1. Software methods for healthy aging or Alzheimer’s disease
Mentions the use and evaluation of convolutional neural networks and open-source frameworks for classification of Alzheimer’s disease from brain imaging data.
1.1 Machine learning and statistical methods for imaging genetics and multi-omics association studies
Computational approaches for associating genetic, genomic, transcriptomic, epigenetic, and multi-omics data with neuroimaging phenotypes, disease risk, and progression, including GWAS, multi-task learning, Bayesian models, and network-based methods.
Link
1.2 Machine learning and statistical methods for single-cell and spatial omics analysis
Computational tools for analyzing single-cell RNA-seq, spatial transcriptomics, and related omics data to identify cell types, disease genes, regulatory networks, and biomarkers related to aging and Alzheimer’s disease.
Link
1.3 Machine learning methods for genetic variant analysis and annotation
Software and algorithms for variant calling, annotation, fine-mapping, and functional interpretation of genetic variants associated with aging and Alzheimer’s disease.
Link
1.4 Machine learning methods for biomarker discovery and disease subtype identification
Approaches for identifying imaging, genetic, molecular, or cellular biomarkers, as well as disease subtypes and heterogeneity, using clustering, feature selection, and multi-modal data integration.
Link
1.5 Methods for longitudinal and progression modeling
Methods for modeling disease progression, aging trajectories, and longitudinal changes in neuroimaging, clinical, or omics data, including time-aware neural networks, longitudinal regression, and trajectory synthesis.
Link
1.6 Methods for preprocessing, harmonization, and quality control
Tools and algorithms for preprocessing, harmonizing, denoising, segmenting, and quality controlling neuroimaging and omics data, including cross-site harmonization and batch-effect correction.
Link
1.7 Machine learning methods for drug discovery and repositioning
Computational approaches for in silico drug repurposing and discovery using network-based and deep learning methods in the context of aging and Alzheimer’s disease.
Link