Abstract
Alzheimer's disease (AD) is a neurodegenerative and progressive disease, which often causes irreversible damages to the cerebrum. The pathogenesis of AD is far from being fully understood, while there are some popular hypotheses. So far, the diagnosis of AD relies only on clinical screening in the form of imaging techniques or cerebrospinal fluid analysis, which may lead to inaccurate evaluation and then cause the delay of suitable treatments. While molecular biomarkers provide promising alternatives of establishing correct relationships between genotypes and phenotypes of clinical symptoms. In this paper, we propose a machine-learning-based method of identifying potential diagnostic biomarkers of AD based on gene coexpression network by integrating gene expression profiles in six brain regions. After building an integrated gene coexpression network of multiple brain regions, we decompose the differential network into some subnetwork modules. The module candidates from these coexpressed gene communities are then identified by screening their discriminative powers in control from disease samples. The potential biomarkers are then validated by multiple cross-validations and functional enrichment analyses. If the biomarkers successfully pass clinical significance tests, they can be used as a reference for clinical diagnosis after wet-experimental validations.
Highlights
Alzheimer’s disease (AD) is a neurodegenerative and progressive disease, which causes irreversible damages to the cerebrum with cognitive and functional impairments (Porteri et al, 2017)
The results indicate the rationality of identifying AD biomarkers by integrating gene expression datasets in several brain regions
We proposed a computational method of detecting AD biomarkers by integrating gene expression data in six brain regions
Summary
Alzheimer’s disease (AD) is a neurodegenerative and progressive disease, which causes irreversible damages to the cerebrum with cognitive and functional impairments (Porteri et al, 2017). It often takes years to decode, reveal and recognize the neuronal dysfunctions and neurodegeneration with dominant symptoms (Hardy and Selkoe, 2002; Goedert and Spillantini, 2006). The diagnosis of AD generally relies on clinical screening in the form of imaging techniques or cerebrospinal fluid analysis (Jack et al, 2010). The discovery of effective and efficacious biomarkers that can establish correct correspondences and relationships with clinical symptoms has become an urgent request (Porteri et al, 2017)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
