MolecularPermutationClassifier-class: Class MolecularPermutationClassifier S4 implementation in R
Description
Virtual class to represent gene-based molecular signature classification
by means of permutation test.
Slots
parameters- named list with at least the following fields:
- $nPerm
- integer with number of permutations. Default:
1e4L
- $where
- character with significant value used. Default
value is "fdr".
- $pCutoff
- numeric with p-value or fdr cutoff used, i.e.,
variable
- $keep
- should null distribution simulation values be kept?.
Default: FALSE
exprs- matrix with gene exprs profile, where genes are in
rows and subjects as columns, a.k.a., M matrix.
annotation- data.frame with individual annotations (genes, etc).
Minimal compulsory fields are:
- $probe
- same characters as in row.names(M).
- $EntrezGene.ID
- integer with NCBI Entrez Data Base.
- $NCBI.gene.symbol
- character with gene mnemonic, a.k.a.
gene symbol.
targets- data.frame with additional subject data (optional).
classification- named list with at least the following fields:
- $class
- factor with all possible class levels.
permutation- named list with at least the following fields:
- $pvalues
- numeric matrix with subjects in row and classes
in columns.
- $fdr
- numeric matrix with False Discovery Rate correction
of p-values by row.
Superclasses
None declared.Subclasses
- PAM50
- Peruo et al. (2000 and 2010) breast cancer subtypes,
i. e., Luminal A, Luminal B, Basal, Her2 or Normal-like
subtypes as implemented in genefu library (Haibe-Kains et
al. 2014).
Functions
MolecularPermutationClassifier S4 class includes the following functions:
- Integrity check:
- validity
- will check appropriate annotation
data.frame minimal required columns, all named
parameters and if exprs and annotation dimension
matches.
- prototype
- just for an empty class with default
values: nPerm=1e4L, where="fdr", pCutoff=0.01,
corCutoff=0.1 and keep=FALSE
.
- Generics:
show,print- basic
class display wrappers.
summary- classifier statistics.
- Constructors (as this class is virtual see subclass'
'documentation).
setAs- MAList to
PAM50 as.PAM50- wrapper for
PAM50
setAs from MAList. loadBCDataset- wrapper to load
BreastCancerXX data (Class, exprs, annotation,
clinical data).
- Getters for the corresponding slots (
parameters,
exprs, annotation,
targets, classification
and permutation).
- Setters for the corresponding slots (
parameters<-,
annotation<- and targets<-).
- Particular (virtual) functions:
filtrate- remove from the
exprs matrix subjects not required by the
classification algorithm. classify- generate subject classification
according to subclasses implementation (PAM50, etc.).
permutate- obtain subject classification
based on the null correlation distribution by means
permutation simulation.
subtypes- obtain the new classification
using permutation results.
subjectReport- a friendly report for
Physician treatment decision support.
databaseReport- a pdf with all
subjectReports, if a database is available.
References
- Haibe-Kains B, Schroeder M, Bontempi G, Sotiriou C and
Quackenbush J, 2014, genefu: Relevant Functions for Gene
Expression Analysis, Especially in Breast Cancer. R package
version 1.16.0, www.pmgenomics.ca/bhklab/
- Perou CM, Sorlie T, Eisen MB, et al., 2000, Molecular
portraits of human breast tumors. Nature 406:747-752
- Perou CM, Parker JS, Prat A, Ellis MJ, Bernard PB., 2010,
Clinical implementation of the intrinsic subtypes of breast
cancer, The Lancet Oncology 11(8):718-719