cell2sentence: create cell sentences from sequencing data
Project description
cell2sentence
Reframing cells as sentences of genes, ordered by expression. Please read the manuscript on bioRxiv for methodological details and examples.
(https://www.biorxiv.org/content/10.1101/2022.09.18.508438)
Stable Setup
Install cell2sentence
from PyPI with
pip install cell2sentence
Convert Anndata Object to Cell Sentences
After your data is loaded into a standard AnnData adata
object, you may
create a cell2sentence object with:
import cell2sentence as cs
csdata = cs.transforms.csdata_from_adata(adata)
and generate a list of cell sentences with:
sentences = csdata.create_sentence_lists()
A tutorial script showing how to use pretrained word vectors to analyze
the pbmc3k
dataset used by Seurat and scanpy in their guided clustering
tutorials is available at
tutorials/pbmc3k_cell_sentences.py
Development Setup
Create a conda environment using python3
using
anaconda with:
conda create -n cell2sentence python=3.8
and activate the environment with
conda activate cell2sentence
finally, you can install the latest development version of cell2sentence
by
running
make install
which simply uses pip -e
.
Loading Data
All data used in the bioRxiv manuscript are publicly available, and details
are outlined in the DATA.md
file in this repository.
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 Distribution
Hashes for cell2sentence-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f06dcced8ca7dbf47fecbbf751c802d5170f2417a945dfae4d756588a0bbe5f0 |
|
MD5 | fe6fb977646797c3f8549f6c9e28e10c |
|
BLAKE2b-256 | ceb34e4f88db0f7c22640de01e9f5ab6886bd0d719f7a6f299aab7dbb28738d6 |