Gregory W. Schwartz

PENNE infers whole-transcriptomic profiles from live-cell images using domain adaptation, capturing temporal gene dynamics and cell-type markers.

ClumPyCells corrects cell size biases in spatial -omics data to accurately measure cell and marker aggregation in tissues.

SPAGHETTI translates phase contrast microscopy images into H&E-like images to improve cell segmentation and analysis using existing deep learning models.

NEST detects cell-cell communication patterns using a deep learning-based attention mechanism, outperforming existing tools and identifying biologically relevant communication in various tissues and diseases.

iSHARC is a pipeline for analyzing scMultiome data, enabling quality control, integration, clustering, annotation, and regulatory analysis in cancer studies.

This study identifies enhancer-promoter hubs in cancer types and shows their role in oncogenesis and drug resistance through topological and transcriptional changes.

AnnoSpat annotates cell types and quantifies cellular arrangements from spatial proteomics data, showing improved performance over existing methods in diabetic tissue analysis.

TooManyCellsInteractive provides an interactive visualization tool for exploring large single-cell datasets and identifies survival pathways in drug-tolerant persister cells across cancers.

The paper identifies a human HSC subset with inflammatory memory that accumulates with age and clonal hematopoiesis, potentially increasing cancer and infection risks.

TooManyCells identifies and visualizes cell clades using graph-based tools, outperforming existing methods in detecting rare populations in single-cell RNA-seq data.

This paper introduces inteGREAT, a method for integrating transcriptome and proteome data to identify prognostic biomarkers across cancers, showing high performance in synthetic and real data analyses.