All Competitors

Genome-scale language model trained on prokaryotic genes and SARS-CoV-2 genomes to model viral evolution and flag emerging variants of concern.

Protein structure prediction model pairing SE(3)-equivariant networks with a coarse-grained representation to fold sequences fast, without MSA inputs.

Blind protein-ligand docking by diffusion over ligand translations, rotations and torsion angles, reaching 38% top-1 accuracy on PDBBind.

Human-in-the-loop cell segmentation framework enabling custom model training from as few as 100-200 corrected annotations.

Large-scale chemical language model trained on 1.1 billion SMILES strings using linear attention transformers for molecular property prediction.

Word2vec-based language model trained on 360 million microbial genes that predicts gene function from genomic context without sequence homology.

Protein language model reading each residue alongside an unsupervised local-fragment token, so one encoder serves residue- and chain-level tasks.

Predicts CLIP-seq crosslink counts along an RNA sequence base by base, separating protein-specific signal from experimental background.

Medical vision-language pretraining framework that injects structured medical knowledge into radiology image-text learning for VQA and retrieval.

Message passing neural network for fixed-backbone protein sequence design. Achieves 52.4% native sequence recovery, far surpassing Rosetta's 32.9%.

Self-supervised vision-language model for zero-shot detection of chest X-ray pathologies, trained on image-report pairs without explicit labels.

Self-supervised medical vision-and-language pretraining via multi-modal masked autoencoders that reconstruct masked image patches and text tokens.

Virtual staining network that turns label-free multiphoton brain-tissue images into H&E and Perls Prussian Blue histology, from unpaired data.

Protein-nucleic acid complex structure prediction from sequence, folding protein, DNA and RNA chains in one network with confidence estimates.

Pretrained transformer for cell type annotation of scRNA-seq data. Trained on 1.1M cells; outperforms supervised methods on cross-dataset transfer.

Small-molecule generation over SMILES through a fixed-size latent space dense enough that gradient-free search over it optimizes chemical properties.

Deep learning model predicting DNA methylation regulatory variants at CpG sites in the human brain, fine-mapping psychiatric disorder risk loci.

Protein model accuracy estimation from MSA co-evolution and homologous templates, predicting per-residue lDDT with a triangular-attention backbone.

RNA foundation model pretrained on 23.7 million non-coding RNA sequences, producing embeddings for structure prediction, annotation, and RNA design.

Motif-oriented DNA pre-training framework that adds motif prediction to an ELECTRA generator-discriminator setup for motif-aware genomic embeddings.

Histopathology tile encoder pairing a CNN stem with a multi-scale Swin Transformer, pretrained on 15.6 million unlabeled H&E patches.

Autoregressive protein language model based on GPT-2 that generates de novo protein sequences sampling unexplored regions of protein space.

In silico directed evolution that designs peptide binders against a chosen protein interface from sequence alone, scored by a frozen AlphaFold2.