ACTIONet single-cell analysis framework
Project description
Installation
Setting Up the Environment (Preinstallation)
For Linux Users
Verify that the cmake version you are using is >=3.19.
For the optimal performance on Intel-based architectures, installing Intel Math Kernel Library (MKL) is highly recommended. After installing, make sure MKLROOT
is defined by running the setvars script.
Install library dependencies
To install the ACTIONet
dependencie on debian-based linux machines, run:
sudo apt-get install libhdf5-dev libsuitesparse-dev libnss3 xvfb libblas-dev liblapack-dev cmake
Note: please use cmake>3.2 For Mac-based systems, you can use brew instead:
brew install hdf5 suite-sparse c-blosc blas lapack
Installing ACTIONet Python Package
Use pip
to install ACTIONet directly from this repository:
pip install git+https://github.com/shmohammadi86/ACTIONet@python-devel
To install from source: git clone --recurse-submodules https://github.com/shmohammadi86/ACTIONet.git make install
Running ACTIONet
Note If you are using MKL
, make sure to properly set the number of threads used prior to running ACTIONet
.
Example Run
Here is a simple example to get you started:
import urllib.request
import ACTIONet as an
import scanpy as sc
# Download example dataset from the 10X Genomics website
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib.request.install_opener(opener)
urllib.request.urlretrieve('http://cf.10xgenomics.com/samples/cell-exp/3.0.0/pbmc_10k_v3/pbmc_10k_v3_filtered_feature_bc_matrix.h5', 'pbmc_10k_v3.h5')
# Read and filter the data
adata = sc.read_10x_h5('pbmc_10k_v3.h5')
adata.var_names_make_unique(join='.')
an.pp.filter_adata(adata, min_cells_per_feature=0.01, min_features_per_cell=1000)
sc.pp.normalize_total(adata)
sc.pp.log1p(adata)
# Run ACTIONet
an.pp.reduce_kernel(adata)
an.run_ACTIONet(adata)
# Annotate cell-types
marker_genes, directions, names = an.tl.load_markers('PBMC_Monaco2019_12celltypes')
cell_labels, confidences, Z = an.tl.annotate_cells_using_markers(adata, marker_genes, directions, names)
adata.obs['celltypes'] = cell_labels
# Visualize output
an.pl.plot_ACTIONet(adata, 'celltypes', transparency_key='node_centrality')
# Export results
adata.write('pbmc_10k_v3.h5ad')
Visualizing results using cellxgene
The output of ACTIONet in the python implementation is internally stored as as AnnData
object, and R ACE
objects can be imported from/exported to AnnData
using functions AnnData2ACE()
and ACE2AnnData()
functions, respectively. AnnData
objects can be directly loaded into cellxgene package, an open-source viewer for interactive single-cell data visualization. cellxgene
can be installed as:
pip install cellxgene
Then to visualize the results of ACTIONet, run:
cellxgene launch pbmc_10k_v3.h5ad
where pbmc_10k_v3.h5ad is the name of the file we exported using adata.write()
function.
Additional tutorials
You can access ACTIONet tutorials from:
- ACTIONet framework at a glance (human PBMC 3k dataset)
- Introduction to the ACTIONet framework (human PBMC Granja et al. dataset)
- Introduction to cluster-centric analysis using the ACTIONet framework
- To batch correct or not to batch correct, that is the question!
- PortingData: Import/export options in the ACTIONet framework
- Interactive visualization, annotation, and exploration
- Constructing cell-type/cell-state-specific networks using SCINET
You can also find a step-by-step guide to learning the core functionalities of the ACTIONet framework.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Hashes for ACTIONet-0.4.1-py3.11-macosx-10.9-x86_64.egg
Algorithm | Hash digest | |
---|---|---|
SHA256 | 477a67032da2bf30f631f40a0623ca3a83404c7546b1469f85a020390d62dd40 |
|
MD5 | bad67685a0db13ce8b337f2b66b8c671 |
|
BLAKE2b-256 | a1f19fa20cc9e434f18f058b1759f591768c4f870d209d2d7294465b37a5704f |
Hashes for ACTIONet-0.4.1-py3.10-macosx-10.9-x86_64.egg
Algorithm | Hash digest | |
---|---|---|
SHA256 | 17fc8df436175f10247cb72458fd13a17eb980be6eac8f6d2d7f7402b27ea497 |
|
MD5 | 70c933802dad474ecf56db141b9c4983 |
|
BLAKE2b-256 | 0ba7b3f8b9198e122788f83e2822494137f10cdaac108b3c66ac1b5dc0c165d0 |
Hashes for ACTIONet-0.4.1-cp311-cp311-manylinux_2_35_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 569d2dff98d132d713a3489855e020e0a308154163dddafed224b05e0b67da2b |
|
MD5 | 3f9aa11afcd00d214a32b62dea4b52ae |
|
BLAKE2b-256 | 9903e0213312df8f149efb29bd372c1f009cac3ecd06cfb0f7e576312c7793c6 |
Hashes for ACTIONet-0.4.1-cp311-cp311-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8cef6c81ca50e41f390c1976fa1d562c9a7dc65d64572f6aab2c43d0b39cb1c1 |
|
MD5 | 2b1a249d06a58be85b42a28459ee48e5 |
|
BLAKE2b-256 | eb3ecf5bfdca0fdfb81cb62a63b0124af69dda9455d9dd01f9a84852fd6a3120 |
Hashes for ACTIONet-0.4.1-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5b52b42bf03a35c279d8aa90ae926034241ac9e981e5a24495681a925e5d9457 |
|
MD5 | bf5832af338688d4c649b4f020617f11 |
|
BLAKE2b-256 | 13654deea05db5e9904247cbb16514045d5ff34b60304161f129ade510ee1711 |
Hashes for ACTIONet-0.4.1-cp310-cp310-manylinux_2_35_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a12e5b32aa9b60c12f09399701e3904bb013865aaa6c40317086b51d69037795 |
|
MD5 | 4df022c6bf7149096607ee60a9de3e54 |
|
BLAKE2b-256 | e04bfe0060746b80ca330bb98b7a371f9596e69fc7648fbc3557ebf454a51c48 |
Hashes for ACTIONet-0.4.1-cp310-cp310-manylinux_2_31_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | efbab513ac9a210fa1d9386171af44c827e05711b12310cbb482343851157a82 |
|
MD5 | ffb923636c3c36ca63953ebee432fc3f |
|
BLAKE2b-256 | de9431aa91e431a825bef465028c67a3efe30a08be5c480e2837225be23d4ef6 |
Hashes for ACTIONet-0.4.1-cp310-cp310-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1ccfc0ecf61d599e4093543689564388143a569a2576b7d6ff765f8daf3707da |
|
MD5 | 2553ccd6554afae0eb121acf547cb491 |
|
BLAKE2b-256 | 0480518d6d1e764d21f86e8b029db7521e14fe833e8bbfb7e0759cb8baae51d5 |
Hashes for ACTIONet-0.4.1-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | bd2392a5233851e4aabee6bfcae5c1ebd4be5538c64d91f6cd759f1e193fbd93 |
|
MD5 | 5987b4d973ce25ad160fcb8c9302a6ff |
|
BLAKE2b-256 | 2cc1616433236399b6aea2a95b594dafac14347fa229525ccaa22a536cd85579 |
Hashes for ACTIONet-0.4.1-cp39-cp39-manylinux_2_35_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b57dcfdf4877daddb4f5f4e5584e668b386480d19a12671884a5f3f60c718316 |
|
MD5 | fa893f3ac0138bf73b87903e52f85921 |
|
BLAKE2b-256 | ed7326288c7fec4c403efeeb2398a998e0b718ffc345fffa0add905c4d043d5f |
Hashes for ACTIONet-0.4.1-cp39-cp39-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b8dbaf9279c915dd856305e050da1194306da2bbb10cf3734dbbf4477982b308 |
|
MD5 | 6aec6c6421ddb11f8e06bb90504f85b2 |
|
BLAKE2b-256 | 39cdbac3ffd0885c39d88f616819085de2074627ea1c8897b6570cebf4ce8ec1 |
Hashes for ACTIONet-0.4.1-cp38-cp38-manylinux_2_35_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1fc953a02db6d6ea80ba44e446a28457f1643fa74377d105407fa480d041eea3 |
|
MD5 | 5cb49a9cfb8a5988c923d531b10c87ff |
|
BLAKE2b-256 | e49528d588aa9bb77037fa65467df81c1f15dede806e743652e55b424004e8ee |
Hashes for ACTIONet-0.4.1-cp38-cp38-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5ca89303d26901342887414da84b1aa67ab51f48db9a57ee627b0f88ed357581 |
|
MD5 | 7d68fd9e35c4c27c701641785a110d2f |
|
BLAKE2b-256 | 332f42ba33f0813dda0d3b8d4ae67274c81c0d7dfa2ff5f7f706c3d64bbafeec |
Hashes for ACTIONet-0.4.1-cp38-cp38-macosx_10_9_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 85c89642b2bf3a1974c482d114bd6a33a1027c031f1ab5805bbec9b7d98263dc |
|
MD5 | f6cd074b9e0c981be5ed85a286bfbe87 |
|
BLAKE2b-256 | 9d5b7e0abefe123ed93b6a194304a5550ce25ebe1eef538b444cf1c0f9e95b3a |