Kristel Van Steen

This study compares genomic signatures of natural selection across Senegalese, Thai, and Peruvian populations to identify immune-related adaptive variants with implications for region-specific vaccine development.

The paper introduces AUC hyper-stability scores to improve the selection of Random Forest implementations for stable short biomarker signature discovery.

The paper develops methods to detect non-linear genetic interactions using visible neural networks and applies them to identify significant epistasis pairs in inflammatory bowel disease.

INMTD integrates omics and 3D imaging data to produce unconfounded individual subgroups with biologically meaningful embeddings.

The paper introduces four VAE-based deconfounding frameworks for multi-omics clustering, showing they reduce confounding effects and improve biological clustering.

The paper introduces NeEDL, a network medicine-based method for detecting higher-order epistatic interactions in complex diseases, showing improved statistical significance and applicability across eight diseases.

netMUG identifies actionable subgroups using network-guided multi-view clustering, showing improved performance over existing methods in synthetic and real data.

The paper identifies epistatic SNP-SNP interactions in long-range LD across five diseases using UK Biobank and eMERGE data, finding associations involving conserved genes and essential genes.

netANOVA identifies groups of graphs through hierarchical ANOVA-based clustering and significance testing, showing high performance in simulations and real data.

The paper identifies differentially expressed genes and modules associated with long-term survival in PDAC patients using integrative transcriptome analysis.

The paper develops a network-guided method for detecting gene-level epistasis in GWAS data, showing it can identify disease-relevant interactions while controlling type I error.

IPCAPS is an R package that uses iterative pruning PCA to resolve fine-scale population structure from SNP data, improving subpopulation detection and reducing misclassification.

This paper introduces SUGIBS, a robust genome-wide ancestry inference method, and applies it to predict ancestry faces using the 1000 Genomes Project and facial imaging data.

The paper introduces strategies to detect gene-gene interactions in structured populations by addressing confounding from population structure using model-based multifactor dimensionality reduction.

The paper introduces IPCAPS, an unsupervised clustering method using iterative pruning to detect fine-scale population structure from SNP data, showing improved accuracy over existing tools in simulations.