Deep learning-based brain transcriptomic signatures associated with the neuropathological and clinical severity of Alzheimer’s disease

Abstract

Brain tissue gene expression from donors with and without Alzheimer’s disease (AD) have been used to help inform the molecular changes associated with the development and potential treatment of this disorder. Here, we use a deep learning method to analyze RNA-seq data from 1,114 brain donors from the Accelerating Medicines Project for Alzheimer’s Disease (AMP-AD) consortium to characterize post-mortem brain transcriptome signatures associated with amyloid-β plaque, tau neurofibrillary tangles, and clinical severity in multiple Alzheimer’s disease dementia populations. Starting from the cross-sectional data in the Religious Orders Memory and Aging Project (ROSMAP) cohort (n = 634), a deep learning framework was built to obtain a trajectory that mirrors Alzheimer’s disease progression. A severity index (SI) was defined to quantitatively measure the progression based on the trajectory. Network analysis was then carried out to identify key gene (index gene) modules present in the model underlying the progression. Within this dataset, severity indexes were found to be very closely correlated with all Alzheimer’s disease neuropathology biomarkers (R ∼ 0.5, p < 1e-11) and global cognitive function (R = -0.68, p < 2.2e-16). We then applied the model to additional transcriptomic datasets from different brain regions (MAYO, n = 266; Mount Sinai Brain Bank, n = 214), and observed that the model remained significantly predictive (p < 1e-3) of neuropathology and clinical severity. The index genes that significantly contributed to the model were integrated with Alzheimer’s disease co-expression regulatory networks, resolving four discrete gene modules that are implicated in vascular and metabolic dysfunction in different cell types respectively. Our work demonstrates the generalizability of this signature to frontal and temporal cortex measurements and additional brain donors with Alzheimer’s disease, other age-related neurological disorders and controls; and revealed the transcriptomic network modules contribute to neuropathological and clinical disease severity. This study illustrates the promise of using deep learning methods to analyze heterogeneous omics data and discover potentially targetable molecular networks that can inform the development, treatment and prevention of neurodegenerative diseases like Alzheimer’s disease.

Unique Transcriptional Signatures Correlate with Behavioral and Psychological Symptom Domains in Alzheimer’s Disease

“…Therefore, it was encouraging to see such a large number of DEGs that are unique to each domain despite the overlapping design, which may suggest that each BPSD domain has distinct biological etiologies despite the common neuropathological driversin this case, AD. These findings may be comparable to other investigations showing distinct pathways associated with cognitive decline in AD at the transcriptomic, proteomic, and methylation levels in brain tissue without overlapping dependence on being correlated with AD pathology [72][73][74][75][76][77][78][79], highlighting the heterogeneity of downstream molecular processes from what is putatively considered the upstream etiological agents, namely A and tau. Though this design has the advantage of increasing statistical power in exploring a wide array of symptoms, it presumes separability that precludes identification of individuals with overlapping psychiatric domains that may have unique molecular mechanisms distinct from if these symptoms presented separately.…”

The Key Factors Predicting Dementia in Individuals With Alzheimer’s Disease-Type Pathology

“…Lastly, the size and scope (quantitative regional neuropathology, longitudinal cognition, and RNA-sequencing) of the ROSMAP dataset means that there was no dataset available where we could replicate the machine learning approach used here. However, both PRTN3 and ADAMTS2 (as well as other highly ranked genes such as PPDPF , SLC6A9 , SLC4A11 ) were recently identified as relevant to AD progression by an independent study using deep learning on the Mount Sinai Brain Bank and ROSMAP transcriptomic datasets ( Wang et al, 2021 ).…”

Artificial intelligence for dementia genetics and omics

“…Wang and colleagues implemented a DL method that analyzes RNA-seq data from brain donors to characterize post mortem brain transcriptome signatures associated with amyloid-β plaques, tau neurofibrillary tangles and clinical severity in multiple AD and related dementia populations. 58 In the proteomics space, Tasaki and colleagues applied a deep neural network approach to predict protein abundance from mRNA expression, in an attempt to track the early protein drivers of AD and related dementia subtypes. 72 These approaches demonstrate how such methodologies can be used to identify potential early protein drivers and possible drug targets for preventing or treating AD and related dementias.…”

“…Huang and colleagues have recently developed EWASplus, a computational method that uses a supervised ML strategy to extend EWAS coverage to the entire genome, 38 and implicates additional epigenetic loci for AD that are not found using array‐based AD EWASs. Wang and colleagues implemented a DL method that analyzes RNA‐seq data from brain donors to characterize post mortem brain transcriptome signatures associated with amyloid‐β plaques, tau neurofibrillary tangles and clinical severity in multiple AD and related dementia populations 58 . In the proteomics space, Tasaki and colleagues applied a deep neural network approach to predict protein abundance from mRNA expression, in an attempt to track the early protein drivers of AD and related dementia subtypes 72 .…”