scverse/pertpy

Single-cell perturbation analysis

What it solves

Pertpy provides a standardized framework for analyzing large-scale single-cell perturbation experiments. It addresses the complexity of understanding how cells respond to various stimuli—such as drug treatments, genetic modifications, and environmental changes—by providing tools to harmonize datasets and automate metadata annotation.

How it works

The library offers an end-to-end pipeline for perturbation analysis, including tools for calculating perturbation distances and analyzing cellular responses. It integrates several specialized tools and solvers, with optional JAX-backed components for advanced models like scCODA, CINEMA-OT, and scGen, as well as dedicated interfaces for differential gene expression and tascCODA.

Who it’s for

It is designed for researchers and bioinformaticians working with single-cell data to study the effects of biological perturbations.

Highlights

  • End-to-end framework: Covers the entire process from data harmonization to response analysis.
  • Diverse stimuli support: Analyzes responses to genetic, chemical, and environmental changes.
  • Automated annotation: Simplifies the process of labeling and organizing perturbation metadata.
  • Extensible ecosystem: Part of the scverse project, ensuring compatibility with other single-cell analysis tools.

Related

  • Project
    scverse/scanpy

    A scalable Python toolkit for analyzing single-cell gene expression data, supporting preprocessing, clustering, and trajectory inference for datasets with over a million cells.

  • Project
    scverse/scvi-tools

    A PyTorch-based library for probabilistic modeling and analysis of single-cell omics data, supporting tasks like dimensionality reduction and data integration.

  • Project
    rendeirolab/LazySlide

    A Python framework for whole slide image analysis in digital pathology that streamlines preprocessing, feature extraction with foundation models, and spatial analysis.

  • Project
    ArcInstitute/state

    A framework for predicting cellular responses to perturbations and generating cell embeddings to model biological state transitions.

  • Project
    galilai-group/stable-worldmodel

    A platform for reproducible world model research and evaluation that provides a unified interface for data collection, training, and model-predictive control evaluation.