Cameron Shand

ESFS improves scRNA-seq data interpretability by identifying gene sets with complex expression dynamics, outperforming traditional methods in diverse biological contexts.

The paper develops a statistic called XORness to measure functional complexity in nanoscale connectomes and shows it is high in both real and generated connectomes with similar network statistics.

This paper introduces asymmetric contrastive objectives for phenotypic screening, improving performance on benchmark datasets and real-world cell screening tasks.

pySuStaIn provides a Python implementation of the SuStaIn algorithm to infer disease subtypes and stages from cross-sectional data.

The paper develops an explainable AI approach to predict skin-related phenotypes from leg skin microbiome data and identifies microbial composition changes linked to these traits.