# Bioptimus Documentation ## Docs - [H-Optimus (H1) tile embedding](https://docs.bioptimus.com/api-reference/embedding/h-optimus-h1-tile-embedding.md): Compute H1 tile embeddings. Input: a 224×224 tile at 0.5 MPP. Output: a 1536-dimensional embedding vector in `output`. - [M-Optimus tile embedding](https://docs.bioptimus.com/api-reference/embedding/m-optimus-tile-embedding.md): Compute M-Optimus tile embeddings. Input: a 224×224 tile at 0.5 MPP. Output: an embedding vector in `output`. - [API reference](https://docs.bioptimus.com/api-reference/introduction.md): The Bioptimus Model Server REST API and SageMaker dispatch. - [M-Optimus gene sets](https://docs.bioptimus.com/api-reference/prediction/m-optimus-gene-sets.md): Returns the ordered input and output gene sets used by the M-Optimus model. - [M-Optimus spatial gene expression prediction](https://docs.bioptimus.com/api-reference/prediction/m-optimus-spatial-gene-expression-prediction.md): Predict spatial gene expression from a tile and optional bulk RNA counts. Input: a 224×224 tile at 0.5 MPP, plus an optional `bulk_rna` vector aligned to the model's input gene set (see GET /api/metadata/m-optimus). When `bulk_rna` is omitted, a zero vector is used (H&E-only mode). Output: predicted… - [Tissue segmentation](https://docs.bioptimus.com/api-reference/prediction/tissue-segmentation.md): Generate a tissue segmentation mask for a tile. Input: a 512×512 tile at 8.0 MPP. Output: a flattened binary mask (0/1) of length H×W in `output`. - [Health check](https://docs.bioptimus.com/api-reference/service/health-check.md): Returns 200 with the loaded model list when the server is ready. Returns 503 with a status reason while loading or if the GPU/CUDA context is unavailable. - [SageMaker dispatch endpoint](https://docs.bioptimus.com/api-reference/service/sagemaker-dispatch-endpoint.md): SageMaker-compatible endpoint. Accepts a SageMakerRequest (ModelRequest plus `model_name` and `mode`) to route to the correct model and mode. Used by the SDK's AWS backend. - [Service discovery](https://docs.bioptimus.com/api-reference/service/service-discovery.md): Returns links to the interactive docs and the OpenAPI schema. - [Changelog](https://docs.bioptimus.com/changelog/changelog.md): Product and model release notes. - [Deployment overview](https://docs.bioptimus.com/deployment/deployment/overview.md): Choose the right way to access Bioptimus models. - [Requirements](https://docs.bioptimus.com/deployment/deployment/requirements.md): Prerequisites for each deployment option. - [Validation & acceptance testing](https://docs.bioptimus.com/deployment/deployment/validation.md): Verify a deployment produces correct, expected outputs. - [AWS & SageMaker](https://docs.bioptimus.com/deployment/platforms/aws-sagemaker.md): Deploy a Bioptimus model from AWS Marketplace to a SageMaker endpoint. - [Hugging Face](https://docs.bioptimus.com/deployment/platforms/hugging-face.md): Load H-Optimus-1 weights directly for non-commercial academic research. - [On-premise](https://docs.bioptimus.com/deployment/platforms/on-premise.md): Load, run, and verify the Bioptimus Model Server container in your own environment. - [How it works](https://docs.bioptimus.com/documentation/concepts.md): The core concepts behind Bioptimus models, for technical and non-technical readers. - [Welcome](https://docs.bioptimus.com/documentation/introduction.md): Deploy and build with foundation models for biology — across histology, transcriptomics, and genomics. - [Benchmarks](https://docs.bioptimus.com/documentation/models/benchmarks.md): Independent benchmark results for Bioptimus pathology models. - [Choosing a model](https://docs.bioptimus.com/documentation/models/choosing-a-model.md): H-Optimus vs. M-Optimus vs. tissue segmentation — pick the right one. - [H-Optimus](https://docs.bioptimus.com/documentation/models/h-optimus.md): A vision foundation model for histology feature extraction. - [M-Optimus](https://docs.bioptimus.com/documentation/models/m-optimus.md): A multimodal, multi-scale foundation model that predicts spatial gene expression from histology. - [Tissue segmentation](https://docs.bioptimus.com/documentation/models/tissue-segmentation.md): Separate tissue from background before feature extraction. - [Quickstart](https://docs.bioptimus.com/documentation/quickstart.md): Pick your model and platform, then run your first inference. - [FAQ](https://docs.bioptimus.com/documentation/resources/faq.md): Common questions about deploying and using Bioptimus models. - [Glossary](https://docs.bioptimus.com/documentation/resources/glossary.md): Key terms used across Bioptimus documentation. - [Support](https://docs.bioptimus.com/documentation/resources/support.md): How to get help and request access. - [Drug target & biomarker discovery](https://docs.bioptimus.com/documentation/use-cases/biomarker-discovery.md): Predict drug target distribution, immune microenvironment, and stromal architecture from routine histology slides. - [Diagnostics & spatial biology](https://docs.bioptimus.com/documentation/use-cases/diagnostics-spatial-biology.md): Integrate histology, spatial transcriptomics, and genomics in a single pipeline. - [Indication expansion](https://docs.bioptimus.com/documentation/use-cases/indication-expansion.md): Identify the patient subsets and indications where a therapeutic is most likely to succeed. - [Use cases](https://docs.bioptimus.com/documentation/use-cases/overview.md): How teams apply Bioptimus models across drug development and diagnostics. - [Treatment response & trial design](https://docs.bioptimus.com/documentation/use-cases/treatment-response.md): Discover multimodal biomarker signatures that distinguish responders from non-responders. - [Inference facade](https://docs.bioptimus.com/guides/get-started/inference-facade.md): Configure the whole pipeline with one object — tissue masking, embeddings, predictions, and reproducible workspaces. - [SDK overview](https://docs.bioptimus.com/guides/get-started/sdk.md): The bioptimus Python SDK — installation and the two ways to use it. - [Visualizing results](https://docs.bioptimus.com/guides/get-started/visualizing-results.md): Load Zarr/HDF5/NPZ outputs and overlay gene expression or tissue masks. - [WSI reader](https://docs.bioptimus.com/guides/reference/wsi-reader.md): Read whole-slide images: pyramid levels, MPP, regions, and thumbnails. - [Cohorts](https://docs.bioptimus.com/guides/workflows/cohort.md): Run a model over a cohort of slides with shared tissue masks and a structured workspace. - [Tile embeddings & PCA](https://docs.bioptimus.com/guides/workflows/embeddings-pca.md): Extract tile embeddings (H-Optimus or M-Optimus) and visualize morphology with PCA. - [Spatial transcriptomics](https://docs.bioptimus.com/guides/workflows/spatial-transcriptomics.md): Predict spatial gene expression from an H&E slide with M-Optimus, end to end. ## OpenAPI Specs - [openapi](https://docs.bioptimus.com/openapi.json) ## Optional - [Website](https://www.bioptimus.com) - [GitHub](https://github.com/bioptimus) - [Knowledge Base](https://www.bioptimus.com/knowledge-base)