ScreenPro2 0.2.1__py2.py3-none-any.whl

ScreenPro2-0.2.1.dist-info/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2022, Abolfazl Arab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

ScreenPro2-0.2.1.dist-info/METADATA

@@ -0,0 +1,7 @@
+Metadata-Version: 2.1
+Name: ScreenPro2
+Version: 0.2.1
+Summary: Analyze pooled CRISPR screens
+Requires-Python: >=3.8
+License-File: LICENSE
+

ScreenPro2-0.2.1.dist-info/RECORD

@@ -0,0 +1,9 @@
+screenpro/__init__.py,sha256=heNcvrsJwuisUqdpi4kljd2pzC9om9eW-RR7SYGLdfs,62
+screenpro/__version__.py,sha256=HfjVOrpTnmZ-xVFCYSVmX50EXaBQeJteUHG-PD6iQs8,22
+screenpro/load.py,sha256=M6d7jEWp_MIj2e6zK9X0DmthMTKHH3TIaWx3EQ1LP0U,2009
+screenpro/phenoScore.py,sha256=cxScAJ8CjM9vwpMbMsZ73l1XQrHuxtgvdiEWqLN-vwE,3178
+ScreenPro2-0.2.1.dist-info/LICENSE,sha256=IHBn522sDxLGxi5EfDS9CZdqnW11ZeDrUxqkRfIbJR4,1072
+ScreenPro2-0.2.1.dist-info/METADATA,sha256=b273X3qBEv3hthvGaBqtMBbA3cmo91OElHilvJKmzQs,139
+ScreenPro2-0.2.1.dist-info/WHEEL,sha256=bb2Ot9scclHKMOLDEHY6B2sicWOgugjFKaJsT7vwMQo,110
+ScreenPro2-0.2.1.dist-info/top_level.txt,sha256=uOEhN69bjK8D-lUo9aFehqGZQiGp8ouTSdzTDvZ4aek,10
+ScreenPro2-0.2.1.dist-info/RECORD,,

ScreenPro2-0.2.1.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.38.4)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+

ScreenPro2-0.2.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+screenpro

screenpro/__init__.py

@@ -0,0 +1,2 @@
+from .__version__ import __version__
+from . import phenoScore

screenpro/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.2.1"

screenpro/load.py

@@ -0,0 +1,44 @@
+"""load screen datasets
+"""
+import pickle
+import pandas as pd
+
+
+def loadScreenProcessingData(experimentName, collapsedToTranscripts=True, premergedCounts=False):
+    """load ScreenProcessing outputs
+    (see original code `here <https://github.com/mhorlbeck/ScreenProcessing/blob/master/screen_analysis.py#L70>`__)
+    """
+    dataDict = {'library': pd.read_csv(experimentName + '_librarytable.txt', sep='\t', header=0, index_col=0),
+                'counts': pd.read_csv(experimentName + '_mergedcountstable.txt', sep='\t', header=list(range(2)),
+                                      index_col=list(range(1))),
+                'phenotypes': pd.read_csv(experimentName + '_phenotypetable.txt', sep='\t', header=list(range(2)),
+                                          index_col=list(range(1)))}
+
+    if premergedCounts:
+        dataDict['premerged counts'] = pd.read_csv(experimentName + '_rawcountstable.txt', sep='\t',
+                                                   header=list(range(3)), index_col=list(range(1)))
+
+    if collapsedToTranscripts:
+        dataDict['transcript scores'] = pd.read_csv(experimentName + '_genetable.txt', sep='\t', header=list(range(3)),
+                                                    index_col=list(range(2)))
+        dataDict['gene scores'] = pd.read_csv(experimentName + '_genetable_collapsed.txt', sep='\t',
+                                              header=list(range(3)), index_col=list(range(1)))
+    else:
+        dataDict['gene scores'] = pd.read_csv(experimentName + '_genetable.txt', sep='\t', header=list(range(3)),
+                                              index_col=list(range(1)))
+
+    return dataDict
+
+
+def write_adata_pkl(adata, name):
+    file_name = f'{name}.pkl'
+    with open(file_name, 'wb') as file:
+        pickle.dump(adata, file)
+        print(f'Object successfully saved to "{file_name}"')
+
+
+def read_adata_pkl(name):
+    file_name = f'{name}.pkl'
+    with open(file_name, 'rb') as f:
+        adata = pickle.load(f)
+    return adata

screenpro/phenoScore.py

@@ -0,0 +1,100 @@
+"""phenoScore module
+"""
+
+import numpy as np
+import pandas as pd
+import anndata as ad
+
+from pydeseq2 import preprocessing
+from scipy.stats import ttest_rel
+# from scipy.stats import mannwhitneyu
+# from statsmodels.stats.multitest import multipletests
+
+
+def seqDepthNormalization(adata):
+    norm_counts, size_factors = preprocessing.deseq2_norm(adata.X)
+
+    adata.obs['size_factors'] = size_factors
+    adata.layers['deseq'] = norm_counts
+
+    
+def getDelta(x,y):
+    """log ratio of y / x, averaged across replicates 
+    """
+    return np.mean(np.log1p(y) - np.log1p(x), axis=1)
+
+
+def getScore(x, y, x_ctrl, y_ctrl, growth_rate):
+    """
+    """
+    ctrl_std = np.std(getDelta(x_ctrl, y_ctrl))
+    ctrl_median = np.median(getDelta(x_ctrl, y_ctrl))
+
+    return ((getDelta(x,y) - ctrl_median) / growth_rate) / ctrl_std
+
+
+def runPhenoScore(adata, cond1, cond2, growth_rate=1, n_reps=2, test='ttest'):
+    # prep fqcounter
+    df_cond1 = adata[adata.obs.query(f'condition=="{cond1}"').index[:n_reps], ].to_df('deseq').T
+    df_cond2 = adata[adata.obs.query(f'condition=="{cond2}"').index[:n_reps], ].to_df('deseq').T
+
+    x = df_cond1.to_numpy()
+    y = df_cond2.to_numpy()
+
+    x_ctrl = df_cond1[adata.var.targetType.eq('negCtrl')].to_numpy()
+    y_ctrl = df_cond2[adata.var.targetType.eq('negCtrl')].to_numpy()
+    
+    # calculate growth score
+    phenotype_score = getScore(x,y,x_ctrl,y_ctrl,growth_rate)
+    
+    adata.var[f'condition_{cond2}_vs_{cond1}_delta'] = phenotype_score
+    
+    # calculate p-values
+    if test == 'MW':
+        # run Mann-Whitney U rank test on replicates
+        pass
+    if test == 'ttest':
+        # run ttest on replicates
+        pvalues = ttest_rel(y, x, axis=1)[1]
+        adata.var[f'condition_{cond2}_vs_{cond1}_pvalue'] = pvalues
+
+    ## calculate FDR
+    # Calculate the adjusted p-values using the Benjamini-Hochberg method
+    # _, adj_pvalues, _, _ = multipletests(adata.var[f'condition_{cond1}_vs_{cond2}_pvalue'], alpha=0.05, method='fdr_bh')
+    # adata.var[f'condition_{cond1}_vs_{cond2}_adj_pvalue'] = adj_pvalues
+    
+    
+def ann_score_df(df_in, up_hit='resistance_hit', down_hit='sensitivity_hit', ctrl_label='non-targeting', threshold=10):
+    df = df_in.copy()
+
+    df.columns = ['target', 'score', 'pvalue']
+    df['score'] = df['score'].astype(float)
+    df['pvalue'] = df['pvalue'].astype(float)
+
+    pseudo_sd = df[df['target'].str.contains(ctrl_label)]['score'].tolist()
+    pseudo_sd = np.std(pseudo_sd)
+    # print (pseudo_sd)
+    
+    df['label'] = '.'
+
+    df.loc[
+        (df['score'] > 0) & (~df['target'].str.contains(ctrl_label)) &
+        (df['score']/pseudo_sd * -np.log10(df['pvalue']) >= threshold), 'label'
+    ] = up_hit
+
+    df.loc[
+        (df['score'] < 0) & (~df['target'].str.contains(ctrl_label)) &
+        (df['score']/pseudo_sd * -np.log10(df['pvalue']) <= -threshold), 'label'
+    ] = down_hit
+
+    df.loc[df['target'].str.contains(ctrl_label), 'label'] = ctrl_label
+
+    df.loc[df['label'] == '.', 'label'] = 'target_non_hit'
+
+    # reorder factors
+    df['label'] = pd.Categorical(
+        df['label'],
+        categories=[down_hit, up_hit, ctrl_label, 'target_non_hit']
+    )
+
+    return df