Getting Started

Data structures

These tutorials teach you how to work with scverse data structures. If you are new to Python and/or scverse, we recommend you read the "getting started" and "axes" tutorials first.

Axes in AnnData and MuData

In this tutorial we showcase operations on independent AnnData objects (scRNAseq matrix + metadata), demonstrating how various processing workflows can be stored in one MuData object.

Working with scverse objects in backed mode

In this tutorial, we demonstrate working with scverse data objects without loading full datasets. (AnnData and MuData are saved as .h5ad and .h5mu files)

Concatenation

In this notebook we showcase how to perform concatenation, meaning to keep all sub elements of each object, and stack these elements in an ordered way.

Concatenation of multimodal data

This tutorial shows how you can concatenate 2 MuData objects that may represent complementary slices of the same dataset or 2 modalities into one AnnData.

Getting started with AnnData

This tutorial helps you to explore the structure and content of single-cell data analysis results in a *.h5ad file using AnnData, Scanpy, and Python.

scRNA-seq

The following tutorials show show to analyze single-cell gene expression data.

Batch-effect removal with scvi-tools

In this tutorial, we demonstrate how to use scvi-tools to fit a model to single-cell count data, correct batch effects, and perform differential gene expression analysis.

Compositional analysis

This tutorial introduces compositional analysis at cell identity cluster level, based on known cell types or states affected by perturbations.

Pseudotemporal ordering

This tutorial show how a pseudotime can be constructed and compares different pseudotimes.

Perturbation modeling

This tutorial covers 3 approaches using single-cell perturbation data: Augur (identify affected cell types), scGen (predict transcriptional response), Mixscape (quantify CRISPR sensitivity).

RNA velocity

This tutorial guides you through how RNA velocity can be inferred from single cell RNA-seq data using scVelo.

Preprocessing, clustering and cell-type annotation

This fundamental tutorial covers common analysis steps: quality control, normalization, feature selection, dimensionality reduction, clustering, and cell-type annotation.

Pseudo-bulk differential expression and functional analysis

This notebook showcases decoupler for pathway and TF enrichment on ~5k Blood myeloid cells from healthy and COVID-19 infected patients.

Spatial

Analyze spatial data generated with different technologies

Spatial analysis with squidpy

This tutorial demonstrate how to use squidpy to analyse transcriptomics data with spatial resolution.

Spatial analysis at subcellular resolution

This tutorial shows how to use bentotools to study gene expression at subcellular resolution.

Adaptive immune cell receptor

Tutorials for analyzing single-cell B-cell and T-cell receptor sequencing data

Single-cell T-cell receptor analysis with scirpy

In this tutorial, we show how to perfrom QC on scTCR-seq data, define clonotype, cluster receptors by their sequence similarity and compute repertoire overlaps between patients.

Surface proteins

CITE-seq analyses

CITE-seq integration

These notebooks showcase CITE-seq analysis of PBMCs with dsb normalization, MOFA+ data integration, and weighted nearest neighbors handling multimodal embeddings.

ATAC-seq

Analyse chromatin accessibility data

Joint analysis of paired and unpaired multiomic data with MultiVI

This tutorial shows how to read multiomic data, create a joint object with paired/unpaired data, train MultiVI model, visualize latent space, and run differential analyses.

Processing chromatin accessibility

This chapter shows multimodal single-cell gene expression and chromatin accessibility analysis. In this notebook, scATAC-seq data processing is described.

Tips & Tricks

Useful tips for data analysis with scverse tools that are independent of specific packages.

Plotting in scanpy

This tutorial explores the visualization possibilities of scanpy, including embeddings and the visualization of marker genes and differentially expressed genes.

Advanced plotting

This tutorial explains how to customize matplotlib plots generated by scanpy or other scverse libraries.

Interoperability

This document lists resources for conversion to other data formats and programming languages, e.g. R, Julia, ...