How to install scvi-tools with GPU support?

Install via conda or pip, but first ensure PyTorch is installed with CUDA support for your GPU. The documentation provides detailed commands and troubleshooting tips to avoid compatibility issues.

scvi-tools vs Scanpy: which one should I use?

Scanpy is a general-purpose toolkit for single-cell analysis, while scvi-tools specializes in probabilistic and deep learning models. They are complementary; use scvi-tools for advanced modeling integrated with Scanpy workflows.

What kind of data can scvi-tools analyze?

It supports single-cell, multi-omics, and spatial omics data, using AnnData objects. Check the user guide for specific model requirements, such as data formats and preprocessing steps.

Is scvi-tools suitable for spatial transcriptomics analysis?

Yes, it includes models for spatial deconvolution and other spatial tasks, as mentioned in the key features. Refer to the documentation for tutorials on applying these to your datasets.

How do I cite scvi-tools in my publication?

Cite the Nature Biotechnology 2022 paper for the library, and include citations for specific models used. The README provides the full reference with DOI to ensure proper attribution.

Can I run scvi-tools without a GPU?

Yes, but performance will be slower, especially for large datasets. The package is optimized for GPU acceleration, so CPU usage is possible but not recommended for scalability.

totalVI

BSD-3-ClausePython1.4.2

A Python library for deep probabilistic modeling and analysis of single-cell and spatial omics data.

Visit Website

What is totalVI?

scvi-tools is a Python library for deep probabilistic analysis of single-cell and spatial omics data. It provides a suite of models for tasks like dimensionality reduction, data integration, and automated annotation, built on modern machine learning frameworks. The library addresses the need for scalable, reproducible analysis methods in computational biology.

Target Audience

Bioinformaticians, computational biologists, and data scientists working with single-cell or spatial omics data who need robust, probabilistic analysis tools. It's also suitable for researchers developing novel analysis methods in this domain.

Value Proposition

Developers choose scvi-tools for its comprehensive set of production-ready models, seamless integration with the Scanpy ecosystem, and GPU acceleration. Its modular design also allows for rapid development and deployment of custom probabilistic models.

Overview

Deep probabilistic analysis of single-cell and spatial omics data

Use Cases

Best For

Integrating single-cell datasets from multiple experiments or technologies

Related Projects

Community-curated · Updated weekly · 100% open source

Found a gem we're missing?

Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.

Submit a project Star on GitHub

GitHub

1.6k stars447 forks0 contributors

Performing dimensionality reduction on large-scale omics data

Automated cell type annotation in single-cell RNA-seq studies

Analyzing spatial transcriptomics data with deconvolution methods

Developing novel probabilistic models for omics data analysis

Detecting and removing doublets in single-cell sequencing data

Not Ideal For

Researchers who prefer graphical user interfaces (GUIs) for data analysis without any programming
Projects focused exclusively on bulk RNA-sequencing or non-omics biological data types
Teams with limited computational resources or no access to GPU hardware for acceleration

Pros & Cons

Pros

GPU-Accelerated Scalability

Built on PyTorch, scvi-tools leverages GPU acceleration to handle large-scale omics datasets efficiently, as emphasized in its focus on scalable, production-ready models.

Seamless Ecosystem Integration

Integrates tightly with Scanpy and AnnData, providing a high-level API that fits into standard single-cell analysis workflows, reducing adoption barriers for existing users.

Comprehensive Model Library

Offers a wide range of pre-implemented models for tasks like dimensionality reduction and data integration, saving time and effort for common analytical needs in omics research.

Modular Development Framework

Includes building blocks powered by PyTorch Lightning and Pyro, enabling rapid prototyping and deployment of novel probabilistic models, as highlighted in the skeleton repository for method development.

Cons

Complex Installation Process

Requires careful setup of PyTorch with GPU compatibility, which can be error-prone and challenging for users unfamiliar with deep learning environments, as noted in the installation instructions.

Steep Knowledge Barrier

Assumes proficiency in probabilistic modeling, deep learning, and single-cell biology, making it less accessible for beginners or researchers from non-computational backgrounds.

Domain-Specific Limitations

Primarily designed for omics data analysis, so it lacks general-purpose machine learning capabilities and is not suitable for other data types or broader biological applications.

Frequently Asked Questions

Home

Computational Biology

scGPT

scGPT is a foundation model designed for single-cell multi-omics data analysis using generative AI. It leverages transformer architecture pretrained on millions of single-cell profiles to enable a wide range of downstream biological tasks, advancing computational biology by providing a powerful, unified model for cellular data. ## Key Features - **Pretrained Model Zoo** — Offers multiple organ-specific and whole-human models trained on millions of cells for various applications. - **Zero-Shot Applications** — Supports tasks like cell embedding and reference mapping without task-specific training. - **Reference Mapping** — Enables fast similarity search across millions of cells using efficient indexing with faiss. - **Multi-Task Fine-Tuning** — Can be adapted for scRNA-seq integration, cell type annotation, perturbation prediction, and GRN inference. - **Online Tools** — Provides accessible web applications for reference mapping, cell annotation, and GRN inference via cloud GPUs. ## Philosophy scGPT aims to build a foundational AI model for single-cell biology, democratizing access to advanced computational methods and accelerating discoveries in multi-omics research through open-source collaboration.

Stars1,546

Forks329

Last commit5 months ago

#probabilistic-modeling

#data-integration

#deep-learning

#single-cell-analysis

Computational Biology122