Summary · Nature Biotechnology, April 2026
Biomedicine × machine learning · Literature briefNature Biotechnology · April 2026
A survey of 220 biomedical foundation models
Biomedical Foundation Models Are Moving From One Modality to Many
A survey of 220 biomedicine-specific foundation models developed over four years. More than half — 53.6% — already combine two or more data modalities, and natural language is emerging as the connective interface between otherwise unrelated kinds of biomedical data. General-purpose large language models such as ChatGPT, Gemini and Claude were deliberately excluded.
- 220models curated, over four years
- 53.6%are multimodal — 118 combine two or more modalities
- 17distinct data modalities in total
- 4domains: language, imaging, omics, sequences
Context · Definitions and the landscape · Content 1 / 3
What Counts as a Biomedical Foundation Model the survey's boundaries
- Large-scale machine learning models trained on varied biomedical and clinical data.
- That data spans genetic sequences, molecular profiling, biomedical imaging and electronic health records.
- They learn generalisable representations to support downstream discovery and clinical work.
- The survey covers four domains: natural language, imaging and signals, omics, and molecular sequences.
- General-purpose LLMs are excluded; the focus is 220 biomedicine-specific models.
The key observation
Natural language is the modality most often paired with others, and is becoming the connective interface between data types. This runs through the whole paper: the emerging citation leaders and the underdeveloped directions both point back to the same structure.
Encoders Dominate architecture breakdown
| Architecture | Count | Share |
|---|---|---|
| Encoder-based | 114 | 51.8% |
| Mixed | 67 | 30.5% |
| Decoder-based | 31 | 14.1% |
| Non-Transformer (e.g. Mamba) | — | 3.6% |
Decoders are scarce not out of architectural preference but because of data: text-generation tasks need high-quality paired image–text annotation, and that is hard to obtain in biomedicine.
Pivot · The evaluation gap and the citation picture · Content 2 / 3
Evaluation Is Still Narrow downstream tasks used
| Task | Share |
|---|---|
| Classification | 50.9% |
| Report generation | 10.9% |
| Question answering | 8.6% |
| Segmentation | 7.3% |
The evaluation gap
There are no multitask benchmarks, little human-in-the-loop assessment, and no combined treatment of data quality, interpretability and translational relevance. Half of these models have been tested on classification alone.
Citation Leaders by Domain * marks a multimodal model
| Domain | Leading models and citations |
|---|---|
| Natural language | BioBERT 6,925 · MultiMedQA 3,707 · PubMedBERT 2,278 |
| Imaging and signals | UNI 1,141 · ConVIRT* 1,003 · MedCLIP* 794 |
| Omics | scGPT 846 · Geneformer 836 · scBERT 509 |
| Molecular sequences | ESM-1b 2,807 · ProtTrans 1,207 · DNABERT 1,051 |
The Risers Since 2025 growth is coming from multimodal work
| Model | Domain | Citations |
|---|---|---|
| BiomedCLIP* | Imaging + language | 498 |
| Quilt-1M* | Pathology + language | 216 |
| ESM3 | Protein sequences | 201 |
| Evo-2 | DNA / RNA | 197 |
| Borzoi | Molecular sequences | 190 |
| MedGemma-27B | Natural language | 165 |
| Nicheformer* | Omics | 81 |
| OmiCLIP* | Imaging + omics | 58 |
Citation growth is being driven by models that integrate heterogeneous modalities rather than by specialists in a single data type. Four of the eight risers are multimodal.
Resolution · Gaps and outlook · Content 3 / 3
The Integrations Nobody Has Built Yet three openings, one shared bottleneck
Mechanistic interpretability
Language ↔ sequence and omics
- A language interface could assist scRNA-seq annotation, pathway enrichment and spatial transcriptomics.
Therapeutic targets
Imaging ↔ omics
- Integration of H&E pathology with omics remains weak.
- The potential to link tissue morphology to molecular mechanism is considerable.
Regulatory layers
DNA, RNA, protein, epigenome
- The layers are only loosely connected, protein to the others most of all.
The bottleneck is not ideas
What blocks this is not a shortage of concepts but the state of the data: paired datasets are scarce, preprocessing and annotation are not standardised, and there is no standard multimodal benchmark. It is the same cause that explains the scarcity of decoders earlier.
What Gets a Model Adopted and what still stands in the way
- It addresses a high-impact application: clinical language processing, protein modelling, digital pathology.
- It is rigorously evaluated: testing across varied downstream tasks builds trust and reuse.
- It is accessible: open pretrained weights, open code, a usable interface.
- And newly decisive: it fits into agent-based AI workflows.
Still unsolved
Data quality, cohort diversity, batch effects, privacy, hallucination and adversarial robustness all still limit real-world deployment. The authors recommend cross-disciplinary collaboration — biologists, clinicians and model developers together — and efficient adaptation of strong pretrained backbones in place of training from scratch.