scverse/scvi-tools

Deep probabilistic analysis of single-cell and spatial omics data

What it solves

scvi-tools provides a framework for the probabilistic modeling and analysis of single-cell omics data. It addresses the challenge of extracting meaningful biological insights from complex, high-dimensional single-cell data across single, multi, and spatial omics modalities.

How it works

Built on PyTorch and AnnData, the library implements a variety of deep generative models (variational inference) that can be applied to biological data. It utilizes PyTorch Lightning and Pyro to provide a scalable architecture for developing and deploying new probabilistic models. The package includes a high-level API that integrates with Scanpy for seamless data analysis workflows.

Who it’s for

Researchers and bioinformaticians working with single-cell omics data who need tools for dimensionality reduction, data integration, and automated annotation.

Highlights

  • Comprehensive Analysis Suite: Supports tasks such as dimensionality reduction, data integration, automated annotation, factor analysis, doublet detection, and spatial deconvolution.
  • GPU Acceleration: Includes standard save/load functions and GPU support for processing large datasets.
  • Model Development Framework: Provides building blocks and a skeleton repository to help developers create and deploy novel probabilistic models.
  • Eco-system Integration: Deeply integrated with the scverse ecosystem, PyTorch, and PyTorch Lightning.

Related

  • Project
    TorchSpatiotemporal/tsl

    A PyTorch-based library for neural spatiotemporal forecasting that provides a unified framework for data preprocessing, model prototyping, and Graph Neural Network implementation.

  • Project
    pyro-ppl/pyro

    A deep probabilistic programming library built on PyTorch that allows users to create and scale universal probabilistic models for large datasets.

  • Project
    meta-pytorch/botorch

    A PyTorch-based library for Bayesian Optimization that provides a modular framework for composing probabilistic models and acquisition functions.

  • Project
    jacobgil/pytorch-grad-cam

    A PyTorch library for explainable AI in computer vision that provides a wide range of pixel attribution methods to visualize and diagnose model predictions.

  • Project
    SegmentationBLWX/sssegmentation

    A PyTorch-based supervised semantic segmentation toolbox providing a unified framework and extensive model zoo for training and testing segmentation algorithms.