All Competitors

BioMed Multi-Omic

62—23

IBM ResearchJune 1, 2025cell_type_annotationfoundation_modelgene_expression+6

Open-source framework for building RNA and DNA foundation models, featuring WCED pretraining for transcriptomics and SNP-aware encoding for genomics.

DNA & Gene

84Openness

TranscriptFormer

15736—

Chan Zuckerberg InitiativeApril 29, 2025cell_type_annotationcross_speciesdisease_prediction+6

Generative single-cell foundation model trained on 112 million cells from 12 species, autoregressively modeling gene identities and expression counts.

Single-cell

67Openness

TEDDY

—9—

Merck & Co.March 5, 2025cell_type_annotationdisease_classificationfoundation_model+3

Single-cell RNA-seq foundation models combining masked modeling with ontology supervision to classify cell states across unseen donors and diseases.

Single-cell

46Openness

Tahoe-100M-SCVI

1.7K123—

Tahoe TherapeuticsFebruary 20, 2025autoencodercancerembeddings+6

scVI variational autoencoder trained on the Tahoe-100M drug-perturbation atlas, giving a 10-dimensional embedding of treated cancer cell states.

Single-cell

93Openness

AIDO.Cell

16817108

genbio.aiNovember 28, 2024bertcell_biologycell_type_annotation+7

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

Single-cell

29Openness

scGenePT

3113—

Chan Zuckerberg InitiativeOctober 28, 2024foundation_modelgene_expressionmultimodal+4

Single-cell perturbation prediction model that adds gene-level language embeddings from NCBI, UniProt, and Gene Ontology to scGPT representations.

Single-cell

90Openness

GeneCompass

119137—

Chinese Academy of SciencesOctober 8, 2024cross_speciesfoundation_modelregulatory_genomics+1

Knowledge-informed cross-species foundation model pre-trained on 101 million human and mouse single-cell transcriptomes to decipher gene regulation.

Single-cell

32Openness

scVI (CELLxGENE Census)

1.7K2.4K—

Chan Zuckerberg InitiativeJuly 1, 2024autoencodercell_type_annotationde_novo_design+6

Variational autoencoder pretrained on 74 million human single-cell transcriptomes from the CELLxGENE Census for batch correction and cell typing.

Single-cell

96Openness

Isoformer

9011722

InstaDeepJune 20, 2024foundation_modelgene_expressionmultimodal+4

Multimodal model fusing pre-trained DNA, RNA, and protein encoders through cross-attention to predict tissue-specific transcript isoform expression.

RNADNA & GeneProtein

26Openness

scFoundation

423596—

Biomap ResearchJune 6, 2024foundation_modeltranscriptomics

Single-cell transcriptomics foundation model with 100 million parameters, pretrained on over 50 million human scRNA-seq profiles for cell embeddings.

Single-cell

57Openness

CellFM

11078—

Sun Yat-sen UniversityJune 6, 2024cell_biologyfoundation_modeltranscriptomics+1

Single-cell foundation model with 800M parameters trained on ~100 million human cells, for annotation, perturbation prediction, and gene analysis.

Single-cell

26Openness

Nicheformer

167144945

Helmholtz Munich +1 otherApril 17, 2024foundation_modelspatial_transcriptomicstranscriptomics+1

Transformer foundation model pretrained on 110M single-cell and spatial transcriptomics profiles, transferring spatial context to dissociated cells.

Single-cell

87Openness

scGPT

1.6K1.2K—

Bowang LabFebruary 26, 2024foundation_modelgene_expressionperturbation+1

Generative pretrained transformer trained on 33 million human cells for single-cell annotation, batch correction, and perturbation prediction.

Single-cell

82Openness

Geneformer

—1.1K4.8K

Broad Institute +1 otherMay 31, 2023foundation_modelgene_networktranscriptomics+1

Single-cell foundation model pretrained on about 30 million human transcriptomes, using rank-value encoding for context-aware gene network inference.

Single-cell

96Openness