# Gene Profile Analysis of Associations between Alzheimer’s Disease and Circadian Rhythmic Patterns of Human Brain Regions Using Machine Learning

> **NIH NIH R21** · UNIVERSITY OF KENTUCKY · 2021 · $420,750

## Abstract

Project Summary
Alzheimer’s disease (AD) is the leading form of dementia, and it has an increasing death rate throughout the
world. It gradually damages a patient’s memory, speech, thinking, and ability to perform routine activities. While
a few drugs may temporarily relieve some mild early AD symptoms, they cannot stop or reverse cognitive and
memory impairment. Multiple studies have shown that circadian rhythm and AD have a close, intricate,
bidirectional relationship. Accumulating evidence indicates that the disorder of circadian rhythm is not only a
pathological marker but a putative risk factor of AD. Improved understanding of the relationship between AD and
the circadian rhythm has the potential to guide the development of effective AD interventions or treatment.
Timed gene expression data human brains are rare because of its highly invasive nature. In general, brain gene
expression studies in neurodegeneration are based on post-mortem tissue samples with no or inaccurate, if any,
time labels. Currently, there is a pending need for characterizing molecular mechanisms which underlie the
relationship of AD with human brain circadian rhythms. However, effective methods are yet to be developed to
analyze whole-genome gene expression data with none or inaccurate time labels to discover AD-specific
differentiated circadian rhythmic patterns. Toward filling this urgent unmet need, our overall aim is to develop
innovative algorithms to discover circadian oscillation patterns based on genome-wide gene profile analysis, and
leverage them to identify and understand the associations of AD with circadian rhythms of different brain regions.
This project will bridge a critical methodological gap to enable innovative discovery from untimed high-
dimensional human brain data. It has a great potential to advance the understanding of the impact of circadian
rhythm on AD, and also provide researchers with a host of potential therapeutic targets for AD, e.g., rhythmic
synchronization of brain regions, to guide the development of future interventions.
This project is highly innovative. For the first time, gene profile analysis based on untimed expression data of
tens of thousands of genes will be performed to pinpoint the AD-specific differentiated rhythmic patterns of
different brain regions. To our knowledge, this is the only capacity of its kind, which permits the most direct
glimpse into the circadian events in the human brain at the brain region- or tissue-level. The algorithms will be
used to find oscillation patterns and rhythmic correlations between brain regions for cohorts with or without AD
and unique subsets of AD patients. Because a clear understanding between AD and the disturbances of human
brain circadian rhythms is elusive, deciphering oscillation patterns of brain regions and accounting for patient
heterogeneity should advance our understanding of the complexity of AD and its intricate relationship with
circadian rhythms of regions.

## Key facts

- **NIH application ID:** 10126568
- **Project number:** 1R21AG070909-01
- **Recipient organization:** UNIVERSITY OF KENTUCKY
- **Principal Investigator:** Qiang Cheng
- **Activity code:** R21 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2021
- **Award amount:** $420,750
- **Award type:** 1
- **Project period:** 2021-03-01 → 2024-08-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10126568

## Citation

> US National Institutes of Health, RePORTER application 10126568, Gene Profile Analysis of Associations between Alzheimer’s Disease and Circadian Rhythmic Patterns of Human Brain Regions Using Machine Learning (1R21AG070909-01). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/10126568. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*