Identifying TRIM11 Upregulators as Therapeutic Targets in Alzheimer’s Disease: A Bayesian Network Approach

Presentation Time: 03:30 PM - 03:42 PM

Abstract Keywords: Causal Inference, Bioinformatics, Computational Biology
Primary Track: Foundations

A recent study shows that TRIM11 is downregulated in Alzheimer’s Disease (AD) but has been shown to improve
cognitive function when overexpressed in mouse AD models. Based on this discovery, our study aims to identify
potential genetic regulators of TRIM11 using single-cell and single-nucleus RNA sequencing, and graph learning
method. In this study we explore two publicly available datasets: GSE173731 and GSE227222. To identify the
potential regulators of TRIM11, we use probabilistic approach and Bayesian networks. Our approach identified a
set of candidate genes in both datasets that may exert regulatory influence on TRIM11, offering potential targets for
further research in future therapeutic strategies in AD.

Speaker:
Sumita Garai, Postdoctoral Researcher/Ph.D
University of Pennsylvania

Authors:
Alvin Pham, Neuroscience - The University of Texas at Austin; Sumita Garai, Postdoctoral Researcher/Ph.D - University of Pennsylvania; Tianhua Zhai, Ph.D. - University of Pennsylvania; Mengyuan Kan, PhD - University of Pennsylvania; Li Shen, Ph.D. - University of Pennsylvania;

---

Variogram Modeling of Spatially Variant Early Response to Therapy in Advanced Non-Small Cell Lung Cancer

Presentation Time: 03:42 PM - 03:54 PM

Abstract Keywords: Clinical Decision Support, Precision Medicine, Imaging Informatics, Machine Learning
Primary Track: Applications
Programmatic Theme: Clinical Research Informatics

Predicting heterogeneity in treatment response for non-small cell lung cancer (NSCLC) at multiple scales, both between patients and spatially within each patient, can support clinical decisions that personalize oncologic management. In this study, we evaluated different variogram models of voxel-level spatial correlation in tumor response in locally advanced NSCLC and metastatic NSCLC from two different clinical trials. The Stable model achieved the lowest root mean squared error (RMSE) on average (mean: 5.2-5.5%), followed by the Matérn model (mean: 5.8-7.4%), both of which performed better than most other models. In contrast, the Exponential model had the highest RMSE (mean: 9.4-15.6%). These results remained consistent across two different cohorts of NSCLC. Given the robust performance of the Stable model, it may generalize for modeling spatial response in other clinical settings beyond NSCLC and should be further studied.

Speaker:
Faisal Yaseen, PhD student in Biomedical and Health Informatics
UW, Seattle

Authors:
Faisal Yaseen, PhD student in Biomedical and Health Informatics - UW, Seattle; Daniel Hippe, MS - Fred Hutchinson Cancer Center, Seattle, WA, USA; Parth Soni, MS - University of Texas, Arlington, TX, USA; Shouyi Wang, PhD - University of Texas, Arlington, TX, USA; Chunyan Duan, PhD - Tongji University, Shanghai, China; John Gennari, PhD - University of Washington, Dept of Biomedical Informatics & Medical Education; Stephen Bowen, PhD - Fred Hutchinson Cancer Center, Seattle, WA, USA;

---

The Digital Alzheimer’s Cell Atlas: A comprehensive brain single-cell transcriptomic resource using a generative AI foundation model

Presentation Time: 03:54 PM - 04:06 PM

Abstract Keywords: Omics (genomics, metabolomics, proteomics, transcriptomics, etc.) and Integrative Analyses, Artificial Intelligence, Bioinformatics
Primary Track: Applications
Programmatic Theme: Translational Bioinformatics

In this study, we constructed a human brain single-nucleus RNA-seq (snRNA-seq) atlas for Alzheimer’s disease (AD) and AD-related dementias (ADRD), integrating deep neuropathological and clinical diagnoses for metadata harmonization, and applying generative AI for transcriptomic integration. The atlas comprises ~14 million nuclei from 2,000+ samples and identifies more than 50 finely resolved cell types. Exploratory bioinformatics analyses demonstrate its value as a foundational digital or virtual resource for studying brain cell biology in neurodegeneration.

Speaker:
Jielin Xu, Ph.D.
Cleveland Clinic

Authors:
Jielin Xu, Ph.D. - Cleveland Clinic; Yadi Zhou, Ph.D. - Cleveland Clinic; Noah Lorincz-Comi, Ph.D. - Cleveland Clinic; Lijun Dou, Ph.D. - Cleveland Clinic; Yuan Hou, Ph.D. - Cleveland Clinic; Yunguang Qiu, Ph.D. - Cleveland Clinic; Feixiong Cheng, PhD - Cleveland Clinic;

---

Deep Contrastive Learning Framework Identifies Cell Type-Specific Alzheimer’s Disease Risk Genes

Presentation Time: 04:06 PM - 04:18 PM

Abstract Keywords: Artificial Intelligence, Deep Learning, Bioinformatics, Machine Learning
Primary Track: Applications

Identifying Alzheimer’s disease (AD) risk genes is instrumental in finding treatments and preventions for AD. Human protein interactome networks shed light on how proteins interact and function. Here, we present a deep contrastive learning framework for identifying AD risk genes (CLARITY). By leveraging single-cell transcriptomics and human brain-specific functional genomic features (i.e., x-QTL), and disease genetic information under the human protein-protein interactome network, CLARITY shows superior performance and discovers novel cell type-specific AD risk genes.

Speaker:
Yuxin Yang, PhD
Cleveland Clinic Genome Center, Lerner Research Institute, Cleveland Clinic

Authors:
Yuxin Yang, PhD - Cleveland Clinic Genome Center, Lerner Research Institute, Cleveland Clinic; Jielin Xu, PhD - Cleveland Clinic; Yadi Zhou, PhD - Cleveland Clinic; Feixiong Cheng, PhD - Cleveland Clinic;

---

Multi-Modal Integrative Risk Model for Late-Onset Alzheimer’s Disease in a Large-Scale Biobank

Presentation Time: 04:18 PM - 04:30 PM

Abstract Keywords: Omics (genomics, metabolomics, proteomics, transcriptomics, etc.) and Integrative Analyses, Computational Biology, Bioinformatics, Machine Learning
Primary Track: Foundations
Programmatic Theme: Translational Bioinformatics

Alzheimer’s Disease (AD) is a genetically heterogenous neurodegenerative disease, which complicates individual-level genetic risk prediction. We constructed a multi-modal integrative risk model for AD risk prediction, leveraging machine learning, clinical data, and imputed transcriptomic and proteomic expression information from the Alzheimer’s Disease Sequencing Project. We identified novel gene-disease and protein-disease associations and achieved superior performance to standard genetic models. This study highlights the importance of integrating multi-modal data to predict individual risk for complex diseases.

Speaker:
Rasika Venkatesh, B.S.
University of Pennsylvania Perelman School of Medicine

Authors:
Anni Moore, Graduate Student - University of Pennsylvania; Marylyn Ritchie, PhD - University of Pennsylvania, Perelman School of Medicine;

---

Single-Cell Transcriptomics of Bronchoalveolar Lavage in Early SARS-CoV-2

Presentation Time: 04:30 PM - 04:42 PM

Abstract Keywords: Bioinformatics, Infectious Diseases and Epidemiology, Precision Medicine
Primary Track: Applications
Programmatic Theme: Translational Bioinformatics

The COVID-19 pandemic, caused by SARS-CoV-2, has profoundly impacted global health and economies since late 2019. Investigating early immune responses is essential to understand disease progression and protection. Using single-cell RNA-sequencing of bronchoalveolar lavage (BAL) cells from SARS-CoV-2-infected rhesus macaques (0-3 days post-infection), we identified crucial immune cells, including macrophages and dendritic cells, activated early and producing key signals to combat the virus. These findings offer valuable insights into early immune responses in a critical COVID-19 model.

Speaker:
Sadia Akter, PhD, FAMIA
Marshall University Joan C. Edward School of Medicine

Authors:
Sadia Akter, PhD, FAMIA - Marshall University; Mushtaq Ahmed, PhD - The University of Chicago; Dhiraj Singh, PhD - Texas Biomedical Research Institute; Kuldeep Chauhan, PhD - The University of Chicago; Deepak Kaushal, PhD - Texas Biomedical Research Institute; Shabaana Khader, PhD - The University of Chicago;

---