All Competitors

Cytometry foundation model for immunology, pretrained by masked-marker prediction on over 100 million immune cells from 53 public ImmPort studies.

Single-cell perturbation response prediction by conditional latent diffusion, trained on the Tahoe-100M atlas of 100 million drug-treated cells.

Single-cell perturbation prediction by conditional flow matching, using one cell-type-conditioned model in place of a separate model per cell type.

Base-resolution chromatin accessibility model that factors out enzyme sequence bias to score regulatory variants and transcription factor footprints.

Raman spectroscopy foundation model that denoises biological spectra and learns embeddings transferable across cell, tissue, and tumor studies.

Single-cell model inferring which developmental signaling pathways are active from scRNA-seq, trained on combinatorial stem-cell perturbation screens.

Spatial omics foundation model that represents tissue as a hierarchical graph of neighboring cells over per-cell gene co-expression networks.

Latent diffusion model that paints high-resolution Cell Painting images of cells responding to a chemical compound or an over-expressed gene.

Peptide-spectrum match rescoring for proteomics, scoring a full MS/MS spectrum against a candidate peptide without training on decoy sequences.

Peptide identification for diaPASEF proteomics, scoring fragment coelution across retention time and ion mobility with a pretrained CNN.

Single-cell cytometry model that tokenizes each cell as marker-expression pairs, letting studies with different antibody panels share one encoder.

Generative model that restores cytoplasm-enriched genes lost in snRNA-seq, recovering cell-cell communication signals from raw nuclear counts.

Explainable autoencoder for transcriptome analysis that uses SHAP attribution on latent variables to identify critical genes driving gene expression.

Spatial gene expression prediction from H&E tumor histology, aligning a pathology foundation model with a single-cell RNA-seq foundation model.

Single-cell perturbation model that generates a transcriptome gene by gene, letting a regulatory-network policy choose which genes come first.

Cross-species brain spatial transcriptomics foundation model pretrained on 133M cells from human, macaque, marmoset, and mouse whole brains.

Spatial proteomics foundation model trained on over 51 million single cells to learn panel-robust cell representations across platforms.

Bulk RNA-seq foundation model that learns patient-level embeddings from binned gene expression for pan-cancer classification and survival prediction.

Regulatory genomics foundation model pretrained on 6,391 human ChIP-seq cistromes, representing how ~1,000 transcription regulators cooperate.

Sparse autoencoder for blood-cell microscopy that decomposes hematology foundation model embeddings into expert-validated sub-cellular concepts.

Zebrafish sequence-to-function model predicting cell-type-specific gene expression from DNA sequence across embryonic development.

Cell phenotyping model for spatial proteomics using a language-informed vision transformer to classify cell types zero-shot across marker panels.

Spatial proteomics imputation model inferring surface protein abundance from transcriptomics-only tissue sections via dual graph attention networks.