All Competitors

Controllable protein sequence generator adapted from Llama-3-8B with LoRA, prompted in plain English to emit enzymes from ten property classes.

Protein language model extending ESM-2 to 2,048-residue inputs with LongFormer-style local windowed attention, re-pretrained on Swiss-Prot.

Retrieval-augmented inverse folding model that fuses structural motif retrieval with a hybrid attention decoder to design sequences for a backbone.

Peptide-protein co-folding and small-molecule docking with an all-atom diffusion transformer. Recovers 59.1% of peptide interfaces to sub-2 Å RMSD.

Protein representation learning from cryo-EM density maps, transferring to flexibility, active-site, binding-affinity, and stability tasks.

Protein language model pairing sequence with quantized local-structure tokens via disentangled attention, for zero-shot variant effect prediction.

Protein solubility mutation-effect predictor built on an anti-symmetric Siamese geometric graph network trained on deep mutational scanning data.

Protein sequence-structure co-embedding model placing domains, full sequences, and short segments in one 32-dimensional contrastive space.

Mixed-modality genomic language model encoding protein coding sequences as amino acids and intergenic DNA as nucleotides in native genomic context.

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

Protein inverse folding model aligning ProteinMPNN by multi-objective preference optimization to improve developability without losing fold fidelity.

Refines AlphaFold2 predictions against cryo-EM, cryo-ET, and X-ray data by optimizing coevolutionary embeddings rather than atomic coordinates.

Pocket-conditioned 3D ligand generator built on rectified flow, reaching -8.50 average Vina Dock and 75.0% diversity on CrossDocked2020.

Enzyme Commission number prediction that pools ESM Cambrian embeddings across unlabeled sequence homologs, scoring 0.788 F1 on full 4-digit EC.

Flexible protein-ligand docking and binding affinity prediction from an apo receptor structure and ligand SMILES, using an 8-layer pair transformer.

Compact protein sequence generator adapted from Phi-3-mini with LoRA, emitting enzymes for ten named property classes from a plain-English prompt.

Zero-shot pathogenicity scoring for in-frame insertions and deletions from protein language model likelihoods over residues both alleles share.

Protein inter-residue distance prediction fusing MSA Transformer coevolution with ESM2 sequence features, reaching a mean absolute error of 2.20 Å.

RNA language model that reads full-length transcripts up to 10,000 nucleotides, pairing bidirectional state space layers with multi-head attention.

Open model that jointly predicts biomolecular structure and small-molecule binding affinity, approaching FEP+ accuracy in seconds on a single GPU.

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

860M-parameter generative single-cell foundation model that jointly represents and generates epigenomic, transcriptomic, and proteomic modalities.

AlphaFold fine-tuned via OpenFold on 944 high-resolution MHC-peptide structures, reaching median peptide RMSD of 0.65 Å on held-out complexes.