Leiden clustering requires additional packages.
Users need the optional leiden extra with pip or Hatch, or must install the graph and Leiden dependencies separately when using conda.
Evidence source ↗S
Scanpy
Scanpy is an open-source Python toolkit for single-cell gene-expression analysis, covering preprocessing, visualization, clustering, trajectory inference and differential expression.
6 key claims verifiedOur editorial team checked this profile against vendor documentation, product documentation, supporting sources. Supported by 4 documented sources.
Editorial overview
Aggregated Overview
The documented toolkit spans common single-cell analysis stages and provides a public Python API. It is free to use, but installation involves a Python environment and dependencies; large-data support through Dask is described as experimental. No third-party review ratings were verified.
This profile combines documented product information and independent evidence where available. It is not a hands-on test unless TechZella explicitly identifies one.
Overview
Scanpy is a Python toolkit for analyzing single-cell gene-expression data. Its documented workflow covers preprocessing, visualization, clustering, trajectory inference and differential-expression testing.
The package works with AnnData and belongs to the scverse ecosystem. That shared data structure supports passing analysis objects to compatible packages such as scvi-tools and Squidpy.
Scanpy is installed in a user’s Python environment rather than provided as a hosted service. Its Dask-compatible functions may help with larger-than-memory workflows, but the documentation marks this support as experimental.
Scanpy Decision Snapshot
A quick way to understand who this product may suit, where its limits matter, and which facts are most relevant before you compare alternatives.
Best suited to
Research teams and computational biologists using Python to analyze single-cell gene-expression data through preprocessing, visualization, clustering and differential expression.
Look elsewhere if
Teams seeking a standalone graphical application, vendor-hosted service or turnkey workflow may find Scanpy’s Python-library and environment-based setup mismatched to their needs, and should evaluate alternatives such as Seurat or scvi-tools instead.
Platforms
Linux, macOS, Python, Windows
TechZella assessment
6.8/10
Scanpy — What Sets It Apart?
These are the product-specific differences that may matter when deciding whether the software fits your workflow. They are based on documented evidence rather than a universal ranking.
- Uses AnnData as its core annotated-data structure, enabling exchange with packages in the scverse ecosystem.
- Combines preprocessing, visualization, clustering, trajectory inference and differential-expression methods in a documented Python API.
- Offers Dask-compatible paths for some workflows, while its documentation cautions that large-data support is experimental.
Scanpy Pros & Cons
Pros
- Covers multiple common single-cell analysis stages in a Python toolkit.
- Uses AnnData, which is shared across scverse packages.
- Has a documented public API and extensive installation and tutorial documentation.
- Is distributed under the BSD-3-Clause license.
Cons
- Requires Python environment setup and management of package dependencies.
- Leiden clustering needs additional packages.
- Dask compatibility is experimental rather than a blanket guarantee across the toolkit.
- Undocumented internal APIs are not guaranteed to remain stable.
Scanpy Gotchas & Operational Limits
These are documented constraints or practical friction points that may matter before you adopt the product.
Dask compatibility is experimental.
Teams planning out-of-memory analysis should verify that the functions in their specific workflow support Dask.
Evidence source ↗Undocumented internal APIs are not guaranteed to remain stable.
Pipelines that import internal modules may need changes across updates; the project documents its supported public API separately.
Evidence source ↗Scanpy Pricing & Plans
Open-source package
$0
free
Free software distributed under the BSD-3-Clause license. Compute, storage and optional dependencies are separate user-environment considerations.
Check current pricing →Pricing may change. Verify current plans on the vendor's website.
Scanpy Competitors & Alternatives
Compare similar products directly, then see which alternatives may make more sense when your requirements differ.
At a glance
Open Source Software| Decision factor | Scanpy | Seurat | scvi-tools |
|---|---|---|---|
| Primary programming environment | Python package with a documented public API. | R package; installation documentation requires R 4.0 or later. Source ↗ | Python package built around probabilistic models and PyTorch. Source ↗ |
| Core analytical scope | Preprocessing, visualization, clustering, trajectory inference and differential-expression testing. | Quality control, analysis and exploration of single-cell RNA-seq, with documented spatial and integration workflows. Source ↗ | Model-centered probabilistic analysis, including dimensionality reduction, integration, differential expression and automated annotation. Source ↗ |
| Data structure and ecosystem | Uses AnnData and interoperates with scverse packages using that shared structure. | Uses its R package workflow and offers separate integrations and companion packages such as Signac and SeuratWrappers. Source ↗ | Built on AnnData and documents interaction with Scanpy, Seurat and Bioconductor workflows. Source ↗ |
Only factors supported by the available research are shown. The comparison is descriptive, not a ranking.
Direct competitors
These products address broadly similar requirements. The descriptions focus on documented reasons a buyer might compare them with Scanpy.
scvi-toolsPrimary programming environment: Python package built around probabilistic models and PyTorch.
Scanpy Features
Preprocessing
- Cell and gene filtering
- Quality-control metrics
- Normalization and log transformation
- Highly variable gene selection
- Principal component analysis
- Batch-effect and data-integration methods
Analysis
- Neighbor graph construction
- Leiden and Louvain clustering
- Trajectory inference
- Differential-expression testing
- Doublet detection with Scrublet
Data and API
- AnnData-based analysis objects
- Documented public Python API
- H5AD and Zarr data access
- Optional Dask-compatible workflows
Scanpy Specifications
| Programming language | Python |
|---|---|
| Operating systems | Linux, macOS and Windows classifiers are listed on PyPI |
| License | BSD-3-Clause |
| Installation | pip and conda |
| API | Documented public Python API |
| Data structure | AnnData |
| Large-data support | Some functions support Dask; documentation describes this as experimental |
| Latest stable version checked | 1.12.5, released October 29, 2026 |
Deployment & System Footprint
Verified installation, hosting, administration, or environment details that can affect implementation.
| Installation or hosting | Install locally in a Python environment with pip or conda; the documentation also describes Docker as an option. Source ↗ |
|---|---|
| Operating systems | PyPI lists macOS, Windows and POSIX/Linux classifiers. Source ↗ |
Migration & Lock-In
Documented portability, standards, export, or switching considerations. No switching-cost score is shown unless the evidence supports one.
Data portability
Scanpy uses AnnData and documents reading and writing H5AD and Zarr formats. The shared AnnData structure is also used across scverse packages.
Evidence source ↗Our evidence-based assessment
TechZella Score
A proprietary editorial score based on product capabilities, usability, value, performance, support and user sentiment evidence.
6.8/10Moderate confidence
The documented toolkit spans common single-cell analysis stages and provides a public Python API. It is free to use, but installation involves a Python environment and dependencies; large-data support through Dask is described as experimental. No third-party review ratings were verified.
Methodology v1.0. The assessment weighs feature coverage (25%), ease of use (15%), value for money (20%), performance (15%), support (10%) and user sentiment (15%), using researched product evidence and verified review evidence where available. It is a TechZella editorial assessment, not a direct user-review average.
Editorial transparency
Our Review Methodology
Key claims are linked to the sources used to verify them. This evidence record is separate from third-party user ratings.
TechZella evaluates software using documented product capabilities, pricing information, usability and value considerations, independent user evidence where available, and competitive context. The assessment is an editorial review, not a hands-on test unless one is explicitly identified. Our editorial assessment is based on 4 documented sources.
What TechZella adds
- Uses AnnData as its core annotated-data structure, enabling exchange with packages in the scverse ecosystem.
- Combines preprocessing, visualization, clustering, trajectory inference and differential-expression methods in a documented Python API.
- Offers Dask-compatible paths for some workflows, while its documentation cautions that large-data support is experimental.
Important limitations
- Scanpy is a Python package, so users need a compatible Python environment and must manage its dependencies.
- Dask compatibility is experimental, and not every function is documented as Dask-compatible.
- Some popular functions, including Leiden clustering, require optional dependencies rather than the base installation.
Evidence-backed claimsScanpy provides methods for preprocessing, visualization, clustering, trajectory inference and differential-expression testing. Scanpy is built jointly with AnnData and is part of the scverse project. The current stable PyPI release is Scanpy 1.12.5, published October 29, 2026. Scanpy is distributed under the BSD-3-Clause license. Scanpy's installation guide documents pip and conda installation, and identifies additional dependencies for Leiden clustering. The documentation describes Dask support as experimental.
The official documentation describes these as included capabilities.
View source ↗Verified 2026-11-11The project documentation identifies AnnData as the paired data framework and Scanpy as part of scverse.
View source ↗Verified 2026-11-11PyPI's release history lists 1.12.5 on October 29, 2026 and separately identifies 1.13.0b1 as a prerelease.
View source ↗Verified 2026-11-11The project metadata and repository license identify BSD-3-Clause.
View source ↗Verified 2026-11-11The guide provides both installation routes and explains the extra packages required for this clustering option.
View source ↗Verified 2026-11-11The official overview states that many functions are Dask-compatible for datasets that exceed memory, with an experimental-status warning.
View source ↗Verified 2026-11-11Scanpy FAQs
Answers begin with the clearest available response, followed by the context that helps you act on it.
Is Scanpy free?
Yes. It is distributed under the BSD-3-Clause license and is available as a Python package.
Does Scanpy have a free trial?
No. A trial is not applicable to the listed package: Scanpy is freely installable open-source software, not a subscription service.
What programming language does Scanpy use?
Scanpy is a Python toolkit with a documented public API.
Can Scanpy analyze datasets larger than memory?
Some functions are compatible with Dask for such workflows, but the documentation labels this support experimental.
Does Scanpy include Leiden clustering in the base installation?
The installation guide says Leiden clustering needs additional packages, available through the documented optional extra or installed separately with conda.
Community feedback
Reviews
No reviews yet. Be the first to share your experience.
Write a Review
Please log in to submit a review.