Loading…
Diffusion-based RNA inverse folding, denoising toward a nucleotide sequence conditioned on a target 3D backbone for higher native sequence recovery.
Single-pass RNA inverse folding: a graph neural network predicts a nucleotide sequence from a target 3D backbone in constant time.
All-atom E(3)-equivariant diffusion model that refines RNA structures by resolving steric clashes and completing missing atoms.
Transformer foundation model for single-cell ATAC-seq that embeds both cells and cis-regulatory elements for annotation and batch correction.
Protein-ligand binding site prediction that ranks pocket residues and pocket center coordinates, staying accurate on AlphaFold-predicted structures.
Binding free energy change (ΔΔG) predictor for protein-protein interfaces, decomposing mutational effects into inverse-folding and energy-model terms.
De novo small-molecule generation inside a protein pocket, diffusing ligand atoms and pocket side chains together so the site adapts as it binds.
Graph neural network that reconstructs chemical bonds and bond orders from 3D coordinates, distorted generated geometries, or bare 2D connectivity.
Attention-based model predicting gene expression from histone modification signals across 56 cell types, with interpretable attention scores.