MARS
MARS is a repository service of Mason Publishing and the Data and Digital Scholarship Services (DDSS) at the George Mason University Libraries. MARS provides enduring, stable, well-indexed access to a wide range of scholarship from the Mason community, such as Electronic Theses and Dissertations (ETDs), articles, presentations, reports, and creative work. Learn more about publishing, sharing, and preserving research data with the George Mason University Institutional Dataverse, and our other repository services.
To start publishing your content in MARS, please contact us by using our online form. Questions? Please email publish@gmu.edu.
Communities in MARS
Select a community to browse its collections.
Recent Submissions
Predicting Alzheimer’s Disease from miRNA Sequence and Expression Data with Machine Learning
(2024-04-25) Monserrate, Sydney; Lockhart, Christopher
Approximately 6.5 million people, most of whom are 65 years of age and older, have been diagnosed with Alzheimer's Disease (AD) in the United States. Diagnosing AD has notoriously been difficult because disease progression can occur before the onset of cognitive impairment, and the physiological changes in AD brains are largely only observable in post-mortem studies. AD screening has been bolstered by novel biomarkers, including expression profiles of exosomal and circulating miRNAs. Although relatively new to biological studies, these miRNAs have become a focal point due to their widespread availability in bodily fluids and potential use in disease diagnostics. The purpose of our study was to investigate the utility of machine learning (ML) to predict AD-associated outcomes with miRNA sequence and expression data. Machine learning was performed leveraging the Orange Data Mining platform, which allowed us to quickly prototype various machine learning models and assess their performance numerically and graphically. To utilize miRNA sequence data, we employed a k-mer bag of words model to quantify subsequences within miRNAs and predict if miRNAs are involved in AD pathways. We found that a random forest model provides the best predictions with an accuracy of 0.772 and an area under the receiver operating characteristic (AUROC) of 0.813. Interestingly, out all k-mers, we found that those rich in purines are the most predictive of miRNA association with AD. As a second modelling effort, we analyzed a previously published dataset [Ludwig et al. (2019) Machine Learning to Detect Alzheimer’s Disease from Circulating Non-Coding RNAs Genom. Proteom. Bioinform. 17(4): 430-440] that measured miRNA expression in AD and healthy patients. A random forest model produced an accuracy of 0.786 and AUROC of 0.862 approximately reproducing the published results. We explored if the likelihood for miRNAs to be associated with AD-related pathways can be used as additional selection criteria for miRNA expression profile analyses and discuss the broader applications of our machine learning models in AD diagnostics. Ultimately, we believe our machine learning models will be useful to determine for new miRNA sequences if they are likely to be involved in AD and to pre-select miRNAs as biomarkers for expression profile analysis, which could be used as a diagnostic tool.
Endoplasmic Reticulum Stress-Induced Apoptosis Resistance Mechanisms in Idiopathic Pulmonary Fibrosis-Derived Fibroblasts
(2024-04-26) Moore, Durwood; Grant, Geraldine
Idiopathic pulmonary fibrosis (IPF) is a devastating fatal interstitial lung disease that is the result of an accumulation of highly secretory senescent fibroblasts. Our group has previously demonstrated that IPF fibroblasts (IPF-F) are resistant to the apoptotic pressures initiated by the unfolded protein response (UPR) during times of ER stress. IPF-F show an upregulation of BAX Inhibitor-1 (BI-1), which has been shown to negatively regulate the dimerization of IRE1α and inhibit BAX-mediated apoptosis. We hypothesize that IPF-F can evade ER stress-induced apoptosis through an upregulation of BI-1, but it is uncertain whether this is primarily through an IRE1α or BAX-driven pathway.
IPF-F and normal human lung fibroblasts (NHLF) were transfected with siRNAs targeting BI-1, IRE1α, and BAX. ER stress was generated through a 0.1 μg/mL tunicamycin challenge. Activation of ER stress-driven apoptosis was assayed through a western blot of apoptosis signaling molecules CHOP and Caspase 3. Cell survival was measured through a CCK-8 cytotoxicity assay.
We demonstrate that both the IRE1α and BAX pathways are important to the cell’s ability to undergo ER stress-driven apoptosis. Silencing each pathway individually did not rescue the cell from tunicamycin-induced apoptosis. This suggests that BI-1 is a multifaceted inhibitor of ER stress-mediated apoptosis. Further characterization of UPR and BAX-driven apoptosis via western blot will be required to better understand the mechanisms by which BI-1 prevents apoptosis.
Machine Learning for Mobile Healthcare
(2024-04-26) Nirmala, Chiranjivan Krishnakumar; Jiang, Weiwen
As AI becomes increasingly ubiquitous across industries, there is a growing demand for ML models to be deployed on edge devices, driven by the democratization of AI. However,
the decision-making processes of AI systems often exhibit biases, prompting a renewed focus on fairness, particularly in industries prioritizing equitable outcomes such as security
surveillance, face recognition, and medical applications like dermatology. This research addresses the need for fairness in mobile healthcare, specifically in dermatology, by developing an Android application for skin disease detection and mobile dermatology assistance in remote areas. While existing AI systems boast high overall accuracies, they often neglect fairness considerations, resulting in subpar performance, especially on datasets representing diverse skin tones. Despite the importance of fairness, most neural network architectures prioritize other metrics, disregarding the need for models to run efficiently on edge devices. To bridge this gap, there is a call for smaller networks optimized for hardware constraints, without compromising fairness.
This study explores the paper ”The Larger The Fairer? Small Neural Networks Can Achieve”, presented at the Design Automation Conference – 2022. Which introduces an automatic neural architecture search (NAS) methodology called as Fairness and Hardwareaware Neural architecture search (FaHaNa) for network selection. FaHaNa employs a freezing
method to accelerate optimization while preserving fairness, effectively minimizing network size and latency for edge devices. The thesis discusses about the successful application of the FaHaNa framework on Android devices illustrates its potential to democratize healthcare diagnostics across diverse demographic and geographic landscapes, making advanced healthcare solutions more accessible and reducing disparities in medical care availability. This work not only showcases the feasibility of achieving fairness in mobile healthcare applications but also sets a solid foundation for future innovations in the domain of equitable, AI-enabled healthcare solutions.
Student–Teacher Relationships from Kindergarten to 3rd Grade for Latine Students in Dual Language Programs
(2024-04-25) Rojas, Diego Josue Ordonez; Winsler, Adam
Student–teacher relationships in early education have been investigated widely. The current thesis expands on this literature by exploring these relationships in the unique context of Dual Language Education (DLE) K-3 programs and by examining Latine students. I explore student–teacher relationships as a function of student–teacher ethnicity-matching in Spanish-English, two-way immersion programs across grades K-3, where some students have one teacher and others have two. Participants included 33 teachers and 203 students in kindergarten through 3rd grade in Spanish-English two-way DLE immersion classrooms in North Carolina. Relationships were measured via teacher report with the Student–Teacher Relationship Scale (STRS, Pianta, 2001a). The main research questions were: 1) What is the quality of student–teacher relationships for all students, and does this vary by grade (in grades K-3)?, 2) Do student–teacher relationships vary as a function of student ethnicity and teacher ethnicity, and if so, does this vary across different grades?, 3) Do student–teacher relationships vary as a function of ethnic match between student and teacher?, and 4) Specifically for Hispanic students, how much does having a Hispanic teacher influence their student–teacher relationship quality? My hypotheses were that students and teachers that share the same ethnicity, and those in earlier grades, will have higher closeness scores (and lower conflict) than those who do not share the same ethnicity or are in later grades. Additionally, I expected Hispanic students to have closer relationships with their teachers than White students.
Results indicate that student–teacher closeness for all students was highest in kindergarten and lower for subsequent grades, with Black students showing particularly high closeness in kindergarten but steeper declines by third grade compared to other students. Boys had more conflictual relationships with their teachers than girls, and Hispanic/Latine English teachers had more closeness with their students than teachers of other ethnicities. Students with two teachers had lower closeness with their teachers than students with only one teacher. Importantly, ethnic match between student and teacher was not associated with teacher closeness or conflict in the current study’s TWI settings. Implications of these findings include ethnic match not being as important as the number of teachers for student–teacher relationship quality, and that, overall, TWI programs are efficient at producing an inclusive environment for families of diverse ethnicities.
The Barriers to Black Unity: An Examination of the Relationship Between The National Pan-Hellenic Council and the Black Community
(2024-04-26) Reed, Olivia; Craig, Richard T.
The National Pan-Hellenic Council (NPHC) was created to uplift the Black community and create a space in which Black people could thrive and succeed, at the same time the NPHC has been the dividing factor in the Black community. This study aims to explore the possible tensions between the NPHC and the broader Black community. This study begins by delving into the rich history behind the NPHC, Black Unity, and Black identity. The findings from the research present three themes: Clashing Identities, Neither by Any Other Oath, and Rejection. Concluding the research, I delve into a discussion around these themes and what these tensions mean for the Black community. Future research can expand upon the LGBTQ+ community and sorority life, as well as bring in more perspectives from current NPHC members themselves.