All Competitors

Protein structure prediction model that folds amino acid sequences into 3D structures with atomic accuracy, scoring a median GDT of 92.4 at CASP14.

Protein structure and complex prediction from sequence, in a three-track network that reasons over alignments, distances, and 3D coordinates at once.

Protein language model for zero-shot variant effect prediction, scoring mutations by log-odds from evolutionary sequences with no MSA or assay data.

Drug repurposing model that predicts a compound's L1000 transcriptional signature from SMILES and ranks it against a disease gene signature.

Sleep staging model that segments polysomnography from any single EEG and EOG channel pair, labelling stages at resolutions finer than 30 s epochs.

Single-cell perturbation prediction model that forecasts transcriptional responses to drug combinations and doses never experimentally measured.

Transformer protein language model trained on 250 million protein sequences that learns structural and functional representations without supervision.

Self-supervised molecular graph model contrastively pretrained on ~10M unlabeled PubChem molecules, then fine-tuned for property prediction.

Bidirectional transformer for DNA using k-mer tokenization, fine-tunable for promoter, splice site, and transcription factor binding prediction.

EEG foundation model pretrained on clinical recordings with a wav2vec 2.0-style contrastive task, transferring to BCI decoding and sleep staging.

Histopathology patch encoder giving 1024-dimensional embeddings for slide search and cancer subtyping, trained on TCGA with weak slide labels.

Chromatin interaction prediction from DNA sequence alone, calling CTCF-, RNA Pol II- and Hi-C-associated loops between open chromatin regions.

BERT-Large pretrained on the BREATHE literature corpus for biomedical question answering and embedding-based re-ranking of literature search.

Generalist deep learning algorithm for cell and nucleus instance segmentation using simulated diffusion flows, without per-dataset retraining.

Multi-organ and tumor segmentation in 3D abdominal CT from a single network whose segmentation kernels are generated per task by a controller.

Chemical language model pretrained on up to 77 million PubChem SMILES strings for molecular property prediction on the MoleculeNet benchmarks.

Chinese biomedical text encoder pretrained by masking whole medical entities and phrases, lifting clinical entity recognition and query understanding.

Cross-species convolutional network trained jointly on human and mouse genomes to predict regulatory sequence activity and noncoding variant effects.

Biomedical language model pretrained from scratch on PubMed abstracts with a WordPiece vocabulary derived from biomedical text rather than the web.

Sparse attention transformer that extends BERT to 8x longer sequences via random, local, and global attention, with genomic sequence applications.

Protein model accuracy estimation predicting per-residue lDDT plus signed residue-pair distance errors that become Rosetta refinement restraints.

RNA virtual screening that reads a binding site's base-pairing graph and predicts the chemical fingerprint of its ligand to rank compound libraries.

Brain MRI segmentation model that labels an entire 7T T1w volume in a single pass, returning six tissue classes plus background in seconds.