SNPranker 2.0: a gene-centric data mining tool for diseases associated SNP prioritization in GWAS

BMC Bioinformatics

Table 1 Default feature weights as result of the optimization process.

Section	Feature Name	Feature Weight
SNPs and Genes	MAF	0.3133
	Localization	0.7052
	Essential Genes	0.2665
	Phylo	0.5797
	Lamina associated domains	0.2444
Epigenetics and transcription regulations	Open Chromatin	0.1596
	Chromatin Structure	0.7525
	Methylation (seq regions)	0.4009
	Methylation	0.3743
	CpG Island	0.8992
	DNase clusters	0.9558
	TSS (eponine)	0.3705
	CpG islands, promoters, first exons	0.9665
	FOX2 CLIP-seq	0.5608
	TAF1 binding sites	0.2468
	Intergenic regulatory elements	0.4006
	TSS (SwitchGear)	0.6773
	Regulatory regions (OregAnno)	0.8818
	TFBS (TRANSFAC)	0.8243
	TXN factor ChIP-Seq	0.4477
	Enhancers (VISTA)	0.9571
Translation regulations	Alternative Splicing	0.7032
	miRNA binding regions	0.8358
Proteins	Hub protein	0.5796
	Protein Domain	0.6316
	PolyPhen	0.5678
	SNPs 3D	0.5977
	LS-SNP	0.3158
	Protein Interactions	0.3728
	PTM	0.5399
Disease	Pathologies OMIM	0.2904

The table presents the SNP features used by SNPranker 2.0 with their default weights, according to the optimization performed using the genetic algorithm (sensitivity = 0.814, specificity = 0.761 and accuracy = 0.761).

ISSN: 1471-2105