All Competitors

A deep generative decoder that infers microRNA expression directly from bulk or single-cell mRNA gene expression via a shared mRNA/miRNA latent space.

A self-supervised masked autoencoder for RNA-seq count data, pretrained on 1.4M public samples to learn transferable transcriptomic representations without per-dataset re-training.

A cell world model pretrained on a 2.4M-cell mouse embryonic atlas that predicts one-step transcriptional state transitions and transfers to perturbation prediction.

A constrained deep flow-matching framework for distributional translation of omics signatures across biological domains, such as mouse-to-human transcriptomics, without paired samples.

A virtual cell foundation model pretrained on 23M+ cells from 5,000 patient samples for drug target and biomarker discovery.

A multi-modal Transformer that fuses LLM gene embeddings with biological knowledge graphs to predict single-cell transcriptomic responses to genetic perturbations.

Meta-learning framework that transfers perturbation responses across cell lines, donors, and drugs from a few seed perturbations, using one-eighth the parameters of typical single-cell foundation models.

An autoregressive nucleotide-and-text foundation model pretrained on ~416B characters from 2,221 eukaryotic species for natural-language-guided conditional generation of DNA and RNA sequences.

A direction-aware foundation model trained on ~23M bulk RNA-seq differential-expression profiles that simulates coordinated gene dynamics in viral infection.

A transcriptome foundation model for precision oncology that generalizes zero-shot across tissue, plasma cfRNA, and tumor-educated platelet biopsy modalities.

A transcriptomics-native single-cell foundation model that couples batch-invariant representation learning with probabilistic virtual-cell generation.

Generates single-cell transcriptomic profiles from structured biological metadata via contrastive language-omics pretraining and a diffusion transformer.

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

A temporal diffusion-forcing generative framework for simulating, interpolating, and forecasting single-cell developmental dynamics from irregularly sampled time-series data.

Functional diffusion model that predicts single-cell perturbation responses by generating over distributions embedded in a Hilbert space, capturing population-level response variability.

A knowledge-graph foundation model that injects cell-type-specific genetic associations into a biomedical knowledge graph to improve drug indication prediction and repurposing.

A discrete-diffusion generative model that operates directly on single-cell gene counts, enabling unconditional and perturbation-conditioned scRNA-seq generation.

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.

Cross-species, multimodal foundation model of immunology and inflammation that harmonizes transcriptomics and histology into unified patient-level representations.

Distributional flow matching model for single-cell perturbation prediction that models population-level expression shifts using a graph-aware differential-attention transformer.

A multimodal generative model that designs molecules from transcriptomic and morphological perturbation phenotypes using rectified flow transformers.

A masked discrete-diffusion single-cell foundation model that jointly generates cell identity and expression, pre-trained on 59 million cells.

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.

Cross-modal cell-language foundation model that aligns single-cell expression with LLM-enriched textual descriptions using a noise-robust contrastive objective.