All Competitors

Multi-species genomics foundation model spanning representation learning, functional-track prediction, and sequence generation at 1 Mb context.

ADMET property prediction for CYP inhibition, PXR activation, hERG, microsomal clearance, and permeability, all trained on public assay data.

Molecular property prediction foundation model pretrained on computed descriptors. Wins 75% of Polaris tasks and 97% of MoleculeACE assays.

Mixed-modality genomic language model encoding protein coding sequences as amino acids and intergenic DNA as nucleotides in native genomic context.

Multi-species genomic foundation model swapping k-mer tokenization for byte pair encoding, matching Nucleotide Transformer with 21x fewer parameters.

Family of transformer-based DNA language models using BPE tokenization and BigBird sparse attention to reach context lengths up to 36,000 base pairs.

DNA foundation models from 500M to 2.5B parameters, trained on 3,200+ human genomes and 850 species for variant effect prediction.

Protein language model family from 8M to 15B parameters, used as a frozen sequence encoder whose representations encode atomic-level structure.

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

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