Manual
User Manual:
Open the PDF directly: View PDF 
.
Page Count: 5
Package ‘CIMLR’
October 15, 2018
Version 1.0.0
Date 2018-10-14
Title Cancer Integration via Multikernel Learning (CIMLR)
Maintainer Luca De Sano <luca.desano@gmail.com>
Depends R (>= 3.5),
Imports parallel, Matrix, stats, methods, Rcpp, pracma, RcppAnnoy,
RSpectra
Suggests BiocGenerics, BiocStyle, testthat, knitr, igraph
Description Outcomes for cancer patients vary greatly even within the same tumor type, and charac-
terization of molecular subtypes of cancer holds important promise for improving
prognosis and personalized treatment. This promise has motivated recent efforts to pro-
duce large amounts of multidimensional genomic ('multi-omic') data, but current
algorithms still face challenges in the integrated analysis of such data. In this package we pro-
vide the implementation of Cancer Integration via Multikernel Learning
(CIMLR), a new cancer subtyping method that integrates multi-
omic data to reveal molecular subtypes of cancer.
Encoding UTF-8
LazyData TRUE
License file LICENSE
URL https://github.com/danro9685/CIMLR
BugReports https://github.com/danro9685/CIMLR
biocViews Clustering, CancerData
RoxygenNote 6.1.0
LinkingTo Rcpp
NeedsCompilation yes
VignetteBuilder knitr
Author Daniele Ramazzotti [aut, cre],
Avantika Lal [aut],
Bo Wang [ctb],
Luca De Sano [aut],
Serafim Batzoglou [ctb],
Arend Sidow [ctb]
1
2CIMLR
Rtopics documented:
CIMLR ........................................... 2
CIMLR_Estimate_Number_of_Clusters . . . . . . . . . . . . . . . . . . . . . . . . . . 3
CIMLR_Feature_Ranking ................................. 3
GliomasReduced ...................................... 4
Index 5
CIMLR CIMLR
Description
perform the CIMLR clustering algorithm
Usage
CIMLR(X, c, no.dim = NA, k = 10, cores.ratio = 1)
Arguments
Xa list of multi-omic data each of which is an (m x n) data matrix of measurements
of cancer patients
cnumber of clusters to be estimated over X
no.dim number of dimensions
ktuning parameter
cores.ratio ratio of the number of cores to be used when computing the multi-kernel
Value
clusters the patients based on CIMLR and their similarities
list of 8 elements describing the clusters obtained by CIMLR, of which y are the resulting clusters:
y = results of k-means clusterings, S = similarities computed by CIMLR, F = results from network
diffiusion, ydata = data referring the the results by k-means, alphaK = clustering coefficients, exe-
cution.time = execution time of the present run, converge = iterative convergence values by T-SNE,
LF = parameters of the clustering
Examples
CIMLR(X = GliomasReduced$in_X, c = 3, cores.ratio = 0)
CIMLR_Estimate_Number_of_Clusters 3
CIMLR_Estimate_Number_of_Clusters
CIMLR Estimate Number of Clusters
Description
estimate the number of clusters by means of two huristics as discussed in the CIMLR paper
Usage
CIMLR_Estimate_Number_of_Clusters(all_data, NUMC = 2:5,
cores.ratio = 1)
Arguments
all_data is a list of multi-omic data each of which is an (m x n) data matrix of measure-
ments of cancer patients
NUMC vector of number of clusters to be considered
cores.ratio ratio of the number of cores to be used when computing the multi-kernel
Value
a list of 2 elements: K1 and K2 with an estimation of the best clusters (the lower values the better)
as discussed in the original paper of SIMLR
Examples
CIMLR_Estimate_Number_of_Clusters(GliomasReduced$in_X,
NUMC = 2:5,
cores.ratio = 0)
CIMLR_Feature_Ranking CIMLR Feature Ranking
Description
perform the CIMLR feature ranking algorithm. This takes as input the combination of the original
input data appended by rows and the corresponding similarity matrix computed by CIMLR
Usage
CIMLR_Feature_Ranking(A, X)
Arguments
Aan (n x n) similarity matrix by CIMLR
Xa set of multi-omic data inputs each of which is an (m x n) data matrix of mea-
surements of cancer patients appended by rows
4GliomasReduced
Value
a list of 2 elements: pvalues and ranking ordering over the n covariates as estimated by the method
Examples
cimlr = CIMLR(X = GliomasReduced$in_X, c = 3, cores.ratio = 0)
input_data = rbind(GliomasReduced$in_X$point_mutations,GliomasReduced$in_X$copy_numbers,
GliomasReduced$in_X$methylations,GliomasReduced$in_X$expression_values)
CIMLR_Feature_Ranking(A = cimlr$S, X = input_data)
GliomasReduced test dataset for CIMLR
Description
example dataset to test CIMLR. This is a reduced version of the dataset from the work by The
Cancer Genome Atlas Research Network.
Usage
data(GliomasReduced)
Format
multi-omic data of cancer patients
Value
list of 1 element: in_X = input dataset as a list of 4 (reduced) multi-omic data each of which is an
(m x n) measurements of cancer patients
Source
Cancer Genome Atlas Research Network. "Comprehensive, integrative genomic analysis of diffuse
lower-grade gliomas." New England Journal of Medicine 372.26 (2015): 2481-2498.
