Benjamin DeMeo

The paper presents a longitudinal multimodal benchmarking dataset and competition to evaluate modality prediction methods for gene regulatory inference, showing top models outperform existing approaches.

The paper organizes a DREAM challenge to benchmark predictive models of single-cell signaling using mass cytometry data from breast cancer cell lines.

This paper introduces surprisal component analysis (SCA) for dimensionality reduction in single-cell data, improving the detection of rare cell populations and downstream imputation accuracy.

Hopper is a sketching algorithm that efficiently analyzes large scRNA-seq datasets by subsampling, preserving transcriptional diversity and enabling analysis on smaller, manageable datasets.

The paper introduces a geometric sketching method to compactly summarize scRNA-seq data, revealing rare cell types and accelerating analysis tasks.