Through the Bloodstream: A Novel Biomarker Search for Early Blood‐Based Alzheimer’s Diagnosis Using an Adversarial Autoencoder

AbstractBackgroundAlzheimer’s Disease (AD) is a neurodegenerative disease marked by loss of memory and cognitive functions. As there is no Alzheimer’s cure, an essential early diagnosis can lead to earlier treatment access and time to prepare financially. Current diagnosis methods are expensive and hard to access, which is why there has been a shift to use blood tests. The problem with blood‐based diagnosis is their use of biomarkers as there are only a few known biomarkers of Alzheimer’s. We used an Adversarial Autoencoder (AAE) to increase sensitivity in identifying potential biomarkers in blood samples.MethodWe applied the AAE to identify potential biomarkers through a single cell RNA sequencing dataset from peripheral blood cells (PBC). We synthesized single cell matrices from the trained AAE using randomly sampled sets from the original dataset, and found common genes among them. Afterwards, we determined the molecular mechanisms of these common genes using a gene ontology (GO) enrichment analysis to validate their genomic functions.ResultFrom the experiment, we succeeded in identifying 157 potential biomarkers for Alzheimer’s using the AAE. Not only are these biomarkers related to the immune response system, the molecular mechanisms of these genes are enriched in Alzheimer’s. This enrichment further indicates the potential of these genes to be useful biomarkers in early diagnosis.ConclusionOur approach using the AAE and the single cell RNA sequence dataset could be a new method for biomarker search in Alzheimer’s early diagnosis.