All Competitors

SMILES generative model for de novo drug design, pretrained on 200 million ZINC20 compounds with a tokenizer built from frequent substructures.

Spatial genomics foundation model that predicts a cell's transcriptome from its neighbours and forward-simulates tissue response to perturbation.

Translates whole-brain imaging phenotypes between humans and mice through a shared latent space built from transcriptomics and connectivity.

Base-pair resolution sequence-to-activity CNN predicting ATAC-seq Tn5 insertion profiles and accessibility across 90 mouse immune cell types.

Gene regulatory network inference from single-cell or bulk RNA-seq with a graph transformer. One checkpoint transfers across species and cell types.

Liquid-liquid phase separation predictor that scores proteins and residues from sequence and designs phase-separating peptides by gradient descent.

Sequence-only TM-score prediction pairing frozen ProtT5 embeddings with a bidirectional GRU and multi-scale convolution for protein homology search.

Histopathology feature extractor distilled from a 1.1B-parameter teacher into a ViT-Base, with leading robustness to staining and scanner variation.

Pretrained variational autoencoder for untargeted blood metabolomics, learning metabolite representations that transfer to clinical prediction tasks.

Histopathology image translation model that standardizes H&E staining style, then generates virtual collagen, reticulin, and trichrome fiber images.

RNA 3D structure generation from sequence and base-pair maps using SE(3) flow matching, with no MSAs or structural templates.

Structure-based drug design model generating 3D ligands inside a protein pocket, aligned by Best-of-K fine-tuning on drug-likeness and docking.

Biomedical vision-language model aligning image regions to UMLS clinical concepts, for zero-shot diagnosis across 10 imaging modalities.

DNA language model pretrained jointly on English, protein, and genomic text under one BPE vocabulary, transferring text segmentation skills to DNA.

Epigenome imputation transformer predicting raw read counts with calibrated confidence intervals, and denoising low-quality experiments in place.

Molecular docking framework that poses several ligands sharing one protein pocket at once, using their consistency to sharpen each prediction.

Nanopore basecaller built on a Squeezeformer encoder, turning raw ion-current signal into DNA at 93.97% average read identity across 11 datasets.

Epitope prediction model scoring whether a peptide is presented by HLA class I or II, with no allele input needed. Built on ESM-2 embeddings.

Protein function annotation model that parses sequences into residue clusters via community detection on ESM-2 attention, then maps them to GO terms.

Computational tumour-infiltrating lymphocyte scoring for breast cancer, regressing the stromal TIL percentage from H&E slide features in one step.

Per-residue membrane contact and solvent accessibility prediction from sequence alone, replacing MSA input with language model embeddings.

DNA foundation model encoding the genome as probabilistic allele frequencies from the 1000 Genomes Project. 86M parameters, single-nucleotide tokens.

Protein language model that jointly embeds a set of sequences and reconstructs phylogenetic trees without alignments or guide trees.