Sovereign 8s.is mirror of standardgalactic/TPHATE
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2025-11-11 10:43:50 -08:00
data package using poetry 2023-02-12 17:12:45 -05:00
docs Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
examples Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
test Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
tphate Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
.gitignore adding dist; update gitignore 2023-04-26 14:56:08 -04:00
LICENSE.md Updated Yale license 2024-08-19 13:16:59 -04:00
pyproject.toml Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
README.md update badge 2025-02-21 13:54:38 -05:00
requirements.txt Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
setup.cfg bumping version 2025-02-21 14:14:56 -05:00
setup.py Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00
verify_release.py Release v1.2.1: Remove unnecessary PHATE/SCPREP dependencies 2025-11-11 10:43:50 -08:00

PyPI versionDOI

Quick Start

If you would like to get started using T-PHATE, check out our example below.

If you have loaded a data matrix data in python (with samples on rows, features on columns, where you believe the samples are non-independent), you can run TPHATE as follows:

import tphate

tphate_op = tphate.TPHATE()
data_tphate = tphate_op.fit_transform(data)

Temporal PHATE

Temporal PHATE (T-PHATE) is a python package for learning robust manifold representations of timeseries data with high temporal autocorrelation. TPHATE does so with a dual-kernel approach, estimating the first view as an affinity matrix based on PHATE manifold geometry, and the second view as summarizing the transitional probability between two timepoints based on the autocorrelation of the signal. For more information, see our publication in Nature Computational Science.

Busch, et al. Multi-view manifold learning of human brain-state trajectories. 2023. Nature Computational Science.

Installation

pip install tphate