Oded Regev

This study identifies sequence features that determine RNA localization to nuclear speckles, showing similarities with splicing codes and linking speckle localization to spliceosome assembly and splicing efficiency.

This study reveals that deep-learning-based RNA splicing models have confounders and blind spots, leading to poor performance on non-reference sequences.

The paper analyzes a large peptide collisional cross section dataset to identify structural determinants of bimodal CCS behavior in peptides.

The paper investigates RNA localization to nuclear speckles and finds that splicing efficiency is linked to transcript enrichment in these organelles.

The paper uses a machine learning-based high-throughput approach to analyze charge state distributions of peptides, revealing two distinct charging regimes with different sequence determinants.

This study introduces an interpretable neural network model for RNA splicing prediction, achieving accuracy comparable to state-of-the-art models while providing insights into splicing logic.