Methods to evaluate profiling dataframes with features and metadata
Project description
Cytominer-eval: Evaluating quality of perturbation profiles
Cytominer-eval contains functions to calculate quality metrics for perturbation profiling experiments.
Installation
Cytominer-eval is still in beta, and can only be installed from GitHub:
pip install git+git://github.com/cytomining/cytominer-eval
Since the project is actively being developed, with new features added regularly, we recommend installation using a hash:
# Example:
pip install git+git://github.com/cytomining/cytominer-eval@5c9fb860d1b27e746ee498d625d033475caceb7e
Usage
Cytominer-eval uses a simple API for all evaluation metrics.
# Working example
import pandas as pd
from cytominer_eval import evaluate
# Load Data
commit = "6f9d350badd0a18b6c1a76171813aaf9a52f8d9f"
url = f"https://github.com/cytomining/cytominer-eval/raw/{commit}/cytominer_eval/example_data/compound/SQ00015054_normalized_feature_select.csv.gz"
df = pd.read_csv(url)
# Define important function arguments
meta_features = df.columns[df.columns.str.startswith("Metadata_")]
features = df.drop(meta_features, axis="columns").columns.tolist()
replicate_groups = ["Metadata_broad_sample", "Metadata_mg_per_ml"]
# Evaluate profile quality
evaluate(
profiles=df,
features=features,
meta_features=meta_features,
replicate_groups=replicate_groups,
replicate_reproducibility_return_median_cor=False,
operation="replicate_reproducibility",
)
Metrics
Currently, four metric operations are supported:
- Replicate reproducibility
- Precision/recall
- mp-value
- Grit
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
cytominer_eval-0.1.tar.gz
(22.1 kB
view details)
File details
Details for the file cytominer_eval-0.1.tar.gz
.
File metadata
- Download URL: cytominer_eval-0.1.tar.gz
- Upload date:
- Size: 22.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/49.6.0.post20201009 requests-toolbelt/0.9.1 tqdm/4.56.2 CPython/3.8.6
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7d9d1080996c8cb4a7e819b55f4e386bc81c41f6a03380ee23db58e7db48c81b |
|
MD5 | bcba14398b6f549a5d04cbdb3cf31426 |
|
BLAKE2b-256 | b4098d7cc7ec518a752448eb1f69de4f70f23ec75990cc45035778647bf3e96b |