Search DIAN Data Resource Requests

Title:PET/MRI-based Alzheimer's Disease Research Using Deep Learning

Date of Request:12/26/2023

Status:pending approval

ID:DIAN-D2327

Aim 1:Longitudinal imaging markers describing changes in AD over time

Aim 2:Explore the relationship with AB deposition, related genes and cognition to obtain the most relevant imaging and biological indicators

Aim 3:Multiple features were extracted and machine learning and deep learning were used to explore their biological markers

Title:Classification based on hippocampal multivariate morphometry statistics

Date of Request:11/19/2023

Status:pending approval

ID:DIAN-D2326

Aim 1:High-dimensional morphological features of the hippocampus were extracted to analyze group differences among different populations

Aim 2:The dimension of high-dimensional morphological features is reduced for subsequent classification

Title:Classification based on hippocampal multivariate morphometry statistics

Date of Request:11/19/2023

Aim 1:Extracting the high-dimensional morphological features of the hippocampus and cerebral ventricle of ADAD

Aim 2:Analyzing high-dimensional features to identify inter-group morphological differences in the hippocampus.

Aim 3:Using high-dimensional features for classification.

Title:Organoid-based lncRNA discovery platform for Alzheimer's Disease.

Date of Request:11/14/2023

Status:pending approval

ID:DIAN-D2325

Aim 1:Generate assembloid cultures (assembled organoids) from familial and sporadic Alzheimer's Disease induced pluripotent stem cell (iPSC) lines, as well as their Crispr-Cas9 generated isogenic controls.

Aim 2:Extract cell-type specific long non-coding RNA (lncRNA) repertoires by using a combination of lineage purification, deep RNA sequencing and ATAC sequencing.

Aim 3:Annotate novel lncRNA and identify transcripts that are dysregulated in patient vs control cells.

Aim 4Use bulk and single-cell transcriptomes from the DIAN cohorts to validate newly identified lncRNA that may be associated with the disease.

Title:Computational Modelling and Inference of Neurodegenerative Disease Propagation (CU-MONDAI)

Date of Request:09/29/2023

Status:pending approval

ID:DIAN-D2324

Aim 1:To provide new insights into how pathology spread is linked to the brain’s connectivity architecture in autosomal dominant Alzheimer’s disease and validate new computational models of pathology propagation in neurodegenerative diseases.

Title:Examining the Predictive Value of Synaptic Dysfunction and Neuronal Injury Measures on Imaging Markers of Disease Presentation and Progression in Alzheimer's Disease

Date of Request:09/26/2023

Status:pending approval

ID:DIAN-D2323

Aim 1:Evaluate association between rates of longitudinal change in CSF levels of Ng, SNAP-25, VILIP-1 and imaging brain changes and cognition in a DIAD cohort.

Aim 2:Evaluate association between rates of longitudinal change in CSF levels of Ng, SNAP-25, VILIP-1 and imaging brain changes and cognition in aged adults LOAD cohort.

Title:Evaluating neural correlates of apathy in Alzheimer’s disease

Date of Request:09/18/2023

Status:pending approval

ID:DIAN-D2322

Aim 1:Aim1. We will seek to determine if apathy is embedded in a larger network of NPS and functional and cognitive impairment using clustering analysis. In the subset of data with neuropathology information, we will identify the association between apathy clusters and neuropathology.

Aim 2:Aim2. We will examine brain morphometry, structural connectivity, metabolism, amyloid PET in reward-sensitive areas, and effort valuation processing areas in apathy and/or its networks.

Aim 3:Aim3. We will evaluate the association between the intrinsic time scale (fMRI) and apathy and apathy networks in the course of disease.

Title:Prediction of Alzheimer's Disease through multimodal approach by machine learning

Date of Request:09/07/2023

Status:pending approval

ID:DIAN-D2321

Aim 1:Develop a multimodal machine learning model to accurately predict Alzheimer's disease progression using a combination of imaging, genetic, and clinical data.

Aim 2:Investigate the potential biomarkers and features from various modalities that contribute significantly to the early detection and progression tracking of Alzheimer's disease.

Aim 3:Evaluate the model's performance in predicting Alzheimer's risk and progression in a diverse patient population, including individuals with different genetic backgrounds and demographics.

Aim 4Explore the interpretability of the multimodal model to gain insights into the underlying mechanisms of Alzheimer's disease, aiding in the development of targeted interventions.

Title:Epigenetic analyses to assess the resilience among DIAN mutation carriers

Date of Request:09/05/2023

Status:pending approval

ID:DIAN-D2320

Aim 1:To investigate the potential epigenetic causes of resilience among DIAN mutation carriers who are discordant in disease courses measured by biomarkers

Title:Knowledge Guided Machine Learning for Prognosis Forecast ing of Alzheimer’s Disease in People with Down Syndrome

Date of Request:08/17/2023

Status:pending approval

ID:DIAN-D2319

Aim 1:explore different methods, such as data augmentation, transfer learning, and knowledge-guided generative adversarial networks (GANs), to address the insufficient training data issue thus improve the quality of data representations

Aim 2:the fusion of the valuable domain-specific knowledge of AD and designs of graph neural networks will be explored to improve the robustness and interpretability in diagnosis and prognosis of AD

Aim 3:develop multimodal machine learning frameworks for early diagnosis and prognosis of AD