debug, new modules, and code improvements

CanDI/__version__.py

@@ -1 +1 @@
-version = "0.1.1"
+version = "0.1.2"

CanDI/candi/__init__.py

@@ -1,4 +1,6 @@
+from . import load
 from . import data
+
 data = data.Data() #Global object data instantiated on import required for access by GeneQuery Objects
-from . import (Gene, CellLine, Organelle, Cancer, CellLineCluster, GeneCluster)
 
+from .candi import (Gene, CellLine, Organelle, Cancer, CellLineCluster, GeneCluster)

CanDI/candi/candi.py

@@ -5,7 +5,7 @@
 import pandas as pd
 import numpy as np
 from . import data, grabber
-from . import entity
+from ..structures import entity
 
 class SubsetHandler(object):
 

CanDI/candi/data.py

@@ -14,10 +14,15 @@ class Data(object):
     can be tuned to load specific datasets upon import by editing config.ini
     can call Data.load() to load any specific dataset
     """
-    def __init__(self):
-
-        self._file_path = Path(os.path.dirname(os.path.realpath(__file__))).parent.absolute() / 'setup'
-        config_path = self._file_path / 'data/config.ini'
+    def __init__(self, config_path='auto', verbose=False):
+
+        if config_path == 'auto':
+            self._file_path = Path(os.path.dirname(os.path.realpath(__file__))).parent.absolute() / 'setup'
+            config_path = self._file_path / 'data/config.ini'
+        elif os.path.exists(config_path) == False:
+            raise FileNotFoundError("Config file not found at {}".format(config_path))
+        elif os.path.exists(config_path) == True:
+            if verbose: print("Using config file at {}".format(config_path))
 
         parser = configparser.ConfigParser() #parses config for data sources
         parser.read(config_path)

CanDI/candi/load.py

@@ -0,0 +1,37 @@
+import numpy as np
+import pandas as pd
+import polars as pl
+from CanDI import candi
+from pathlib import Path
+
+
+def coessentiality(pvalue_threshold = 10**-3, data_dir='auto'):
+    if data_dir == 'auto':
+        data_dir=str(Path(candi.__path__[0]).parent.absolute()) + '/setup/data/coessentiality'
+    else:
+        # check if the path exists and it contains the necessary files
+        if not Path(data_dir).exists():
+            raise ValueError(f"Path {data_dir} does not exist")
+        if not Path(data_dir+'/genes.txt').exists():
+            raise ValueError(f"Path {data_dir}/genes.txt does not exist")
+        if not Path(data_dir+'/GLS_sign.npy').exists():
+            raise ValueError(f"Path {data_dir}/GLS_sign.npy does not exist")
+        if not Path(data_dir+'/GLS_p.npy').exists():
+            raise ValueError(f"Path {data_dir}/GLS_p.npy does not exist")
+
+    gene_names = pd.read_csv(f'{data_dir}/genes.txt',header=None,names=['gene_name'])['gene_name']
+
+    GLS_sign = np.load(f'{data_dir}/GLS_sign.npy')
+    GLS_p = np.load(f'{data_dir}/GLS_p.npy')
+
+    coessentiality_mat = pd.DataFrame((-1*np.log10(GLS_p)) * GLS_sign, columns = gene_names, index = gene_names).reset_index()
+    coessentiality_mat = pl.from_dataframe(coessentiality_mat)
+
+    coessentiality_df = coessentiality_mat.melt('gene_name')
+    coessentiality_df.columns = ['gene_1','gene_2','coessentiality']
+    coessentiality_df = coessentiality_df.filter(~(pl.col('gene_1') == pl.col('gene_2')))
+    coessentiality_df = coessentiality_df.filter(pl.col('coessentiality') > -np.log10(pvalue_threshold))
+
+    out = coessentiality_df.to_pandas()
+
+    return out

CanDI/pipelines/diffexp.py

@@ -0,0 +1,52 @@
+import numpy as np
+import pandas as pd
+import anndata as ad
+
+from pydeseq2.dds import DeseqDataSet
+from pydeseq2.default_inference import DefaultInference
+from pydeseq2.ds import DeseqStats
+from adpbulk import ADPBulk
+
+
+def pseudobulk_by_group(adt, groups, method="mean"):
+    # initialize the object
+    adpb = ADPBulk(adt, groupby=groups, method=method)
+
+    # perform the pseudobulking
+    pseudobulk_matrix = adpb.fit_transform()
+
+    # retrieve the sample metadata (useful for easy incorporation with edgeR)
+    sample_meta = adpb.get_meta()
+
+    out = ad.AnnData(
+        X=pseudobulk_matrix,
+        obs=sample_meta.set_index('SampleName')
+    )
+
+    return out
+
+
+def run_deseq(adata, design, tested_level, ref_level, n_cpus=8):
+
+    inference = DefaultInference(n_cpus=n_cpus)
+
+    dds = DeseqDataSet(
+        counts=adata.to_df().astype(int),
+        metadata=adata.obs,
+        design_factors=design,  # compare samples based on the "condition"
+        refit_cooks=True,
+        inference=inference,
+    )
+
+    dds.deseq2()
+
+    stat_res = DeseqStats(
+        dds, 
+        contrast=[design, tested_level, ref_level], 
+        inference=inference
+    )
+    stat_res.summary()
+
+    df = stat_res.results_df
+
+    return df

CanDI/setup/install.py

@@ -1,21 +1,22 @@
 import argparse
-from .manager import Manager
+from manager import DataverseDepMap, BroadDepMap
+
 
 def main():
     parser = argparse.ArgumentParser()
     parser.add_argument("--source", help="Specify the download source", default="dataverse")
-    parser.add_argument("--data_dir", help="Specify the data directory", default=None)
+    parser.add_argument("--data_dir", help="Specify the data directory", default='auto')
     args = parser.parse_args()
 
     if args.source == 'dataverse':
         print("Downloading data from Dataverse")
-        m = Manager(download_source=args.source, data_dir=args.data_dir)
+        m = DataverseDepMap(manager_path=args.data_dir, verbose=True)
         m.download_reformatted_data()
         m.write_config(m.cfig_path, m.parser)
 
     elif args.source == 'depmap':        
         print("Downloading data from DepMap")
-        m = Manager(download_source=args.source, data_dir=args.data_dir)
+        m = BroadDepMap(manager_path=args.data_dir, verbose=True)
         m.get_depmap_info()
         m.write_config(m.cfig_path, m.parser)
         m.download_defaults()