{"entity":{"id":"single-cell-foundation-models","kind":"term","name":"Single-cell and transcriptome foundation models: UCE, GeneCompass, BulkFormer, BulkRNABert","aka":["BulkFormer","BulkRNABert","GeneCompass","UCE model","Universal Cell Embeddings","scFoundation model","transcriptome foundation model","bulk transcriptome model"],"tldr":"These are transformer models pretrained on expression profiles: UCE and GeneCompass on tens of millions of single cells, BulkFormer and BulkRNABert on bulk tumour and tissue transcriptomes.","summary":"Universal Cell Embeddings (Rosen and colleagues) is a 650-million-parameter cell model that represents genes by their ESM2 protein embeddings so it works across species; GeneCompass (Yang and colleagues) is a knowledge-informed model trained on over a hundred million human and mouse cells. Bulk-native models are fewer: BulkFormer (Kang and colleagues, Cell Systems 2026) is a 147-million-parameter model trained on about half a million bulk profiles and released with code and weights; BulkRNABert (Gélard and colleagues, InstaDeep) is a language model for bulk RNA-seq cancer prognosis under a research-only licence. Frozen bulk embeddings have not consistently beaten a genome-wide linear baseline on TCGA survival, so their value is still being established.","asOf":"2026-09-24","links":[{"label":"Rosen et al., Universal Cell Embeddings: a foundation model for cell biology (bioRxiv 2023)","url":"https://doi.org/10.1101/2023.11.28.568918"},{"label":"Yang et al., GeneCompass (Cell Research 2024)","url":"https://doi.org/10.1038/s41422-024-01034-y"},{"label":"Kang et al., BulkFormer: a large-scale foundation model for bulk transcriptomes (Cell Systems 2026)","url":"https://doi.org/10.1016/j.cels.2026.101657"},{"label":"Gélard et al., BulkRNABert: cancer prognosis from bulk RNA-seq based language models (bioRxiv 2024)","url":"https://doi.org/10.1101/2024.06.18.599483"},{"label":"BulkRNABert code (InstaDeep)","url":"https://github.com/instadeepai/multiomics-open-research"}],"tags":["cansim-terms"],"related":["cellxgene-hca","cancer-ai-vocabulary"],"cancers":[],"sections":[],"technologies":["scfoundation","nicheformer"],"targets":[],"drugs":[],"companies":[],"institutions":[],"pathways":[],"terms":["foundation-model","tokenisation","fine-tuning-vs-frozen","single-cell-rna-seq"],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":["Listed in the CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme; CanSim page path /terms/bulkformer."],"provenance":{"editedBy":"OnCo CanSim terms wave (Wikipedia summaries, standards and project pages, GDC and FDA pages, Europe PMC)","editedOn":"2026-09-24","note":"CanSim terms map 1.0.0 (docs/onco/terms.json, generated 2026-09-24), CC BY 4.0, attribution: CanSim project, an open, public-data-first cancer foundation-model programme"},"category":"Methods and models"},"route":"/terms/single-cell-foundation-models/","neighbours":{"collection":[{"id":"cellxgene-hca","kind":"collection","name":"CZ CELLxGENE / Human Cell Atlas","route":"/collections/cellxgene-hca/"}],"term":[{"id":"cancer-ai-vocabulary","kind":"term","name":"Cancer AI vocabulary (CanSim terms map)","route":"/terms/cancer-ai-vocabulary/"},{"id":"fine-tuning-vs-frozen","kind":"term","name":"Fine-tuning versus frozen features, and LoRA","route":"/terms/fine-tuning-vs-frozen/"},{"id":"foundation-model","kind":"term","name":"Foundation model","route":"/terms/foundation-model/"},{"id":"single-cell-rna-seq","kind":"term","name":"Single-cell RNA sequencing (scRNA-seq, 10x Chromium)","route":"/terms/single-cell-rna-seq/"},{"id":"tokenisation","kind":"term","name":"Tokenisation (genes, tiles and sequence as tokens)","route":"/terms/tokenisation/"}],"technology":[{"id":"nicheformer","kind":"technology","name":"Nicheformer (spatial single-cell)","route":"/technologies/nicheformer/"},{"id":"scfoundation","kind":"technology","name":"scFoundation (BioMap)","route":"/technologies/scfoundation/"}]}}