All Competitors

Transmembrane topology predictor covering alpha-helical and beta-barrel proteins, with per-residue labels and signal peptide cleavage sites.

Inverse folding model predicting protein sequence from backbone coordinates, trained on 12 million AlphaFold2-predicted structures.

Resolution enhancement for Hi-C contact matrices, reconstructing full-depth 10 kb maps from libraries sequenced at a fraction of the read depth.

BERT-based predictor of DNA N6-methyladenine (6mA) modification sites, using word2vec encoding and cross-species transfer learning.

RNA language model that learns base-level embeddings capturing sequence context and secondary structure, enabling fast structural alignment.

SMILES language model pretrained on 100M molecules, transferring to forward reaction prediction, retrosynthesis, molecular optimisation, and QSAR.

Protein language model that fuses Gene Ontology knowledge graphs with masked language modeling, improving protein function and interaction prediction.

Protein language model pretrained on UniRef90 with masked language modeling and Gene Ontology annotation prediction, at 16 million parameters.

Transformer that imputes missing CpG methylation states from sparse single-cell bisulfite sequencing, modeling genomic and cell-level structure.

Antibody-specific language model trained on the OAS database for restoring missing residues and generating high-quality sequence representations.

Medical-domain CLIP fine-tuned on radiology image-caption pairs from ROCO, serving as a drop-in visual encoder for medical visual question answering.

Mass spectrometry proteomics foundation model that jointly embeds MS/MS spectra and peptides in one space, for open and error-tolerant search.

Rigid protein-protein docking model that predicts a complex from two unbound structures in one pass, with no candidate sampling or refinement.

BERT adaptation for structured OMOP electronic health records that inserts artificial time tokens between visits so intervals shape the embeddings.

Multi-modal self-supervised transformer for regulatory genomics, pre-trained on DNA sequence together with transcription factor binding matrices.

Protein complex structure prediction model extending AlphaFold 2 with paired MSA processing and ipTM scoring for multi-chain, multimeric assemblies.

Transformer that predicts gene expression and epigenomic signals from 200kb of DNA sequence, capturing distal enhancers up to 100kb from a promoter.

Protein model quality assessment predicting per-residue lDDT from a single structure, using ultrafast shape recognition to encode residue topology.

Histopathology patch encoder self-supervised with BYOL on 2.7M unlabeled H&E tiles, using attention that gates feature channels with pooled context.

Residue-level binding site prediction from a bare protein sequence, ensembling six neural nets over protein, DNA/RNA and small-molecule interfaces.

Metabolite-likeness scoring ranks any chemical structure by its distance from a learned hypersphere of known endogenous metabolites.

Suite of six protein language models, including ProtBERT and ProtT5, trained on up to 393 billion amino acids without multiple sequence alignments.

Per-residue AlphaFold2 pLDDT confidence regressed from sequence by a bidirectional LSTM, with no structure prediction and no database lookup.