Ilan Shomorony

The paper introduces a statistical test based on tetranucleotide frequency to detect and correct inverted misassemblies in bacterial genomes.

JIND improves automated cell-type annotation in single-cell RNA-seq by learning a latent space for reliable classification and batch alignment without retraining.

This paper introduces Spectral Jaccard Similarity, a method to estimate pairwise sequence alignments by addressing k-mer distribution biases, showing improved performance on PacBio reads.

This paper develops a model combining polygenic risk scores and quantitative MRI to predict dementia onset up to eight years earlier than traditional methods.

The paper integrates multimodal health data to identify novel biomarker signatures for health and disease, showing better predictive power for diabetes and hypertension than traditional biomarkers.

HINGE improves repeat resolution in long-read genome assembly by distinguishing resolvable from unresolvable repeats, producing more finished assemblies than existing methods.