genbio.ai

Sparse mixture-of-experts DNA encoder pretrained on multi-species genomes at 235M to 1B parameters, reading 64 kb of context and 256 kb at 235M.

Transformer U-Net pretrained on 6 trillion tokens of multi-species DNA, predicting expression and epigenomic tracks across 1 Mb of context.

World model that simulates a human cell as one persistent state, propagating drug and gene perturbations from DNA through to whole-cell morphology.

Histopathology foundation model with 1.1B parameters, trained entirely on public data using JEDI, a dual-stage strategy combining JEPA and DINO.

Multimodal protein language model that adds a continuous-token diffusion head to a discrete pLM, modeling structure without vector quantization.

Spatial transcriptomics foundation model pretrained on 22 million cells, encoding each cell with its neighbors for niche and density prediction.

Protein structure tokenizer that discretizes backbones into 512 discrete tokens and reconstructs all-atom structures, including side chains.

DNA foundation model scaling an encoder-only transformer to 7 billion parameters for variant effect prediction, gene expression, and sequence design.

Mixture-of-experts protein language model scaling to 16 billion parameters, applied to variant effect prediction and de novo protein design.

Single-cell RNA-seq foundation model pretrained on 50 million human cells, encoding the full transcriptome for annotation and perturbation modeling.

RNA foundation model with 1.6 billion parameters, pretrained on 42 million non-coding RNA sequences for structure prediction and RNA sequence design.