Jian Wang

The paper introduces SCRU-DB, a database of RNA units, and two models, SCRU-Seq and SCRU-Diff, to design RNA sequences with high structural accuracy.

ChironRNA resolves steric clashes and reconstructs missing atoms in RNA structures using an E(3)-equivariant diffusion model, achieving high precision on test data.

YuelPocket predicts small molecule binding sites on proteins using a graph neural network with a global graph design, achieving high AUC-ROC scores on benchmark datasets.

The paper introduces ATLAS, a 3D RNA motif library with graph representations and non-Watson-Crick interactions, enabling motif-based RNA structure prediction and design.

YuelBond improves bond reconstruction in molecular design by handling 3D structures, distorted compounds, and 2D graphs with high accuracy.

This study identifies IL-1/IRAK1/4 signaling as a therapeutic target in AML stem cells, showing that UR241-2 inhibits LSC clonogenicity and engraftment in both diagnosis and relapse.

YuelDesign generates molecules for flexible protein pockets using a diffusion framework, producing drug-like molecules with diverse functional groups and comparable docking energies to native ligands.

The paper introduces Yuel 2, a transfer learning-based model for predicting protein-small molecule interactions, showing improved accuracy in binding affinity metrics.

This paper uses deep machine learning to identify molecular mechanisms by which levodopa affects iron metabolism in Parkinson's disease, revealing interactions with iron transporters and pathways.

This study shows APOE regulates GM1 transport, which influences Aβ aggregation, linking APOE to Alzheimer's disease etiology.

This paper applies quantum tensor networks to classify proteins by sub-cellular location, achieving 94% accuracy with a compact quantum model compared to a large classical model.

The paper introduces a method using molecular beacons to directly detect miRNAs and isomiRs in cells and extracellular vesicles without RNA isolation, leveraging electrophoretic mobility and computational design for m6A modifications.

The paper assesses the limitations of current methods for analyzing prefrontal cortex neural activity and proposes dynamic time warping as a potential approach for correlating neural signals with behavior.

Yuel predicts compound-protein interactions with high generalizability, outperforming existing deep learning methods in predicting interactions between unknown compounds and proteins.