Manifold Learning Python Packages

palantir

Single cell trajectory detection

minisom

:red_circle: MiniSom is a minimalistic implementation of the Self Organizing Maps

phate

PHATE (Potential of Heat-diffusion for Affinity-based Transition Embedding) is a tool for visualizing high dimensional data.

torchdr

TorchDR - PyTorch Dimensionality Reduction

cellrank

CellRank: dynamics from multi-view single-cell data

manifolds-rs

Various embedding methods such as UMAP, tSNE, diffusion maps etc. implemented in Rust. Now with Python bindings

manifold-genetics

An end-to-end pipeline from PLINK genotypes to publication-ready visualizations.

neembed-geoopt

Fine-tune Sentence Transformers with Geoopt for hyperbolic and mixed-curvature embeddings, semantic retrieval, and hierarchy-aware learning.

topometry

Systematically learn and evaluate the latent geometry of high-dimensional data, with a focus on scRNAseq analysis

pytorch-bsf

PyTorch implementation of Bezier simplex fitting

dreimac

Dimensionality Reduction with Eilenberg-MacLane Coordinates

snpmanifold

Manifold learning for single-cell single-nucleotide genetic variations

pressio4py

Python bindings to pressio

mlx-vis

Pure MLX implementations of UMAP, t-SNE, PaCMAP, TriMap, DREAMS, CNE, MMAE, and NNDescent for Apple Silicon. Metal GPU for computation and video rendering.

cub-tools

A set of notebooks as a guide to the process of fine-grained image classification of birds species, using PyTorch based deep neural networks.

embedding-condensation

[𝗜𝗖𝗠𝗟 𝟮𝟬𝟮𝟲] Dispersion loss counteracts embedding condensation and improves generalization in small language models

jaxsne

A library for doing dimensionality reduction with different curvature

vitali

Multiscale geometric analysis of point clouds: geometric multi-resolution analysis and diffusion wavelets, in Rust, with Python bindings and a MATLAB bridge

pamona

The software of Pamona, a partial manifold alignment algorithm.

heatgeo

Embedding with the Heat-geodesic dissimilarity

dse-dsmi

[ICMLW 2023, IEEE CISS 2024] Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy

topometry-nosc

An independently maintained, heavily modified fork of TopOMetry: geometry-first topological dimensionality reduction and manifold learning.

miaaim-python

MIAAIM: Multi-omics Image Alignment and Analysis by Information Manifolds