Improving single-cell GRN Inference using Dropout Augmentation
Project description
DAZZLE
This repository include code and documentation for our manuscript "Improving Gene Regulatory Network Inference using Dropout Augmentation".
Install
This package is available on pip
pip install grn-dazzle
Basic Usage
The core function runDAZZLE
requires the following two things to get started:
- Single cell gene expression table. We suggest you use log transformation to normalize the data
- Experiment Configs. We also provide two sets of default configs with this package, namely
DEFAULT_DAZZLE_CONFIGS
andDEFAULT_DEEPSEM_CONFIGS
. They are just two python dictionaries. If you need to make modifications, just save them to a variable and adjust the values.
Quick Example
from dazzle import load_beeline, runDAZZLE, get_metrics, DEFAULT_DAZZLE_CONFIGS
bl_data, bl_ground_truth = load_beeline(
data_dir='data',
benchmark_data="hESC",
benchmark_setting="500_STRING"
)
model, adjs = runDAZZLE(bl_data.X, DEFAULT_DAZZLE_CONFIGS)
get_metrics(model.get_adj(), bl_ground_truth)
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
grn_dazzle-0.0.2.tar.gz
(20.2 kB
view hashes)
Built Distribution
grn_dazzle-0.0.2-py3-none-any.whl
(24.3 kB
view hashes)
Close
Hashes for grn_dazzle-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4dc989e9b56e26ac887c646887291a80debc85081913ae472e9f745253ff4499 |
|
MD5 | 2124f550d25eab964897a3894d54d660 |
|
BLAKE2b-256 | 1e97aa9442c8978549a4fec3d750dc08be9aaa48af9181d04a5bffafc3f6e9da |