Consensus embedding: theory, algorithms and application to segmentation and classification of biomedical data

BMC Bioinformatics

Table 5 Classification accuracies for different representation strategies for gene-expression data

Dataset	ϕ^Acc(F)	ϕ^Acc(X_SSGE)	$ϕ^{A c c} ({\tilde{X}}_{P C A}^{S})$	$ϕ^{A c c} ({\tilde{X}}_{P C A}^{U S})$	$ϕ^{A c c} ({\tilde{X}}_{G E}^{S})$	$ϕ^{A c c} ({\tilde{X}}_{G E}^{U S})$
Prostate Tumor	73.53	73.53	97.06	100	100	76.47
Breast Cancer Relapse	68.42	63.16	63.16	57.89	63.16	57.89
Lung Cancer	89.93	10.07	99.33	96.64	98.66	100
Lymphoma	58.82	61.76	97.06	76.47	97.06	67.65

Classification accuracies for testing cohorts of 4 different binary class gene-expression datasets, comparing (1) supervised random forest classification of original feature space (F), (2) unsupervised hierarchical clustering of semi-supervised DR space (X_SSGE), and (3) unsupervised hierarchical clustering of consensus embedding space $({\tilde{X}}_{G E}, {\tilde{X}}_{P C A})$ .

ISSN: 1471-2105