All Competitors

A spatial-transcriptomics foundation model for the tumor microenvironment that produces TME-aware embeddings and enables in silico perturbation from a fixed pretrained checkpoint.

Multipurpose generative adversarial network trained once on single-cell and bulk RNA-seq to perform stratification, marker analysis, data generation, and vectorization.

A decoder-only single-cell foundation model that forecasts future single-cell gene expression in cancer evolution from prior cell states, generalizing zero-shot to held-out cancers.

A pan-cancer pretrained latent diffusion model that enhances spatial transcriptomics, imputing genome-wide expression from sparse panels with zero-shot generalization.

Large causal cell model trained on cancer perturbation data that generalizes zero-shot to patient-derived cells for therapeutic target prioritization.

LLM-based generative model that synthesizes complete single-cell RNA-seq profiles from tissue and disease metadata alone, treating cells as gene-expression token sequences.

A pair of spatially aware transcriptomic foundation models (50um-Local and 250um-Extended) for multi-scale analysis of spot-resolution cancer spatial transcriptomes.

A multimodal vision-language copilot for human pathology that analyzes histology images and answers diverse pathology queries in natural language.

Whole-slide pathology foundation model pretrained on 1.3 billion tiles from 171,189 clinical WSIs. Achieves state-of-the-art on 25 of 26 pathology benchmark tasks.