Identify Alzheimer's disease subtypes and makers from multi-omic data of human brain and blood with a subspace merging algorithm
Song, Z.; Huang, X.; Jannu, A. J.; Johnson, T. S.; Zhang, J.; Huang, K.
Show abstract
Identifying Alzheimers disease (AD) subtypes is essential for AD diagnosis and treatment. We integrated multiomics data from brain tissues of the ROSMAP and MSBB studies using a subspace merging algorithm and identified two AD patient clusters with notable cognitive and AD pathology differences. Analysis of differentially expressed genes (DEGs) in brain and blood samples pinpointed the LDLR gene as a potential blood biomarker linked to brain gene expression changes. Furthermore, we conducted PheWAS analysis on All of Us Projects EHR and WGS dataset for 105 eQTLs associated with the DEGs and revealed significant associations between these eQTLs and several phenotypes, shedding light on potential regulatory roles of these genes in diverse physiological processes. Our study successfully integrated multiomics data and proposes LDLR as a candidate blood biomarker for AD subtyping. The identified phenotypic signatures provide valuable insights on molecular mechanisms underlying AD heterogeneity, paving the way for personalized AD treatment.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Genome wide association neural networks (GWANN) identify novel genes linked to family history of Alzheimer’s disease in the UK Biobank 95%
- LRcell: detecting the source of differential expression at the sub-cell type level from bulk RNA-seq data 94%
- nMAGMA: a network enhanced method for inferring risk genes from GWAS summary statistics and its application to schizophrenia 93%
Similar papers in this journal
- Identification of functionally connected multi-omic biomarkers for Alzheimer’s Disease using modularity-constrained Lasso 97%
- c-Triadem: A constrained, explainable deep learning model to identify novel biomarkers in Alzheimer’s disease 96%
- Analysis of modular gene co-expression networks reveals molecular pathways underlying Alzheimer’s disease and progressive supranuclear palsy 96%
Similar papers in this journal
- Network medicine links SARS-CoV-2/COVID-19 infection to brain microvascular injury and neuroinflammation in dementia-like cognitive impairment 96%
- Polygenic effects on the risk of Alzheimer’s disease in the Japanese population 95%
- AlzGPS: A Genome-wide Positioning Systems Platform to Catalyze Multi-omics for Alzheimer's Therapeutic Discovery 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.