52,13 @@
 #'
 #' @return A list that contains :
 #' \itemize{
-#' \item{two vectors containing the cutpoints for each variable : \emph{cutpoints1} corresponds to /emph{myDist1}, /emph{cutpoints2} corresponds to /emph{myDist2}.}
+#' \item{two vectors containing the cutpoints for each variable :
+#' \emph{cutpoints1} corresponds to \emph{X},
+#' \emph{cutpoints2} corresponds to \emph{Y}.}
 #' \item{\emph{niterations} is the number of iterations performed before convergence of the (C)MI estimation.}
 #' \item{\emph{iterationN}, lists contatining the cutpoint vectors for each iteration.}
 #' \item{\emph{info} and \emph{infok}, the estimated (C)MI value and (C)MI minus the complexity cost.}
-#' \item{if $emph{plot} == TRUE, a plot object (requires ggplot2 and gridExtra).}
+#' \item{if \emph{plot} == TRUE, a plot object (requires ggplot2 and gridExtra).}
 #' }
 #' @export
 #' @useDynLib miic