AI for Alzheimer's Disease Research Since 2023
Bridging Multimodal Data with Classical and Next-Gen Intelligence
Explore Who We Are
ADAM-1: An AI Reasoning and Bioinformatics Model for Alzheimer’s Disease Detection and Microbiome...
Alzheimer’s Disease Analysis Model Generation 1 (ADAM-1) is a multi-agent reasoning large language model (LLM) framework designed to integrate and analyze multimodal data, including microbiome profiles, clinical datasets, and external knowledge bases, to improve the understanding and classification of Alzheimer’s disease (AD). By utilizing the agentic system with LLM, ADAM-1 generates insights from various data sources and contextualizes the findings with literature-based evidence. A comparative evaluation with XGBoost showed a significantly higher mean F1 score and notably lower variance for ADAM-1, demonstrating its robustness and consistency, especially when using human biological data. Although currently focused on binary classification tasks with two data modalities, future versions will aim to include additional data types, such as neuroimaging and peripheral biomarkers, and extend to predict disease progression. This will broaden ADAM-1’s scalability and practical use in AD research and diagnostics.
Utilizing Latent Dirichlet Allocation and Differential Abundance to Identify Microbial Communities..
Emerging evidence indicates that the oral and gut microbiomes, along with their metabolic byproducts, contribute to the pathophysiology of Alzheimer’s disease (AD). This study analyzed metagenomic sequencing data from paired oral and fecal microbiomes, integrated with clinical variables, to identify bacterial communities associated with AD and elucidate interactions within the oral–gut microbial axis, distinguishing AD from healthy controls (HC). The study included 43 participants with AD and 223 HCs. Paired oral and fecal samples, along with demographic and clinical data, were collected at each visit and subjected to metagenomic profiling. Latent Dirichlet Allocation (LDA) was applied to uncover latent microbial community structures associated with AD status across both body sites, followed by differential abundance (DA) analysis to identify taxa with significant abundance differences between groups. In the oral microbiome, 27 LDA topics were identified, with key AD-associated taxa including Alistipes (β = 0.3919), Paraprevotella xylaniphila (β = 0.1228), Desulfovibrio (β = 0.0601), and Lachnospiraceae (β = 0.0230). In the gut microbiome, 50 topics were identified, reflecting greater compositional complexity, with notable taxa such as Actinomyces oricola (β = 0.6959), Roseburia (β = 0.0886), Bacteroidetes (β = 0.5011), and Actinomyces gerencseriae (β = 0.0305). Distinct microbial community patterns were observed between AD and HC groups, with evidence of oral species, including A. gerencseriae, detected in the gut of AD patients, suggesting microbial translocation along the oral–gut axis. These findings support the concept that altered oral–gut microbial dynamics may contribute to AD pathogenesis through systemic pathways linking microbial dysbiosis, inflammation, and neurodegeneration.
Collaborative Research
We believe that scientific progress is best achieved through collaboration. That's why we work closely with other laboratories, universities, and research institutions to share knowledge and expertise. Our collaborative approach ensures that our research is always at the cutting edge of science.
Innovative Research
Our laboratory is dedicated to pushing the boundaries of scientific knowledge. We are always exploring new areas of research and developing innovative solutions to scientific challenges. Our goal is to make a meaningful contribution to our understanding of the world around us.
State-of-the-Art Facilities
Our laboratory is equipped with the latest technology and equipment, enabling us to conduct cutting-edge research and experiments. Our facilities include advanced microscopes, centrifuges, and spectrometers, among other tools.
Commitment to Excellence
At Foundation Lab Scientific Laboratory, we are committed to excellence in everything we do. We strive to maintain the highest standards of scientific rigor and integrity, ensuring that our research is reliable, accurate, and impactful.
Contact Us
Better yet, see us in person!
We are a group of AI enthusiasts at UMass Chan Medical School passionate about advancing Alzheimer’s disease research. Our work combines artificial intelligence, bioinformatics, and biomedical knowledge to drive innovation in diagnosis and discovery. We study both the latest technologies and traditional tools to bridge the gap between cutting-edge methods and foundational Alzheimer’s research.
