All Competitors

Protein language model classifiers that call human DNA- and RNA-binding proteins from sequence alone and localize the attention behind each score.

B-cell epitope prediction from antigen sequence alone. Fine-tunes ESM-2 with LoRA instead of freezing it, and scores antigens up to 1,724 residues.

Sequence-conditioned generative framework that reconstructs missing prostate MRI contrasts and restores artefact-degraded acquisitions.

Peptide-focused instruction-tuned LLM that describes function, designs sequences, predicts eight bioactivity properties and edits physicochemistry.

RNA–small-molecule interaction model that scores binding and localizes the pocket to individual nucleotides in one pass, from sequence and SMILES.

Single-molecule localisation microscopy analyser that infers interpretable structural descriptors and regenerates matched synthetic datasets.

Cell-level pathology foundation model that types every nucleus on a routine H&E slide, supervised by paired Xenium spatial transcriptomics.

RNA inverse folding model conditioned on a context-free-grammar parse tree of the target secondary structure, with explicit GC-content control.

Medical imaging foundation model unifying pathology and radiology, serving classification and segmentation on 2D, 3D and gigapixel inputs.

Contrastive encoder aligning NMR metabolomics to the plasma proteome, adding proteome-level disease risk signal to cohorts with no proteomics.

Sleep staging from one behind-the-ear electrode pair, feeding automated REM-sleep-without-atonia scoring and REM sleep behaviour disorder detection.

Self-supervised stereo-EEG encoder that localizes the seizure onset zone in drug-resistant epilepsy from peri-ictal superlet spectrograms.

Olfactory receptor-odorant interaction prediction from sequence and SMILES, pairing protein and chemical language models through cross-attention.

Graph transformer VAE that encodes ligand binding sites into latent point clouds, turning template search into a Chamfer distance lookup.

Single-cell perturbation model that generates a transcriptome gene by gene, letting a regulatory-network policy choose which genes come first.

Conformational ensemble generation between two anchor structures, mixing inverse-folding probabilities to prompt a frozen structure predictor.

Single-cell cytometry model that tokenizes each cell as marker-expression pairs, letting studies with different antibody panels share one encoder.

Infers gene-centered chromatin interactions from bulk RNA-seq alone, mapping 3D genome changes across 12,347 tumor and normal transcriptomes.

Protein druggability classification from sequence alone, stacking a self-attentive BiLSTM and Transformer encoder on frozen ESM-2 embeddings.

Hierarchical Enzyme Commission number annotation mapping frozen ESM-2 embeddings onto Random Forest classifiers, at 0.90 weighted F1 on 4-digit EC.

Drug-target affinity model scoring small molecules across the whole human proteome to yield tissue-weighted off-target binding profiles.

Brain MRI morphometry framework turning one T1w scan into 13 descriptors and a normative deviation profile shared across 19 clinical diagnoses.

Self-supervised single-lead ECG encoder pretrained on ten-minute ambulatory windows, giving patient-consistent embeddings for rhythm detection.