pavlin-policar/openTSNE

Health v2 · maintenance only

Adoption not part of the score

1621 stars · 176 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

openTSNE is a modular Python library implementing t-Distributed Stochastic Neighbor Embedding (t-SNE) for visualizing high-dimensional data. It includes parallelized, fast implementations that scale to millions of points and supports adding new data points to existing embeddings.

Use cases

• visualize high-dimensional datasets in 2D
• embed single-cell transcriptomics data
• reduce dimensionality of large datasets with millions of points
• add new data points to an existing t-SNE embedding
• preserve global structure in t-SNE visualizations
• speed up t-SNE with parallel computation

When to choose

• you need a fast, scalable t-SNE implementation in Python
• you want to transform new data into an existing embedding
• you work with large datasets like single-cell RNA-seq
• you need better global alignment of t-SNE clusters

When to avoid

• you need general-purpose dimensionality reduction like PCA or UMAP alternatives
• you need GPU-accelerated t-SNE specifically
• you need a non-Python environment

Facets

library · maturity stable

machine-learning data-visualization math machine-learning data-visualization data-science python cross-platform tsne dimensionality-reduction embedding parallel-computing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="pavlin-policar/openTSNE")