Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
HomeTop ChartsExploreCategories
TypesWeb apps1,894Agents585Plugins416APIs376Mobile apps152Datasets85
AdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise hereAdvertisingYour product hereReach people browsing AI tools on Ploba.Advertise here
  1. Explore
  2. /
  3. Developer Tools
  4. /
  5. Universal Cell Embeddings
Developer Tools
Universal Cell Embeddings icon

Universal Cell Embeddings

by Arc Institute

Universal Cell Embeddings is a PyTorch implementation of the UCE model for embedding single-cell RNA sequencing datasets. It adds a cell embedding to each cell in an AnnData file.

Web app·Free

View on GitHub(opens in a new tab)

About Universal Cell Embeddings

Key features of Universal Cell Embeddings

  • Embeds scRNA-seq datasets in AnnData format
  • Adds embeddings to the AnnData obsm slot
  • Pretrained 4 layer model by default
  • Optional 33 layer model from the paper
  • Species option
  • Batch size setting per GPU
  • Automatic download of required model files
  • Processed datasets and analysis code linked

Who Universal Cell Embeddings is for

  • Single-cell genomics researchers
  • Machine learning researchers working with cell embeddings

How to use Universal Cell Embeddings

  1. 1

    Step 1: Install the dependencies with pip install -r requirements.txt.

  2. 2

    Step 2: Prepare an h5ad file with counts and gene names as variable names.

  3. 3

    Step 3: Run the eval_single_anndata.py script with your data path, output directory, species, model location and batch size.

  4. 4

    Step 4: Use the nlayers option to run the larger model if you downloaded it.

  5. 5

    Step 5: Read the embeddings from the X_uce slot of the output AnnData.

Universal Cell Embeddings FAQ

What input does it need?

An h5ad file where the main matrix holds scRNA-seq counts and the variable names are gene names rather than Ensembl IDs.

Where do the embeddings end up?

In the obsm slot named X_uce of the output AnnData file, saved in your working directory.

Can I mix embeddings from both models?

No. Embeddings from the 33 layer model are not compatible with those from the 4 layer model.

How do I set the batch size?

It is per GPU. The README suggests 25 for the 33 layer model and 100 for the 4 layer model on an 80GB GPU.

Details

Pricing
Free
Type
Web app
Platforms
  • CLI
Categories
Developer ToolsResearch
Added
Sep 16, 2026
Arc Institute iconPublisherArc Institute

Built from public sources

We put this page together from Universal Cell Embeddings’s own website and docs so you can compare it with other tools. Ploba isn’t affiliated with Universal Cell Embeddings.

Work at Universal Cell Embeddings? Claim the listing to manage it yourself.

Something wrong here?

More from Arc Institute

View publisher
Evo 2 iconEvo 2Arc Institute · FreeEvo 2 is a genomic foundation model from Arc Institute for prediction and design across DNA, RNA and proteins. It models sequences at single-nucleotide resolution.Developer Tools · FreeEvo iconEvoArc Institute · FreeBiological foundation model for sequence generation and prediction across DNA, RNA, and protein-related genomic tasksDeveloper Tools · Free

Related tools

See more
Devin Ask iconDevin AskCognition · SubscriptionDevin Ask uses AI for codebase research interface for asking technical questions and tracing answers across large repositories.Developer Tools · SubscriptionMatGL iconMatGLMaterials Virtual Lab · FreeGraph deep-learning library for materials science with pretrained interatomic potentials and property-prediction modelsDeveloper Tools · FreeArize AX iconArize AXArize AI · FreemiumArize AX is an AI-focused web app for developer tools workflows, giving users practical model-powered capabilities through a dedicated product or developer interface.Developer Tools · Freemium