Multiomics machine learning identifies sleep and inflammation molecular pathways in prodromal Alzheimer's Disease

Mild Cognitive Impairment (MCI) is a phase that can precede Alzheimers Disease (AD). To better understand the molecular mechanisms underlying conversion from MCI to AD, we applied a battery of machine learning algorithms on 800 samples from the EMIF-AD MBD study. The cohort comprised participants diagnosed as 230 normal cognition (NC), 386 MCI (with longitudinal data on AD conversion or remaining stable) and 184 AD-type dementia. Data consisted of metabolites (n=540) and proteins (n=3630) measured in plasma coupled to clinical data (n=26). Multiclass models selected oleamide, MMSE and the priority language as the most confident features while MCI conversion models selected pTau, tTau and JPH3, CFP, SNCA and PI15 proteins. These proteins selected for MCI conversion have been previously associated with AD-related phenotype. Oleamide, a possible anti-inflammatory, prompted in-vitro experiments in rodent microglia. The results demonstrated that disease-associated microglia synthesize oleamide which were excreted in vesicles. In addition, plasma vesicles extracted from participants with AD showed elevated oleamide levels compared to controls (P<0.05). This study uncovered MCI conversion pathways that involve inflammation, neuronal regulation and protein degradation. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=108 SRC="FIGDIR/small/23286674v3_ufig1.gif" ALT="Figure 1"> View larger version (39K): org.highwire.dtl.DTLVardef@55426forg.highwire.dtl.DTLVardef@17c88a8org.highwire.dtl.DTLVardef@eff242org.highwire.dtl.DTLVardef@109ec5c_HPS_FORMAT_FIGEXP M_FIG C_FIG