Shanghai Institute of Materia Medica

Molecular glue degrader activity prediction from SMILES and protein sequence, with two-stage cross-attention that follows E3-then-substrate binding.

Diffusion-based generative RNA model for de novo sequence design, conditioned on function, RNA family, structure, or binding proteins.

Structure-based virtual screening model that jointly predicts protein-ligand complex structures and binding fitness from sequence and SMILES.

Structure-based drug design model that generates 3D ligands inside a protein pocket by interpolating distribution parameters instead of samples.

Relative protein-ligand binding affinity prediction from docked complexes, matching Schrodinger FEP+ ranking accuracy zero-shot on the FEP benchmark.

Molecular conformation description language encoding 3D geometry as SMILES plus internal-coordinate tokens, turning 3D modeling into a sequence task.

Structure-based drug design that schedules noise separately for 3D coordinates and 2D topology, reaching a 95.9% PoseBusters valid rate on CrossDock.

Structure-based molecular generation guided by imputed ligand electron density, assembling drug-like compounds into a pocket fragment by fragment.

Protein conformational ensemble generator using SE(3) flow matching from a perturbed ESMFold prior, sampling MD-like dynamics from sequence alone.

Structure-based molecule optimization that steers a Bayesian flow network with property gradients over 3D coordinates and atom types at once.

Structure-based drug design that generates 3D ligands for a protein pocket entirely in the continuous parameter space of a Bayesian flow network.

3D molecule generation that models atom coordinates and element types as distribution parameters updated by Bayesian inference, not by denoising.

Equivariant heterogeneous graph network that rescores docked protein-ligand poses for virtual screening and ranks structural analogs by activity.