Gene Expression and Alternative Splicing Analysis in a Large-Scale Multiple Sclerosis Study.

Multiple Sclerosis (MS) is an autoimmune neurodegenerative disease affecting approximately 3 million people globally. Despite rigorous research on MS, aspects of its development and progression remain unclear. We utilized a publicly available RNA-seq dataset (GSE138614) consisting of the post-mortem white matter tissues of five donors without any neurological disorders and ten MS patient donors.

Reduced HyperBF networks: regularization by explicit complexity reduction and scaled Rprop-based training.

Hyper basis function (HyperBF) networks are generalized radial basis function neural networks (where the activation function is a radial function of a weighted distance). Such generalization provides HyperBF networks with high capacity to learn complex functions, which in turn make them susceptible to overfitting and poor generalization. Moreover, training a HyperBF network demands the weights, centers, and local scaling factors to be optimized simultaneously.

Effect of single nucleotide polymorphisms on Affymetrix match-mismatch probe pairs.

Microarrays provide a means of studying expression level of tens of thousands of genes by providing one or more oligonucleotide probe(s) for each transcript studied. Affymetrix(R) GeneChiptrade mark platforms historically pair each 25-base perfect match (PM) probe with a mismatch probe (MM) differing by a complementary base located in the 13(th) position to quantify and deflate effects of cross-hybridization. Analytical routines for analyzing these arrays take into account difference in expression levels of MM and PM probes to determine which ones are useful for further study.