All Competitors

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

Diffusion model predicting single-cell responses to genetic or drug perturbations, generating over distributions to capture population variability.

Conditional variational autoencoder for antimicrobial peptide design that disentangles sequence, function, and length for independent control.

Protein evolution model that learns indel dynamics and epistasis from unaligned sequences, simulating trajectories that yield functional proteins.

Single-cell foundation model applying discrete diffusion directly to scRNA-seq counts, generating unconditional and perturbation-conditioned profiles.

Genomic foundation model training framework whose joint-embedding predictive objective learns functional representations of masked DNA, not tokens.

BERT-style language model for somatic mutations, pretrained on cancer sequencing from 210,000+ patients for tumor subtyping and therapy response.

Multimodal single-cell foundation model whose multiway Transformer jointly models scRNA-seq and scATAC-seq from RNA-only, ATAC-only, or paired inputs.

Retrieval-augmented framework for de novo peptide binder design that conditions generation on retrieved, structurally aligned binding evidence.

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

Transformer that infers whole-genome DNA methylation from gene expression, generalizing zero-shot to unmeasured CpG sites and unseen samples.

Flow-matching generative model for peptide sequence design that learns the protein semantic distribution, fine-tuned for antimicrobial peptides.

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

Genomic language models fine-tuned to detect and classify antibiotic resistance genes, catching divergent ARGs that reference alignment misses.

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

Vision-omics finetuning that aligns pathology foundation models with spatial transcriptomics so morphology features predict local gene expression.

Single-cell foundation model that forecasts how cancer cells evolve, autoregressively generating future gene expression from prior cell states.

Protein language model that encodes sequences as discrete words from a learned vocabulary for zero-shot function inference and protein design.

Latent diffusion model that designs D-peptide binders against native L-protein targets, generalizing across chirality via axial vector features.

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

Pan-cancer pretrained diffusion model imputing genome-wide expression from sparse spatial transcriptomics panels, zero-shot and reference-free.

Multimodal generative model predicting viral antigenic change zero-shot from disentangled evolutionary, physicochemical, and structural signals.

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

Tokenizer-free genomic foundation model that adaptively chunks raw nucleotides, enabling zero-shot variant fitness and gene essentiality prediction.