All Competitors

SE(3)-equivariant flow-matching model for pocket-aware 3D ligand generation, predicting binding affinity and confidence in the same network.

Diffusion model for multichannel fluorescent cell microscopy, generating morphologically plausible images aligned to OpenPhenom phenotypic embeddings.

Potts-model inverse folding that conditions on a structural ensemble rather than a single backbone, improving designability and self-consistency.

Protein binder design model post-trained from a multimodal protein language model to bind proteins, peptides, small molecules, and nucleic acids.

Single-sequence protein structure predictor that adapts image diffusion to generate 2D inter-residue templates, folding proteins without an MSA.

Generative single-cell foundation model trained on 112 million cells from 12 species, autoregressively modeling gene identities and expression counts.

Sparse mixture-of-experts autoregressive protein language model family pretrained on 1.5 trillion amino acid tokens with compute-optimal scaling.

Retrieval-augmented protein language model that conditions ESM-2 on homologous sequences via cross-attention for conditional sequence generation.

Medical vision-language model trained with reinforcement learning for generalizable reasoning across eight imaging modalities and five question types.

Patch-based 3D diffusion model that generates teravoxel-scale virtual mouse brain volumes conditioned on spatially resolved gene expression.

Latent diffusion model for single-cell multi-omics generation and modality translation, with gradient-based inference of gene regulatory networks.

Genomic foundation model trained on 9.3 trillion DNA base pairs across all domains of life, with 40B parameters and a 1-million-token context.

scVI variational autoencoder trained on the Tahoe-100M drug-perturbation atlas, giving a 10-dimensional embedding of treated cancer cell states.

4B-parameter generative genome foundation model trained on assembled environmental metagenomes for microbial representation and de novo DNA design.

Text-to-image diffusion model that generates synthetic medical images across imaging modalities and organs to augment scarce clinical training data.

Variational autoencoder that learns interpretable representations of protein subtomograms from cryo-ET, trained on 5.8 million synthetic particles.

Codon optimization framework that adds a generative head to a frozen ProtBert protein language model to design highly expressed coding sequences.

Generative model that emulates protein equilibrium ensembles, sampling cryptic pockets and unfolded states far faster than molecular dynamics.

Latent diffusion model for controllable all-atom protein generation that co-designs sequence and structure while training on sequences alone.

Antibody language model that generates paired heavy and light variable domains, with a developability-conditioned variant for manufacturable designs.

Biochemistry-aware inverse folding model that augments backbone geometry with physicochemical point clouds, reaching ~90% sequence recovery on CATH.

Autoregressive temporal convolutional network for synthetic yeast promoter design, trained with guidance from a sequence-to-expression predictor.

Diffusion model translating in both directions between protein sequences and fluorescence microscopy images to predict subcellular localization.

Generative foundation model for cryo-EM density maps using flow matching, enabling zero-shot denoising, map sharpening, and missing wedge restoration.