All Competitors

Binder motif prediction from receptor structure alone, mapping 14 functional-group types across a protein surface as reusable interaction profiles.

Drug-target interaction model that compresses any compound into a 15-bit hierarchical code, so billion-compound libraries can be screened in seconds.

Fragment-based molecular generation by masked discrete diffusion over SAFE strings, covering de novo design, linker design, and lead optimization.

Autoregressive graph transformer generating molecules as node and edge token sequences, fine-tunable for goal-directed design and property prediction.

Cell Painting generative model encoding lab, batch, and well position as causal variables, predicting mechanism and target for unseen compounds.

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

Surrogate machine learning force field reusing a reference model's node features from earlier steps, running molecular dynamics eight times faster.

De novo 3D drug design that turns a pharmacophore arrangement into a molecule through an SE(3)-equivariant diffusion bridge.

Latent diffusion model that paints high-resolution Cell Painting images of cells responding to a chemical compound or an over-expressed gene.

Retention time prediction for peptides whose post-translational modifications were never seen during training, using molecular-structure encodings.

Protein-ligand binding affinity prediction from multimodal representations. Retains accuracy on predicted rather than crystal complex structures.

Drug-conditional adapter inside a frozen single-cell foundation model, predicting transcriptional responses to unseen drugs and cell lines.

Geometric foundation model matching enzymes to the reactions they catalyze, trained on 1.5 million structure-informed enzyme-reaction pairs.

Latent diffusion model generating Cell Painting images for a compound from its predicted bioactivity profile, reaching unfamiliar chemical matter.

PROTAC degrader generation pipeline that screens target-binding fragments, then builds molecules under structure and physicochemical constraints.

Multimodal foundation model integrating protein sequence, structure, and natural language to model and generate protein phenotypes across scales.

Ligand identification in cryoEM and X-ray density maps, classifying a density blob into one of 219 ligand groups from its 3D point cloud shape.

SMILES language model pretrained by editing: substructures are dropped and restored, giving fragment-level supervision for property prediction.

Pocket-conditioned 3D ligand generator built on rectified flow, reaching -8.50 average Vina Dock and 75.0% diversity on CrossDocked2020.

Drug-target affinity prediction pairing an SE(3)-equivariant GNN over 3D protein structure with a molecular GNN and residue-atom cross-attention.

Molecular formula identification from tandem mass spectra at 88.3% top-1 accuracy, more than 10x faster than fragmentation-tree search.

Flexible protein-ligand docking that repacks the pocket side chains from the backbone and the ligand graph before a physics sampler places the ligand.

Vector-based virtual screening model that co-embeds proteins and small molecules so a drug-target interaction reduces to a single dot product.