All Competitors

Context-aware protein sequence search, where a genomic language model fine-tuned for retrieval lets neighboring genes shape the query embedding.

Peptide identification for diaPASEF proteomics, scoring fragment coelution across retention time and ion mobility with a pretrained CNN.

Protein-protein interaction prediction from structure alone, embedding each protein once so a proteome-wide dot product replaces pairwise queries.

Hydration-site prediction placing water molecules on protein surfaces by score-based diffusion, within 0.3 Å of crystallographic positions.

Target-conditioned generative language model that designs drug-like SMILES from a protein sequence, tuned on regulator-approved drug-target pairs.

Structure-based molecule optimization that steers a Bayesian flow network with property gradients over 3D coordinates and atom types at once.

Prompt-guided protein sequence design conditioned on 3D backbones, fold blueprints, and functional tags. 63.21% native sequence recovery on CATH.

Protein function prediction from 3D structure and sequence, assigning Gene Ontology terms with an ensemble built around rare long-tail terms.

Predicts protein properties from sequence alone by LoRA fine-tuning ESM-2 and ESM-C backbones, with contact maps biasing attention pooling.

Macrocyclic peptide binder design against protein targets, cyclizing a diffusion backbone generator's positional encoding so it closes rings.

Immune protein structure prediction for TCRs, antibodies, and nanobodies. Adapts ESMFold with LoRA, reaching 1.31 Å RMSD on the CDR3-beta loop.

Peptide-spectrum match rescoring for DDA proteomics, learned end to end from raw MS2 spectra and peptide sequence across 271 million PSMs.

Missense pathogenicity prediction that folds wild-type and mutant sequences with ESMFold and encodes each structure as a graph autoencoder embedding.

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

Sparse autoencoders on ESM-2 embeddings that expose thousands of interpretable features per layer, tied to binding sites, motifs, and domains.

De novo atomic model building from cryo-EM density maps, adapting AlphaFold2 with local attention and a 3D rotary position embedding.

DIA proteomics scoring model that identifies and quantifies peptide precursors, pretrained across 952 mass spectrometry runs instead of one.

Antibody-antigen binding affinity prediction and sequence optimization, pre-trained on 7.5 million quantitative yeast-display affinity measurements.

Protein language models that split translated algal genomes into real genes and contaminants, classifying the dark proteome without homology search.

Text-guided protein design that generates functional sequences from natural language prompts through a contrastive protein-text embedding space.

De novo enzyme design conditioned on the reaction to be catalysed: substrate and product SMILES in, catalytic pocket, enzyme, and docked complex out.

Generative masked protein language model with an interpretable concept layer, letting designers set 718 biophysical and annotation concepts directly.

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