Browsing by Subject "Biological network"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Integrating Interpretable Machine Learning and Multi-omics Systems Biology for Personalized Biomarker Discovery and Drug Repurposing in Alzheimer’s Disease
    (bioRxiv, 2025-03-28) Mottaqi, Mohammadsadeq; Zhang, Pengyue; Xie, Lei; Biostatistics and Health Data Science, Richard M. Fairbanks School of Public Health
    Background: Alzheimer's disease (AD) is a complex neurodegenerative disorder with substantial molecular variability across different brain regions and individuals, hindering therapeutic development. This study introduces PRISM-ML, an interpretable machine learning (ML) framework integrating multiomics data to uncover patient-specific biomarkers, subtissue-level pathology, and drug repurposing opportunities. Methods: We harmonized transcriptomic and genomic data of three independent brain studies containing 2105 post-mortem brain samples (1363 AD, 742 controls) across nine tissues. A Random Forest classifier with SHapley Additive exPlanations (SHAP) identified patient-level biomarkers. Clustering further delineated each tissue into subtissues, and network analysis revealed critical "bottleneck" (hub) genes. Finally, a knowledge graph-based screening identified multi-target drug candidates, and a real-world pharmacoepidemiologic study evaluated their clinical relevance. Results: We uncovered 36 molecularly distinct subtissues, each defined by a set of associated unique biomarkers and genetic drivers. Through network analysis of gene-gene interactions networks, we highlighted 262 bottleneck genes enriched in synaptic, cytoskeletal, and membrane-associated processes. Knowledge graph queries identified six FDA-approved drugs predicted to target multiple bottleneck genes and AD-relevant pathways simultaneously. One candidate, promethazine, demonstrated an association with reduced AD incidence in a large healthcare dataset of over 364000 individuals (hazard ratios ≤ 0.43; p < 0.001). These findings underscore the potential for multi-target approaches, reveal connections between AD and cardiovascular pathways, and offer novel insights into the heterogeneous biology of AD. Conclusions: PRISM-ML bridges interpretable ML with multi-omics and systems biology to decode AD heterogeneity, revealing region-specific mechanisms and repurposable therapeutics. The validation of promethazine in real-world data underscores the clinical relevance of multi-target strategies, paving the way for more personalized treatments in AD and other complex disorders.
  • Thumbnail Image
    Item
    Integrative analysis of multi-omics and imaging data with incorporation of biological information via structural Bayesian factor analysis
    (Oxford University Press, 2023) Bao, Jingxuan; Chang, Changgee; Zhang, Qiyiwen; Saykin, Andrew J.; Shen, Li; Long, Qi; Alzheimer’s Disease Neuroimaging Initiative; Radiology and Imaging Sciences, School of Medicine
    Motivation: With the rapid development of modern technologies, massive data are available for the systematic study of Alzheimer's disease (AD). Though many existing AD studies mainly focus on single-modality omics data, multi-omics datasets can provide a more comprehensive understanding of AD. To bridge this gap, we proposed a novel structural Bayesian factor analysis framework (SBFA) to extract the information shared by multi-omics data through the aggregation of genotyping data, gene expression data, neuroimaging phenotypes and prior biological network knowledge. Our approach can extract common information shared by different modalities and encourage biologically related features to be selected, guiding future AD research in a biologically meaningful way. Method: Our SBFA model decomposes the mean parameters of the data into a sparse factor loading matrix and a factor matrix, where the factor matrix represents the common information extracted from multi-omics and imaging data. Our framework is designed to incorporate prior biological network information. Our simulation study demonstrated that our proposed SBFA framework could achieve the best performance compared with the other state-of-the-art factor-analysis-based integrative analysis methods. Results: We apply our proposed SBFA model together with several state-of-the-art factor analysis models to extract the latent common information from genotyping, gene expression and brain imaging data simultaneously from the ADNI biobank database. The latent information is then used to predict the functional activities questionnaire score, an important measurement for diagnosis of AD quantifying subjects' abilities in daily life. Our SBFA model shows the best prediction performance compared with the other factor analysis models. Availability: Code are publicly available at https://github.com/JingxuanBao/SBFA.
  • Thumbnail Image
    Item
    Three human cell types respond to multi-walled carbon nanotubes and titanium dioxide nanobelts with cell-specific transcriptomic and proteomic expression patterns
    (Taylor & Francis, 2014-08) Tilton, Susan C.; Karin, Norman J.; Tolic, Ana; Xie, Yumei; Lai, Xianyin; Hamilton Jr., Raymond F.; Waters, Katrina M.; Holian, Andrij; Witzmann, Frank A.; Orr, Galya; Cellular & Integrative Physiology, School of Medicine
    The growing use of engineered nanoparticles (NPs) in commercial and medical applications raises the urgent need for tools that can predict NP toxicity. We conducted global transcriptome and proteome analyses of three human cell types, exposed to two high aspect ratio NP types, to identify patterns of expression that might indicate high vs. low NP toxicity. Three cell types representing the most common routes of human exposure to NPs, including macrophage like (THP-1), small airway epithelial (SAE), and intestinal (Caco-2/HT29-MTX) cells, were exposed to TiO2 nanobelts (TiO2-NB; high toxicity) and multi-walled carbon nanotubes (MWCNT; low toxicity) at low (10 μg/ml) and high (100 μg/ml) concentrations for 1 and 24 h. Unique patterns of gene and protein expressions were identified for each cell type, with no differentially expressed (p<0.05, 1.5-fold change) genes or proteins overlapping across all three cell types. While unique to each cell-type, the early response was primarily independent of NP type, showing similar expression patterns in response to both TiO2-NB and MWCNT. The early response might therefore indicate a general response to insult. In contrast, the 24 h response was unique to each NP type. The most significantly (p<0.05) enriched biological processes in THP-1 cells indicated TiO2-NB regulation of pathways associated with inflammation, apoptosis, cell cycle arrest, DNA replication stress and genomic instability, while MWCNT regulated pathways indicating increased cell proliferation, DNA repair and anti-apoptosis. These two distinct sets of biological pathways might therefore underlie cellular responses to high and low NP toxicity, respectively.