AI4AD (Artificial Intelligence for Alzheimer’s Disease): Ultrascale Machine Learning to Empower Discovery in Alzheimer’s Disease Biobanks
- PI
- Saykin, Andrew
- DAR ID
- 10480
- Initial Approval Date
- November 17, 2021
- Current DAR Status
- Active
- PI Institution
- Indiana University School of Medicine
- PI Institution Country
- United States
- PI Institution Type
- Non-Profit
Requested Datasets (1)
Research Use Statement
The AI4AD (Artificial Intelligence for Alzheimer’s Disease) Initiative aims to create and develop advanced AI methods, and apply them to genomic, imaging and cognitive data, in order to 1) identify AD genotypes and endophenotypes that dissect AD’s heterogeneity; 2) relate said genotypes and endophenotypes with clinical progression in pre-dementia patients; 3) identify novel treatment targets for AD by analyzing whole genome and associated phenotypic data. The goals of this multisite initiative (Paul Thompson, USC; Christos Davatzikos, Li Shen, Penn; Andy Saykin, IU; Heng Huang, Pitt, Paul Crane, UW; Adam Brickman, Columbia; Tim Hohman, Vanderbilt; Gyungah Jun, BU; Duygu Tosun, UCSF; Alexander Zaranek, Curii) leverage the promise of machine learning (ML) to contribute to precision diagnostics, prognostication, and targeted and novel treatments.
We will develop ML and deep learning methods to apply to large scale biobanks of whole genome sequences (WGS), neuroimaging, cognitive, and clinical data, aiming to discover new genomic features that influence biological processes of AD. We will apply methods of genome representation and tiling to WGS repositories to create inputs for AI methods.
We will develop novel, interpretable, biological knowledge guided deep learning methods to discover genomic motifs associated with AD, AD risk, and biological processes of AD as defined by NIA-AA criteria. To quantify subtypes and disentangle biological processes of AD, we will apply computational methods to multimodal MRI and amyloid- and tau-sensitive PET to stratify and subtype patient groups; novel imaging genomics methods will detect genomic markers and pathways that modulate the developing pathology as detected in the images, and that predict future clinical decline or resilience. We hypothesize that advanced deep learning methods combined with whole genome data will outperform traditional methods and GWAS for predicting AD onset and progression, and will assist with disease subtyping and discovering treatable targets in the genome. A team will rank and repurpose existing, and identify novel drugs and targets in the genome based on the discovered genetic motifs affecting AD.
We will develop ML and deep learning methods to apply to large scale biobanks of whole genome sequences (WGS), neuroimaging, cognitive, and clinical data, aiming to discover new genomic features that influence biological processes of AD. We will apply methods of genome representation and tiling to WGS repositories to create inputs for AI methods.
We will develop novel, interpretable, biological knowledge guided deep learning methods to discover genomic motifs associated with AD, AD risk, and biological processes of AD as defined by NIA-AA criteria. To quantify subtypes and disentangle biological processes of AD, we will apply computational methods to multimodal MRI and amyloid- and tau-sensitive PET to stratify and subtype patient groups; novel imaging genomics methods will detect genomic markers and pathways that modulate the developing pathology as detected in the images, and that predict future clinical decline or resilience. We hypothesize that advanced deep learning methods combined with whole genome data will outperform traditional methods and GWAS for predicting AD onset and progression, and will assist with disease subtyping and discovering treatable targets in the genome. A team will rank and repurpose existing, and identify novel drugs and targets in the genome based on the discovered genetic motifs affecting AD.
Non-Technical Summary
The AI4AD (Artificial Intelligence for Alzheimer’s Disease) Initiative aims to create and develop advanced AI methods, and apply them to extensive and rich genomic, imaging and cognitive data, in order to 1) identify genotypes and endophenotypes of AD that dissect the heterogeneity of the disease; 2) relate these genotypes and endophenotypes with clinical progression, in pre-dementia patients; 3) identify novel treatment targets for AD, by analyzing whole genome and associated phenotypic data at a previously impossible scale. Collectively, the goals of this highly collaborative multi-site initiative leverage the promise of machine learning to contribute to precision diagnostics, prognostication, and targeted and novel treatments.
Reported Publications (34)
Publications shown are those reported by investigators through NIAGADS DAR reporting and renewal processes and may not represent a complete list of publications associated with the project.
- A genetically informed brain atlas for enhancing brain imaging genomics. Bao J, et al. Nature communications. 2025. PMID: 40229250
- Addressing overfitting bias due to sample overlap in polygenic risk scoring. Jeong S, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 40189831
- Anxious-depressive symptoms and sleep disturbances across the Alzheimer disease spectrum. Chai Y, et al. Nature. Mental health. 2025. PMID: 40964168
- Approximate diffusion tractography from FLAIR MRI and anatomical context using recurrent neural networks. Li Z, et al. Proceedings of SPIE--the International Society for Optical Engineering. 2025. PMID: 41445918
- Cell-specific transcriptional signatures of vascular cells in Alzheimer's disease: perspectives, pathways, and therapeutic directions. Chaudhuri S, et al. Molecular neurodegeneration. 2025. PMID: 39876020
- Characterizing Amyloid Pathogenic Spread in Alzheimer's Disease Through A Network Diffusion Model. Xu FH, et al. ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine. 2025. PMID: 41488126
- Comprehensive characterization of the transcriptional landscape in Alzheimer's disease (AD) brains. Chen C, et al. Science advances. 2025. PMID: 39752483
- Enabling Few-Shot Alzheimer's Disease Diagnosis on Biomarker Data with Tabular LLMs. Kearney S, et al. ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine. 2025. PMID: 41488128
- Exploring potential mechanisms of an African protective locus for Alzheimer's disease in APOEε4 carriers. Bertholim-Nasciben L, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 40704449
- Fair CCA for Fair Representation Learning: An ADNI Study. Hou B, et al. ACM-BCB ... ... : the ... ACM Conference on Bioinformatics, Computational Biology and Biomedicine. ACM Conference on Bioinformatics, Computational Biology and Biomedicine. 2025. PMID: 41488125
Show more
- Functional insight into East Asian-specific genetic risk loci for Alzheimer's disease. Cho M, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 39991798
- Instantaneous Frequency: A New Functional Biomarker for Dynamic Brain Causal Networks. Tang H, et al. AI in neuroscience. 2025. PMID: 40917272
- Locus coeruleus tau is linked to successive cortical tau accumulation. Yi D, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 39641328
- Longitudinal non-linear changes in the microstructure of the hippocampal subfields in older adults. Zia G, et al. Neurobiology of aging. 2025. PMID: 40752038
- MG-TCCA: Tensor Canonical Correlation Analysis Across Multiple Groups. Zhou Z, et al. IEEE transactions on computational biology and bioinformatics. 2025. PMID: 39348263
- Multi-Modal Diagnosis of Alzheimer's Disease Using Interpretable Graph Convolutional Networks. Zhou H, et al. IEEE transactions on medical imaging. 2025. PMID: 39042528
- Multi-modal Imaging-based Pseudotime Analysis of Alzheimer progression. He B, et al. Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2025. PMID: 39670403
- Multi-omics analysis for identifying cell-type-specific and bulk-level druggable targets in Alzheimer's disease. Liu S, et al. Journal of translational medicine. 2025. PMID: 40653482
- Multi-Omics Analysis for Identifying Cell-Type-Specific Druggable Targets in Alzheimer's Disease. Liu S, et al. medRxiv : the preprint server for health sciences. 2025. PMID: 39830273
- Plasma proteomic analysis identifies proteins and pathways related to Alzheimer's risk. Huang YN, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 40810263
- Protein-based Diagnosis and Analysis of Co-pathologies Across Neurodegenerative Diseases: Large-Scale AI-Boosted CSF and Plasma Classification. Xu Y, et al. medRxiv : the preprint server for health sciences. 2025. PMID: 40672487
- Reconstructing brain causal dynamics for subject and task fingerprints using fMRI time-series data. Song D, et al. Health information science and systems. 2025. PMID: 41170153
- Scalable, reproducible, and cost-effective processing of large-scale medical imaging datasets. Kim ME, et al. Proceedings of SPIE--the International Society for Optical Engineering. 2025. PMID: 41450588
- The Cognitive Change Index in the Alzheimer's Disease Research Center setting: Self- and informant-ratings for perceived cognitive decline. Abughofah Y, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 41027849
- Transcriptome analysis of early- and late-onset Alzheimer's disease in Korean cohorts. Han SW, et al. Alzheimer's & dementia : the journal of the Alzheimer's Association. 2025. PMID: 39935412
- Traumatic Brain Injury and Alzheimer's Disease Biomarkers: A Systematic Review of Findings from Amyloid and Tau Positron Emission Tomography. Dybing KM, et al. Journal of neurotrauma. 2025. PMID: 39639808
- TrimNN: characterizing cellular community motifs for studying multicellular topological organization in complex tissues. Yu Y, et al. Nature communications. 2025. PMID: 40830137
- Uncertainty-aware genomic classification of Alzheimer's disease: a transformer-based ensemble approach with Monte Carlo dropout. Jo T, et al. Briefings in bioinformatics. 2025. PMID: 41212591
- Deep Trans-Omic Network Fusion for Molecular Mechanism of Alzheimer's Disease. Xie L, et al. Journal of Alzheimer's disease : JAD. 2024. PMID: 38728189
- Fairness-Aware Estimation of Graphical Models. Zhou Z, et al. Advances in neural information processing systems. 2024. PMID: 40855882
- Brain-wide genome-wide colocalization study for integrating genetics, transcriptomics and brain morphometry in Alzheimer's disease. Bao J, et al. NeuroImage. 2023. PMID: 37634885
- Circular-SWAT for deep learning based diagnostic classification of Alzheimer's disease: application to metabolome data. Jo T, et al. EBioMedicine. 2023. PMID: 37806288
- Deep learning-based identification of genetic variants: application to Alzheimer's disease classification. Jo T, et al. Briefings in bioinformatics. 2022. PMID: 35183061
- Identifying highly heritable brain amyloid phenotypes through mining Alzheimer's imaging and sequencing biobank data. Bao J, et al. Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2022. PMID: 34890141