Caleb Hallinan

STARIT converts spatial transcriptomics data into image tensors for deep learning analysis, enabling subcellular heterogeneity-based cell state identification.

This study examines how data quality affects deep learning predictions of spatial gene expression from histology images, showing that improving data quality can enhance predictive performance.

The paper identifies off-target probe binding in 10x Genomics Xenium gene panels and develops a tool to assess its impact on spatial transcriptomic accuracy.

The paper introduces spatialMNN, an algorithm that integrates spatial transcriptomics data to identify spatial domains by incorporating 2D spatial information into mutual nearest neighbors analysis.

This paper introduces PHet, a method for selecting features that preserve disease heterogeneity and improve subtype discovery in single-cell data.