Training Datasets for iC10 Package

Description

Training datasets for iC10; which implements the classifier described in the paper 'Genome-driven integrated classification of breast cancer validated in over 7,500 samples' (Ali HR et al., Genome Biology 2014). It uses copy number and/or expression form breast cancer data, trains a pamr classifier (Tibshirani et al.) with the features available and predicts the iC10 group. Genomic annotation for the training dataset has been obtained from Mark Dunning's lluminaHumanv3.db package. Training datasets for iC10; which implements the classifier described in the METABRIC paper 'The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups' (Curtis et al., Nature 2012). It uses copy number and/or expression form breast cancer data, trains a pamr classifier (Tibshirani et al.) with the features available and predicts the iC10 group.

Details

The DESCRIPTION file:

Index of help topics:

IntClustMemb            Class Membership for the training set
Map.All                 Probe mapping of the complete set of features
                        of the training set
Map.CN                  Probe mapping of the copy number features of
                        the training set.
Map.Exp                 Probe mapping of the Expression features of the
                        training set
iC10TrainingData-package
                        Training Datasets for iC10 Package
train.CN                Copy number data for the training set
train.Exp               Expression data for the training set.

Training datasets for iC10; which implements the classifier described in the METABRIC paper 'The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups' (Curtis et al., Nature 2012). It uses copy number and/or expression form breast cancer data, trains a pamr classifier (Tibshirani et al.) with the features available and predicts the iC10 group.

Author(s)

Oscar M Rueda and Jose Antonio Seoane Fernandez

Maintainer: Oscar M. Rueda <Oscar.Rueda@mrc-bsu.cam.ac.uk>

References

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352. Tibshirani et al. Diagnosis of multiple cancer types by shrunken centroids of gene expression. PNAS 2002; 99(10):6567-6572.

See Also

iC10

Examples

data(train.CN)
data(train.Exp)

Class Membership for the training set

Description

iC10 assignment for the Metabric training dataset (997 samples).

Usage

data(IntClustMemb)

Format

The format is: Factor w/ 10 levels "1","2","3","4",..: 2 9 3 3 8 6 7 7 7 3 ... - attr(*, "names")= chr [1:997] "MB.0135" "MB.0167" "MB.0136" "MB.3403" ...

Source

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.

Examples

data(IntClustMemb)
barplot(table(IntClustMemb))

Probe mapping of the complete set of features of the training set

Description

Probe mapping of the complete set of features of the training set

Usage

data(Map.All)

Format

A data frame with 714 observations on the following 10 variables:

Probe_ID

a character vector with the Illumina probe ids that flank the features

Gene_symbol

a factor with the hugo gene names

Ensembl_ID

a factor with the ensemble ids

Cytoband

a factor with the cytobands (on hg18)

Genomic_location_hg18

a factor with the genomic locations on hg18

chromosome_name_hg18

a numeric vector with the chromosome on hg18

start_position_hg18

a numeric vector with the start position on hg18

end_position_hg18

a numeric vector with the end position on hg18

Synonyms_0

a character vector with the gene name synonyms of the feature

Gene.Chosen

a character vector (YES or NO) specifiying the probe chosen for gene-based selection

Genomic_location_hg19

a factor with the genomic locations on hg19

chromosome_name_hg19

a numeric vector with the chromosome on hg19

start_position_hg19

a numeric vector with the start position on hg19

end_position_hg19

a numeric vector with the end position on hg19

chromosome_name_hg38

a numeric vector with the chromosome on hg38

start_position_hg38

a numeric vector with the start position on hg38

end_position_hg38

a numeric vector with the end position on hg38

Source

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.

Examples

data(Map.All)
head(Map.All)

Probe mapping of the copy number features of the training set.

Description

Probe mapping of the copy number features of the training set.

Usage

data(Map.CN)

Format

A data frame with 38 observations on the following 8 variables.

Probe_ID

a character vector with the Illumina probe ids that flank the features

Gene_symbol

a factor with the hugo gene names

Ensembl_ID

a factor with the ensemble ids

Cytoband

a factor with the cytobands (on hg18)

Genomic_location_hg18

a factor with the genomic locations on hg18

chromosome_name_hg18

a numeric vector with the chromosome on hg18

start_position_hg18

a numeric vector with the start position on hg18

end_position_hg18

a numeric vector with the end position on hg18

Genomic_location_hg19

a factor with the genomic locations on hg19

chromosome_name_hg19

a numeric vector with the chromosome on hg19

start_position_hg19

a numeric vector with the start position on hg19

end_position_hg19

a numeric vector with the end position on hg19

chromosome_name_hg38

a numeric vector with the chromosome on hg38

start_position_hg38

a numeric vector with the start position on hg38

end_position_hg38

a numeric vector with the end position on hg38

Source

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.

Examples

data(Map.CN)
head(Map.CN)

Probe mapping of the Expression features of the training set

Description

Probe mapping of the Expression features of the training set

Usage

data(Map.Exp)

Format

A data frame with 711 observations on the following 10 variables.

Probe_ID

a character vector with the Illumina probe ids that flank the features

Gene_symbol

a factor with the hugo gene names

Ensembl_ID

a factor with the ensemble ids

Cytoband

a factor with the cytobands (on hg18)

Genomic_location_hg18

a factor with the genomic locations on hg18

chromosome_name_hg18

a numeric vector with the chromosome on hg18

start_position_hg18

a numeric vector with the start position on hg18

end_position_hg18

a numeric vector with the end position on hg18

Synonyms_0

a character vector with the gene name synonyms of the feature

Gene.Chosen

a character vector (YES or NO) specifiying the probe chosen for gene-based selection

Genomic_location_hg19

a factor with the genomic locations on hg19

chromosome_name_hg19

a numeric vector with the chromosome on hg19

start_position_hg19

a numeric vector with the start position on hg19

end_position_hg19

a numeric vector with the end position on hg19

Source

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.

Examples

data(Map.Exp)
head(Map.Exp)

Copy number data for the training set

Description

Copy number data for the training set

Usage

data(train.CN)

Format

A matrix with 714 rows and 997 columns. Rows are features and columns are training samples.

Details

Each row corresponds to one copy number feature for all samples in the training set. Note that it includes all features in the classifier. Note also that, depending on the data available and the type of matching (gene or probe) only some of the features will be used.

Source

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.

Examples

data(train.CN)
summary(train.CN)

Expression data for the training set.

Description

Expression data for the training set.

Usage

data(train.Exp)

Format

A matrix with 714 rows and 997 columns. Rows are features and columns are training samples.

Details

Each row corresponds to one expression feature for all samples in the training set. Note that it includes all features in the classifier. Note that, depending on the data available and the type of matching (gene or probe) only some of the features will be used.

Source

Curtis et al. The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature 2012; 486:346-352.

Examples

data(train.Exp)
summary(train.Exp)