EMERGING RESEARCH SCHOLARS AI PhD MENTORS
Dr. Babajani’s lab is dedicated to advancing the integration of neuroimaging and electrophysiological modalities, such as magnetoencephalography (MEG), intracranial electroencephalography (EEG), and functional MRI (fMRI), with cutting-edge AI techniques, including deep learning algorithms. We focus on developing AI-driven methodologies to better understand and diagnose neurological disorders, particularly epilepsy and neurodegenerative diseases such as Alzheimer’s Disease (AD), Lewy Body Dementia (LBD), and Parkinson’s Disease (PD). By leveraging multi-modal neuroimaging and electrophysiological data, we aim to uncover novel biomarkers and neural patterns that can enhance diagnostic accuracy, guide therapeutic interventions, and deepen our understanding of disease mechanisms. Additionally, we are exploring innovative AI approaches to decode speech from brain signals, with the goal of creating advanced brain-computer interface (BCI) systems. These systems hold significant potential for enhancing communication capabilities in individuals with speech impairments, particularly in patients with conditions such as amyotrophic lateral sclerosis (ALS) or those recovering from stroke, offering new pathways for interaction and improving quality of life. We welcome ERS-AI PhD students with a background in AI and a passion for interdisciplinary research to join our team in pushing the boundaries of neuroscience and AI integration.
In the Bedenbaugh Lab, we have two overarching research questions: how does an individual choose between satiating hunger versus fulfilling other need states, and how do perturbations during critical periods of development influence neural circuit formation, physiology and behavior across the lifespan. To answer these questions, we use a whole brain approach to reveal brain regions at the intersection of feeding and other motivated behaviors and identify how developmental perturbations disrupt neural networks. One of the main components of this approach is an advanced neuroanatomical pipeline that combines tissue clearing and light sheet microscopy with computational neural mapping. This pipeline employs deep learning algorithms to detect labeled neurons and register their precise locations within the Allen Brain Atlas Common Coordinate Framework, enabling systematic analysis of circuit-wide patterns. Through the use of this unbiased, whole brain approach, we hope to identify new brain regions and neural networks that may aid us in the treatment of several metabolic and neuropsychiatric diseases.
Yijiang Chen, Ph.D.
Dr. Yijiang Chen’s research focuses on using multimodal artificial intelligence to solve complex problems in precision medicine. His lab emphasizes integrating digital pathology, clinical records, and spatial biology multi-omics data modalities to uncover actionable biomarkers for disease diagnosis, prognosis, and treatment response assessment. By developing advanced deep learning and machine learning frameworks, his team bridges high-resolution whole slide image analysis with spatial transcriptomics, enabling a comprehensive, molecularly-informed view of the tissue microenvironment. To ensure these tools can be trusted by healthcare providers, his work actively explores explainable AI and LLM-based reasoning, creating transparent models that can clearly explain their biological logic. This multimodal reasoning capability is foundational to his lab’s development of patient digital twins—dynamic virtual models capable of simulating a patient’s health trajectory to test personalized clinical interventions. Spanning computational pathology and biomedical data science, the overarching goal of this research is translating AI-driven discoveries into clinically meaningful precision medicine tools that improve patient outcomes. Dr. Chen welcomes ERS-AI PhD students with backgrounds in AI, machine learning, bioinformatics, or biomedical engineering who are passionate about advancing the frontiers of data-driven medicine.
Recent Advances in artificial intelligence (AI), including natural language processing (NLP) and large language models (LLMs), offer powerful tools to enhance autism spectrum disorder (ASD) phenotyping, early risk prediction, and the development of clinical decision support (CDS) tools. These models can extract nuanced features from unstructured notes, such as developmental delays and behavioral observations, that are rarely captured in structured electronic health record (EHR) fields. However, few studies have applied LLMs to ASD research or tested their utility in real-world pediatric settings. Existing ASD prediction models typically rely on structured codes and static features, which limits their accuracy and generalizability. Furthermore, clinical implementation of AI models remains limited due to concerns about workflow compatibility, clinician trust, and performance biases. To address these gaps, we propose to integrate advanced AI methods with multi-sourced EHR data to develop scalable tools for early ASD detection, evaluated through a silent trial in routine care.
In this project, we propose to develop, validate, and test analytic tools that integrate advanced AI methods with large-scale, multi-sourced EHR data for early ASD detection. We will leverage longitudinal EHR data from UF Health and the OneFlorida+ Clinical Research Network.
Landmark scientific discoveries support the neural population doctrine, where the neuronal population, not the single neuron, are the essential unit of computation in many brain regions. New computing technologies have enabled neuroscience research at the level of the neural population. The long-term goal of our research is to apply artificial intelligence to the analysis of dopamine neural populations to decode neural dynamics. We recently employed live-cell calcium imaging in the midbrain slices of DAT-cre/loxP-GCaMP6f (DAT-GCaMP6f) mice of either sex and computational analyses to show that functional network connectivity greatly differs between substantia nigra pars compacta (SNc) and ventral tegmental area (VTA) regions. Using complex network analysis, we found a higher incidence of hyperconnected (i.e. hub-like) neurons in the VTA than the SNc. The lower number of hyperconnected neurons in the SNc is consistent with the interpretation of a lower dopamine neuronal network resilience to the SNc’s neuronal loss-implicated in neurological disorders. Our ongoing studies expand this work to in vivo studies in freely moving DAT-GCaMP6f mice of either sex via live cell calcim imaging through microendoscopic lenses. This approach enables imaging of previously inaccessible dopamine neuronal populations deep within the midbrain of freely moving animals exposed to saline or methamphetamine.
My long-term research goal is to develop innovative Artificial Intelligence/Machine Learning (AI/ML) methods to support Predictive, Preventive, Personalized, and Participatory (P4) medicine. The ERS-AI PhD student will be working on collaborative research projects that address challenges in EHR-data analysis such as federated learning, transfer learning, and personalized learning for more accurate and robust disease prediction and risk factor identification. Developing AI/ML algorithms that will improve model reproducibility, interpretability, transportability, and fairness will be a central focus of the research projects. The first project to which the student will be recruited will involve model development for acute kidney injury (AKI) prediction, prognosis, and sub-phenotyping using multi-institutional electronic health records (EHRs).
In the Martínez-Rivera Lab, we are committed to incorporating bioinformatic, computational, and artificial intelligence (AI) approaches to advance the understanding of fundamental mechanisms of maladaptive behaviors, including those involving substance abuse, depression, aggression, decision making, and stress. Our projects are focused on generating behavioral, cellular, and transcriptional/genetic datasets using innovative techniques integrating machine learning and statistical tools, such as behavioral tracking systems, cellular recordings, and RNA-sequencing pipelines. These efforts are combined with the HiPerGator’s infrastructure, essential for the data collection, storage, and subsequent analyses.
Adeno-associated virus (AAV) vectors are widely used in gene therapy due to their safety-profile and ability to deliver genetic material to a wide range of tissues. However, challenges such as immune response, limited tissue specificity, and cargo capacity constrain their broader application. Leveraging artificial intelligence (AI), particularly machine learning and deep learning, offers a transformative approach to optimizing AAV design by harnessing structural insights from their three-dimensional (3D) capsid architecture.
AI models provide the opportunity to interrogate high-resolution 3D structures of AAV capsids to identify patterns that govern tissue tropism, immune evasion, and transduction efficiency. A structural dataset of capsid structures, obtained through cryo-electron microscopy and X-ray crystallography, affords the opportunity to train algorithms to predict the functional impact of amino acid substitutions or insertions on capsid performance. For instance, generative models can potentially propose novel capsid variants with desired properties, such as reduced immunogenicity or enhanced specificity for target tissues to the brain.
Furthermore, AI should be able to assist in mapping antigenic regions on the capsid surface that are recognized by neutralizing antibodies. By identifying and redesigning these regions, AI-guided engineering could produce capsids that better evade pre-existing immunity in patients. Additionally, AI models could simulate protein folding and stability, helping predict whether engineered variants will maintain structural integrity and function under physiological conditions.
In summary, AI-driven design pipelines have the potential to significantly accelerate the discovery cycle, reducing reliance on labor-intensive trial-and-error experimentation. Tools like AlphaFold and Rosetta, integrated with reinforcement learning or evolutionary algorithms, allow for rapid in silico screening of capsid libraries to select promising candidates for experimental validation.
Dr. Merritt’s project uses AI approaches, primarily neural networks, for automated quantitation and denoising of nuclear magnetic resonance (NMR) data. AI has well known abilities for performing image recognition, and by its very nature, a neural network can evaluate a target image almost instantaneously once it is trained. The speed and robustness of neural network approaches suggest that its application to the spectra denoising/fitting and quantitation problem in NMR could be very profitable. Initial results using a deep learning neural network produced an increase in signal-to-noise ratio (SNR) of 200to 1for13C NMR spectra(1).Using traditional Fourier transformation methods, the SNR is proportional to (square root of # of scans) the which means that it takes 4 times the number of scans to give twice the SNR. A gain in SNR of 200 is equivalent to running the same sample 40000 times longer. Given that most13C spectra acquired in my lab take at least 6 hours to acquire, the time savings possible with this approach are truly transformational.
The Oliveira Lab is dedicated to uncovering how disruptions in the brain–lung axis contributes to the pathophysiology of pulmonary hypertension (PH). Our research focuses on the role of neuro-immune interactions in driving maladaptive neural plasticity and sustaining sympathetic overactivation, a key feature of PH progression.
To investigate these mechanisms, we integrate advanced neuroscience tools with established cardiopulmonary techniques. Our approach includes live-cell imaging in brain slices, right heart catheterization, immunohistochemistry, and molecular analyses, paired with translational validation in human tissues and cells. By bridging brain function with cardiopulmonary outcomes, our lab aims to identify novel targets for therapeutic intervention in pulmonary hypertension.
The Padilla-Coreano Lab studies how the brain facilitates social behaviors using tools at the intersection of neuroscience and Artificial Intelligence. Specifically, the lab studies the neural mechanisms of social competence, that is how we adjust our social behavior based on information, using mouse models. Two key elements of this research goal are: being able to measure social behaviors and understanding the relationship between behavior and brain activity. The lab uses Artificial Intelligence to tackle both key elements. The PI is a co-developer of a recent Deep Learning tool (AlphaTracker) that does pose estimation for multiple animal tracking (Padilla-Coreano et al., 2020 preprint). Furthermore, this lab has active collaborations with machine learning scientists at UF to create new tools to analyze behavior incorporating temporal information and structure for unbiased automatic behavior classification. Furthermore, the lab is focused on studying neural function at the network level. By recording neural activity of multiple brain regions simultaneously we can identify what circuits and sequences of circuits lead to important social behaviors. Given the complexity of the data (both neural and behavioral),Artificial Intelligence helps identify the causal relationship between neural activity and behavior. The PI has applied similar approaches to predict behaviors and conditions from neural activity and the lab will expand this approach to consider neural activity from a whole network.
The Giusti-Rodriguez Lab works at the intersection of neuroscience, human genetics, and functional genomics, and aims to maximize the tools and techniques of these fields to advance our understanding of the genetics of neuropsychiatric disorders. AI in genomics is growing rapidly, and deep learning methods have been applied to the analysis of diverse datatypes, including DNA and RNA-sequencing, methylation, DNA accessibility and chromatin, and 3Dgenome organization. The Giusti-Rodríguez lab will generate diverse data types using mouse, postmortem human brain tissue, iPSCs, etc., and has access to many external datasets through existing collaborations and or publicly available datasets. The Giusti-Rodríguez lab will apply machine learning and artificial intelligence approaches to multiomics datatypes relevant to understanding specific susceptibilities to psychiatric disorders and to parse out genetic underpinnings in individuals from diverse populations and complex admixture.
Dr. Sarder’s lab develops novel computational methods to study and understand tissue micro-anatomy using multi-modal whole-slide microscopy images as well as associated molecular omics data. Our method facilitates decision making in a clinical work-flow (both for diagnosis and predicting progression of diseases), and also allows studying fundamental systems biology of disease dynamics. Currently, our major focus involves studying chronic kidney diseases as well as ‘reference’ organ systems across scale.
The ERS-AI PhD student will be recruited into projects exploring the application of multi-modal foundation models for a variety of clinical applications and patient health modeling. Briefly, foundation models comprise a recent class of large-scale machine learning frameworks based on the Transformer model architecture that are designed to formulate scalable data-driven representations from voluminous data, merging AI principles of supervised, unsupervised, and self-supervised learning techniques; such data representations can be applied to several downstream AI tasks. Currently popularized by innovations in natural language processing (NLP),the ERS-AI PhD student will research the translation of these discoveries into the healthcare domain by developing foundation models of patient health that integrate granular and temporal health data from multiple modalities (e.g. continuous and discrete electronic health record measurements, clinical notes, radiography, omics data) for unified health representations that can be applied to downstream clinical prediction tasks (e.g. sepsis, acute kidney injury, mortality). Methods to measure and improve explainability, fairness, and causality of foundation models will be a large focus of the research projects. The first project to which the student will be recruited will involve the development of a Transformer foundation model for dynamic monitoring of acute kidney injury (AKI).
Department of applied physiology and kinesiology, College of health human & performance
David Vaillancourt, Ph.D.
Dr. David Vaillancourt holds the Orchid Chair as a Distinguished Professor of Applied Physiology & Kinesiology at the University of Florida, with joint appointments in Biomedical Engineering and the Fixel Institute for Neurological Disorders. He is an internationally recognized leader in neuroimaging applications for dementia and parkinsonism. His research program uniquely integrates cross-sectional and longitudinal human studies with mechanistic investigations in mouse models, leveraging multimodal imaging platforms ranging from 3T to 17T to enable rigorous translational discovery and accelerate the development of imaging-based diagnostics and outcome measures. His laboratory has been at the forefront of developing and applying advanced structural and functional imaging methods, machine learning approaches, and translational biomarkers to enhance differential diagnosis and monitoring of Parkinson’s disease, atypical Parkinsonian disorders, Alzheimer’s disease, dystonia, and essential tremor. In addition to pioneering work in free-water imaging he has expertise in PET, fMRI, neuromelanin imaging, iron imaging, T1 imaging, and neurophysiological modalities including tremor analysis, electromyography, and electroencephalography. Dr. Vaillancourt has record of sustained scientific productivity, leadership, and NIH support, receiving funding from R01/U01/P50/P30/R41/R42/T32 awards, with continuous NIH funding since 1999. He has authored more than 200 peer-reviewed publications in leading journals such as Brain, Lancet Neurology, Lancet Digital Health, Science Translational Medicine, JAMA Neurology, Journal of Neuroscience, Neurobiology of Aging, Movement Disorders, Neurology, and NeuroImage.
The Wong lab’s research focuses on leveraging advanced artificial intelligence to unravel the complex mechanisms of action underlying deep brain stimulation for movement disorders, while simultaneously decoding the physiology that underpins the functionality of the basal ganglia. To achieve this, the team integrates high-resolution electrophysiology data with comprehensive neuroimaging connectomic datasets, fusing these disparate modalities through an innovative method known as spectral connectomic mapping. By developing cutting-edge machine learning and deep learning frameworks, the lab aims to bridge macro-scale network dynamics with micro-scale neural oscillations, providing a molecularly and structurally informed view of network dysfunction. This AI-powered multimodal reasoning capability is foundational to gaining unprecedented insights into neurodegenerative diseases, enabling the identification of novel biomarkers for disease progression and targeted therapeutic responses. Ultimately, spanning computational neuroscience and biomedical data science, the overarching goal of this research is to translate these data-driven discoveries into clinically meaningful precision neurology tools that optimize stimulation parameters and improve patient outcomes.
In the last two decades, the introduction of targeted anticancer therapies has revolutionized the treatment of hematological malignancies such as multiple myeloma, chronic myeloid leukemia, and solid malignancies such as breast and renal carcinoma. Contemporary cancer therapy has led to a 23% reduction in cancer-related mortality rate and a rapid increase in cancer survivorship in the last 15 years. However, some devastating side effects of these treatments have also resulted in increased morbidity and mortality. For example, cardiotoxicity is one of the well-documented adverse events of cancer treatments resulting either from accelerated development of cardiovascular diseases in cancer patients or from the direct effects of the treatment on the structure and function of the heart. The goal of this project is to develop predictive models for the identification of cancer patients with a high risk of cardiotoxicity to prevent or minimize the risk of cardiotoxicity in cancer treatments.
Gene expression, the flow of genetic information from DNA to messenger RNA (mRNA) to protein, involves delicate regulation by a group of small RNAs named microRNAs (miRNA). The development of high throughput technology of next-generation sequencing and the advancement in artificial intelligence provides new opportunities for miRNA target identification. We aim to develop an innovative machine learning framework to efficiently predict high-confidence miRNA-mRNA interaction pairs in cancer patients with contrastive convolutional neural networks based on the combination of heterogenous RNA-seq data (miRNA, mRNA and miRNA-mRNA hybrids). We will also anticipate profiling and validating the effect of discovered miRNA-mRNA pairs in patient samples to facilitate the hypothesis generation process for potential cancer therapeutics. Collectively, our efforts will result in rapid and accurate identification of high-quality miRNA-mRNA pairs with our proposed model, which would accelerate the process of elucidating the underlying mechanism of cancer progression and provide the basis for improving current therapeutic interventions. Additionally, apart from identifying the miRNA-mRNA pairs, our proposed framework also has the potential to be applied in other types of cancer to facilitate the development of cancer therapeutics.
To develop machine learning methods for the identification of Alzheimer’s disease (AD) and its related dementias (ADRD) sub-phenotypes. Using electronic health records (EHRs) from patients diagnosed with AD/ADRD, we will retrospectively review their structured EHRs, clinical notes, and neuroimages and develop machine learning methods for connecting these data sources and computationally deriving AD/ADRD sub-phenotypes based on hierarchical clustering. Interfaces with Data Science/AI: Students are required to develop machine learning methods to connect different data modalities and develop AI methods to derive disease subtypes from large-scale health data.
In this project, we will develop and validate research-grade computable phenotyping (CP) algorithms and tools, leveraging advanced natural language processing (NLP) methods, to accurately identify AD/ADRD drug repurposing study cohorts and then extract and standardize relevant patient characteristics (e.g., APOE) and outcomes (e.g., ADRD subtypes and severity) from RWD. The algorithms will be developed and internally validated at OneFlorida and externally validated with INSIGHT data. This work will address misclassification errors and incomplete information through CP and clinical NLP. Neither NLP nor CP is a novel method; nevertheless, there has been no systematic investigation for AD/ADRD drug repurposing. Our effort will be the first to make publicly available resources to support AD/ADD drug repurposing research using real-world data (RWD). With the CP/NLP pipeline, we can accurately identify study cohorts, extract drug exposures, outcomes, and other important confounders and potential effect modifiers, which enables more precise estimation of the treatment effects for the candidate repurposing drugs from RWD.