Selin Aviyente

The paper proposes a multiview graph learning method to reconstruct gene regulatory networks from single-cell RNA sequencing data, showing improved performance on synthetic and real datasets.

scSGL infers gene regulatory networks from single-cell RNA sequencing data by learning signed graphs that capture both activating and inhibitory gene relationships, while handling cell-cycle heterogeneity and dropouts.

This paper introduces a graph-to-signal transformation to extract features from functional connectivity networks, showing improved discriminative power compared to traditional graph measures.