May Dongmei Wang

This study uses optogenetic manipulations to distinguish instructive from permissive roles of brain circuits in visual detection, showing that midbrain regions can compensate for primary visual cortex loss.

This study develops novel methods to assess modality importance in multimodal electrophysiology classifiers, finding EEG is globally most important for sleep stages except stage 1, with subject-level differences influenced by sex, medication, and age.

This study classifies sleep stages using multimodal electrophysiology data and introduces an ablation method to assess modality importance, finding EEG is most important for most stages and EOG for REM and nonREM.

This paper introduces a local ablation method to explain multimodal classifiers, showing EEG's importance in sleep staging and identifying demographic effects on classification.

The paper introduces a gradient-based explainability method for multimodal electrophysiology classifiers, showing EEG's dominance in sleep stage classification.

The paper analyzes micro-inversions in human and nonhuman primate genomes to explore their role in population genetics and evolutionary history.

MotifMark identifies DNA-binding sites and ranks their specificity using graph theory and machine learning, outperforming existing methods on protein binding microarray data.

The paper develops two models for predicting cause of death using mortality data, finding that a deep learning model with LSTMs outperforms N-gram based models by capturing temporal patterns.

DeeperBind predicts DNA binding specificities using a deep learning model, achieving high accuracy on high-throughput datasets.