phate

PHATE is a tool for visualizing high dimensional data. In particular, PHATE is well-suited for visualizing data with natural progressions or trajectories such as single-cell data. PHATE uses a novel conceptual framework for learning and visualizing the manifold inherent to the system in which smooth transitions mark the progressions of data points (e.g. cells) from one state to another. To see how PHATE can be applied to datasets such as facial images and single-cell data from human embryonic stem cells, check out our preprint on BioRxiv.

PHATE has been implemented in Python >=3.5, R and MATLAB.

Python installation and dependencies

Installation with pip

The Python version of PHATE can be installed using:

pip install --user phate

Installation from source

The Python version of PHATE can be installed from GitHub by running the following from a terminal:

git clone --recursive git://github.com/KrishnaswamyLab/PHATE.git
cd Python
python setup.py install --user

Quick Start

If you have loaded a data matrix data in Python (cells on rows, genes on columns) you can run PHATE as follows:

import phate
phate_op = phate.PHATE()
data_phate = phate_op.fit_transform(data)

PHATE accepts the following data types: numpy.array, scipy.spmatrix, pandas.DataFrame and anndata.AnnData.

Usage

PHATE has been implemented with an API that should be familiar to those with experience using scikit-learn. The core of the PHATE package is the PHATE class which is a subclass of sklearn.base.BaseEstimator. To get started, import phate and instantiate a phate.PHATE() object. Just like most sklearn estimators, PHATE() objects have both fit() and fit_transform() methods. For more information, check out our notebook below.

If you want to try running our test script on a DLA fractal tree, run the following in a Python interpreter:

import phate
tree_data, tree_clusters = phate.tree.gen_dla()
phate_operator = phate.PHATE(k=15, t=100)
tree_phate = phate_operator.fit_transform(tree_data)
phate.plot.scatter2d(phate_operator, c=tree_clusters) # or phate.plot.scatter2d(tree_phate, c=tree_clusters)
phate.plot.rotate_scatter3d(phate_operator, c=tree_clusters)

Jupyter Notebooks

A demo on PHATE usage and visualization for single cell RNA-seq data can be found in this Jupyter notebook. A second tutorial is available here which works with the artificial tree shown above in more detail. You can also access interactive versions of these tutorials on Google Colaboratory: single cell RNA seq, artificial tree.

Help

If you have any questions or require assistance using PHATE, please contact us at https://krishnaswamylab.org/get-help

Metadata

Release files for phate 0.3.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for phate 0.3.1
File	Size	Uploaded
phate-0.3.1.tar.gz	24.4 kB	Dec 22, 2018	Details

Built distributions (wheels)

Table of built distributions (wheels) for phate 0.3.1
File	Interpreter	ABI	Platform	Reset
phate-0.3.1-py3.7.egg 52.5 kB Dec 22, 2018	Legacy Egg format	-	-	Details
phate-0.3.1-py3.6.egg 52.5 kB Dec 22, 2018	Legacy Egg format	-	-	Details
phate-0.3.1-py3.5.egg 53.2 kB Dec 22, 2018	Legacy Egg format	-	-	Details
phate-0.3.1-py3-none-any.whl 25.2 kB Dec 22, 2018	Python 3	none	any	Details

Total release size: 207.8 kB

Release files / phate-0.3.1.tar.gz

Download URL	phate-0.3.1.tar.gz
Size	24.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`a6bb5c85f74b148edf9676ca1f87bf1a9f9ae204631179f5e60f02b65659cd69`
BLAKE2b-256 checksum How to use checksums	`f2dbfef9395cc6eae6f8be7be9d6f86742269fceca550a0f3f83beec8ba3c4d6`
Upload date	Dec 22, 2018
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/1.12.1 pkginfo/1.4.2 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.6.3`

Release files / phate-0.3.1-py3.7.egg

Download URL	phate-0.3.1-py3.7.egg
Size	52.5 kB
Tags	Egg
SHA-256 checksum How to use checksums	`dd4c94f4f7386e1d1d3cb6390fc2ca529ed850aa80dbad5ae5a65d1732048677`
BLAKE2b-256 checksum How to use checksums	`43f66b944b6018cfc5ad5e85c2996bed1361cd64c38b044a1437ba7a837b46cd`
Upload date	Dec 22, 2018
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/1.12.1 pkginfo/1.4.2 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.7.0a4+`

Release files / phate-0.3.1-py3.6.egg

Download URL	phate-0.3.1-py3.6.egg
Size	52.5 kB
Tags	Egg
SHA-256 checksum How to use checksums	`39ede7f6e2caabe70d0882227f3162b0098fcaf67d7e527ce13ce13e7844cc6e`
BLAKE2b-256 checksum How to use checksums	`73a289463908e61bde2dd7f1d5cadd4a042d29140a87b7effa2ff510b343a2c0`
Upload date	Dec 22, 2018
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/1.12.1 pkginfo/1.4.2 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.6.3`

Release files / phate-0.3.1-py3.5.egg

Download URL	phate-0.3.1-py3.5.egg
Size	53.2 kB
Tags	Egg
SHA-256 checksum How to use checksums	`0dc51d6973ea339d172811aa31ca05a583b41093447a8c9aa2a33e13cee11bb1`
BLAKE2b-256 checksum How to use checksums	`b8ef6c8d1142a9fd206b9d7144f9b1ff8f8777b408075b3c04d5c938796da360`
Upload date	Dec 22, 2018
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/1.12.1 pkginfo/1.4.2 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.5.6`

Release files / phate-0.3.1-py3-none-any.whl

Download URL	phate-0.3.1-py3-none-any.whl
Size	25.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`46ff088a50f69fc9d4f31fb0b76625f5e22a61dddf13988750031a257b19f84f`
BLAKE2b-256 checksum How to use checksums	`a7ece386f2da0e5d24ec1c4c20e3684f55fc919dee187116d402d9035c3fca85`
Upload date	Dec 22, 2018
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/1.12.1 pkginfo/1.4.2 requests/2.21.0 setuptools/40.6.3 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.6.3`