Alexander B. Rosenberg

The paper develops COMPASS, a method to assess splicing variant effects across cell types, identifying disease-associated variants and cell type-specific splicing programs.

This paper introduces an improved combinatorial barcoding method for scRNA-seq that significantly increases sensitivity, detecting more transcripts and genes per cell across various sample types.

This study maps the spatial and single-cell transcriptional landscape of human cerebellar development, revealing cell-type-specific gene expression and implications for neurological disorders.

This paper introduces Deep Exploration Networks (DENs) to generate high-fitness DNA sequences, demonstrating improved performance in engineering RNA isoforms compared to gradient ascent methods.

This paper introduces APARENT, a deep learning model that predicts alternative polyadenylation from DNA sequence, outperforming models trained on endogenous data and identifying genetic variants impacting APA in disease contexts.

The paper introduces SPLiT-seq, a scalable scRNA-seq method, and applies it to analyze 109,069 cells from a mouse brain, identifying 13 main cell populations and developmental substructures.

The paper trains a CNN to predict translational efficiency of yeast 5' UTRs using synthetic sequences and validates it on native sequences and evolved designs.