Abstract
Niemann-Pick Class 1 (NPC1) disease is a rare, debilitating neurodegenerative lysosomal storage disease;
however, urinary biomarkers available for it and its prognosis are currently limited. In order to identify and establish such biomarkers, we employed high-resolution 1H NMR analysis coupled to a range of multivariate (MV) analysis approaches,
i.e. PLS-DA, RFs and uniquely the cross-validated correlated component regression (CCR) strategy in order to discern
differences between the urinary metabolic profiles of 13 untreated NPC1 disease and 47 heterozygous (parental) carrier
control participants. Novel computational intelligence techniques (CITs) involving genetic algorithms (GAs) were also
employed for this purpose. These 1
Keywords:
3-Aminoisobutyrate, bile acids, correlated component regression, genetic algorithms, metabolomics, niemann-Pick
type C disease, nuclear magnetic resonance spectroscopy, urine.
Graphical Abstract