Package {MosaiClusteR}

Type:	Package
Title:	An Umbrella Framework for Multi-Source and Multi-Omics Clustering
Version:	0.1.0
Description:	An umbrella framework ("MoSaIC" = Multi-Omics Source-Agnostic Integration Clustering in R) that unifies a large collection of multi-source / multi-omics clustering methodologies behind a single, consistent list-of-matrices interface. It spans five integration paradigms - direct, similarity-based, graph-based, voting-based consensus, and hierarchy-based - and bundles a complete downstream workflow for method comparison and evaluation. The package features the multi-source the ability to compare many algorithms on the same footing, a data-nugget based feature-weighting scheme as a robust, big-data-friendly alternative to variance weighting, and a downstream suite for cluster characterisation, visualisation and biological interpretation.
License:	GPL-3
Encoding:	UTF-8
LazyData:	false
Depends:	R (≥ 4.0)
Imports:	stats, utils, methods, graphics, grDevices, cluster, fastcluster, matrixStats, FD, ade4, e1071, gtools, data.table, Rcpp, Rdpack
LinkingTo:	Rcpp
Suggests:	SNFtool, datanugget, WCluster, LUCIDus, igraph, lsa, analogue, FactoMineR, pls, circlize, gplots, dendextend, plotrix, limma, MLP, biomaRt, org.Hs.eg.db, Biobase, a4Core, a4Base, plyr, genefilter, ggplot2, gridExtra, uwot, Rtsne, MOFAdata, testthat (≥ 3.0.0), knitr, rmarkdown
RdMacros:	Rdpack
Config/testthat/edition:	3
VignetteBuilder:	knitr
URL:	https://github.com/lucp12891/MosaiClusteR
BugReports:	https://github.com/lucp12891/MosaiClusteR/issues
NeedsCompilation:	yes
Config/roxygen2/version:	8.0.0
Packaged:	2026-07-20 16:19:03 UTC; hp
Author:	Bernard Isekah Osang'ir [aut, cre], Marijke Van Moerbeke [aut], Ziv Shkedy [ctb], Surya Gupta [ctb], Jürgen Claesen [ctb]
Maintainer:	Bernard Isekah Osang'ir <bernard.osangir@sckcen.be>
Repository:	CRAN
Date/Publication:	2026-07-29 18:30:07 UTC

MosaiClusteR: An Umbrella Framework for Multi-Source and Multi-Omics Clustering

Description

MosaiClusteR ("MoSaIC" = Multi-Omics Source-Agnostic Integration Clustering in R) unifies a large family of multi-source clustering methodologies behind a single, consistent list-of-matrices interface, and wraps them in a complete analysis framework: preprocessing, single-source baselines, integrative clustering across five paradigms, and downstream comparison/evaluation.

The MoSaIC framework (how to use the package)

1. Preprocess each source with Normalization and Distance.

2. Baseline each source on its own (any hierarchical clusterer) to motivate integration.

3. Integrate with one or more methods, e.g. M_ABCpp, M_ABCdist, WeightedClust, SNF, CEC, HierarchicalEnsembleClustering.

4. Evaluate and compare solutions with compare_clusterings and cluster_agreement.

Every clustering method returns a list containing at least DistM (a dissimilarity matrix) and Clust (a hierarchical-clustering object), so results are directly comparable and composable.

Feature weighting with data nuggets

The M-ABC family weights features for subsampling. Beyond the classic variance ("var") and coefficient-of-variation ("cv") schemes, MosaiClusteR adds weighting = "nugget", a robust, Big-Data-friendly alternative based on create_data_nuggets. See nugget_feature_weights and ABCpp.SingleInMultiple.

Author(s)

Maintainer: Bernard Isekah Osang'ir bernard.osangir@sckcen.be (ORCID)

Authors:

• Bernard Isekah Osang'ir bernard.osangir@sckcen.be (ORCID)

• Marijke Van Moerbeke

Other contributors:

• Ziv Shkedy [contributor]

• Surya Gupta [contributor]

• Jürgen Claesen [contributor]

See Also

Useful links:

• https://github.com/lucp12891/MosaiClusteR

• Report bugs at https://github.com/lucp12891/MosaiClusteR/issues

Single-source ABC with a deep-learning (autoencoder) Step 4 (ABCdeep)

Description

A deep-learning variant of ABCpp.SingleInMultiple that keeps the ABC algorithm of (Amaratunga et al. 2008) intact and replaces only Step 4: instead of clustering the raw feature sub-matrix, a neural autoencoder embeds the objects into a latent space and the latent vectors are clustered into NC base clusters. The stacked label matrix is fused across sources by f.clustABC.MultiSource, exactly as in M_ABCpp.

Usage

ABCdeep.SingleInMultiple(
  data,
  weighting = "var",
  normalize = NULL,
  gr = c(),
  bag = TRUE,
  numsim = 1000,
  numvar = 100,
  NC = NULL,
  topk_frac = 0.2,
  latent_dim = "auto",
  hidden_units = 32L,
  ae_epochs = 80L,
  ae_lr = 0.001,
  cluster_in_latent = "ward",
  linkage = "ward.D2",
  nugget_type = "between",
  nugget_args = list(),
  min_samples = 40L,
  seed = NULL
)

Arguments

Value

A data frame, numsim rows by one column per object; entries are base-cluster labels (0 = object not selected that iteration) – the same contract as ABCpp.SingleInMultiple.

Speed (trained once, forward pass per iteration)

The autoencoder is trained a single time on the source's top-topk_frac most-informative features; each of the numsim iterations then performs only a forward pass over the bootstrapped objects. The network is a self-contained, vectorised R autoencoder (He initialisation, ReLU, Adam, MSE) – there is no Python, TensorFlow or torch dependency, and no PCA or other fallback: a single code path.

References

Amaratunga D, Cabrera J, Kovtun V (2008). “Microarray Learning with ABC.” Biostatistics, 9(1), 128–136. doi:10.1093/biostatistics/kxm017. https://academic.oup.com/biostatistics/article-abstract/9/1/128/254198.

See Also

M_ABCdeep, ABCpp.SingleInMultiple, f.clustABC.MultiSource

Examples

data(mosaic_toy)
lab <- ABCdeep.SingleInMultiple(mosaic_toy$List[[1]], numsim = 40, NC = 3,
                                ae_epochs = 40, seed = 1)
dim(lab)

Single-source ABC with distance accumulation

Description

A variant of ABCpp.SingleInMultiple that accumulates the mean scaled pairwise distance between co-selected objects across iterations, yielding a [0, 1] dissimilarity matrix that M_ABCdist fuses across sources.

Usage

ABCdist.SingleInMultiple(
  data,
  distmeasure = "euclidean",
  weighting = "var",
  normalize = NULL,
  gr = c(),
  bag = TRUE,
  numsim = 1000,
  numvar = 100,
  linkage = "ward.D",
  NC = NULL,
  mds = FALSE,
  nfeat = NULL,
  nugget_type = "between",
  nugget_args = list()
)

Arguments

Value

A list with D (N \times N dissimilarity), NC and ng (per-iteration feature count); if mds = TRUE also mds_coords.

References

(Amaratunga et al. 2008)

See Also

M_ABCdist, ABCpp.SingleInMultiple

Examples

data(mosaic_toy)
out <- ABCdist.SingleInMultiple(mosaic_toy$List[[1]], numsim = 40)
dim(out$D)

Single-source Aggregating Bundles of Clusters (ABC), C++-accelerated engine

Description

The canonical single-source ABC engine of (Amaratunga et al. 2008). Over numsim iterations it (optionally) bootstraps the objects, draws a weighted subsample of features, clusters the sub-matrix with fastcluster::hclust, and records each selected object's base-cluster label. M_ABCpp turns the stacked label matrix into a consensus dissimilarity using the C++ co-clustering kernel.

Usage

ABCpp.SingleInMultiple(
  data,
  distmeasure = "euclidean",
  weighting = "var",
  normalize = NULL,
  gr = c(),
  bag = TRUE,
  numsim = 1000,
  numvar = 100,
  linkage = "ward.D2",
  NC = NULL,
  mds = FALSE,
  nfeat = NULL,
  nugget_type = "between",
  nugget_args = list()
)

Arguments

Value

A data frame, numsim rows by one column per object; entries are base-cluster labels (0 = object not selected that iteration).

Feature weighting (incl. data nuggets)

Features are subsampled with probability proportional to a rank-transformed importance score:

• "var" – feature variance (the classic ABC choice);

• "cv" – coefficient of variation;

• "nugget" – NEW: the data-nugget between-group weighted variance (create_data_nuggets), a robust, Big-Data-friendly alternative to the raw variance;

• anything else – equal weights.

References

Amaratunga D, Cabrera J, Kovtun V (2008). “Microarray Learning with ABC.” Biostatistics, 9(1), 128–136. doi:10.1093/biostatistics/kxm017. https://academic.oup.com/biostatistics/article-abstract/9/1/128/254198.

See Also

M_ABCpp, create_data_nuggets

Examples

data(mosaic_toy)
lab <- ABCpp.SingleInMultiple(mosaic_toy$List[[1]], numsim = 40, NC = 3,
                              weighting = "nugget")
dim(lab)

Aggregated data clustering

Description

Aggregated Data Clustering (ADC) is a direct clustering multi-source technique. The data matrices are merged into a single fused data matrix on which a dissimilarity matrix is computed. Hierarchical clustering is then performed on this dissimilarity matrix.

Usage

ADC(
  List,
  distmeasure = "tanimoto",
  normalize = FALSE,
  method = NULL,
  clust = "agnes",
  linkage = "flexible",
  alpha = 0.625
)

Arguments

Value

The returned value is a list with the following three elements.

The value has class 'ADC'. The Clust element will be of interest for further applications.

References

Fodeh, S. J., Punch, W. & Tan, P.-N. (2013). On unifying multi-source information from probabilistically generated functional data. Proteins 81:1298-1310.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res_ADC <- ADC(List=L, distmeasure="euclidean", normalize=FALSE, method=NULL,
               clust="agnes", linkage="flexible", alpha=0.625)

## End(Not run)

Aggregated data ensemble clustering

Description

Aggregated Data Ensemble Clustering (ADEC) is a direct clustering multi-source technique. ADEC is an iterative procedure which starts with the merging of the data sets. In each iteration, a random sample of the features is selected and/or a resulting dendrogram is divided into k clusters for a range of values of k.

Usage

ADEC(
  List,
  distmeasure = "tanimoto",
  normalize = FALSE,
  method = NULL,
  t = 10,
  r = NULL,
  nrclusters = NULL,
  clust = "agnes",
  linkage = "flexible",
  alpha = 0.625
)

Arguments

Details

If r is specified and nrclusters is a fixed number, only a random sampling of the features will be performed for the t iterations (ADECa). If r is NULL and the nrclusters is a sequence, the clustering is performed on all features and the dendrogam is divided into clusters for the values of nrclusters (ADECb). If both r is specified and nrclusters is a sequence, the combination is performed (ADECc). After every iteration, either be random sampling, multiple divisions of the dendrogram or both, an incidence matrix is set up. All incidence matrices are summed and represent the distance matrix on which a final clustering is performed.

Value

The returned value is a list with the following three elements.

The value has class 'ADEC'. The Clust element will be of interest for further applications.

References

Fodeh, S. J., Punch, W. & Tan, P.-N. (2013). On unifying multi-source information from probabilistically generated functional data. Proteins 81:1298-1310.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res_ADEC <- ADEC(List=L, distmeasure="euclidean", normalize=FALSE, method=NULL,
                 t=5, r=50, nrclusters=5, clust="agnes", linkage="flexible", alpha=0.625)

## End(Not run)

Visualization of characteristic binary features of multiple data sets

Description

A tool to visualize characteristic binary features of a set of objects in comparison with the remaining objects for multiple data sets. The result is a matrix with coloured cells. Columns represent objects and rows represent the specified features. A feature which is present is give a coloured cell while an absent feature is represented by a grey cell. The labels on the right indicate the names of the features while the labels on the bottom are the names of the objects.

Usage

BinFeaturesPlot_MultipleData(
  leadCpds,
  orderLab,
  features = list(),
  data = list(),
  validate = NULL,
  colorLab = NULL,
  nrclusters = NULL,
  cols = NULL,
  name = c("Data1", "Data2"),
  colors1 = c("gray90", "blue"),
  colors2 = c("gray90", "green"),
  margins = c(5.5, 3.5, 0.5, 5.5),
  cexB = 0.8,
  cexL = 0.8,
  cexR = 0.8,
  spaceNames = 0.2,
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot visualizing the presence and absence of the characteristic binary features across multiple data sets.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

Comps=FindCluster(list(MCF7_F),nrclusters=10,select=c(1,8))

MCF7_Char=CharacteristicFeatures(List=NULL,Selection=Comps,binData=
list(fingerprintMat,targetMat),datanames=c("FP","TP"),nrclusters=NULL,
topC=NULL,sign=0.05,fusionsLog=TRUE,weightclust=TRUE,names=c("FP","TP"))

FeatFP=MCF7_Char$Selection$Characteristics$FP$TopFeat$Names[c(1:10)]
FeatTP=MCF7_Char$Selection$Characteristics$TP$TopFeat$Names[c(1:10)]

BinFeaturesPlot_MultipleData(leadCpds=Comps,orderLab=MCF7_Char$Selection$
objects$OrderedCpds,features=list(FeatFP,FeatTP),data=list(fingerprintMat,targetMat),
validate=NULL,colorLab=NULL,nrclusters=NULL,cols=NULL,name=c("FP","TP"),colors1=
c('gray90','blue'),colors2=c('gray90','green'),margins=c(5.5,3.5,0.5,5.5),cexB=0.80,
cexL=0.80,cexR=0.80,spaceNames=0.20,plottype="new",location=NULL)

## End(Not run)

Visualization of characteristic binary features of a single data set

Description

A tool to visualize characteristic binary features of a set of objects in comparison with the remaining objects for a single data set. The result is a matrix with coloured cells. Columns represent objects and rows represent the specified features. A feature which is present is give a coloured cell while an absent feature is represented by a grey cell. The labels on the right indicate the names of the features while the labels on the bottom are the names of the objects.

Usage

BinFeaturesPlot_SingleData(
  leadCpds = c(),
  orderLab = c(),
  features = c(),
  data = NULL,
  colorLab = NULL,
  nrclusters = NULL,
  cols = NULL,
  name = c("Data"),
  colors1 = c("gray90", "blue"),
  colors2 = c("gray90", "green"),
  highlightFeat = NULL,
  margins = c(5.5, 3.5, 0.5, 5.5),
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot visualizing the presence and absence of the characteristic binary features.

Examples

## Not run: 
data(fingerprintMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

Comps=FindCluster(list(MCF7_F),nrclusters=10,select=c(1,8))

MCF7_Char=CharacteristicFeatures(List=list(fingerprintMat),Selection=Comps,
binData=list(fingerprintMat),datanames=c("FP"),nrclusters=NULL,topC=NULL,
sign=0.05,fusionsLog=TRUE,weightclust=TRUE,names=c("FP"))
Feat=MCF7_Char$Selection$Characteristics$FP$TopFeat$Names[c(1:10)]

BinFeaturesPlot_SingleData(leadCpds=Comps,orderLab=MCF7_Char$Selection$
objects$OrderedCpds,features=Feat,data=fingerprintMat,colorLab=NULL,
nrclusters=NULL,cols=NULL,name=c("FP"),colors1=c('gray90','blue'),colors2=
c('gray90','green'),highlightFeat=NULL,margins=c(5.5,3.5,0.5,5.5),
plottype="new",location=NULL)

## End(Not run)

Box plots of one distance matrix categorized against another distance matrix.

Description

Given two distance matrices, the function categorizes one distance matrix and produces a box plot from the other distance matrix against the created categories. The option is available to choose one of the plots or to have both plots. The function also works on outputs from ADEC and CEC functions which do not have distance matrices but incidence matrices.

Usage

BoxPlotDistance(
  Data1,
  Data2,
  type = c("data", "dist", "clusters"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  lab1,
  lab2,
  limits1 = NULL,
  limits2 = NULL,
  plot = 1,
  StopRange = FALSE,
  plottype = "new",
  location = NULL
)

Arguments

Value

One/multiple box plots.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)


BoxPlotDistance(MCF7_F,MCF7_T,type="cluster",lab1="FP",lab2="TP",limits1=c(0.3,0.7),
limits2=c(0.3,0.7),plot=1,StopRange=FALSE,plottype="new", location=NULL)

## End(Not run)

Complementary ensemble clustering

Description

Complementary Ensemble Clustering (CEC) Complementary Ensemble Clustering (CEC, Fodeh2013) shows similarities with ADEC. However, instead of merging the data matrices, ensemble clustering is performedon each data matrix separately. The resulting incidence matrices for each data sets are combined in a weighted linear equation. The weighted incidence matrix is the input for the final clustering algorithm. Similarly as ADEC, there are versions depending of the specification of the number of features to sample and the number of clusters.

Usage

CEC(
  List,
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  t = 10,
  r = NULL,
  nrclusters = NULL,
  weight = NULL,
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  weightclust = 0.5
)

Arguments

Details

If r is specified and nrclusters is a fixed number, only a random sampling of the features will be performed for the t iterations (CECa). If r is NULL and the nrclusters is a sequence, the clustering is performedon all features and the dendrogam is divided into clusters for the values of nrclusters (CECb). If both r is specified and nrclusters is a sequence, the combination is performed (CECc). After every iteration, either be random sampling, multiple divisions of the dendrogram or both, an incidence matrix is set up. All incidence matrices are summed and represent the distance matrix on which a final clustering is performed.

Value

The returned value is a list of four elements:

The value has class 'CEC'.

References

Fodeh SJ, Punch W, Tan P (2013). “On Unifying Multi-source Information to Improve Subcellular Protein Localization Prediction.” Proteins: Structure, Function, and Bioinformatics, 81, 1298–1310.

Cumulative Voting Aggregation (CVAA / W-CVAA)

Description

CVAA performs cumulative voting consensus clustering. A reference partition is used to align the individual source partitions, which are then aggregated into a consensus stochastic membership matrix. Two variants are available: cumulative voting ("CVAA") and the information-weighted variant ("W-CVAA").

Usage

CVAA(
  Reference = NULL,
  nrclustersR = 7,
  List,
  typeL = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  votingMethod = c("CVAA", "W-CVAA"),
  optimalk = nrclustersR
)

Arguments

Details

Cumulative voting aggregation aligns each source membership matrix to a running consensus by least-squares voting, then averages cumulatively. The weighted variant orders the partitions by average information content and weights their contribution accordingly. When optimalk is smaller than nrclustersR the JS-ALink agglomeration is used to merge reference clusters.

Value

A list of two elements:

The value has class 'Ensemble'.

References

Ayad H.G. and Kamel M.S. (2008). Cumulative voting consensus method for partitions with variable number of clusters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(1), 160-173.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
Ref <- Cluster(L[[1]], type = "data", distmeasure = "euclidean")
attr(Ref, "method") <- "Single"
res <- CVAA(Reference = Ref, nrclustersR = 5, List = L, typeL = "data",
  distmeasure = c("euclidean","euclidean"), votingMethod = "CVAA", optimalk = 5)

## End(Not run)

Determine the characteristic features of clusters

Description

CharacteristicFeatures identifies the features that are characteristic for the objects of each cluster of one or more clustering results. Binary features are evaluated with Fisher's exact test, continuous features with the t-test. Multiplicity correction is included.

Usage

CharacteristicFeatures(
  List,
  Selection = NULL,
  binData = NULL,
  contData = NULL,
  datanames = NULL,
  nrclusters = NULL,
  sign = 0.05,
  topChar = NULL,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Value

A list with for each method the found (top) characteristics of the feature data per cluster.

References

Perualila-Tan N. et al. (2016). Weighted similarity-based clustering of chemical structures and bioactivity data in early drug discovery.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
MCF7_Char=CharacteristicFeatures(List=L,Selection=NULL,binData=list(fingerprintMat),
contData=NULL,datanames=c("FP"),nrclusters=7,topChar=20)

## End(Not run)

Interactive plot to determine DE Genes and DE features for a specific cluster

Description

If desired, the function produces a dendrogram of a clustering result. One or multiple clusters can be indicated by a mouse click. From these clusters DE genes and characteristic features are determined. It is also possible to provide the objects of interest without producing the plot.

Usage

ChooseCluster(
  Interactive = TRUE,
  leadCpds = NULL,
  clusterResult = NULL,
  colorLab = NULL,
  binData = NULL,
  contData = NULL,
  datanames = c("FP"),
  geneExpr = NULL,
  topChar = 20,
  topG = 20,
  sign = 0.05,
  nrclusters = NULL,
  cols = NULL,
  n = 1
)

Arguments

Details

This function may require the suggested packages 'a4Base', 'a4Core' and 'limma' when a gene expression matrix is supplied.

Value

A list with one element per cluster of interest with elements objects, Characteristics and (optionally) Genes.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

MCF7_Interactive=ChooseCluster(Interactive=TRUE,leadCpds=NULL,clusterResult=MCF7_T,
colorLab=MCF7_F,binData=list(fingerprintMat),datanames=c("FP"),geneExpr=geneMat,
topChar = 20, topG = 20,nrclusters=7,n=1)

## End(Not run)

Single-source base clustering

Description

Cluster one data (or distance) matrix with agglomerative hierarchical clustering. This is the Layer-2 baseline primitive of the MoSaIC framework: run it on each tile on its own to see what each modality recovers before integrating. It also underpins HierarchicalEnsembleClustering.

Usage

Cluster(
  Data,
  type = c("data", "dist"),
  distmeasure = "euclidean",
  normalize = FALSE,
  method = NULL,
  clust = "agnes",
  linkage = "ward",
  alpha = 0.625,
  StopRange = TRUE,
  ...
)

Arguments

Value

A list with DistM (the dissimilarity matrix) and Clust (an agnes object).

See Also

Distance, M_ABCpp

Examples

data(mosaic_toy)
base1 <- Cluster(t(mosaic_toy$List[[1]]), type = "data",
                 distmeasure = "euclidean")
mosaic_labels(base1, k = 3)[1:6]

Helper that colours dendrogram leaves by cluster membership

Description

Internal helper applied via dendrapply that colours the leaves and edges of a dendrogram according to the cluster a leaf belongs to, or to a specific selection of objects. Used by ClusterPlot.

Usage

ClusterCols(x, Data, nrclusters = NULL, cols = NULL, colorComps = NULL)

Arguments

Value

The dendrogram node x with coloured nodePar and edgePar attributes.

Colouring clusters in a dendrogram

Description

Plot a dendrogram with leaves colored by a result of choice.

Usage

ClusterPlot(
  Data1,
  Data2 = NULL,
  nrclusters = NULL,
  cols = NULL,
  colorComps = NULL,
  hangdend = 0.02,
  plottype = "new",
  location = NULL,
  ...
)

Arguments

Value

A plot of the dendrogram of the first clustering result with colored leaves. If a second clustering result is given in Data2, the colors are based on this clustering result.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(Colors1)

MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

ClusterPlot(MCF7_T ,nrclusters=7,cols=Colors1,plottype="new",location=NULL,
main="Clustering on Target Predictions: Dendrogram",ylim=c(-0.1,1.8))

## End(Not run)

Clustering aggregation

Description

The ClusteringAggregation includes the ensemble clustering methods Balls, Agglomerative (Aggl.) and Furthest which are graph-based consensus methods.

Usage

ClusteringAggregation(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  agglMethod = c("Balls", "Aggl", "Furthest", "LocalSearch"),
  improve = TRUE,
  distThresh_B = 0.5,
  distThresh_A = 0.8
)

Arguments

Details

Gionis, Mannila and Tsaparas (2007) propose heuristic algorithms in order to find a solution for the consensus problem. In a first step, a weighted graph is built from the objects with weights between two vertices determined by the fraction of clusterings that place the two vertices in different clusters. In a second step, an algorithm searches for the partition that minimizes the total number of disagreements with the given partitions. The Balls algorithm is an iterative process which finds a cluster for the consensus partition in each iteration. For each object, all objects at a distance of at most 0.5 are collected and the average distance of this set to the object of interest is calculated. If the average distance is less or equal to a parameter the objects form a cluster; otherwise the object forms a singleton. The Agglomerative (Aggl.) algorithm starts by considering every object as a singleton cluster. Next, the two closest clusters are merged if the average distance between the clusters is less than 0.5. If there are no two clusters with an average distance smaller than 0.5, the algorithm stops and returns the created clusters as a solution. The Furthest algorithm starts by placing all objects into a single cluster. In each iteration, the pair of objects that are the furthest apart are considered as new cluster centers. The remaining objects are appointed to the center that increases the cost of the partition the least and the new cost is computed. The cost is the sum of the all distances between the obtained partition and the partitions in the ensemble. The iteration continues until the cost of the new partition is higher than the previous partition.

Value

The returned value is a list of two elements:

The value has class 'Ensemble'.

References

Gionis, A., Mannila, H. and Tsaparas, P. (2007). Clustering aggregation. ACM Transactions on Knowledge Discovery from Data, 1(1), 4-es.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
Aggl_toy <- ClusteringAggregation(List = L, type = "data",
  distmeasure = c("euclidean", "euclidean"), normalize = c(FALSE, FALSE),
  method = c(NULL, NULL), clust = "agnes", linkage = c("ward", "ward"),
  alpha = 0.625, nrclusters = c(7, 7), agglMethod = "Aggl",
  improve = TRUE, distThresh_B = 0.5, distThresh_A = 0.8)

## End(Not run)

Create a color palette to be used in the plots

Description

In order to facilitate the visualization of the influence of the different methods on the clustering of the objects, colours can be used. The function ColorPalette is able to pick out as many colours as there are clusters. This is done with the help of the ColorRampPalette function of the grDevices package

Usage

ColorPalette(colors = c("red", "green"), ncols = 5)

Arguments

Value

A vector containing the hex codes of the chosen colors.

Examples

Colors1<-ColorPalette(c("cadetblue2","chocolate","firebrick2",
"darkgoldenrod2", "darkgreen","blue2","darkorchid3","deeppink2"), ncols=8)

Function that annotates colors to their names

Description

The ColorsNames function is used on the output of the ReorderToReference and matches the cluster numbers indicated by the cell with the names of the colors. This is necessary to produce the plot of the ComparePlot function and is therefore an internal function of this function but can also be applied separately.

Usage

ColorsNames(matrixColors, cols = NULL)

Arguments

Value

A matrix containing the hex code of the color that corresponds to each cell of the matrix to be colored. This function is called upon by the ComparePlot function.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(Colors1)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
names=c("FP","TP")

MatrixColors=ReorderToReference(List=L,nrclusters=7,fusionsLog=TRUE,weightclust=TRUE,
names=names)

Names=ColorsNames(matrixColors=MatrixColors,cols=Colors1)

## End(Not run)

Interactive comparison of single and multiple source clustering results

Description

The function CompareInteractive produces an interactive plot of the multiple source clustering results in ListM. By identifying a cluster or a method, a comparison with the single source clustering results in ListS is shown in a new plotting window.

Usage

CompareInteractive(
  ListM,
  ListS,
  nrclusters = NULL,
  cols = NULL,
  fusionsLogM = FALSE,
  fusionsLogS = FALSE,
  weightclustM = FALSE,
  weightclustS = FALSE,
  namesM = NULL,
  namesS = NULL,
  marginsM = c(2, 2.5, 2, 2.5),
  marginsS = c(8, 2.5, 2, 2.5),
  Interactive = TRUE,
  n = 1
)

Arguments

Value

A plot of the comparison of the elements of ListM, on which multiple clusters and/or methods can be identified to compare them to the elements in ListS.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(Colors1)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(fingerprintMat,targetMat)

MCF7_W=WeightedClust(List=L,type="data",distmeasure=c("tanimoto","tanimoto"),
normalize=c(FALSE,FALSE),method=c(NULL,NULL),weight=seq(1,0,-0.1),weightclust=0.5,
clust="agnes",linkage="ward",StopRange=FALSE)

ListM=list(MCF7_W)
namesM=c(seq(1.0,0.0,-0.1))

ListS=list(MCF7_F,MCF7_T)
namesS=c("FP","TP")

CompareInteractive(ListM,ListS,nrclusters=7,cols=Colors1,fusionsLogM=FALSE,
fusionsLogS=FALSE,weightclustM=FALSE,weightclustS=TRUE,namesM,namesS,
marginsM=c(2,2.5,2,2.5),marginsS=c(8,2.5,2,2.5),Interactive=TRUE,n=1)

## End(Not run)

Comparison of clustering results over multiple methods

Description

A visual comparison of the clustering results of several methods. The function relies on ReorderToReference and ColorsNames and renders the resulting matrix either as a rectangular heatmap (using the plotrix package) or in a circular format (using the circlize package).

Usage

ComparePlot(
  List,
  nrclusters = NULL,
  cols = NULL,
  fusionsLog = FALSE,
  weightclust = FALSE,
  names = NULL,
  margins = c(8.1, 3.1, 3.1, 4.1),
  circle = FALSE,
  canvaslims = c(-1, 1, -1, 1),
  Highlight = NULL,
  substr = NULL,
  cex.highlight = 1,
  cex.labels = 0.7,
  trackheightdend = 0.5,
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot which translates the matrix output of ReorderToReference.

Compares medoid clustering results based on silhouette widths

Description

The function CompareSilCluster compares the results of two medoid clusterings. The null hypothesis is that the clustering is identical. A test statistic is calculated and a p-value obtained with bootstrapping.

Usage

CompareSilCluster(
  List,
  type = c("data", "dist"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  nrclusters = NULL,
  names = NULL,
  nboot = 100,
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot of the density of the statistic under the null hypothesis. Further a list with two elements:

.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

List=list(fingerprintMat,targetMat)

Comparison=CompareSilCluster(List=List,type="data",
distmeasure=c("tanimoto","tanimoto"),normalize=c(FALSE,FALSE),method=c(NULL,NULL),
nrclusters=7,names=NULL,nboot=100,plottype="new",location=NULL)

Comparison

## End(Not run)

Comparison of clustering results for the single and multiple source clustering.

Description

The function CompareSvsM plots the comparison of the single source clustering results on the left and that of the multiple source clustering results on the right such that a visual comparison is possible.

Usage

CompareSvsM(
  ListS,
  ListM,
  nrclusters = NULL,
  cols = NULL,
  fusionsLogS = FALSE,
  fusionsLogM = FALSE,
  weightclustS = FALSE,
  weightclustM = FALSE,
  namesS = NULL,
  namesM = NULL,
  margins = c(8.1, 3.1, 3.1, 4.1),
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot with on the left the comparison over the objects in ListS and on the right a comparison over the objects in ListM.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(Colors1)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(fingerprintMat,targetMat)

MCF7_W=WeightedClust(List=L,type="data", distmeasure=c("tanimoto","tanimoto"),
normalize=c(FALSE,FALSE),method=c(NULL,NULL),weight=seq(1,0,-0.1),weightclust=0.5
,clust="agnes",linkage="ward",StopRange=FALSE)

ListM=list(MCF7_W)
namesM=seq(1.0,0.0,-0.1)

ListS=list(MCF7_F,MCF7_T)
namesS=c("FP","TP")

CompareSvsM(ListS,ListM,nrclusters=7,cols=Colors1,fusionsLogS=FALSE,
fusionsLogM=FALSE,weightclustS=FALSE,weightclustM=FALSE,namesS,
namesM,plottype="new",location=NULL)

## End(Not run)

Voting-based consensus clustering

Description

Consensus Clustering performs voting-based consensus on a set of single-source partitions. Each data matrix is clustered separately and the resulting label matrix is reconciled into a single consensus partition by an iterative voting scheme. Three voting methods are available: Iterative Voting Consensus (IVC), Iterative Probabilistic Voting Consensus (IPVC) and Iterative Pairwise Consensus (IPC).

Usage

ConsensusClustering(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  votingMethod = c("IVC", "IPVC", "IPC"),
  optimalk = 7
)

Arguments

Value

The returned value is a list of two elements:

The value has class 'Ensemble'.

References

Nguyen N. and Caruana R. (2007). Consensus Clusterings. Seventh IEEE International Conference on Data Mining (ICDM 2007), 607-612.

Examples

## Not run: 
data(mosaic_toy)
fit <- ConsensusClustering(List = mosaic_toy$List, type = "data",
  distmeasure = c("euclidean", "euclidean"), normalize = c(FALSE, FALSE),
  method = c(NULL, NULL), clust = "agnes", linkage = c("ward", "ward"),
  nrclusters = c(3, 3), gap = FALSE, votingMethod = "IVC", optimalk = 3)

## End(Not run)

Plot of continuous features

Description

The function ContFeaturesPlot plots the values of continuous features. It is possible to separate between objects of interest and the other objects.

Usage

ContFeaturesPlot(
  leadCpds,
  data,
  nrclusters = NULL,
  orderLab = NULL,
  colorLab = NULL,
  cols = NULL,
  ylab = "features",
  addLegend = TRUE,
  margins = c(5.5, 3.5, 0.5, 8.7),
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot in which the values of the features of the leadCpds are separeted from the others.

Examples

## Not run: 
data(Colors1)
Comps=c("Cpd1", "Cpd2", "Cpd3", "Cpd4", "Cpd5")

Data=matrix(sample(15, size = 50*5, replace = TRUE), nrow = 50, ncol = 5)
colnames(Data)=colnames(Data, do.NULL = FALSE, prefix = "col")
rownames(Data)=rownames(Data, do.NULL = FALSE, prefix = "row")
for(i in 1:50){
	rownames(Data)[i]=paste("Cpd",i,sep="")
}

ContFeaturesPlot(leadCpds=Comps,orderLab=rownames(Data),colorLab=NULL,data=Data,
nrclusters=7,cols=Colors1,ylab="features",addLegend=TRUE,margins=c(5.5,3.5,0.5,8.7),
plottype="new",location=NULL)

## End(Not run)

Comparison of clustering results over multiple results in circular format

Description

A visual comparison of all methods is handy to see which objects will always cluster together independent of the applied methods. To this aid the function Cyclogram has been written. The function relies on methods of the circlize package.

Usage

Cyclogram(
  List,
  nrclusters = NULL,
  cols = NULL,
  fusionsLog = FALSE,
  weightclust = FALSE,
  names = NULL,
  canvaslims = c(-1, 1, -1, 1),
  margins = c(8.1, 3.1, 3.1, 4.1),
  Highlight = NULL,
  cex.highlight = 1,
  substr = NULL,
  cex.labels = 0.7,
  plottype = "new",
  location = NULL
)

Arguments

Details

This function makes use of the functions ReorderToReference and Colorsnames. Given a list with the outputs of several methods, the first step is to call upon ReorderToReference and to produce a matrix of which the columns are ordered according to the ordering of the objects of the first method in the list. Each cell represent the number of the cluster the object belongs to for a specific method indicated by the rows. The clusters are arranged in such a way that these correspond to that one cluster of the referenced method that they have the most in common with. The circlize package is used to visualize the matrix is a circular format. The inner element of the circle is the first element of the List parameter, the second inner element is the second element of the list and so on. The object names are written on the circular dendrogram portayed in the center of the circle.

Value

A plot which translates the matrix output of the function ReorderToReference into a circular format.

Determines an optimal weight for weighted clustering by silhouettes widths.

Description

The function DetermineWeight_SilClust determines an optimal weight for weighted similarity clustering by calculating silhouettes widths. For each given weight, a linear combination of the distance matrices of the single data sources is obtained, medoid clustering is performed and the silhouette widths are regressed against the cluster memberships. A statistic is derived and a p-value obtained via bootstrapping.

Usage

DetermineWeight_SilClust(
  List,
  type = c("data", "dist", "clusters"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  weight = seq(0, 1, by = 0.01),
  nrclusters = NULL,
  names = NULL,
  nboot = 10,
  StopRange = FALSE,
  plottype = "new",
  location = NULL
)

Arguments

Value

Two plots and a list with two elements:

.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)

MC7_Weight=DetermineWeight_SilClust(List=L,type="clusters",distmeasure=
c("tanimoto","tanimoto"),normalize=c(FALSE,FALSE),method=c(NULL,NULL),
weight=seq(0,1,by=0.01),nrclusters=c(7,7),names=c("FP","TP"),nboot=10,
StopRange=FALSE,plottype="new",location=NULL)

## End(Not run)

Determines an optimal weight for weighted clustering by similarity weighted clustering.

Description

The function DetermineWeight_SimClust determines an optimal weight for performing weighted similarity clustering. For each given weight, each separate clustering is compared to the clustering on a weighted dissimilarity matrix and a Jaccard coefficient is calculated. The ratio of the Jaccard coefficients closest to one indicates an optimal weight.

Usage

DetermineWeight_SimClust(
  List,
  type = c("data", "dist", "clusters"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  weight = seq(0, 1, by = 0.01),
  nrclusters = NULL,
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  linkageF = "ward",
  alpha = 0.625,
  gap = FALSE,
  maxK = 15,
  names = NULL,
  StopRange = FALSE,
  plottype = "new",
  location = NULL
)

Arguments

Value

The returned value is a list with three elements:

.

References

Perualila-Tan, N. et al. (2016). Weighted similarity-based clustering of chemical structures and bioactivity data in early drug discovery. Journal of Bioinformatics and Computational Biology.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",alpha=0.625,gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",alpha=0.625,gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)

MCF7_Weight=DetermineWeight_SimClust(List=L,type="clusters",weight=seq(0,1,by=0.01),
nrclusters=c(7,7),distmeasure=c("tanimoto","tanimoto"),normalize=c(FALSE,FALSE),
method=c(NULL,NULL),clust="agnes",linkage=c("flexible","flexible"),linkageF="ward",
alpha=0.625,gap=FALSE,maxK=50,names=c("FP","TP"),StopRange=FALSE,plottype="new",location=NULL)

## End(Not run)

Find differentially expressed genes

Description

The DiffGenes function looks for differentially expressed genes for each cluster of a clustering result by comparing the objects of a cluster against all other objects. The limma method is applied to find the differentially expressed genes.

Usage

DiffGenes(
  List,
  Selection = NULL,
  geneExpr = NULL,
  nrclusters = NULL,
  method = "limma",
  sign = 0.05,
  topG = NULL,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Details

This function relies on the suggested Bioconductor package 'limma'.

Value

The result is a list with an element per method. Each element is again a list with for each cluster the found differentially expressed genes.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
names=c('FP','TP')

MCF7_FT_DE = DiffGenes(List=L,geneExpr=geneMat,nrclusters=7,method="limma",sign=0.05,
topG=10,fusionsLog=TRUE,weightclust=TRUE,names=names)

## End(Not run)

Differential expression for a selection of objects

Description

Internal function of DiffGenes.

Usage

DiffGenesSelection(
  List,
  Selection,
  geneExpr = NULL,
  nrclusters = NULL,
  method = "limma",
  sign = 0.05,
  topG = NULL,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Examples

## Not run: 
MCF7_FT_DE = DiffGenes(List=L,Selection=c("Cpd1","Cpd2"),geneExpr=geneMat,method="limma")

## End(Not run)

Compute a distance matrix

Description

Dispatcher computing an object-by-object distance matrix under a range of measures suitable for continuous, binary and mixed-type data.

Usage

Distance(
  Data,
  distmeasure = c("tanimoto", "jaccard", "euclidean", "hamming", "cont tanimoto",
    "MCA_coord", "gower", "chi.squared", "cosine"),
  normalize = NULL,
  method = NULL
)

Distance_v2(Data, distmeasure = "tanimoto", normalize = NULL)

Arguments

Details

"cosine", "chi.squared" and "MCA_coord" require the suggested packages lsa, analogue and FactoMineR respectively.

Value

A symmetric numeric distance matrix.

Examples

m <- matrix(rbinom(40, 1, 0.5), nrow = 8)
D <- Distance(m, distmeasure = "tanimoto")
dim(D)

Ensemble hierarchical clustering via graph partitioning (METIS / MST)

Description

Ensemble Hierarchical Clustering (EHC) builds a cluster association graph from the agglomerative clustering results of each data source. Strengths of association between pairs of objects are accumulated across the dendrograms (weighted by cluster depth and intra-cluster proximity), yielding a weighted adjacency matrix that is then partitioned.

Two partitioning strategies are available through graphPartitioning:

"METIS"

Delegates the partitioning of the association graph to an external graph-partitioning executable (METIS / gpmetis / shmetis, or the corresponding MATLAB hmetis routine). These binaries are not bundled with the package and must be configured through the executable argument. When executable=FALSE (the default), or when the configured executable cannot be located, the function stops with an informative error.

"MST"

A pure-R minimum spanning tree partitioning that needs no external executable. It does require the igraph package; if igraph is not installed the function stops with an informative error.

Usage

EHC(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  gap = FALSE,
  maxK = 15,
  graphPartitioning = c("METIS", "MST"),
  optimalk = 7,
  waitingtime = 300,
  file_number = 0,
  executable = FALSE
)

Arguments

Value

The returned value is a list of two elements:

The value has class 'Ensemble'.

References

Mirzaei A. and Rahmati M. (2010). A novel hierarchical-clustering-combination scheme based on fuzzy-similarity relations. IEEE Transactions on Fuzzy Systems, 18(1), 27-39.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List

# METIS path requires an external graph-partitioning executable / MATLAB
# configured through the 'executable' argument.
res <- EHC(List = L, type = "data",
  distmeasure = c("euclidean", "euclidean"), normalize = c(FALSE, FALSE),
  method = c(NULL, NULL), clust = "agnes",
  linkage = c("flexible", "flexible"), alpha = 0.625, gap = FALSE,
  maxK = 15, graphPartitioning = "METIS", optimalk = 7,
  executable = "./MetisAlgorithm")

# MST path is pure R but needs the igraph package.
res2 <- EHC(List = L, type = "data", graphPartitioning = "MST")

## End(Not run)

Ensemble clustering via graph partitioning (CSPA / HGPA / MCLA)

Description

Cluster-based ensemble clustering that combines several single-source partitions into a single consensus partition through the graph-partitioning algorithms of Strehl and Ghosh: the Cluster-based Similarity Partitioning Algorithm (CSPA), the HyperGraph Partitioning Algorithm (HGPA) and the Meta-CLustering Algorithm (MCLA), as well as a "Best" selection strategy.

External executable required. This method does not run in pure R. It writes the stacked label matrix to disk and delegates the actual graph partitioning to an external graph-partitioning executable (e.g. a compiled CSPA/HGPA/MCLA binary backed by METIS / gpmetis / shmetis) or to a MATLAB session. These binaries are not bundled with the package; the user must supply and configure them. The path to the executable is selected through the executable argument. When executable=FALSE (the default), or when the configured executable cannot be located, the function stops with an informative error rather than attempting to launch an unavailable program.

Usage

EnsembleClustering(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  ensembleMethod = c("CSPA", "HGPA", "MCLA", "Best"),
  waitingtime = 300,
  file_number = 0,
  executable = FALSE
)

Arguments

Value

The returned value is a list of two elements:

The value has class 'Ensemble'.

References

Strehl A. and Ghosh J. (2002). Cluster ensembles - a knowledge reuse framework for combining multiple partitions. Journal of Machine Learning Research, 3, 583-617.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List

# Requires an external graph-partitioning executable / MATLAB to be
# configured through the 'executable' argument.
res <- EnsembleClustering(List = L, type = "data",
  distmeasure = c("euclidean", "euclidean"), normalize = c(FALSE, FALSE),
  method = c(NULL, NULL), clust = "agnes",
  linkage = c("flexible", "flexible"), nrclusters = c(7, 7),
  gap = FALSE, maxK = 15, ensembleMethod = "CSPA",
  executable = "./EnsembleClusteringC")

## End(Not run)

Evidence accumulation clustering (co-association)

Description

EvidenceAccumulation builds a co-association (similarity) matrix from the individual source partitions and extracts a consensus partition by graph partitioning. Three graph-partitioning options are available: a minimum-spanning-tree procedure ("MST", requires the igraph package), a thresholded single-link procedure ("SL"), and an agnes single-link procedure ("SL_agnes").

Usage

EvidenceAccumulation(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  graphPartitioning = c("MST", "SL", "SL_agnes"),
  t = NULL
)

Arguments

Details

The co-association matrix S records the fraction of source partitions in which two objects are co-clustered. "MST" prunes a minimum spanning tree of the similarity graph (optionally at threshold t); "SL" performs a thresholded single-link grouping; and "SL_agnes" runs agnes single linkage on the dissimilarity 1-S. The "MST" path requires the suggested package igraph.

Value

A list of two elements:

The value has class 'Ensemble' (or 'Single Clustering' for "SL_agnes").

References

Fred A.L.N. and Jain A.K. (2005). Combining multiple clusterings using evidence accumulation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(6), 835-850.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res <- EvidenceAccumulation(List = L, type = "data",
  distmeasure = c("euclidean","euclidean"), nrclusters = c(5,5),
  graphPartitioning = "SL_agnes")

## End(Not run)

Determine the characteristic features of a cluster or selection

Description

FeatSelection determines the characteristic features of a selection of objects or of a specific cluster across the methods. Binary features are evaluated with Fisher's exact test, continuous features with the t-test.

Usage

FeatSelection(
  List,
  Selection = NULL,
  binData = NULL,
  contData = NULL,
  datanames = NULL,
  nrclusters = NULL,
  topChar = NULL,
  sign = 0.05,
  fusionsLog = TRUE,
  weightclust = TRUE
)

Arguments

Value

A list with the found (top) characteristics of the feature data.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F)
MCF7_FeatSel=FeatSelection(List=L,Selection=4,binData=list(fingerprintMat),
datanames=c("FP"),nrclusters=7,topChar=20)

## End(Not run)

List all features present in a selected cluster of objects

Description

The function FeaturesOfCluster lists the number of features objects of the cluster have in common. A threshold can be set selecting among how many objects of the cluster the features should be shared. An optional plot of the features is available.

Usage

FeaturesOfCluster(
  leadCpds,
  data,
  threshold = 1,
  plot = TRUE,
  plottype = "new",
  location = NULL
)

Arguments

Value

A list with 2 items: the number of shared features among the objects, and a character vector of the plotted features.

Examples

## Not run: 
data(fingerprintMat)

Lead=rownames(fingerprintMat)[1:5]

FeaturesOfCluster(leadCpds=Lead,data=fingerprintMat,
threshold=1,plot=TRUE,plottype="new",location=NULL)

## End(Not run)

Find a selection of objects in the output of ReorderToReference

Description

FindCluster selects the objects belonging to a cluster after the results of the methods have been rearranged by ReorderToReference.

Usage

FindCluster(
  List,
  nrclusters = NULL,
  select = c(1, 1),
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Value

A character vector containing the names of the objects in the selected cluster.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res <- list(Cluster(L[[1]], type = "data", distmeasure = "euclidean"),
            Cluster(L[[2]], type = "data", distmeasure = "euclidean"))
Comps <- FindCluster(List = res, nrclusters = 5, select = c(1, 2),
                     weightclust = FALSE)

## End(Not run)

Find an element in a data structure

Description

The function FindElement is used internally in the PreparePathway function but might come in handy for other uses as well. Given the name of an object, the function searches for that object in the data structure and extracts it. When multiple objects have the same name, all are extracted.

Usage

FindElement(what = NULL, object = NULL, element = list())

Arguments

Value

The returned value is a list with an element for each object found. The element contains everything the object contained in the original data structure.

Examples

## Not run: 
obj <- list(a = 1, b = list(TopDE = 42, c = list(TopDE = 7)))
FindElement(what = "TopDE", object = obj)

## End(Not run)

Find the genes shared across methods

Description

The FindGenes function collects the differentially expressed genes per cluster per method (the output of DiffGenes) and determines which genes are found across the methods.

Usage

FindGenes(dataLimma, names = NULL)

Arguments

Value

The result is a list with for each cluster a list of the found genes and the methods that found them.

Examples

## Not run: 
MCF7_SharedGenes=FindGenes(dataLimma=MCF7_FT_DE,names=c("FP","TP"))

## End(Not run)

Intersection over resulting gene sets of PathwaysIter function

Description

The function Geneset.intersect collects the results of the PathwaysIter function per method for each cluster and takes the intersection over the iterations per cluster per method. This is to see if over the different resamplings of the data, similar pathways were discovered.

Usage

Geneset.intersect(
  PathwaysOutput,
  Selection = FALSE,
  sign = 0.05,
  names = NULL,
  seperatetables = FALSE,
  separatepvals = FALSE
)

Arguments

Value

The output is a list with an element per method. For each method, it is portrayed per cluster which pathways belong to the intersection over all iterations and their corresponding mean p-values.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)
data(GeneInfo)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)

MCF7_Paths_FandT=PathwaysIter(List=L, geneExpr = geneMat, nrclusters = 7, method =
c("limma", "MLP"), geneInfo = GeneInfo, geneSetSource = "GOBP", topP = NULL,
topG = NULL, GENESET = NULL, sign = 0.05,niter=2,fusionsLog = TRUE,
weightclust = TRUE, names =names)

MCF7_Paths_intersection=Geneset.intersect(PathwaysOutput=MCF7_Paths_FandT,
sign=0.05,names=c("FP","TP"),seperatetables=FALSE,separatepvals=FALSE)

str(MCF7_Paths_intersection)

## End(Not run)

Intersection over resulting gene sets of PathwaysIter function for a selection of objects

Description

Internal function of Geneset.intersect.

Usage

Geneset.intersectSelection(
  list.output,
  sign = 0.05,
  names = NULL,
  seperatetables = FALSE,
  separatepvals = FALSE
)

Arguments

Examples

## Not run: 
Geneset.intersectSelection(MCF7_Paths_FandT,sign=0.05)

## End(Not run)

Hybrid Bipartite Graph Formulation

Description

The HBGF function implements the Hybrid Bipartite Graph Formulation, a graph-based consensus clustering method. A bipartite graph is constructed from the cluster ensemble (objects on one side, clusters on the other) and partitioned with a spectral method based on the singular value decomposition followed by k-means.

Usage

HBGF(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  graphPartitioning = "Spec",
  optimalk = 7
)

Arguments

Value

The returned value is a list of two elements:

The value has class 'Ensemble'.

References

Fern, X. Z. and Brodley, C. E. (2004). Solving cluster ensemble problems by bipartite graph partitioning. Proceedings of the Twenty-First International Conference on Machine Learning (ICML).

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
HBGF_toy <- HBGF(List = L, type = "data",
                 distmeasure = c("euclidean", "euclidean"),
                 normalize = c(FALSE, FALSE), method = c(NULL, NULL),
                 clust = "agnes", linkage = c("ward", "ward"),
                 nrclusters = c(7, 7), graphPartitioning = "Spec", optimalk = 7)

## End(Not run)

A heatmap of the comparison of two clustering results.

Description

A function to plot a heatmap of the agreement between two clustering results.

These are the clusters to which a comparison is made. A matrix is set up of which the columns are determined by the ordering of clustering of method 2 and the rows by the ordering of method 1. Every column represent one object just as every row and every column represent the color of its cluster. A function visits every cell of the matrix. If the objects represented by the cell are still together in a cluster, the color of the column is passed to the cell. This creates the distance matrix which can be given to the HeatmapCols function to create the heatmap.

Usage

HeatmapPlot(
  Data1,
  Data2,
  names = NULL,
  nrclusters = NULL,
  cols = NULL,
  plottype = "new",
  location = NULL
)

Arguments

Value

A heatmap based on the distance matrix created by the function with the dendrogram of method 2 on top of the plot and the one from method 1 on the left. The names of the objects are depicted on the bottom in the order of clustering of method 2 and on the right by the ordering of method 1. Vertically the cluster of method 2 can be seen while horizontally those of method 1 are portrayed.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(Colors1)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
clust="agnes",linkage="flexible",gap=FALSE,maxK=15)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
clust="agnes",linkage="flexible",gap=FALSE,maxK=15)


L=list(MCF7_F,MCF7_T)
names=c("FP","TP")

HeatmapPlot(Data1=MCF7_T,Data2=MCF7_F,names=rownames(fingerprintMat)
,nrclusters=7,cols=Colors1,plottype="new", location=NULL)

## End(Not run)

A function to select a group of objects via the similarity heatmap.

Description

The function HeatmapSelection plots the similarity values between objects. The plot is similar to the one produced by SimilarityHeatmap but without the dendrograms on the sides. The function is rather explorative and experimental and is to be used with some caution. By clicking in the plot, the user can select a group of objects of interest. See more in Details.

A similarity heatmap is created in the same way as in SimilarityHeatmap. The user is now free to select two points on the heatmap. It is advised that these two points are in opposite corners of a square that indicates a high similarity among the objects. The points do not have to be the exact corners of the group of interest, a little deviation is allowed as rows and columns of the selected subset of the matrix with sum equal to 1 are filtered out. A sum equal to one, implies that the compound is only similar to itself.

The function is meant to be explorative but is experimental. The goal was to make the selection of interesting objects easier as sometimes the labels of the dendrograms are too distorted to be read. If the figure is exported to a pdf file with an appropriate width and height, the labels can be become readable again.

Usage

HeatmapSelection(
  Data,
  type = c("data", "dist", "clust", "sim"),
  distmeasure = "tanimoto",
  normalize = FALSE,
  method = NULL,
  linkage = "flexible",
  cutoff = NULL,
  percentile = FALSE,
  dendrogram = NULL,
  width = 7,
  height = 7
)

Arguments

Value

A heatmap with the names of the objects on the right and bottom. Once points are selected, it will return the names of the objects that are in the selected square provided that these show similarity among each other.

Examples

## Not run: 
data(fingerprintMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55)

HeatmapSelection(Data=MCF7_F$DistM,type="dist",cutoff=0.90,percentile=TRUE,
dendrogram=MCF7_F,width=7,height=7)

## End(Not run)

Hierarchical ensemble clustering

Description

(Zheng et al. 2014) proposed the Hierarchical Ensemble Clustering (HEC) algorithm. For each dendrogram, the cophenetic distances between the object are calculated. The distances are aggregated across the data sets and an ultra-metric which is the closest to the distance matrix is determined. A final hierarchical clustering is based on the ultra-metric values.

Usage

HierarchicalEnsembleClustering(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625
)

Arguments

Value

The returned value is a list of two elements:

The value has class 'HEC'.

References

Zheng X, Chen BM, Zheng G (2014). “A Novel Approach for Hierarchical Ensemble Clustering.” IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 957–970.

LUCID: latent unknown clustering integrating omics with an outcome

Description

Thin wrapper around LUCIDus' estimate_lucid. LUCID is a model-based, supervised integrative clustering method: it defines a categorical latent variable (the clusters) jointly from upstream exposures G, multi-omics data Z and an outcome Y via an EM algorithm (a quasi-mediation model). Unlike the unsupervised methods in MosaiClusteR it requires an outcome and returns posterior cluster membership.

Usage

LUCID(
  G,
  Z,
  Y,
  K,
  lucid_model = c("early", "parallel", "serial"),
  family = c("normal", "binary"),
  ...
)

Arguments

Value

A list of class "LUCID" with the fitted model and the posterior cluster assignment per object.

References

Zhao, Y., Jia, K., Goodrich, J. & Conti, D. V. (2024). LUCIDus: an R package for implementing LUCID with phenotypic traits. The R Journal 16(2).

See Also

M_ABCpp, intNMF

Examples

## Not run: 
# requires the 'LUCIDus' package
data(mosaic_toy)
Z <- mosaic_toy$List[[1]]
G <- mosaic_toy$List[[2]][, 1:3]
Y <- as.numeric(mosaic_toy$truth)
fit <- LUCID(G = G, Z = Z, Y = Y, K = 3)
table(fit$cluster)

## End(Not run)

Helper that colours specific dendrogram leaves

Description

Internal helper applied via dendrapply that colours the leaves and edges of a dendrogram for one or two selections of objects. Used by LabelPlot.

Usage

LabelCols(x, Sel1, Sel2 = NULL, col1 = NULL, col2 = NULL)

Arguments

Value

The dendrogram node x with coloured nodePar and edgePar attributes.

Coloring specific leaves of a dendrogram

Description

The function plots a dendrogrmam of which specific leaves are coloured.

Usage

LabelPlot(Data, sel1, sel2 = NULL, col1 = NULL, col2 = NULL)

Arguments

Value

A plot of the dendrogram of which the leaves of the selection(s) are colored.

Examples

## Not run: 
data(fingerprintMat)
MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

ClustF_6=cutree(MCF7_F$Clust,6)

SelF=rownames(fingerprintMat)[ClustF_6==6]
SelF

LabelPlot(Data=MCF7_F,sel1=SelF,sel2=NULL,col1='darkorchid')

## End(Not run)

Link-based cluster ensembles

Description

Link-based cluster ensembles combine multiple base clusterings into a single, refined similarity matrix by exploiting the link structure between clusters of the ensemble. Three refinement schemes are available: Connected-Triple-Based Similarity ("cts"), SimRank-Based Similarity ("srs") and Approximate SimRank-Based Similarity ("asrs"). The refined object-by-object similarity matrix is turned into a dissimilarity matrix on which a final agglomerative hierarchical clustering is performed.

Usage

LinkBasedClustering(
  List,
  type = c("data", "dist", "clust"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625,
  nrclusters = c(7, 7),
  gap = FALSE,
  maxK = 15,
  linkBasedMethod = c("cts", "srs", "asrs"),
  decayfactor = 0.8,
  niter = 5,
  linkBasedLinkage = "ward",
  waitingtime = 300,
  file_number = 0,
  executable = FALSE
)

Arguments

Details

Each base clustering of the ensemble is represented as a hard partition. The clusters of all partitions form the vertices of a weighted graph; the link weights between clusters are derived from shared objects. The refined object-by-object similarity is obtained by propagating these cluster-to-cluster links ("cts", "srs", "asrs"). See Iam-On et al. (2010).

Value

The returned value is a list of two elements:

The value has class 'LinkBased'.

References

Iam-On, N., Boongoen, T., Garrett, S. and Price, C. (2010). Link-based cluster ensembles for the combination of multiple clusterings. IEEE Transactions on Knowledge and Data Engineering, 23(12), 1839-1853.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res <- LinkBasedClustering(List = L, type = "data",
  distmeasure = c("euclidean", "euclidean"), normalize = c(FALSE, FALSE),
  linkBasedMethod = "cts", decayfactor = 0.8, niter = 5,
  linkBasedLinkage = "ward", nrclusters = c(3, 3))

## End(Not run)

Multi-source M-ABC with a deep-learning (autoencoder) Step 4 (M-ABCdeep)

Description

The deep-learning counterpart of M_ABCpp: runs ABCdeep.SingleInMultiple per source (autoencoder embedding + latent clustering for the base partitions), row-stacks the per-iteration label matrices, and builds one consensus dissimilarity via f.clustABC.MultiSource. The ABC algorithm of (Amaratunga et al. 2008) is preserved end to end; only Step 4 is deep. There is no Python/torch dependency and no PCA fallback (see ABCdeep.SingleInMultiple).

Usage

M_ABCdeep(
  List,
  weighting = rep("var", length(List)),
  normalize = rep(FALSE, length(List)),
  gr = c(),
  bag = rep(TRUE, length(List)),
  numsim = 500,
  numvar = rep(100, length(List)),
  NC = NULL,
  dissimilarity = "mabc",
  final_linkage = "ward",
  alpha = 0.625,
  mds = FALSE,
  topk_frac = 0.2,
  latent_dim = "auto",
  hidden_units = 32L,
  ae_epochs = 80L,
  ae_lr = 0.001,
  cluster_in_latent = "ward",
  linkage = rep("ward.D2", length(List)),
  nugget_type = "between",
  nugget_args = list(),
  min_samples = 40L,
  seed = NULL
)

Arguments

Value

A list of class "M_ABC" with DistM and Clust.

References

Amaratunga D, Cabrera J, Kovtun V (2008). “Microarray Learning with ABC.” Biostatistics, 9(1), 128–136. doi:10.1093/biostatistics/kxm017. https://academic.oup.com/biostatistics/article-abstract/9/1/128/254198.

See Also

ABCdeep.SingleInMultiple, M_ABCpp, f.clustABC.MultiSource

Examples

data(mosaic_toy)
fit <- M_ABCdeep(mosaic_toy$List, numsim = 40, NC = 3, ae_epochs = 40, seed = 1)
table(stats::cutree(stats::as.hclust(fit$Clust), 3))

Multi-source M-ABC with distance accumulation

Description

Runs ABCdist.SingleInMultiple on each source to obtain a [0, 1] dissimilarity, combines them as a weighted mean D = \sum_k w_k D_k and applies a final agglomerative clustering.

Usage

M_ABCdist(
  List,
  source_weights = NULL,
  distmeasure = rep("euclidean", length(List)),
  weighting = rep("var", length(List)),
  normalize = rep(list(NULL), length(List)),
  gr = c(),
  bag = rep(TRUE, length(List)),
  numsim = 1000L,
  numvar = rep(100L, length(List)),
  linkage = rep("ward.D", length(List)),
  NC = NULL,
  NC2 = NULL,
  final_linkage = "ward",
  alpha = 0.625,
  mds = FALSE,
  nfeat = NULL,
  nugget_type = "between",
  nugget_args = list()
)

Arguments

Value

A list of class "M_ABCdist" with source_D, DistM, weights and Clust.

References

(Amaratunga et al. 2008)

See Also

M_ABCpp, ABCdist.SingleInMultiple, M_ABCdist.WC

Examples

data(mosaic_toy)
fit <- M_ABCdist(mosaic_toy$List, numsim = 40, weighting = c("var", "nugget"))
dim(fit$DistM)

Multi-source M-ABC fused with WeightedClust

Description

Runs ABCdist.SingleInMultiple on each source, then feeds the per-source dissimilarities to WeightedClust (type = "dist") to explore convex combinations over a weight grid and return the focus-weight clustering.

Usage

M_ABCdist.WC(
  List,
  distmeasure = rep("euclidean", length(List)),
  weighting = rep("var", length(List)),
  normalize = rep(list(NULL), length(List)),
  gr = c(),
  bag = rep(TRUE, length(List)),
  numsim = 1000L,
  numvar = rep(100L, length(List)),
  linkage = rep("ward.D", length(List)),
  NC = NULL,
  NC2 = NULL,
  StopRange = FALSE,
  wc_weight = seq(1, 0, -0.1),
  wc_weightclust = 0.5,
  wc_linkage = "ward",
  wc_alpha = 0.625,
  mds = FALSE,
  nugget_type = "between",
  nugget_args = list()
)

Arguments

Value

A list of class "M_ABCdist_WC" with source_D, the full WC object, the focus DistM and Clust, and the weight_grid.

References

(Amaratunga et al. 2008)

See Also

M_ABCdist, WeightedClust

Examples

data(mosaic_toy)
fit <- M_ABCdist.WC(mosaic_toy$List, numsim = 40,
                    wc_weight = seq(1, 0, -0.25), wc_weightclust = 0.5)
dim(fit$DistM)

Multi-source Aggregating Bundles of Clusters (M-ABC), C++-accelerated

Description

Extends the single-source ABC algorithm of (Amaratunga et al. 2008) to K \ge 2 sources: runs ABCpp.SingleInMultiple per source, row-stacks the per-iteration label matrices, and builds a single consensus dissimilarity via f.clustABC.MultiSource (C++ kernel when available).

Usage

M_ABCpp(
  List,
  distmeasure = rep("euclidean", length(List)),
  weighting = rep("var", length(List)),
  normalize = rep(FALSE, length(List)),
  gr = c(),
  bag = rep(TRUE, length(List)),
  numsim = 1000,
  numvar = rep(100, length(List)),
  linkage = rep("ward.D2", length(List)),
  NC = NULL,
  dissimilarity = "mabc",
  final_linkage = "ward",
  alpha = 0.625,
  mds = FALSE,
  nfeat = NULL,
  nugget_type = "between",
  nugget_args = list()
)

Arguments

Value

A list of class "M_ABC" with DistM and Clust.

Data-nugget weighting

Set weighting = "nugget" (per source, recycled) to weight features by the data-nugget between-group variance instead of the classic variance; see ABCpp.SingleInMultiple and create_data_nuggets.

References

Amaratunga D, Cabrera J, Kovtun V (2008). “Microarray Learning with ABC.” Biostatistics, 9(1), 128–136. doi:10.1093/biostatistics/kxm017. https://academic.oup.com/biostatistics/article-abstract/9/1/128/254198.

See Also

ABCpp.SingleInMultiple, f.clustABC.MultiSource, create_data_nuggets

Examples

data(mosaic_toy)
fit <- M_ABCpp(mosaic_toy$List, numsim = 50, NC = 3,
               weighting = c("var", "nugget"))
table(stats::cutree(stats::as.hclust(fit$Clust), 3))

NEMO: neighborhood-based multi-omics clustering

Description

NEMO (Wang et al. 2014) integrates several omics by building a locally-scaled, k-nearest-neighbour affinity network for each one and averaging them, for every pair of objects, over only the omics in which both objects are measured. Partial / missing modalities are therefore handled without imputation. The integrated affinity is clustered spectrally.

Usage

NEMO(List, k = NULL, NN = 20, normalize = TRUE)

Arguments

Value

A list of class "NEMO" with FusedM (integrated affinity), DistM (1 - FusedM), cluster (labels) and Clust (an agnes object on DistM for interoperability).

References

(Wang et al. 2014); Rappoport, N. & Shamir, R. (2019). NEMO: cancer subtyping by integration of partial multi-omic data. Bioinformatics 35:3348-3356.

See Also

SNF, spectral_clustering

Examples

data(mosaic_toy)
fit <- NEMO(mosaic_toy$List, k = 3, NN = 15)
table(fit$cluster)

Normalisation of features

Description

When data of different scales are combined it is recommended to normalise so that the structures are comparable.

Usage

Normalization(
  Data,
  method = c("Quantile", "Fisher-Yates", "Standardize", "Range", "Q", "q", "F", "f", "S",
    "s", "R", "r")
)

Arguments

Details

"Quantile" performs quantile normalisation (common in omics); "Fisher-Yates" uses normal scores based only on the number of rows; "Standardize" centres and scales each column (base scale); "Range" maps the matrix to [0, 1].

Value

The normalised matrix.

Examples

x <- matrix(rnorm(100), 10, 10)
Norm_x <- Normalization(x, method = "R")

Pathway analysis with intersection over iterations

Description

The PathwayAnalysis function performs pathway analysis multiple times via PathwaysIter and takes the intersection over the iterations via Geneset.intersect.

Usage

PathwayAnalysis(
  List,
  Selection = NULL,
  geneExpr = NULL,
  nrclusters = NULL,
  method = c("limma", "MLP"),
  geneInfo = NULL,
  geneSetSource = "GOBP",
  topP = NULL,
  topG = NULL,
  GENESET = NULL,
  sign = 0.05,
  niter = 10,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL,
  seperatetables = FALSE,
  separatepvals = FALSE
)

Arguments

Details

This function relies on the suggested Bioconductor packages 'MLP', 'biomaRt' and 'org.Hs.eg.db'.

Value

The intersection over the iterations of the pathway analysis.

Examples

## Not run: 
MCF7_PathsFandT=PathwayAnalysis(List=L, geneExpr = geneMat, nrclusters = 7,
method = c("limma","MLP"), geneInfo = GeneInfo, geneSetSource = "GOBP",niter=2)

## End(Not run)

Pathway analysis for multiple clustering results

Description

A pathway analysis per cluster per method is conducted.

Usage

Pathways(
  List,
  Selection = NULL,
  geneExpr = NULL,
  nrclusters = NULL,
  method = c("limma", "MLP"),
  geneInfo = NULL,
  geneSetSource = "GOBP",
  topP = NULL,
  topG = NULL,
  GENESET = NULL,
  sign = 0.05,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Details

After finding differently expressed genes, it can be investigated whether pathways are related to those genes. This can be done with the help of the function Pathways which makes use of the MLP function of the MLP package. Given the output of a method, the cutree function is performed which results into a specific number of clusters. For each cluster, the limma method is performed comparing this cluster to the other clusters. This to obtain the necessary p-values of the genes. These are used as the input for the MLP function to find interesting pathways. By default the candidate gene sets are determined by the AnnotateEntrezIDtoGO function. The default source will be GOBP, but this can be altered. Further, it is also possible to provide own candidate gene sets in the form of a list of pathway categories in which each component contains a vector of Entrez Gene identifiers related to that particular pathway. The default values for the minimum and maximum number of genes in a gene set for it to be considered were used. For MLP this is respectively 5 and 100. If a list of outputs of several methods is provided as data input, the cluster numbers are rearranged according to a reference method. The first method is taken as the reference and ReorderToReference is applied to get the correct ordering. When the clusters haven been re-appointed, the pathway analysis as described above is performed for each cluster of each method.

This function relies on the suggested Bioconductor packages 'MLP', 'biomaRt' and 'org.Hs.eg.db'.

Value

The returned value is a list with an element per cluster per method.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)
data(GeneInfo)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
names=c('FP','TP')

MCF7_PathsFandT=Pathways(List=L, geneExpr = geneMat, nrclusters = 7, method = c("limma",
"MLP"), geneInfo = GeneInfo, geneSetSource = "GOBP", topP = NULL,
topG = NULL, GENESET = NULL, sign = 0.05,fusionsLog = TRUE, weightclust = TRUE,
 names =names)
 
## End(Not run)

Iterations of the pathway analysis

Description

The MLP method to perform pathway analysis is based on resampling of the data. Therefore it is recommended to perform the pathway analysis multiple times to observe how much the results are influenced by a different resample. The function PathwaysIter performs the pathway analysis as described in Pathways a specified number of times. The input can be one data set or a list as in Pathway.2 and Pathways.

Usage

PathwaysIter(
  List,
  Selection = NULL,
  geneExpr = NULL,
  nrclusters = NULL,
  method = c("limma", "MLP"),
  geneInfo = NULL,
  geneSetSource = "GOBP",
  topP = NULL,
  topG = NULL,
  GENESET = NULL,
  sign = 0.05,
  niter = 10,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Details

This function relies on the suggested Bioconductor packages 'MLP', 'biomaRt' and 'org.Hs.eg.db'.

Value

A list with an element per iteration, each being the output of Pathways.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)
data(GeneInfo)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
names=c('FP','TP')

MCF7_Paths_FandT=PathwaysIter(List=L, geneExpr = geneMat, nrclusters = 7, method =
c("limma", "MLP"), geneInfo = GeneInfo, geneSetSource = "GOBP", topP = NULL,
topG = NULL, GENESET = NULL, sign = 0.05,niter=2,fusionsLog = TRUE,
weightclust = TRUE, names =names)

## End(Not run)

Pathway analysis for a selection of objects

Description

Internal function of Pathways.

Usage

PathwaysSelection(
  List = NULL,
  Selection,
  geneExpr = NULL,
  nrclusters = NULL,
  method = c("limma", "MLP"),
  geneInfo = NULL,
  geneSetSource = "GOBP",
  topP = NULL,
  topG = NULL,
  GENESET = NULL,
  sign = 0.05,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Details

This function relies on the suggested Bioconductor packages 'MLP', 'biomaRt' and 'org.Hs.eg.db'.

Examples

## Not run: 
PathwaysSelection(List=L,Selection=c("Cpd1","Cpd2"),geneExpr=geneMat,geneInfo=GeneInfo)

## End(Not run)

A GO plot of a pathway analysis output.

Description

The PlotPathways function takes an output of the PathwayAnalysis function and plots a GO graph with the help of the plotGOgraph function of the MLP package.

Usage

PlotPathways(
  Pathways,
  nRow = 5,
  main = NULL,
  plottype = "new",
  location = NULL
)

Arguments

Value

The output is a GO graph.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)
data(GeneInfo)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
names=c('FP','TP')

MCF7_PathsFandT=PathwayAnalysis(List=L, geneExpr = geneMat, nrclusters = 7, method = c("limma",
"MLP"), geneInfo = GeneInfo, geneSetSource = "GOBP", topP = NULL,
topG = NULL, GENESET = NULL, sign = 0.05,niter=2,fusionsLog = TRUE, weightclust = TRUE,
 names =names,seperatetables=FALSE,separatepvals=FALSE)

PlotPathways(MCF7_PathsFandT$FP$"Cluster 1"$Pathways,nRow=5,main=NULL)

## End(Not run)

Prepare data for pathway analysis

Description

The PreparePathway function prepares the input for the pathway analysis by computing differentially expressed genes (via limma) for a selection of objects if these were not provided.

Usage

PreparePathway(Object, geneExpr, topG, sign)

Arguments

Details

This function may rely on the suggested Bioconductor package 'limma'.

Value

A list with the p-values of the genes, the objects and the genes.

Examples

## Not run: 
PreparePathway(Object=MCF7_F,geneExpr=geneMat,topG=NULL,sign=0.05)

## End(Not run)

Plotting gene profiles

Description

In ProfilePlot, the gene profiles of the significant genes for a specific cluster are shown on 1 plot. Therefore, each gene is normalized by subtracting its the mean.

Usage

ProfilePlot(
  Genes,
  Comps,
  geneExpr = NULL,
  raw = FALSE,
  orderLab = NULL,
  colorLab = NULL,
  nrclusters = NULL,
  cols = NULL,
  addLegend = TRUE,
  margins = c(8.1, 4.1, 1.1, 6.5),
  extra = 5,
  plottype = "new",
  location = NULL
)

Arguments

Value

A plot which contains multiple gene profiles. A distinction is made between the values for the objects in Comps and the others.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)
data(geneMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
	method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
	method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
names=c('FP','TP')

MCF7_FT_DE = DiffGenes(List=L,geneExpr=geneMat,nrclusters=7,method="limma",sign=0.05,topG=10,
fusionsLog=TRUE,weightclust=TRUE)

Comps=SharedComps(list(MCF7_FT_DE$`Method 1`$"Cluster 1",MCF7_FT_DE$`Method 2`$"Cluster 1"))[[1]]

MCF7_SharedGenes=FindGenes(dataLimma=MCF7_FT_DE,names=c("FP","TP"))

Genes=names(MCF7_SharedGenes[[1]])[-c(2,4,5)]

colscl=ColorPalette(colors=c("red","green","purple","brown","blue","orange"),ncols=9)

ProfilePlot(Genes=Genes,Comps=Comps,geneExpr=geneMat,raw=FALSE,orderLab=MCF7_F,
colorLab=NULL,nrclusters=7,cols=colscl,addLegend=TRUE,margins=c(16.1,6.1,1.1,13.5),
extra=4,plottype="sweave",location=NULL)

## End(Not run)

Relabel and reorder clusterings to a reference

Description

ReorderToReference relabels and reorders the clusters of a series of clustering results so that the cluster numbers of every method are matched, via a Gale-Shapley stable-matching scheme, to those of the first (reference) method. The result is a matrix in which the columns represent the objects (ordered as for the reference method) and the rows represent the methods. Each cell contains the number of the cluster the object belongs to for that method, relabelled to the reference. It is a possibility that two or more clusters are fused together compared to the reference; in that case the function alerts the user and asks to set fusionsLog to TRUE.

Usage

ReorderToReference(
  List,
  nrclusters = NULL,
  fusionsLog = FALSE,
  weightclust = FALSE,
  names = NULL
)

Arguments

Value

A matrix of which the cells indicate to what cluster the objects belong to according to the rearranged methods.

Note

The ReorderToReference function was optimized for the situations presented by the data sets at hand. It is noted that the function might fail in a particular situation which results in an infinite loop.

References

Van Moerbeke, M. (2017). MoSaiClusteR: integrative clustering of multi-source data. Hasselt University.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res <- list(Cluster(L[[1]], type = "data", distmeasure = "euclidean"),
            Cluster(L[[2]], type = "data", distmeasure = "euclidean"))
M <- ReorderToReference(res, nrclusters = 5, fusionsLog = FALSE,
                        weightclust = FALSE, names = c("S1", "S2"))

## End(Not run)

Similarity network fusion

Description

Similarity Network Fusion (SNF) is a similarity-based multi-source clustering technique. SNF consists of two steps. In the initial step a similarity network is set up for each data matrix. The network is the visualization of the similarity matrix as a weighted graph with the objects as vertices and the pairwise similarities as weights on the edges. In the network-fusion step, each network is iteratively updated with information of the other network which results in more alike networks every time. This eventually converges to a single network.

Usage

SNF(
  List,
  type = c("data", "dist", "clusters"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  StopRange = FALSE,
  NN = 20,
  mu = 0.5,
  T = 20,
  clust = "agnes",
  linkage = "ward",
  alpha = 0.625
)

Arguments

Details

If r is specified and nrclusters is a fixed number, only a random sampling of the features will be performed for the t iterations (ADECa). If r is NULL and the nrclusters is a sequence, the clustering is performedon all features and the dendrogam is divided into clusters for the values of nrclusters (ADECb). If both r is specified and nrclusters is a sequence, the combination is performed (ADECc). After every iteration, either be random sampling, multiple divisions of the dendrogram or both, an incidence matrix is set up. All incidence matrices are summed and represent the distance matrix on which a final clustering is performed.

Value

The returned value is a list with the following three elements.

The value has class 'SNF'.

References

Wang B, Mezlini AM, Demir F, Fiume M, Tu Z, Brudno M, Haibe-Kains B, Goldenberg A (2014). “Similarity Network Fusion for Aggregating Data Types on a Genomic Scale.” Nature Methods, 11, 333–337.

Select the number of clusters via silhouette widths

Description

For each element of List, partitions around medoids (cluster::pam) are computed over a range of cluster numbers and the average silhouette width is recorded. The number of clusters maximising the average silhouette width is reported per source and for the across-source average. The analytical result (the silhouette table and the chosen number of clusters) is returned and is testable without producing any plot.

Usage

SelectnrClusters(
  List,
  type = c("data", "dist", "pam"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  nrclusters = seq(5, 25, 1),
  names = NULL,
  StopRange = FALSE,
  plottype = "none",
  location = NULL
)

Arguments

Value

A list with two elements: Silhoutte_Widths (a matrix of average silhouette widths per source and their mean) and Optimal_Nr_of_CLusters (a one-row data frame with the silhouette optimal number of clusters per source and overall).

References

Kaufman, L. and Rousseeuw, P. J. (1990). Finding Groups in Data: An Introduction to Cluster Analysis. Wiley, New York.

Examples

## Not run: 
data(mosaic_toy)
sel <- SelectnrClusters(mosaic_toy$List, type = "data",
                        distmeasure = c("euclidean", "euclidean"),
                        nrclusters = seq(2, 5), plottype = "none")
sel$Optimal_Nr_of_CLusters

## End(Not run)

Objects shared across clusterings

Description

SharedComps determines, per cluster, which objects are shared across all listed clustering results. The clusterings are first rearranged to a common reference with ReorderToReference and the intersection of the lead objects of every method is taken per cluster.

Usage

SharedComps(
  List,
  nrclusters = NULL,
  fusionsLog = FALSE,
  weightclust = FALSE,
  names = NULL
)

Arguments

Value

A list containing the shared objects of all listed elements per cluster.

Examples

## Not run: 
data(mosaic_toy)
L <- mosaic_toy$List
res <- list(Cluster(L[[1]], type = "data", distmeasure = "euclidean"),
            Cluster(L[[2]], type = "data", distmeasure = "euclidean"))
Comps <- SharedComps(List = res, nrclusters = 5, fusionsLog = FALSE,
                     weightclust = FALSE, names = c("S1", "S2"))

## End(Not run)

Shared genes, pathways and features across methods

Description

The SharedGenesPathsFeat function takes the intersection of the differentially expressed genes, the pathways and the characteristic features over the methods per cluster.

Usage

SharedGenesPathsFeat(
  DataLimma = NULL,
  DataMLP = NULL,
  DataFeat = NULL,
  names = NULL,
  Selection = FALSE
)

Arguments

Value

A list with a Table summarizing the shared elements and a Which element detailing the shared genes, pathways and features per cluster.

Examples

## Not run: 
SharedGenesPathsFeat(DataLimma=MCF7_FT_DE,DataMLP=MCF7_Paths_intersection,names=c("FP","TP"))

## End(Not run)

Intersection of genes and pathways over multiple methods for a selection of objects.

Description

Internal function of SharedGenesPathsFeat.

Usage

SharedSelection(
  DataLimma = NULL,
  DataMLP = NULL,
  DataFeat = NULL,
  names = NULL
)

Arguments

Value

A list with a Table and a Which element for the selection.

Examples

## Not run: 
SharedSelection(DataLimma=MCF7_FT_DE,names="Selection")

## End(Not run)

Intersection of genes over multiple methods for a selection of objects.

Description

Internal function of SharedGenesPathsFeat.

Usage

SharedSelectionLimma(DataLimma = NULL, names = NULL)

Arguments

Value

A list with a Table and a Which element for the shared genes.

Examples

## Not run: 
SharedSelectionLimma(DataLimma=MCF7_FT_DE)

## End(Not run)

Intersection of pathways over multiple methods for a selection of objects.

Description

Internal function of SharedGenesPathsFeat.

Usage

SharedSelectionMLP(DataMLP = NULL, names = NULL)

Arguments

Value

A list with a Table and a Which element for the shared pathways.

Examples

## Not run: 
SharedSelectionMLP(DataMLP=MCF7_Paths_intersection)

## End(Not run)

A heatmap of similarity values between objects

Description

The function SimilarityHeatmap plots the similarity values between objects. The darker the shade, the more similar objects are. The option is available to set a cutoff value to highlight the most similar objects.

Usage

SimilarityHeatmap(
  Data,
  type = c("data", "clust", "sim", "dist"),
  distmeasure = "tanimoto",
  normalize = FALSE,
  method = NULL,
  linkage = "flexible",
  cutoff = NULL,
  percentile = FALSE,
  plottype = "new",
  location = NULL
)

Arguments

Details

If data is of type "clust", the distance matrix is extracted from the result and transformed to a similarity matrix. Possibly a range normalization is performed. If data is of type "dist", it is also transformed to a similarity matrix and cluster is performed on the distances. If data is of type "sim", the data is tranformed to a distance matrix on which clustering is performed. Once the similarity mattrix is obtained, the cutoff value is applied and a heatmap is drawn. If no cutoff value is desired, one can leave the default NULL specification.

Value

A heatmap with the names of the objects on the right and bottom and a dendrogram of the clustering at the left and top.

Examples

## Not run: 
data(fingerprintMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55)

SimilarityHeatmap(Data=MCF7_F,type="clust",cutoff=0.90,percentile=TRUE)
SimilarityHeatmap(Data=MCF7_F,type="clust",cutoff=0.75,percentile=FALSE)


## End(Not run)

Similarity of a set of clusterings to a reference

Description

Given a colour/label matrix (clusterings in rows, objects in columns) or a list of clustering outputs, the proportion of objects sharing the label of the first (reference) row is computed for every row. When a list is supplied it is first aligned with ReorderToReference; supplying the label matrix directly avoids that dependency.

Usage

SimilarityMeasure(
  List,
  nrclusters = NULL,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL
)

Arguments

Value

A numeric vector of similarities in [0, 1], one per row, where the first entry is the reference compared to itself (always 1).

References

Fodeh, S. J., Brandt, C., Luong, T. B., Haddad, A., Schultz, M., Murphy, T. and Krauthammer, M. (2013). Complementary ensemble clustering of biomedical data. Journal of Biomedical Informatics, 46(3), 436-443.

Examples

## Not run: 
M <- rbind(c(1, 1, 2, 2, 3, 3),
           c(1, 1, 2, 3, 3, 3),
           c(2, 2, 1, 1, 3, 3))
SimilarityMeasure(M)

## End(Not run)

Track a cluster or a selection of objects across multiple methods

Description

TrackCluster follows a selection of objects or a specific cluster across a sequence of clustering results, recording how the objects are distributed over the clusters of each method and optionally producing tracking plots.

Usage

TrackCluster(
  List,
  Selection,
  nrclusters = NULL,
  followMaxComps = FALSE,
  followClust = TRUE,
  fusionsLog = TRUE,
  weightclust = TRUE,
  names = NULL,
  selectionPlot = FALSE,
  table = FALSE,
  completeSelectionPlot = FALSE,
  ClusterPlot = FALSE,
  cols = NULL,
  legendposx = 0.5,
  legendposy = 2.4,
  plottype = "sweave",
  location = NULL
)

Arguments

Value

A list with one element per method describing how the selection is distributed across the clusters, and optionally a tracking table.

Examples

## Not run: 
data(fingerprintMat)
data(targetMat)

MCF7_F = Cluster(fingerprintMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)
MCF7_T = Cluster(targetMat,type="data",distmeasure="tanimoto",normalize=FALSE,
method=NULL,clust="agnes",linkage="flexible",gap=FALSE,maxK=55,StopRange=FALSE)

L=list(MCF7_F,MCF7_T)
MCF7_Track=TrackCluster(List=L,Selection=4,nrclusters=7,followMaxComps=FALSE,
followClust=TRUE,selectionPlot=TRUE,table=TRUE,cols=NULL)

## End(Not run)

Weighted clustering

Description

Weighted Clustering (Weighted) is a similarity-based multi-source clustering technique. Weighted clustering is performed with the function WeightedClust. Given a list of the data matrices, a dissimilarity matrix is computed of each with the provided distance measures. These matrices are then combined resulting in a weighted dissimilarity matrix. Hierarchical clustering is performed on this weighted combination with the agnes function and the ward link

Usage

WeightedClust(
  List,
  type = c("data", "dist", "clusters"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  StopRange = FALSE,
  weight = seq(1, 0, -0.1),
  weightclust = 0.5,
  clust = "agnes",
  linkage = "ward",
  alpha = 0.625
)

Arguments

Details

The weight combinations should be provided as elements in a list. For three data matrices an example could be: weights=list(c(0.5,0.2,0.3),c(0.1,0.5,0.4)). To provide a fixed weight for some data sets and let it vary randomly for others, the element "x" indicates a free parameter. An example is weights=list(c(0.7,"x","x")). The weight 0.7 is now fixed for the first data matrix while the remaining 0.3 weight will be divided over the other two data sets. This implies that every combination of the sequence from 0 to 0.3 with steps of 0.1 will be reported and clustering will be performed for each.

Value

The returned value is a list of four elements:

The value has class 'Weighted'.

References

Perualila-Tan N, Kasim A, Talloen W, Göhlmann H, Shkedy Z (2016). “Weighted Similarity-Based Clustering of Chemical Structures and Bioactivity Data in Early Drug Discovery.” Journal of Bioinformatics and Computational Biology, 14, 1650018.

Weighted hierarchical clustering (weighted Ward)

Description

Agglomerative clustering of weighted observations using the weighted Ward merge cost. Intended for the small set of data-nugget centres.

Usage

Whclust(x, weights = rep(1, nrow(x)))

Arguments

Value

An hclust object.

References

Dey et al. (2025). WCluster.

See Also

Wkmeans, nugget_cluster

Examples

set.seed(1)
x <- rbind(matrix(rnorm(8 * 3, 0), 8), matrix(rnorm(8 * 3, 5), 8))
stats::cutree(Whclust(x, weights = rep(2, 16)), k = 2)[1:4]

Weighted k-means (minimises WWCSS)

Description

k-means in which each observation carries a non-negative weight. Cluster centres are weighted means and the objective is the Weighted Within-Cluster Sum of Squares \sum_c \sum_{i \in c} w_i \lVert x_i - \mu_c \rVert^2.

Usage

Wkmeans(x, k, weights = rep(1, nrow(x)), nstart = 10, max_iter = 100)

Arguments

Value

A list with cluster, centers and wwcss.

References

Dey, T., Duan, Y., Cabrera, J. & Cheng, X. (2025). WCluster: Clustering and PCA with Weights, and Data Nuggets Clustering.

See Also

nugget_cluster, Whclust

Examples

set.seed(1)
x <- rbind(matrix(rnorm(20 * 3, 0), 20), matrix(rnorm(20 * 3, 5), 20))
Wkmeans(x, k = 2, weights = runif(40, 1, 5))$cluster[1:5]

Weighting on Membership clustering

Description

Weighting on Membership (WonM) is a hierarchy-based consensus technique. Each data matrix is hierarchically clustered and the resulting dendrogram is cut into a range of K values. For every cut a co-membership matrix is built, recording which objects fall in the same cluster. These matrices are averaged within and across data sets to produce an overall consensus matrix, which is transformed into a dissimilarity and clustered a final time.

Usage

WonM(
  List,
  type = c("data", "dist", "clusters"),
  distmeasure = c("tanimoto", "tanimoto"),
  normalize = c(FALSE, FALSE),
  method = c(NULL, NULL),
  nrclusters = list(seq(5, 25), seq(5, 25)),
  clust = "agnes",
  linkage = c("flexible", "flexible"),
  alpha = 0.625
)

Arguments

Value

The returned value is a list of two elements:

The value has class 'WonM'.

References

Saeed F., Salim N. and Abdo A. (2012). Voting-based consensus clustering for combining multiple clusterings of chemical structures. Journal of Cheminformatics, 4, 37.

Examples

## Not run: 
data(mosaic_toy)
fit <- WonM(List = mosaic_toy$List, type = "data",
  distmeasure = c("euclidean", "euclidean"), normalize = c(FALSE, FALSE),
  method = c(NULL, NULL), nrclusters = list(seq(3, 6), seq(3, 6)),
  clust = "agnes", linkage = c("ward", "ward"))

## End(Not run)

Characterise clusters with external (biological / clinical) variables

Description

For a clustering, summarise how each external variable differs across the clusters. Continuous variables get n, mean, SD, median, IQR and range per cluster, an overall Kruskal-Wallis test, a rank \eta^2 effect size, and gradient detection (are the cluster means monotonically ordered?). Categorical variables get per-cluster counts and column percentages, a chi-squared / Fisher test and Cramer's V. The emphasis is on effect sizes and descriptive summaries rather than p-values alone.

Usage

characterize_clusters(labels, metadata, continuous = NULL, categorical = NULL)

Arguments

Value

A list with continuous (per-cluster summary, long format), continuous_tests (one row per variable: KW_p, eta2, gradient – the clusters ordered by mean – and a monotone-trend trend_rho/trend_p), categorical (counts and column percentages) and categorical_tests (p, cramers_v).

See Also

plot_cluster_profile, cluster_biology_panel

Examples

data(mosaic_toy)
fit <- M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3)
cl  <- mosaic_labels(fit, 3)
meta <- data.frame(score = rnorm(length(cl)), grp = sample(c("A", "B"), length(cl), TRUE))
ch  <- characterize_clusters(cl, meta)
ch$continuous_tests

Agreement between two partitions

Description

Computes the adjusted Rand index (ARI), normalised mutual information (NMI) and pairwise Jaccard between two label vectors of equal length.

Usage

cluster_agreement(a, b)

Arguments

Details

ARI rule of thumb: >0.90 excellent; 0.75-0.90 good; 0.50-0.75 moderate; <0.50 weak.

Value

A named numeric vector c(ARI, NMI, Jaccard).

Examples

cluster_agreement(c(1, 1, 2, 2), c(2, 2, 1, 1))   # identical up to relabel

Panel of cluster characterisation plots

Description

Lay out plot_cluster_profile for every external variable in a single figure – boxplots for continuous variables, bar plots for categorical ones – ready for the manuscript.

Usage

cluster_biology_panel(labels, metadata, vars = NULL, ncol = 3)

Arguments

Value

Invisibly NULL.

See Also

characterize_clusters

Show the clustering at every k (see how it deteriorates)

Description

Rather than only reporting the best k, project the objects to a fixed 2-D embedding and recolour them by the k-cut for each candidate k in a grid, annotating the average silhouette per panel. This makes it visible how the structure splits and degrades as k grows.

Usage

cluster_k_sweep(
  x,
  k_range = 2:6,
  linkage = "ward.D2",
  embed = c("pca", "umap", "tsne"),
  ncol = 3
)

Arguments

Value

Invisibly a named numeric vector of the average silhouette per k.

See Also

cluster_selection_plot, embedding_plot

Examples

data(mosaic_toy)
fit <- M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3)
cluster_k_sweep(fit, k_range = 2:6)

Justify the number of clusters (silhouette + elbow / scree)

Description

For a fused dissimilarity (or a fitted result, or a List of sources) compute, over a range of k, the average silhouette width and the total within-cluster dispersion (an elbow / scree curve), and plot them so the chosen k can be justified in the manuscript.

Usage

cluster_selection_plot(
  x,
  k_range = 2:8,
  linkage = "ward.D2",
  select = c("elbow", "silhouette"),
  plot = TRUE
)

Arguments

Value

Invisibly a data frame with k, silhouette and within_dispersion, plus attributes "best_k", "elbow_k" and "silhouette_k".

See Also

embedding_plot, SelectnrClusters

Examples

data(mosaic_toy)
fit <- M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3)
cluster_selection_plot(fit, k_range = 2:6)

Compare clustering solutions to each other (no ground truth needed)

Description

Given several labellings of the same objects (e.g. different weightings or methods), compute their pairwise agreement (ARI) and each object's stability – how consistently it is co-clustered across the solutions. Useful for real data where no ground truth is available.

Usage

clustering_concordance(labels_list)

Arguments

Value

A list with agreement (pairwise ARI matrix), stability (mean pairwise co-membership per object) and changed (objects whose label is not constant across solutions).

See Also

cluster_agreement, compare_clusterings

Examples

data(mosaic_toy)
v <- mosaic_labels(M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3,
                           weighting = c("var", "var")), 3)
n <- mosaic_labels(M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3,
                           weighting = c("nugget", "nugget")), 3)
clustering_concordance(list(var = v, nugget = n))$agreement

Compare two clusterings derived from distance matrices

Description

Clusters two dissimilarity matrices with the same linkage and number of clusters and reports their agreement (ARI, NMI, pairwise Jaccard) and the contingency table.

Usage

compare_clusterings(
  D1,
  D2,
  NC = NULL,
  linkage = "ward.D2",
  labels = c("D1", "D2"),
  verbose = TRUE
)

Arguments

Value

Invisibly, a list with the two label vectors, ARI, NMI, pair_Jaccard and the contingency table.

Examples

set.seed(1)
D1 <- as.matrix(dist(matrix(rnorm(60), 20)))
D2 <- as.matrix(dist(matrix(rnorm(60), 20)))
compare_clusterings(D1, D2, NC = 3, verbose = FALSE)$ARI

Visually compare clustering solutions with ComparePlot (no ground truth)

Description

Aligns several clustering solutions of the same objects and draws them with ComparePlot so their agreement can be read off directly – which objects the methods place together and where they disagree – without any ground truth. Each solution may be a fitted result (with $Clust / $DistM) or a plain label vector; label vectors are turned into a co-membership dissimilarity so every solution is comparable.

Usage

compare_methods_plot(
  solutions,
  nrclusters,
  cols = NULL,
  cex.labels = 0.5,
  margins = c(5, 11, 3, 2),
  ...
)

Arguments

Value

Invisibly NULL; called for the plot. Needs circlize and plotrix.

See Also

clustering_concordance, ComparePlot

Examples

data(mosaic_toy)
sols <- list(
  var    = M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3, weighting = c("var", "var")),
  nugget = M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3, weighting = c("nugget", "nugget")),
  NEMO   = NEMO(mosaic_toy$List, k = 3)$cluster)
## Not run: compare_methods_plot(sols, nrclusters = 3)

Create data nuggets from a data matrix

Description

create_data_nuggets compresses n observations into M <= n representative "nuggets". Each nugget stores a centre (location), a weight (the number of member observations) and a scale (within-nugget variability). Data nuggets preserve the covariance structure of the data - including the periphery - far better than a random sub-sample, which makes them a robust, memory-light surrogate for the full data set when clustering or computing feature weights.

Usage

create_data_nuggets(
  x,
  max_nuggets = NULL,
  min_size = 1L,
  engine = c("native", "datanugget"),
  scale_features = TRUE,
  seed = NULL,
  ...
)

Arguments

Details

With the native engine the number of nuggets defaults to min(nrow(x), max(2, floor(nrow(x) / 10))) when n > 50, and to n otherwise (in which case every observation is its own nugget and the nugget-weighted variance reduces to the ordinary variance - a safe fallback for small samples). The partition is obtained with stats::kmeans; missing values are mean-imputed for the partition step only.

Value

An object of class "data_nugget": a list with elements

References

Cherasia KE, Cabrera J, Fernholz LT, Fernholz R (2023). “Data Nuggets in Supervised Learning.” In Robust and Multivariate Statistical Methods: Festschrift in Honor of David E. Tyler, 429–449. Springer.

Dey T, Duan Y, Cabrera J, Cheng X (2025). WCluster: Clustering and PCA with Weights, and Data Nuggets Clustering. R package version 1.3.0.

See Also

nugget_feature_weights, M_ABCpp

Examples

set.seed(1)
x <- rbind(matrix(rnorm(200 * 5,  0), ncol = 5),
           matrix(rnorm(200 * 5,  4), ncol = 5))
dn <- create_data_nuggets(x, max_nuggets = 40)
dn

Determine the distance in a heatmap

Description

Internal function of HeatmapPlot

Usage

distanceheatmaps(Data1, Data2, names = NULL, nrclusters = 7)

Arguments

Two-dimensional cluster visualisation (PCA / UMAP / t-SNE)

Description

Project the objects to two dimensions and colour them by cluster. "pca" uses classical MDS of the fused dissimilarity (always available); "umap" needs uwot and "tsne" needs Rtsne.

Usage

embedding_plot(
  x,
  labels,
  method = c("pca", "umap", "tsne"),
  col = NULL,
  main = NULL
)

Arguments

Value

Invisibly the 2-column coordinate matrix.

See Also

cluster_selection_plot

Examples

data(mosaic_toy)
fit <- M_ABCpp(mosaic_toy$List, numsim = 40, NC = 3)
embedding_plot(fit, mosaic_labels(fit, 3), method = "pca")

Consensus clustering from stacked ABC label matrices

Description

Turns a row-stacked matrix of per-iteration cluster labels (K \cdot R rows by N columns) into a co-clustering dissimilarity and applies cluster::agnes. S_{ij} is the co-clustering probability over iterations selecting both objects (B6). The co-clustering counts use the compiled C++ kernel count_coclustering_cpp (from src/mcpp_sampling.cpp) when available, otherwise a pure-R loop.

Usage

f.clustABC.MultiSource(
  res,
  numclust = NULL,
  dissimilarity = "mabc",
  linkage = "ward",
  alpha = 0.625,
  mds = FALSE
)

Arguments

Value

A list with DistM, Clust and (if numclust given) cut.

References

(Amaratunga et al. 2008)

See Also

M_ABCpp

Integrative NMF clustering (intNMF)

Description

Joint non-negative matrix factorisation across data sources: a single shared basis matrix W (objects \times rank) and source-specific coefficient matrices H_k minimise \sum_k \alpha_k \lVert X_k - W H_k \rVert_F^2 with all factors non-negative. Sources are weighted by \alpha_k = \max_j \overline{SS}_j / \overline{SS}_k. Object clusters are obtained by consensus of the dominant-factor assignment across restarts.

Usage

intNMF(List, k, nstart = 10, max_iter = 200, seed = NULL)

Arguments

Value

A list of class "intNMF" with cluster, the consensus DistM, an agnes Clust, the best-fit basis W and source weights alpha.

References

Chalise, P. & Fridley, B. L. (2017). Integrative clustering of multi-level omic data based on non-negative matrix factorization. PLoS ONE 12:e0176278. Reviewed in Zhang et al. (2022), WIREs Comput Stat 14:e1553.

See Also

M_ABCpp, SNF

Examples

data(mosaic_toy)
fit <- intNMF(mosaic_toy$List, k = 3, nstart = 5, seed = 1)
table(fit$cluster)

Extract a flat partition from a MosaiClusteR result

Description

Cuts the hierarchical clustering carried in a MosaiClusteR result object into k groups. Works with any method returning a Clust element (an agnes/hclust object) and/or a DistM.

Usage

mosaic_labels(object, k, linkage = "ward")

Arguments

Value

An integer vector of cluster labels, named by object.

Examples

set.seed(1)
s <- paste0("o", 1:20)
L <- list(matrix(rnorm(20 * 40), 20, dimnames = list(s, NULL)),
          matrix(rnorm(20 * 50), 20, dimnames = list(s, NULL)))
fit <- M_ABCpp(L, numsim = 30)
mosaic_labels(fit, k = 3)

Simulate a multi-source data set with planted clusters

Description

Generates K feature-by-sample matrices that share a common set of n samples drawn from g ground-truth groups. Each source has its own informative features (shifted between groups) plus noise features, so the clusters are only partially visible in any single source - the canonical setting in which multi-source integration helps.

Usage

mosaic_sim(
  n = 60,
  g = 3,
  p = c(120, 150),
  informative = c(20, 25),
  effect = 2.5,
  K = 2,
  seed = NULL
)

Arguments

Value

A list with List (the K matrices, objects in rows, features in columns) and truth (the integer group label per object).

Examples

sim <- mosaic_sim(n = 30, g = 3, K = 2, seed = 1)
lengths(lapply(sim$List, dim))

Toy multi-omics example data

Description

A small two-source example produced by mosaic_sim with three planted groups, bundled for examples and tests.

Usage

data(mosaic_toy)

Format

A list with two elements:

List

A list of two numeric matrices with the 60 shared objects in rows and features in columns (120 and 150 features).

truth

Integer vector of the 60 ground-truth group labels.

Examples

data(mosaic_toy)
str(mosaic_toy, max.level = 2)

Data-nugget clustering

Description

Cluster a (potentially large) data set by first compressing its observations into weighted data nuggets (create_data_nuggets), clustering the nugget centres with a weighted clusterer, and mapping the nugget labels back to the original observations. This is the clustering analogue of the data-nugget weighting used by M_ABCpp and follows DN.Wkmeans / DN.Whclust from the WCluster package.

Usage

nugget_cluster(
  data,
  k,
  method = c("kmeans", "ward"),
  max_nuggets = NULL,
  nugget_args = list()
)

Arguments

Value

A list of class "nugget_cluster" with cluster (labels for the original objects), nugget_cluster (labels for the nuggets) and the nuggets object.

References

Cherasia et al. (2023); Dey et al. (2025), WCluster.

See Also

create_data_nuggets, Wkmeans

Examples

data(mosaic_toy)
X <- do.call(cbind, mosaic_toy$List)        # fuse sources (objects in rows)
fit <- nugget_cluster(X, k = 3, max_nuggets = 30)
table(fit$cluster)

Feature weights derived from data nuggets

Description

Computes a per-feature importance score from a data-nugget (create_data_nuggets) object built over the observations (samples). This score is the data-nugget analogue of the feature variance used by the ABC / M-ABC family: it rewards features that separate the representative groups while discounting within-nugget noise, giving a robust, Big-Data-friendly weighting.

Usage

nugget_feature_weights(nuggets, type = c("between", "ratio", "inv_scale"))

Arguments

Value

A named numeric vector of length ncol(centers) of non-negative feature scores.

References

Cherasia KE, Cabrera J, Fernholz LT, Fernholz R (2023). “Data Nuggets in Supervised Learning.” In Robust and Multivariate Statistical Methods: Festschrift in Honor of David E. Tyler, 429–449. Springer.

See Also

create_data_nuggets, M_ABCpp

Examples

set.seed(1)
x <- cbind(signal = c(rnorm(50, 0), rnorm(50, 5)),  # separates groups
           noise  = rnorm(100))                      # pure noise
dn <- create_data_nuggets(x, max_nuggets = 20)
nugget_feature_weights(dn, type = "between")

Plot one external variable by cluster

Description

Boxplot (continuous) or grouped bar plot of column proportions (categorical) of an external variable across clusters – the per-cluster distribution and gradient the manuscript should show.

Usage

plot_cluster_profile(labels, x, name = deparse(substitute(x)), col = NULL)

Arguments

Value

Invisibly NULL; called for the plot.

See Also

characterize_clusters, cluster_biology_panel

Simulate data for evaluating feature-weighting schemes (variance vs CV)

Description

Generates a multi-source data set with a known cluster structure in which the discriminative signal is carried either by high-absolute-variance features (regime = "variance") or by high-coefficient-of-variation features buried under high-abundance, high-variance decoys (regime = "cv"). It is intended for benchmarking the "var", "cv" and "nugget" weightings of the ABC family (and any other feature-weighting method) on the same footing.

Usage

simulate_weighting_regime(
  regime = c("cv", "variance"),
  n_samples = 120,
  n_clusters = 3,
  n_sources = 2,
  n_signal = 40,
  n_decoy = 500,
  n_noise = 60,
  effect = NULL,
  seed = NULL
)

Arguments

Value

A list with List (the sources, objects in rows), truth (cluster labels), signal_features (indices of the discriminative features), regime and params.

See Also

M_ABCpp (the weighting argument), mosaic_sim

Examples

cv  <- simulate_weighting_regime("cv", seed = 1)
# variance weighting is misled by high-abundance decoys, CV recovers the truth:
fit_var <- M_ABCpp(cv$List, numsim = 80, NC = 3, weighting = c("var", "var"))
fit_cv  <- M_ABCpp(cv$List, numsim = 80, NC = 3, weighting = c("cv",  "cv"))
c(var = cluster_agreement(mosaic_labels(fit_var, 3), cv$truth)[["ARI"]],
  cv  = cluster_agreement(mosaic_labels(fit_cv,  3), cv$truth)[["ARI"]])

Spectral clustering of an affinity matrix

Description

Normalised (Ng-Jordan-Weiss) spectral clustering. Given a symmetric, non-negative affinity matrix it forms the normalised Laplacian, embeds the objects in the space of its leading eigenvectors and applies k-means.

Usage

spectral_clustering(affinity, k = NULL, max_k = 10, nstart = 10)

Arguments

Value

A list with cluster (named integer labels), k and the spectral embedding.

References

Ng, A. Y., Jordan, M. I. & Weiss, Y. (2002). On spectral clustering: analysis and an algorithm. NIPS 14.

See Also

NEMO, SNF

Examples

set.seed(1)
X <- rbind(matrix(rnorm(20 * 5, 0), 20), matrix(rnorm(20 * 5, 6), 20))
A <- exp(-as.matrix(dist(X))^2 / 2)
spectral_clustering(A, k = 2)$cluster[1:5]