OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Scvi Tools

Scvi Tools is a Python library for probabilistic modeling and analysis of single-cell, multi-omics and spatial omics data, built on PyTorch and AnnData.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Scvi Tools — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Scvi Tools when a Python-based probabilistic modeling workflow is needed for single-cell or spatial omics analysis, or when developing a new model in this area.

Who it is for

  • Researchers analyzing single-cell, multi-omics or spatial omics datasets.
  • Developers creating novel probabilistic models for omics research.

Documented uses

  • Reduce the dimensionality of single-cell data.
  • Integrate data and perform automated annotation or factor analysis.
  • Detect doublets in single-cell datasets.
  • Apply spatial deconvolution models.
  • Develop and deploy novel probabilistic models using the library’s building blocks.
Before you choose

Requirements & limits

The project provides pip and conda installation instructions and identifies its repository license as BSD-3-Clause.

  • The core stack uses PyTorch and AnnData, with model APIs that interact with Scanpy.
  • GPU acceleration is listed among the model API capabilities; GPU users should select a compatible PyTorch version.
  • PyTorch Lightning and Pyro are among the frameworks used to power model-development building blocks.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install scvi-tools with pip or conda

Install the scvi-tools package using one of the documented package managers.

Before you start

  • Python package environment with pip or conda available.
  • If using GPU acceleration, install a PyTorch version compatible with the GPU.

Steps

  1. Choose pip or conda as the package manager.

  2. For pip, run the command below; for conda, run conda install scvi-tools -c conda-forge.

    Documented command
    pip install scvi-tools

  3. If applicable, ensure the installed PyTorch version is compatible with your GPU.

Expected outcome

The README provides commands to install scvi-tools through pip or conda.

Guide limitations

  • These steps cover installation only; they do not describe executing an analysis.
  • No installation verification procedure is specified.
  • GPU compatibility is noted, but no specific PyTorch version is provided.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
scverse/scvi-tools · Official homepage title · retained in its source language
How we review sourcesSuggest a correction