All Competitors

Single-cell foundation model inferring context-specific protein-protein interactions from cancer transcriptomes via a variational graph autoencoder.

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.

De novo protein design from natural language: a 16B-parameter framework turning text descriptions into sequences via structure-conditioned generation.

Protein dynamics model predicting per-residue probability of microsecond-millisecond conformational exchange from sequence or structure.

Protein structure embedding model that compresses each 3D fold into a single fixed-length vector for proteome-wide similarity search and clustering.

Protein sequence design model that represents small molecules, nucleotides, and metals at atomic resolution, enabling ligand-aware enzyme design.

Unified science foundation model treating molecules, proteins, RNA, DNA, and materials as one sequence language, in 1B, 8B, and 46.7B sizes.

Open-source PyTorch reproduction of AlphaFold 3 under Apache 2.0, matching or exceeding AF3 on protein-ligand, protein-protein, and RNA benchmarks.

Multimodal 80B-parameter protein-language model that answers natural language questions about protein function from sequence and structure.

Text-guided protein design framework aligning language with sequences for text-conditioned generation, zero-shot editing, and property prediction.

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

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

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.

Protein language model family at 300M, 600M, and 6B parameters, purpose-built for representation learning and outperforming ESM-2 at smaller scale.

Mixture-of-experts protein language model scaling to 16 billion parameters, applied to variant effect prediction and de novo protein design.

LoRA fine-tuning framework for ESM-2 with multi-head attention pooling and contact map enhancement for sequence-only protein property prediction.

Open-source structure prediction model for proteins, nucleic acids, and small molecules, trained on public data to AlphaFold3-level accuracy.

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.

Protein language model that captures short- and long-range residue co-evolution through a dual pre-training objective, at 3B parameters.

Multi-modal, multi-task biological foundation model trained on 2 billion samples spanning proteins, small molecules, and single-cell gene expression.

Protein domain annotation model pairing an ESM-2 backbone with a probabilistic decoder, bringing language-model sensitivity to Pfam-style assignment.