Artificial intelligence-driven meta-analysis of brain gene expression identifies novel gene candidates and a role for mitochondria in Alzheimer’s disease

Finney, Caitlin A.; Delerue, Fabien; Gold, Wendy; Brown, David A.; Shvetcov, Artur

doi:10.1016/j.csbj.2022.12.018

Cited by 13 publications

(15 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further supporting this, a PCA indicated a clear group separation between the AD cases and healthy controls (Figure 1). Using GSE97760, we then performed our established two-stage machine learning pipeline as previously described in Finney et al [8]. Briefly, we first analyzed all genes (>15,000) using PCA (Figure 6).…”

Section: Methodsmentioning

confidence: 99%

“…The clusters were then characterized by biological processes and cellular localization using Gene Ontology (GO) [59] and the central gene nodes in each cluster were selected. Central gene nodes were identified as those with the highest number of connections with other genes in the network, a method used to increase the likelihood of identifying biomarker candidates that are fundamental to biological processes [8].…”

Section: Methodsmentioning

confidence: 99%

“…We then used the eight top important genes from PC1 and PC2 clusters in AD in a random forest model (Figure 6). We first merged the two AD datasets (GSE63061 and GSE63060) into a single dataset using z-scores as we've done previously [8]. This merged dataset was then used as a training dataset to train, tune, and validate our models.…”

Section: Supervised Machine Learning To Identify If Ad Gene Biomarker...mentioning

confidence: 99%

“…However, historically there has been a tendency to use these high-throughput techniques to test a priori hypotheses, potentially limiting the full appreciation of their diagnostic capacity. Further, these datasets are often analyzed using arbitrary, yet commonly used fold change and corrected p -value thresholds, which can bias the results and their interpretation [8]. One way around these limitations is to distil new perspectives in high-throughput data, without preconceptions, using machine learning.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Blood-based transcriptomic biomarkers are predictive of neurodegeneration rather than Alzheimer’s disease

Shvetcov,

Thomson,

Spathos

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Alzheimers disease (AD) is a growing global health crisis, affecting millions and incurring substantial economic costs. However, clinical diagnosis remains challenging, with misdiagnoses and underdiagnoses prevalent. There is an increased focus on putative, blood-based biomarkers that may be useful for the diagnosis, as well as early detection, of AD. In the present study, we used an unbiased combination of machine learning and functional network analyses to identify blood gene biomarker candidates in AD. Using supervised machine learning, we also determine whether these candidates were indeed unique to AD or whether they were indicative of other neurodegenerative diseases Parkinsons disease (PD) and amyotrophic lateral sclerosis (ALS). Our analyses showed that genes involved in spliceosome assembly, RNA binding, transcription, protein synthesis, mitoribosomes, and NADH dehydrogenase were the best performing genes for identifying AD patients relative to cognitively healthy controls. This transcriptomic signature, however, was not unique to AD and subsequent machine learning showed that this signature could also predict PD and ALS relative to controls without neurodegenerative disease. Combined, our results suggest that mRNA from whole blood can indeed be used to screen for patients with neurodegeneration but may be less effective at diagnosing the specific neurodegenerative disease.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Supervised Machine Learning To Identify If Ad Gene Biomarker...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Blood-based transcriptomic biomarkers are predictive of neurodegeneration rather than Alzheimer’s disease

Shvetcov,

Thomson,

Spathos

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among the upregulated genes in Cav-1 brain and placenta and downregulated in wildtype we found Il1rl1, which is the receptor for IL33 (Palmer et al, 2008), and was found to improve the beta amyloid pathology in microglial cells in AD brain (Lau, Chen, et al, 2020). Additionally, ATP5l, which was identified as one of the major genes in creating a model for Alzheimer's and affects the dysregulated oxidative phosphorylation in mitochondria in the frontal cortex of brain (Finney et al, 2022), was also upregulated in Cav-1 KO. Moreover, Fgfbp1 which was found to be a Wnt/Beta-catenin-regulated gene in the endothelial cells in mouse brain to maintain blood brain barrier (Cottarelli et al, 2020), was also upregulated in the knockout brain-placenta genes along with HOXC4, which is a Wnt-induced spinal marker (B.-C. .…”

Section: Discussionmentioning

confidence: 84%

Regulation of fetal brain development in short versus long lived mice

Islam¹

View full text Add to dashboard Cite

How fetal brain development is regulated in mice with reduced life span is a primary objective of this research. Three studies were performed to investigate the fetal brain development in short and lived mice strains. The scientific premise and background of brain development and aging are provided review of literature (Chapter 1). In the first study (Chapter 2), experiments were performed to test early-life origin of brain aging. Mouse epigenetic clock (epiclock) database which represents specific genomic sites that are methylated in an age-correlated manner was profiled in three life stages: fetal (gestation day 15), postnatal (day 5), and adult (week 70) brains of male and female C57BL/6J inbred mice. Data analysis showed that the female adult brain was epigenetically younger than the male adult brain even when the chronological age (time from birth) was the same (week 70). Specific methylations in the developing brain predictive of epigenetic differences in the aging brain between sexes were identified by predictive modeling by neural network. This study also showed that gene expression of epiclock genes were similar between placenta and fetal brain. However, genes unrelated to epiclock did not show this pattern. Whole-genome bisulfite sequencing identified sites that were methylated in a coordinated manner in the placenta and in a sex-specific manner in the fetal brain. These sites showed that methylation level in the epiclock genes and genes associated with gonadotropin-releasing hormone (GnRH) signaling pathway genes changes in a fetal-sex dependent manner both in the placenta and fetal brain. Furthermore, these methylations were maintained in the brain in the adult life stages. These findings suggested the fetal origin of sex differences in brain aging is epigenetically linked to the placenta. In the second study (Chapter 3), experiments were performed to test if reducing life span of mouse by ablating Caveolin 1 (Cav-1), a prolongevity gene that codes for an abundant structural protein of plasma membrane in endothelial cells, dysregulate brain development at the fetal stage. Further relevance of studying this specific gene is that mice lacking Cav-1 show neurodegeneration and multiple hallmarks of Alzheimer's disease (AD) at an early age. As a result, most Cav-1- null mice die within a year. Gene expression in bulk brain tissue as well as single cells were analyzed in the Cav-1-null fetal brain compared to the wildtype (WT). The results of this study showed that lack of Cav-1 leads to extensive dysregulation of genes of fetal brain at specific gestation time (day 15). Several epigenetic clock genes were differentially methylated in Cav-1-KO compared to WT mouse fetal brain. Single nuclei RNA sequencing identified specific glial and neuronal cells being dysregulated in the fetal brain due to the absence of Cav-1. In addition, methylation analysis was performed to investigate effect of Cav-1 on epiclock genes. Based on these results, a model was proposed for fetal links of Alzheimer's symptoms in mice lacking Cav-1. Lastly, in the third study (Chapter 4), experiments were performed to test if reduced lifespan in mice due to murine leukemia virus induced cancer influences fetal brain development. In this experiment, gene expression pattern of fetal brain and placenta of AKR/J mice, which mostly survive for a year due to onset of cancer, was compared with C57BL/6J mice to understand molecular and cellular links between aging and leukemia. The C57BL/6J has longer life span ([greater than] 2 years) and is refractory to AK virus that causes leukemia in AKR/J mice. The gene expression studies showed that genes related to aging and neurodegenerative diseases are differentially regulated in the fetal brain and placenta of AKR/J mice compared to that in C57BL/6J. Targeted methylation profiling of a total of 2,045 single bases of mouse genome, which are associated with mouse epigenetic clock data, showed that brain of AKR/J mice ages faster than C57BL/6J mice suggesting a link between leukemia and neuronal aging. By generating a F2 mapping population from AKR/J x C57BL/6J crosses, Bulk Segregant Analysis (BSA) was performed with the pooled DNA of F2 progenies by whole-genome sequencing to identify genetic variants associated with accelerated brain aging in AKR/J mice. Single-cell ATAC-seq (Assay for Transposase-Accessible Chromatin by sequencing) analysis further predicted that specific transcription factors are involved in the differential gene regulation of fetal brain in AKR/J mice compared to C57BL/6J mice. Together, the results of these study provide foundational knowledge to establish molecular and cellular links between reproduction and aging.

show abstract

Cerebellum in Alzheimer's disease and other neurodegenerative diseases: an emerging research frontier

Yang,

Liu,

Chen

et al. 2024

MedComm

View full text Add to dashboard Cite

The cerebellum is crucial for both motor and nonmotor functions. Alzheimer's disease (AD), alongside other dementias such as vascular dementia (VaD), Lewy body dementia (DLB), and frontotemporal dementia (FTD), as well as other neurodegenerative diseases (NDs) like Parkinson's disease (PD), amyotrophic lateral sclerosis (ALS), Huntington's disease (HD), and spinocerebellar ataxias (SCA), are characterized by specific and non‐specific neurodegenerations in central nervous system. Previously, the cerebellum's significance in these conditions was underestimated. However, advancing research has elevated its profile as a critical node in disease pathology. We comprehensively review the existing evidence to elucidate the relationship between cerebellum and the aforementioned diseases. Our findings reveal a growing body of research unequivocally establishing a link between the cerebellum and AD, other forms of dementia, and other NDs, supported by clinical evidence, pathological and biochemical profiles, structural and functional neuroimaging data, and electrophysiological findings. By contrasting cerebellar observations with those from the cerebral cortex and hippocampus, we highlight the cerebellum's distinct role in the disease processes. Furthermore, we also explore the emerging therapeutic potential of targeting cerebellum for the treatment of these diseases. This review underscores the importance of the cerebellum in these diseases, offering new insights into the disease mechanisms and novel therapeutic strategies.

show abstract

Artificial intelligence-driven meta-analysis of brain gene expression identifies novel gene candidates and a role for mitochondria in Alzheimer’s disease

Cited by 13 publications

References 61 publications

Blood-based transcriptomic biomarkers are predictive of neurodegeneration rather than Alzheimer’s disease

Blood-based transcriptomic biomarkers are predictive of neurodegeneration rather than Alzheimer’s disease

Regulation of fetal brain development in short versus long lived mice

Cerebellum in Alzheimer's disease and other neurodegenerative diseases: an emerging research frontier

Contact Info

Product

Resources

About