Skip to main content
M-Optimus is a multimodal, multi-scale foundation model. The current generation, M-Optimus-1 (M1), learns across three biological layers at once — H&E pathology, bulk RNA-seq, and spatial transcriptomics — to build a unified representation of a patient across tissue and molecular scales. Its headline capability is predicting spatial gene expression directly from a routine H&E tile, across up to 6,002 genes, optionally refined with bulk RNA-seq — recovering an expensive molecular readout from a low-cost slide. M-Optimus also produces the same 1536-d tile embeddings as H-Optimus. It is trained on proprietary multimodal cohorts, powered by the STELA data engine.

​
What makes it different

Where H-Optimus stops at features, M-Optimus adds a prediction head over a defined set of output genes. Provide a tile and (optionally) a bulk RNA vector, and it returns predicted expression per output gene — which you can render as spatial heatmaps. Because it is multimodal at both training and inference, it can ingest H&E alone or H&E + bulk RNA, with no retraining needed to benefit from the extra modality.
EPCAM overlay predicted from H&E: with bulk RNA vs image only

​
Performance

Results below are from the M-Optimus-1 report; rankings and metrics are task- and dataset-dependent.
ResultFinding
Spatial gene expression from H&E+60% vs. DeepSpot, a leading H&E→ST model (~30% from proprietary pretraining data, ~30% from the multimodal method)
Adding bulk RNA at inference+4% over H&E-only, with no retraining (late-binding)
HEST (gene expression from histology)0.440 avg. Pearson vs. 0.423 for H-Optimus-1
Classification (mean AUC, 9 tasks)0.664 vs. 0.661 for H-Optimus-1 — matches the image-only SOTA while adding molecular prediction
Generalist vs. specialists+8% on colon and head & neck vs. indication-specific models; strong zero-shot generalization to unseen tissues (e.g. kidney, skin)

​
Modes

  • Endpoint: POST /api/predict/m-optimus
  • Input: 224×224 tile at 0.5 µm/px, plus optional bulk_rna aligned to the model’s input gene set. Omitting bulk RNA uses a zero vector (H&E-only mode).
  • Output: predicted expression for each output gene.
  • Gene sets are available at GET /api/metadata/m-optimus.
The SDK aligns and reorders your bulk RNA to the model’s input gene set automatically. See Add bulk RNA for the full input contract and transform pipeline.

​
Specifications

PropertyValue
TasksSpatial gene-expression prediction (spot-level); tile embedding
GenesUp to 6,002 (model’s defined output set; see GET /api/metadata/m-optimus)
Input224×224 RGB tile at 0.5 µm/px (+ optional bulk RNA)
Bulk RNA inputTPM-normalized expression values, Ensembl gene IDs
Bulk RNA transformsServer-side: log1p on input, expm1 on output
Embedding1536-d
SageMaker dispatchmodel_name: "m-optimus"
Recommended instanceml.g5.xlarge

​
What you can build

M-Optimus turns routine slides into a molecular map for translational research:

Biomarker discovery

Surface candidate biomarkers and molecular signatures from H&E at scale.

Patient stratification & trials

Enrich and stratify cohorts; analyze legacy trial slides retrospectively.

​
Access & deploy

M-Optimus is available now by request. Contact Bioptimus to discuss access, then deploy on AWS SageMaker or on-premise — see the Deployment overview for setup steps.
M-Optimus is not available on Hugging Face. For academic-only H&E feature extraction, use H-Optimus on Hugging Face.

​
Guides

Spatial transcriptomics

Predict spatial gene expression end to end.

Cohorts

Run a model over many slides.