Research Direction：bioinformatics Alzheimer’s Disease

Work roughly: read paper weekly report find data download data (source: NIH, ROSMAP,
ANDI,NDRI) run data from articles from github (python, R)

Following are some papers I have read:

1. Prediction of Alzheimer’s disease based on deep neural network by

integrating gene expression and DNA methylation dataset

2. Differential Expression Analysis of Blood MicroRNA in Identifying Potential Genes Relevant to

Alzheimer’s Disease Pathogenesis, Using an Integrated Bioinformatics and Machine Learning
Approach

Recent research has focused on the deregulation of microRNAs (miRNAs) in blood as the
potential biomarkers for AD. As such, a differential expression analysis of miRNAs was conducted
in this study using an integrated framework that utilized the advantages of statistical and
machine learning approaches.
The roles and functions of the identified differentiated miRNA candidates with AD development
were verified by predicting their target mRNAs, and their networks of interaction in AD
pathogenesis were investigated.

3. A ML approach to unmask novel gene signatures and prediction of AD within different brain
regions
The article employed the ensemble of random-forest and regularized regression model (LASSO)
to the AD-associated microarray datasets from four brain regions - Prefrontal cortex, Middle
temporal gyrus, Hippocampus, and Entorhinal cortex- to discover novel genetic biomarkers
through a machine learning-based feature-selection classification scheme.
The proposed scheme unraveled the most optimum and biologically significant classifiers within
each brain region, which achieved by far the highest prediction accuracy of AD in 5-fold cross-
validation (99% average).
Interestingly, along with the novel and prominent biomarkers including CORO1C, SLC25A46,
RAE1, ANKIB1, CRLF3, PDYN, numerous non-coding RNA genes were also observed as
discriminator, of which AK057435 and BC037880 are uncharacterized long non-coding RNA
genes.

4. SCOT: Single-Cell Multi-Omics Alignment with Optimal Transport

The paper presents single-cell alignment with optimal transport (SCOT), an unsupervised
algorithm that uses the Gromov–Wasserstein （no need from same data sets, compare metric
spaces directly ）optimal transport to align single-cell multi-omics data sets. (fewer
hyperparameters)
Learning Summary: According to WHO, there will be approximately 139 million people with AD
worldwide by 2050.

There is no empirical evidence that specific drugs or nutritional supplements are effective in
treating the disease. There are no treatments that can stop or reverse the course of the disease,
and only a few methods that might temporarily relieve or improve symptoms.

AD The only method that can be established to confirm AD is using slices of a person's brain after
death, Brain Biopsy cafter autopsy

The only way to confirm AD is to use brain slices from people after they die, Brain Biopsy cafter
autopsy. The method that is currently being learned is to use gene expression data, DNA
methylation dataset to combine data with different models to predict AD, and the earlier AD is
detected and the earlier it can be prevented, the better.

The earlier AD is detected, the better it is prevented. There is also the microRNA extraction from
spinal blood to predict AD.

Recently, I've been studying optimal transport, "computational optimal transport".