Hussein A. Hejase

Systematic assessment of machine learning-based variant annotation methods for rare variant association testing

The paper benchmarks five machine learning-based variant annotation methods for rare variant association testing across 350,377 UK Biobank participants, finding CADD provides best signal separation and GPN-MSA highest enrichment for loss-of-function intolerant genes.

SIA: Selection Inference Using the Ancestral Recombination Graph

SIA detects and quantifies positive selection using deep learning on the ancestral recombination graph, showing performance comparable to existing methods and identifying novel selection signals in human and bird populations.

Non-parametric and semi-parametric support estimation using SEquential RESampling random walks on biomolecular sequences

The paper introduces a new non-parametric/semi-parametric sequential resampling method for support estimation in biomolecular sequences, showing comparable or better performance than existing methods.

Fast and accurate inference of phylogenetic networks using large-scale genomic sequence data

This study introduces FastNet, a new method for inferring phylogenetic networks from genomic data, showing improved efficiency and accuracy over existing methods.

Coal-Miner: A Coalescent-Based Method For GWA Studies Of Quantitative Traits With Complex Evolutionary Origins

Coal-Miner improves statistical power and type I error control in GWA studies by accounting for local genealogical variation in sample relatedness.