Wei Wang

The paper develops DeepAnchor, a deep learning model to characterize CTCF binding patterns and predict CTCF-anchored loops across human tissues, revealing sequence and chromatin features that influence loop formation and disease mechanisms.

The paper predicts mRNA abundance from promoter sequences using interpretable neural networks and identifies regulatory motifs and their combinatorial rules.

The paper develops a framework to derive linear formulas linking DNA motifs to gene expression using an interpretable neural network model, identifying 300 motifs with regulatory roles across 154 cell types.

The paper identifies essential regulatory elements that maintain chromatin organization and cell viability through their role in 3D chromatin contacts, showing that non-essential genes can synergize to cause cell death.

The paper introduces a method to convert position weight matrices into compact consensus sequences with minimal information loss, showing improved performance in identifying transcription factor binding sites.