Machine learning with the TCGA-HNSC dataset: improving usability by addressing inconsistency, sparsity, and high-dimensionality

Table 4 RNA SPCA Enriched GO Terms

SPC	Contributing Genes (Gene Name\|GeneID)	Enriched GO Biological Processes
X6	ADAM6\|8755, FBP4\|2167, FN1\|2335, GAPDH\|2597, KRT13\|3860, KRT16\|3868, KRT17\|3872, LOC96610\|96,610	Cornification
X2	COL1A1\|1277, COL1A2\|1278, COL3A1\|1281, FN1\|2335, KRT13\|3860, KRT14\|3861, KRT16\|3868, KRT17\|3872, KRT5\|3852, KRT6A\|3853, SPARC\|6678	Cornification^a, keratinocyte differentiation, wound healing, cell-substrate junction assembly^a, collagen fibril organization^a
X9	ACTB\|60, ADAM6\|8755, COL1A1\|1277, COL1A2\|1278, FN1\|2335, LAMC2\|3918, TGFBI\|7045	Skin morphogenesis, protein heterotrimerization, platelet activation^a, cell junction assembly, cell junction organization, extracellular matrix organization, extracellular structure organization, blood vessel development^a, cell adhesion
X7	ADAM6\|8755, FABP4\|2167, KRT16\|3868, KRT17\|3872, KRT5\|3852, KRT6B\|3854, LOC96610\|96,610, PI3\|5266	Cornification^a, programmed cell death, cell death, keratinization, skin development
X1	KRT14\|3861, KRT16\|3868, KRT17\|3872, KRT5\|3852, KRT6A\|3853, KRT6B\|3854, KRT6C\|286,887, S100A9\|6280	Cornification^a, intermediate filament cytoskeleton organization^a, cell death, hair cycle
X3	COL1A1\|1277, COL1A2\|1278, COL3A1\|1281, KRT13\|3860, KRT14\|3861, KRT16\|3868, KRT17\|3872, KRT5\|3852, KRT6A\|3853, KRT6B\|3854, KRT6C\|286,887, SFN\|2810	Cornification^a, multicellular organism development, intermediate filament cytoskeleton organization^a, collagen fibril organization

SPC gene sets listing both gene names and Entrez gene IDs; PANTHER annotation terms found to be enriched in each of the SPC gene sets. Annotation terms are reported in increasing order of p-value, with all p < 0.001. ^a indicates some lower level hierarchical terms omitted for brevity

ISSN: 1471-2105