All Competitors

Toxicity screening foundation model that encodes Tox21 concentration-response curves and assay metadata into reusable 768-dimensional embeddings.

Protein sequence embedding model, contrastively fine-tuned from ESM-2, that places functionally and structurally related proteins close together.

Graph attention model that learns context-aware protein embeddings from protein-protein interaction, co-expression, and tissue association networks.

Post-hoc method that restores monotonic scaling to ESM-2 embeddings, yielding Matryoshka-style nested representations for variant effect prediction.

Cross-modal protein encoder that aligns ESM-2 sequence embeddings with ProteinMPNN structure embeddings in a shared space for cross-modal retrieval.

Enzyme function prediction model that uses contrastive learning to assign the first three EC digits to enzymes with functions unseen during training.

Cross-species multimodal foundation model of immunology and inflammation, harmonizing transcriptomics and histology into patient-level embeddings.

Protein structural homology search from sequence alone, embedding proteins so that structural similarity becomes a fast nearest-neighbor lookup.

Annotation-free metagenome embedding pipeline that encodes raw DNA reads with genomic language models and pools them via FAISS k-means clustering.

470M-parameter microbial genome foundation model trained on 234.5B base pairs for multi-scale genomic representation and trait prediction.

Pan-viral genomic language model producing fixed genome-level embeddings of viral DNA and RNA, reused across classification tasks without retraining.

Antibody language model pretrained only on CDR-H3 loops, giving embeddings for immune repertoire analysis and antibody sequence classification.

Structure-based conformational B-cell epitope predictor that scores local antigen surface patches with ESM-2 embeddings and an ensemble MLP.

Foundation model for tandem mass spectrometry that embeds MS/MS spectra into a learned chemical space, resolving isomers and classifying disease.

Siamese protein language model whose embedding distances approximate TM-score and lDDT, enabling alignment-free protein structure comparison.

Zebrafish single-cell foundation model built on the Geneformer framework, producing frozen gene and cell embeddings for developmental analysis.

Medically tuned SigLIP encoder from Google that maps medical images and text into one embedding space for zero-shot classification and retrieval.

Protein structure embedding model that compresses each 3D fold into a single fixed-length vector for proteome-wide similarity search and clustering.

scVI variational autoencoder trained on the Tahoe-100M drug-perturbation atlas, giving a 10-dimensional embedding of treated cancer cell states.

RNA-RNA interaction prediction framework that scores pairing between long transcripts directly from sequence using Nucleotide Transformer embeddings.

Genomics foundation model for genome-scale SNP analysis, handling imputation, phasing, ancestry, and relatedness from one 0.8B-parameter checkpoint.

Protein language model that captures short- and long-range residue co-evolution through a dual pre-training objective, at 3B parameters.

Chest X-ray embedding model built on ELIXR, producing image and image-text embeddings for data-efficient and zero-shot radiograph classification.

DNA embedding model built on DNABERT-2, using contrastive learning to cluster sequences by species for metagenomic binning without labeled data.