All Competitors

Chemical language model that generates matched molecular pair transformations from SMILES and SMARTS to design medicinal-chemistry analogs.

Chemical language models pretrained on SMILES for therapeutic peptides, natively representing non-canonical residues, cyclization, and conjugation.

Molecular linker design model fine-tuned from Llama 3 that emits PROTAC and fragment linkers as SMILES from natural-language geometry prompts.

Protein foundation model for de novo enzyme design that co-designs sequence and 3D structure under small-molecule ligand guidance, at 730M parameters.

Molecular foundation models pretrained on density functional theory data, encoding 3D geometry and quantum behavior for ADMET and drug discovery.

Multimodal molecular foundation model fusing SELFIES, 2D graphs, text, and knowledge graphs via contrastive pretraining for property prediction.

Dual-encoder contrastive model that retrieves enzymes for query reactions by matching reaction fingerprints to protein sequence embeddings.

Geometric deep learning model that learns atomic-scale representations of molecular interfaces across proteins, small molecules, and nucleic acids.

All-atom generative foundation model that designs small molecules, peptides, and nanobodies against a target binding site from a single checkpoint.

Generative virtual-cell model predicting whole-transcriptome responses to unseen compounds and genetic perturbations, from cell lines to organoids.

Molecular reasoning model built on DeepSeek-7B, using chain-of-thought and reinforcement learning for property prediction, generation, and reactions.

Small-molecule drug discovery foundation model covering ADMET, retrosynthesis, drug-target activity, and molecular optimization in a 2.6B checkpoint.

Multimodal foundation model pretrained on ~500K unlabeled PubChem molecules that jointly predicts nine thermophysical properties of small molecules.

Knowledge-graph-grounded model that predicts single-cell transcriptomic responses to small molecules, with zero-shot prediction for unprofiled drugs.

Knowledge-graph foundation model for drug repurposing, grounding a biomedical graph in cell-type-specific genetic associations to rank indications.

Polarizable machine-learning interatomic potential extending MACE with long-range electrostatics, trained on 100M OMol25 DFT calculations.

Retrieval-augmented model for matched molecular pair transformations, proposing localized analog edits guided by retrieved reference compounds.

SMILES molecular encoder on a DeBERTaV2 backbone, pretrained on 123M PubChem molecules with physicochemical and structural-similarity objectives.

Diffusion model that generates continuous-time, all-atom biomolecular trajectories, reproducing conformational kinetics far more cheaply than MD.

Universal all-atom machine-learning force field for molecular dynamics, with ab initio-level accuracy on solvated biomolecules of ~1,500 atoms.

Protein-ligand foundation model that maps coarse-grained structural representations directly to binding affinity, running ~26x faster than Boltz-2.

Protein-ligand scoring function that conditions probabilistic geometric potentials on language model priors to rank docked poses and binding affinity.

E(3)-equivariant diffusion model for macrocycle design that turns acyclic molecules into macrocycles, with a transformer choosing where to cyclize.

Full-atom SE(3)-equivariant diffusion model that inpaints binding interfaces to design proteins that bind DNA, RNA, and small molecules.