Analysis of confounders by Rank-to-Group scores
Project description
Rank-To-Group (RTG) score evaluates contribution of confounders
Batch, cell line, donor, plate, reprogramming, protocol — these and other confounding factors influence cell cultures in vitro.
RTG score tracks contribution of different factors to variability by estimating how Rank maps To Group. Scoring relies on ranking by similarity, so there are no explicit or implicit assumptions of linearity.
RTG perfectly works with both well-interpretable data (gene expressions, cell types) and embeddings provided by deep learning.
Usage
rtg_score
is python package. Installation:
pip install rtg_score
RTG score requires two DataFrames: one with confounds and ane with embeddings (or other features, e.g. gene expressions)
from rtg_score import compute_RTG_score
# following code corresponds to computing element of the figure above
#
score = compute_RTG_score(
metadata=confounders_metadata,
include_confounders=['batch', 'donor'],
exclude_confounders=['organoid_id'],
embeddings=qpcr_delta_ct,
)
An example of code to compute and plot table above is available in example
subfolder.
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 rtg_score-0.1.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5c7f70f13ee5ef0ee0d662f6d76e730e3dbe62d31d19629f5262b964d9397b80 |
|
MD5 | 840f804bd499f19814a15cbcf7d4b0b8 |
|
BLAKE2b-256 | ecd69a4b587bb0a5b30219a89c819ddfc6bd20759110c1b08e755395bc64e691 |