AI Population Genomics Research

Variant Annotation and Functional Prediction

Interns will develop and optimize machine learning pipelines to annotate genetic variants and predict their functional impacts on protein structure and disease susceptibility. Work includes training neural networks on existing variant databases and validating predictions against clinical phenotype data from population cohorts.

Population Stratification and Ancestry Analysis

Interns will apply dimensionality reduction techniques and clustering algorithms to analyze genetic ancestry patterns across diverse populations using large-scale genomic datasets. Projects involve implementing PCA, UMAP, and admixture analysis tools to characterize population structure and identify ancestry-specific genetic effects.

Genome-Wide Association Study (GWAS) Pipeline Development

Interns will design and implement automated GWAS pipelines using Python and R to identify genetic loci associated with complex traits and diseases at population scale. This includes quality control workflows, statistical association testing, and integration of results with biological databases for interpretation.

Polygenic Risk Score Construction and Validation

Interns will develop computational methods to construct polygenic risk scores from GWAS summary statistics and validate their predictive accuracy across different populations and cohorts. Work involves exploring methods to reduce population bias and improve clinical utility of risk predictions.

Single-Cell Population Genomics and Multi-omics Integration

Interns will apply machine learning techniques to integrate single-cell transcriptomic data with population-level genomic variation to understand cell-type-specific genetic effects. Projects include developing computational frameworks for linking genetic variants to cellular phenotypes using scRNA-seq and population genomics data.