Crispy - modelling CRISPR dropout data
Project description
Crispy
============
Identify associations between genomic alterations (e.g. structural variation, copy-number variation) and CRISPR-Cas9 knockout response.
[Tandem duplications lead to loss of fitness effects in CRISPR-Cas9 data](https://www.biorxiv.org/content/early/2018/05/25/325076)
Description
--
Crispy uses [Sklearn](http://scikit-learn.org/stable/index.html) implementation of [Gaussian Process Regression](http://scikit-learn.org/stable/modules/generated/sklearn.gaussian_process.GaussianProcessRegressor.html#sklearn.gaussian_process.GaussianProcessRegressor), fitting by default each chromosome of each sample independently.
Example
--
```python
import pandas as pd
from crispy.association import CRISPRCorrection
# Import data
data = pd.read_csv('extdata/association_example_data.csv', index_col=0)
# Association analysis
crispy = CRISPRCorrection()\
.fit_by(by=data['chr'], X=data[['cnv']], y=data['fc'])
# Export
crispy = pd.concat([v.to_dataframe() for k, v in crispy.items()])\
.sort_values(['cnv', 'k_mean'], ascending=[False, True])
```
Install
--
```
python setup.py install
```
Enrichment module has Cython files, to compile run:
```
python crispy/enrichment/gsea_setup.py build_ext --inplace
```
Regression module has Cython files, to compile run:
```
python crispy/regression/linear_setup.py build_ext --inplace
```
============
Identify associations between genomic alterations (e.g. structural variation, copy-number variation) and CRISPR-Cas9 knockout response.
[Tandem duplications lead to loss of fitness effects in CRISPR-Cas9 data](https://www.biorxiv.org/content/early/2018/05/25/325076)
Description
--
Crispy uses [Sklearn](http://scikit-learn.org/stable/index.html) implementation of [Gaussian Process Regression](http://scikit-learn.org/stable/modules/generated/sklearn.gaussian_process.GaussianProcessRegressor.html#sklearn.gaussian_process.GaussianProcessRegressor), fitting by default each chromosome of each sample independently.
Example
--
```python
import pandas as pd
from crispy.association import CRISPRCorrection
# Import data
data = pd.read_csv('extdata/association_example_data.csv', index_col=0)
# Association analysis
crispy = CRISPRCorrection()\
.fit_by(by=data['chr'], X=data[['cnv']], y=data['fc'])
# Export
crispy = pd.concat([v.to_dataframe() for k, v in crispy.items()])\
.sort_values(['cnv', 'k_mean'], ascending=[False, True])
```
Install
--
```
python setup.py install
```
Enrichment module has Cython files, to compile run:
```
python crispy/enrichment/gsea_setup.py build_ext --inplace
```
Regression module has Cython files, to compile run:
```
python crispy/regression/linear_setup.py build_ext --inplace
```
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
cy-0.1.0.dev225.tar.gz
(353.4 kB
view hashes)
Built Distribution
cy-0.1.0.dev225-py3-none-any.whl
(309.6 kB
view hashes)
Close
Hashes for cy-0.1.0.dev225-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c534142245cbf9821231fbcfab5a0ba507449a3f8fc777926f68edc118f1fcc5 |
|
MD5 | b437042c4b223232e9368bffa41e799b |
|
BLAKE2b-256 | 27a598a13e905c4502826b9631af40232c94b48a6596147cf8a91f1831967af1 |