Atharva Naik's research focuses on Alzheimer’s disease (AD), a brain disorder that gradually impairs cognitive functions and memory. The project aims to differentiate AD and healthy brain cells using the single-cell Generative Pretrained Transformer model (scGPT) for cell-type annotation. The scGPT model, with its self-attention mechanism, can understand cell-cell relationships and produce accurate clusters. The research uses a dataset of single-cell RNA sequences from both AD and healthy cells. The pre-trained brain-specific scGPT model generates cell-type annotations to correctly label clusters, helping identify cells associated with Alzheimer’s. This work is crucial as it deepens our understanding of genetic distinctions within AD, potentially paving the way for effective therapeutic strategies.

Apoorva Krovvidi's project focuses on understanding the structures of nucleotide bases in RNA sequences and their modifications. The research uses the 'simplified molecular input line entry system' (SMILES) to translate a chemical's 3D structure into a computer-readable string. With 4 nucleotide bases and 30 modifications, the project uses computational functions to compute the similarity between these structures. Using R programming, a code is created for each SMILES string, resulting in a heat map that shows the similarity scores between structures. The ultimate goal is to identify similar modifications and assign them a unique identifier for future reference.

Chelsea's study compared two validated computable phenotypes to assess variations in performance and potential biases. The analysis used accuracy measurements to identify variations across social factors. Data was extracted from the Indiana Network for Patient Care (INPC), one of the largest health information exchanges in the country. An initial cohort of patients with preliminary evidence of diabetes was identified, and clinical observations and demographics were extracted. The diabetes computable phenotypes were implemented on this cohort, generating two separate cohorts for comparison. A random sample from these cohorts was manually reviewed to confirm diabetes status.

Harsh's research focuses on optimizing the Human Activity Recognition Transformer (HART) model to improve the accuracy of wearable health technology in tracking daily activities. The HART model, fine-tuned with specific datasets, is integrated into the WearOS application. The goal is to create a user-friendly tool that can accurately detect and display ten daily activities. Initial testing was conducted with five healthy individuals, with plans for future expansion to include participants with conditions like Parkinson's disease. The project aims to enhance wearable health technology's role in healthcare by providing a reliable activity monitoring solution.

Jane's project focuses on addressing neonatal hypothermia, a significant health concern for premature and low birth weight infants, especially in low/middle-income countries. A preventive method, Kangaroo Mother Care (KMC), was utilized. The NeoRoo app was developed to monitor infants' vital signs and KMC activities, providing parents and healthcare professionals with real-time updates. The app sends alerts about the baby's breathing and temperature, allows parents to notify medical professionals of concerns, and offers self-care tips and reminders for parents. The NeoRoo app aims to reduce parental anxiety about their baby's well-being.

Manjinder's research focuses on the critical role of RNA modifications in gene expression and cellular function. The study extensively explores N6-methyladenosine (m6A), pseudouridine (Ψ), 5-methylcytosine (m5C), and N1-methyladenosine (m1A), each contributing uniquely to the RNA regulatory network. The review highlights the biological roles of these modifications and the emerging drugs designed to target them. It discusses how these drugs interact with RNA and its associated proteins to modulate gene expression and cellular processes. The therapeutic potential of these drugs in treating various diseases, including cancer and metabolic disorders, is also examined. The research underscores the transformative potential of targeting RNA modifications in drug development, offering novel insights for precision medicine.

Nelson's research focuses on Matrix Metalloproteinases (MMPs), calcium-dependent endopeptidases crucial in cardiovascular disease processes. Despite MMPs being identified as biomarkers for cardiovascular aging diseases, their production regulation is not well understood. Using Mendelian randomization, data from the Genotype-Tissue Expression project and Genome-Wide Association Studies were analyzed to identify genetic variations affecting MMP levels. The study hypothesizes a direct link between specific MMPs and cardiovascular diseases like atrial fibrillation and heart failure. The expected results aim to identify which MMPs are associated with specific cardiovascular diseases, paving the way for further research into their pathophysiology, potential use as disease biomarkers, or new treatment targets.

Nimra's research focuses on the disparities in COVID-19 outcomes between urban and rural populations. The study aims to quantify differences in ICU utilization and mortality rates and determine if rurality is associated with COVID-19 related ICU admissions and mortality. Data was extracted from the Indiana Network for Patient Care (INPC), one of the largest health information exchanges in the country. A cohort of patients hospitalized for COVID-19 between March 1, 2020, and June 30, 2023 was identified. The study used descriptive statistics and logistic regression analyses to examine the relationships between rurality and COVID-19 outcomes. The analysis was stratified by variant era, race, gender, age, and vaccination status to identify disparities.

Priyanka's research utilizes RNA-sequencing, a genomic approach for detecting and analyzing RNA molecules, to study cellular responses. The focus is on single-cell RNA-sequencing, a technique that allows for the examination of individual cells. This powerful tool is used to identify and examine cells from a brain diagnosed with Alzheimer's Disease, revealing prevalent genes and features in each cell. The study provides a clear comparison of cells from brains affected and unaffected by Alzheimer's Disease.

Sahiti's research focuses on the role of N6-Methyladenosine (m6A) modifications in the mRNA transcriptome of the malaria-causing parasite, Plasmodium falciparum. The study aims to understand the influence of m6A modifications, particularly their impact on poly(A) tail length, in the unique genetic context of P. falciparum. Using single nucleotide direct RNA sequencing, the research analyzes samples of P. falciparum subjected to heat shock and compares them with control samples. The findings will provide insights into the potential of m6A as a target for therapeutic intervention in malaria.

Shaouyang’s project titled “Using sc-Big Small Patch to Analyze Spatiotemporal Gene Expression of Mouse Embryos” is a cutting-edge research endeavor. It involves the application of the sc-Big Small Patch method, a sophisticated technique, to study the spatiotemporal gene expression in mouse embryos. The project aims to uncover the complex dynamics of gene expression during embryonic development. By analyzing these patterns, Shaouyang hopes to gain deeper insights into developmental biology and potentially uncover key factors in embryonic growth and differentiation

Srihas's research focuses on diagnosing Alzheimer's Disease, a progressive neurodegenerative disease, by using a multinomics approach. This interdisciplinary method analyzes genomics, proteomics, epigenomics, and transcriptomics data. The study uses a Neural Network machine learning model trained on data from sources like Genehancer and ROSmap to identify correlations between Single Nucleotide Polymorphisms (SNPs) from Proteins, Genes, and Enhancers and the presence of Alzheimer's Disease. The project aims to demonstrate the effectiveness of machine learning and multinomics in diagnosing Alzheimer's.

Tanuj is leading a project to enhance Parkinson’s disease detection using accelerometer data and advanced machine learning. The research involves developing and testing various machine learning models, identifying efficient algorithms for symptom detection, and emphasizing the role of project management and communication. The project aims to improve diagnostic tools and treatment strategies for Parkinson’s disease, ultimately benefiting patient care.