diff --git a/.github/workflows/python-package.yml b/.github/workflows/python-package.yml
index af02bed..e5e6c9a 100644
--- a/.github/workflows/python-package.yml
+++ b/.github/workflows/python-package.yml
@@ -16,7 +16,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9"] # ["3.8", "3.9", "3.10"]
+        python-version: ["3.11"]
 
     steps:
     - uses: actions/checkout@v3
diff --git a/.github/workflows/python-publish.yml b/.github/workflows/python-publish.yml
index 4a1e620..9913050 100644
--- a/.github/workflows/python-publish.yml
+++ b/.github/workflows/python-publish.yml
@@ -15,7 +15,7 @@ jobs:
       fail-fast: false
       matrix:
         os-version: ["ubuntu-latest"]
-        python-version: ["3.9"] # ["3.8", "3.9", "3.10"]
+        python-version: ["3.11"]
 
     steps:
     - uses: actions/checkout@v3
diff --git a/.gitignore b/.gitignore
index 2bab4d9..cdbe076 100644
Binary files a/.gitignore and b/.gitignore differ
diff --git a/CanDI/__version__.py b/CanDI/__version__.py
index cab7576..1fee926 100644
--- a/CanDI/__version__.py
+++ b/CanDI/__version__.py
@@ -1 +1 @@
-version = "0.1.1"
\ No newline at end of file
+version = "0.2.0"
\ No newline at end of file
diff --git a/CanDI/candi/__init__.py b/CanDI/candi/__init__.py
index 7fc3fbd..a2245f0 100644
--- a/CanDI/candi/__init__.py
+++ b/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)
diff --git a/CanDI/candi/candi.py b/CanDI/candi/candi.py
index c422fd8..eab6e45 100644
--- a/CanDI/candi/candi.py
+++ b/CanDI/candi/candi.py
@@ -1,11 +1,11 @@
 # Classes for handling data aggregations
 import operator
-from collections import OrderedDict, MutableSequence
+from collections.abc import MutableSequence
 import itertools as it
 import pandas as pd
 import numpy as np
 from . import data, grabber
-from . import entity
+from ..structures import entity
 
 class SubsetHandler(object):
 
diff --git a/CanDI/candi/data.py b/CanDI/candi/data.py
index 5a2921c..24fafcb 100644
--- a/CanDI/candi/data.py
+++ b/CanDI/candi/data.py
@@ -14,21 +14,27 @@ 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):
+    def __init__(self, config_path='auto', verbose=False):
 
-        self._file_path = Path(os.path.dirname(os.path.realpath(__file__))).parent.absolute() / 'setup'
-        config_path = self._file_path / 'data/config.ini'
+        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)
 
         self._parser = parser
-        #self._verify_install()
+        self._verify_install()
         self._init_sources()
         self._init_depmap_paths()
-        # self._init_index_tables()
+        self._init_index_tables()
 
     def _verify_install(self): #ensures data being loaded is present
+        #TODO: add more checks for different data sources
         try:
             assert "depmap_urls" in self._parser.sections()
         except AssertionError:
@@ -91,6 +97,7 @@ def _handle_autoload(method, path):
             df = pd.read_csv(path,
                              memory_map=True,
                              low_memory=False,
+                             sep='\t',
                              index_col="DepMap_ID")
 
         elif method == "locations":
diff --git a/CanDI/pipelines/__init__.py b/CanDI/pipelines/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/CanDI/pipelines/coessentiality/__init__.py b/CanDI/pipelines/coessentiality/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/CanDI/pipelines/diffexp.py b/CanDI/pipelines/diffexp.py
new file mode 100644
index 0000000..ea4a581
--- /dev/null
+++ b/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
\ No newline at end of file
diff --git a/CanDI/setup/dataverse.py b/CanDI/setup/dataverse.py
index 1dac195..ea0aee6 100644
--- a/CanDI/setup/dataverse.py
+++ b/CanDI/setup/dataverse.py
@@ -9,6 +9,18 @@
 
 CANDI_DATAVERSE_DOI = 'doi:10.7910/DVN/JIAT0H'
 
+
+### Datasets Metadata ###
+
+coessentiality_dataset_names = [
+    'genes',
+    # 10273535
+    'GLS_p',
+    # 10273534
+    'GLS_sign',
+    # 10273533
+]
+
 depmap_dataset_names = [
     'CCLE_expression',
     'CCLE_fusions',
@@ -22,6 +34,11 @@
 ]
 
 name2type = {
+    # Coessentiality datasets
+    'genes': 'txt',
+    'GLS_p': 'npy',
+    'GLS_sign': 'npy',
+    # DepMap datasets
     'CCLE_expression': 'csv',
     'CCLE_fusions': 'csv',
     'CCLE_gene_cn': 'csv',
@@ -34,6 +51,11 @@
 }
 
 name2id = {
+    # Coessentiality datasets
+    'genes': 10273535,
+    'GLS_p': 10273534,
+    'GLS_sign': 10273533,
+    # DepMap datasets
     'CCLE_expression': 8076862,
     'CCLE_fusions': 10085763,
     'CCLE_gene_cn': 8076861,
@@ -46,6 +68,7 @@
 }
 
 
+### Utility functions ###
 def print_sys(s):
     """system print
 
@@ -55,80 +78,102 @@ def print_sys(s):
     print(s, flush = True, file = sys.stderr)
 
 
-def dataverse_download(url, path, name, types):
-    """dataverse download helper with progress bar
-
-    Args:
-        url (str): the url of the dataset
-        path (str): the path to save the dataset
-        name (str): the dataset name
-        types (dict): a dictionary mapping from the dataset name to the file format
-    """
-    save_path = os.path.join(path, f"{name}.{types[name]}")
-    response = requests.get(url, stream=True)
-    total_size_in_bytes = int(response.headers.get("content-length", 0))
-    block_size = 1024
-    progress_bar = tqdm(total=total_size_in_bytes, unit="iB", unit_scale=True)
-    with open(save_path, "wb") as file:
-        for data in response.iter_content(block_size):
-            progress_bar.update(len(data))
-            file.write(data)
-    progress_bar.close()
-
-
-def download_wrapper(name, path, return_type=None):
-    """wrapper for downloading a dataset given the name and path, for csv,pkl,tsv or similar files
-
-    Args:
-        name (str): the rough dataset query name
-        path (str): the path to save the dataset
-        return_type (str, optional): the return type. Defaults to None. Can be "url", "name", or ["url", "name"]
+### Downloading scripts ###
+
+class Downloader:
+    def __init__(self):
+        pass
+
+    def _dataverse_download(self, url, path, name, types):
+        """dataverse download helper with progress bar
+
+        Args:
+            url (str): the url of the dataset
+            path (str): the path to save the dataset
+            name (str): the dataset name
+            types (dict): a dictionary mapping from the dataset name to the file format
+        """
+        save_path = os.path.join(path, f"{name}.{types[name]}")
+        response = requests.get(url, stream=True)
+        total_size_in_bytes = int(response.headers.get("content-length", 0))
+        block_size = 1024
+        progress_bar = tqdm(total=total_size_in_bytes, unit="iB", unit_scale=True)
+        with open(save_path, "wb") as file:
+            for data in response.iter_content(block_size):
+                progress_bar.update(len(data))
+                file.write(data)
+        progress_bar.close()
+
+
+    def _download_wrapper(self, name, path, return_type=None):
+        """wrapper for downloading a dataset given the name and path, for csv,pkl,tsv or similar files
+
+        Args:
+            name (str): the rough dataset query name
+            path (str): the path to save the dataset
+            return_type (str, optional): the return type. Defaults to None. Can be "url", "name", or ["url", "name"]
+
+        Returns:
+            str: the exact dataset query name
+        """
+        server_path = "https://dataverse.harvard.edu/api/access/datafile/"
+
+        url = server_path + str(name2id[name])
+
+        if not os.path.exists(path):
+            os.mkdir(path)
+
+        file_name = f"{name}.{name2type[name]}"
+
+        if os.path.exists(os.path.join(path, file_name)):
+            print_sys("Found local copy...")
+            os.path.join(path, file_name)
+        else:
+            print_sys("Downloading...")
+            self._dataverse_download(url, path, name, name2type)
+        
+        if return_type == "url":
+            return url
+        elif return_type == "name":
+            return file_name
+        elif return_type == ["url", "name"]:
+            return url, file_name
 
-    Returns:
-        str: the exact dataset query name
-    """
-    server_path = "https://dataverse.harvard.edu/api/access/datafile/"
-
-    url = server_path + str(name2id[name])
-
-    if not os.path.exists(path):
-        os.mkdir(path)
-
-    file_name = f"{name}.{name2type[name]}"
-
-    if os.path.exists(os.path.join(path, file_name)):
-        print_sys("Found local copy...")
-        os.path.join(path, file_name)
-    else:
-        print_sys("Downloading...")
-        dataverse_download(url, path, name, name2type)
     
-    if return_type == "url":
-        return url
-    elif return_type == "name":
-        return file_name
-    elif return_type == ["url", "name"]:
-        return url, file_name
-
-
-def depmap_dataverse_download(path, return_type=None):
-    """download all datasets to the path
+    def run(self, path, datasets, return_type=None):
+        """download all datasets to the path
+
+        Args:
+            path (str): the path to save the datasets
+            return_type (str, optional): the return type. Defaults to None. Can be "url", "name", or ["url", "name"]
+        """
+        url_list = []
+        file_names = []
+
+        for name in datasets:
+            url, file_name = self._download_wrapper(name, path, return_type=["url", "name"])
+            url_list.append(url)
+            file_names.append(file_name)
+        
+        if return_type == "url":
+            return url_list
+        elif return_type == "name":
+            return file_names
+        elif return_type == ["url", "name"]:
+            return url_list, file_names
+
+
+class DepMapDownloader(Downloader):
+    def __init__(self):
+        super().__init__()
+    
+    def download(self, path, return_type=None):
+        return self.run(path, depmap_dataset_names, return_type)
 
-    Args:
-        path (str): the path to save the datasets
-        return_type (str, optional): the return type. Defaults to None. Can be "url", "name", or ["url", "name"]
-    """
-    url_list = []
-    file_names = []
 
-    for name in depmap_dataset_names:
-        url, file_name = download_wrapper(name, path, return_type=["url", "name"])
-        url_list.append(url)
-        file_names.append(file_name)
+class CoessentialityDownloader(Downloader):
+    def __init__(self):
+        super().__init__()
     
-    if return_type == "url":
-        return url_list
-    elif return_type == "name":
-        return file_names
-    elif return_type == ["url", "name"]:
-        return url_list, file_names
+    def download(self, path, return_type=None):
+        return self.run(path, coessentiality_dataset_names, return_type)
\ No newline at end of file
diff --git a/CanDI/setup/install.py b/CanDI/setup/install.py
index 0042e94..29eed77 100644
--- a/CanDI/setup/install.py
+++ b/CanDI/setup/install.py
@@ -1,30 +1,45 @@
 import argparse
-from .manager import Manager
+from . import manager
+
 
 def main():
     parser = argparse.ArgumentParser()
+    parser.add_argument("--database", help="Specify the database to download", default="depmap")
     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("--directory", help="Specify the parent 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.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.get_depmap_info()
-        m.write_config(m.cfig_path, m.parser)
-        m.download_defaults()
-        m.write_config(m.cfig_path, m.parser)
-        m.depmap_autoformat()
-        m.write_config(m.cfig_path, m.parser)
+    if args.database == 'depmap':
+        if args.source == 'dataverse':
+            print("Downloading data from Dataverse")
+            m = manager.DataverseDepMap(manager_path=args.directory, 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.BroadDepMap(manager_path=args.directory, verbose=True)
+            m.get_depmap_info()
+            m.write_config(m.cfig_path, m.parser)
+            m.download_defaults()
+            m.write_config(m.cfig_path, m.parser)
+            m.depmap_autoformat()
+            m.write_config(m.cfig_path, m.parser)
 
-    else:
-        raise ValueError("Invalid source. Please specify either 'dataverse' or 'depmap'")
+        else:
+            raise ValueError("Invalid source. Please specify either 'dataverse' or 'depmap'")
     
+    if args.database == 'coessentiality':
+        if args.source == 'dataverse':
+            print("Downloading data from Dataverse")
+            m = manager.DataverseCoessentiality(manager_path=args.directory, verbose=True)
+            m.download_raw_files()
+            m.coessentiality_autoformat()
+            m.write_config(m.cfig_path, m.parser)
+        
+        else:
+            raise ValueError("Invalid source. Coessentiality data is only available on `dataverse`!")
+
+
 if __name__ == "__main__":
     main()
\ No newline at end of file
diff --git a/CanDI/setup/manager.py b/CanDI/setup/manager.py
index 5d2c3c4..8efacf0 100644
--- a/CanDI/setup/manager.py
+++ b/CanDI/setup/manager.py
@@ -1,39 +1,114 @@
+"""
+The manager module handles interations with the datasources
+and the config file. It is used to setup of the config file upon installation.
+All data downloading is done by Manager class and its subclasses.
+"""
+
 import os
 import configparser
 import json
 import time
 import requests
-import shutil
+import numpy as np
+import polars as pl
 import pandas as pd
 from time import sleep
 from pathlib import Path
 from concurrent.futures import ThreadPoolExecutor
-from .dataverse import depmap_dataverse_download
+from . import dataverse
+
 
 class Manager(object):
-    """The Manager class handles interations with the datasources
-    and the config file. It is used to setup of the config file upon installation.
-    All data downloading is done by Manager
-    """
-    def __init__(self, download_source=None, data_dir=None):
-
-        if data_dir:
-            manager_path = data_dir
-        else:
+    def __init__(self, manager_path='auto', cfig_path='auto', verbose=False):
+        """Initializes the Manager class
+
+        Args:
+            manager_path (str, optional): The path to the manager directory. This is where the data will be stored.
+            cfig_path (str, optional): The path to the config file.
+        """
+        if manager_path == 'auto':
             manager_path = os.path.dirname(os.path.realpath(__file__))
-        
-        cfig_path = manager_path + "/data/config.ini"
+        else:
+            # make sure the path is a directory and exists or create it
+            if not os.path.exists(manager_path):
+                os.makedirs(manager_path)
+
+        if cfig_path == 'auto':
+            cfig_path = manager_path + "/data/config.ini"
+
+        if verbose:
+            print(f"Manager Path: {manager_path}")
+            print(f"Config Path: {cfig_path}")
+
         parser = configparser.ConfigParser()
         parser.read(cfig_path.replace(".ini", ".draft.ini"))
 
         self.manager_path = manager_path
         self.cfig_path = Path(cfig_path)
         self.parser = parser
-        self.download_source = download_source
+
+    @staticmethod    
+    def write_config(cfig_path, parser):
+
+        print("Writing config file")
+        with open(cfig_path, "w") as f:
+            parser.write(f)
+            f.close()
+
+
+class DataverseDepMap(Manager):
+    def __init__(self, manager_path='auto', cfig_path='auto', verbose=False):
+        super().__init__(manager_path, cfig_path, verbose)
+        self.release = '21Q4' # default release uploded to CanDI dataverse
+        self.download_source = 'dataverse, ' + dataverse.CANDI_DATAVERSE_DOI
     
-    def sanger_download():
-        pass
+    def download_reformatted_data(self):
+        if not os.path.exists(self.manager_path + '/data/'):
+            os.makedirs(self.manager_path + '/data/')
+
+        if not os.path.exists(self.manager_path + '/data/depmap/'):
+            os.makedirs(self.manager_path + '/data/depmap/')
+
+        session = dataverse.DepMapDownloader()
+        urls, file_names = session.download(
+            self.manager_path + '/data/depmap/', 
+            return_type= ["url", "name"]
+        )
 
+        depmap_urls = {
+            file: url for url, file in zip(urls, file_names)
+        }
+
+        depmap_files = {}
+        for file in file_names:
+            f_key = file.split('.')[0]
+            f_key = f_key.replace('CCLE_','')
+            f_key = f_key.replace('CRISPR_','')
+            depmap_files[f_key] = file 
+
+        formatted = {
+            f'{self.manager_path}/data/depmap/{file}': file for file in file_names 
+            if 'readme' not in file.lower()
+        }
+
+        data_paths = {
+            'depmap':   'data/depmap/',
+            'genes':    'data/genes/',
+            'corum':    'data/complexes/',
+            'location': 'data/location/'
+        }
+        
+        self.parser["depmap_urls"] = depmap_urls
+        self.parser["depmap_files"] = depmap_files
+        self.parser["formatted"] = formatted
+        self.parser["data_paths"] = data_paths
+
+
+class BroadDepMap(Manager):
+    def __init__(self, manager_path='auto', cfig_path='auto', verbose=False):
+        super().__init__(manager_path, cfig_path, verbose)
+        self.download_source = 'Broad DepMap, https://depmap.org/'
+        
     def get_depmap_info(self, release="latest"):
 
         depmap = self.parser["download_urls"]["depmap"]
@@ -48,7 +123,6 @@ def get_depmap_info(self, release="latest"):
         self.parser["depmap_urls"] = self.download_info
         self.parser["depmap_files"] = self.depmap_files
 
-
     def parse_release(self):
 
         download_urls = {}
@@ -74,16 +148,21 @@ def get_release(self, release):
 
         return release_info["releaseName"]
 
-    def format_filename(self, filename):
+    def format_filename(self, filename, release):
 
+        # set candi_name to the filename without the extension
         candi_name = filename.split(".")[0]
 
-        if "CRISPR_" in candi_name:
-            candi_name = candi_name[len("CRISPR_"):]
-        elif "CCLE_" in candi_name:
-            candi_name = candi_name[len("CCLE_"):]
-        if 'v2' in candi_name:
-            candi_name = candi_name[:-len("_v2")]
+        if release == "21Q4":
+            if "CRISPR_" in candi_name:
+                candi_name = candi_name[len("CRISPR_"):]
+            elif "CCLE_" in candi_name:
+                candi_name = candi_name[len("CCLE_"):]
+            if 'v2' in candi_name:
+                candi_name = candi_name[:-len("_v2")]
+        else:
+            #TODO: add more cases for different releases, e.g. 24Q4 new file formats
+            pass
 
         return candi_name
 
@@ -118,14 +197,12 @@ def fetch_url(self, entry):
 
             downloads[filename] = str(path)
 
-
     def parallel_fetch(self, entries):
         print("Starting Pool")
         with ThreadPoolExecutor(max_workers=4) as executor:
             for i in entries:
                 executor.submit(self.fetch_url, i)
 
-
     def download_defaults(self):
 
         default_sources = json.loads(self.parser.get("defaults","downloads"))
@@ -134,7 +211,6 @@ def download_defaults(self):
         entries = [self.manage_request(i, "depmap") for i in to_download]
         self.parallel_fetch(entries)
 
-
     def manage_request(self, name, path, filename=False):
 
         if filename:
@@ -173,44 +249,48 @@ def depmap_autoformat(self):
                 df = pd.read_csv(v, low_memory=False, memory_map=True)
                 self.format_depmap_data(df, v)
 
-    def format_depmap_data(self, df, path):
+    def format_depmap_data(self, df, path, release):
 
-        if ("AAAS (8086)" in df.columns) or ("AAAS (ENSG00000094914)" in df.columns):
+        if release == "21Q4":
+            if ("AAAS (8086)" in df.columns) or ("AAAS (ENSG00000094914)" in df.columns):
 
-            df.rename(columns = lambda s: s.split(" ")[0], inplace=True)
+                df.rename(columns = lambda s: s.split(" ")[0], inplace=True)
 
-            if "Unnamed:" in df.columns:
-                df.rename(columns={"Unnamed:":"DepMap_ID"}, inplace=True)
+                if "Unnamed:" in df.columns:
+                    df.rename(columns={"Unnamed:":"DepMap_ID"}, inplace=True)
 
-            df = df.set_index("DepMap_ID").T
-            df.reset_index(inplace=True)
-            df.rename(columns={"index":"gene"}, inplace=True)
-            df.set_index("gene", inplace=True)
-            df.to_csv(path)
+                df = df.set_index("DepMap_ID").T
+                df.reset_index(inplace=True)
+                df.rename(columns={"index":"gene"}, inplace=True)
+                df.set_index("gene", inplace=True)
+                df.to_csv(path)
 
-        if "Protein_Change" in df.columns:
+            if "Protein_Change" in df.columns:
 
-            try:
-                df.drop("Unnamed: 0", axis=1, inplace=True)
-                df.to_csv(path, index=False)
-            except KeyError:
-                pass
+                try:
+                    df.drop("Unnamed: 0", axis=1, inplace=True)
+                    df.to_csv(path, index=False)
+                except KeyError:
+                    pass
 
-        if "Hugo_Symbol" in df.columns:
-            try:
-                df.rename(columns={"Hugo_Symbol": "gene"}, inplace=True)
-                df.to_csv(path, index=False)
-            except KeyError:
-                pass
+            if "Hugo_Symbol" in df.columns:
+                try:
+                    df.rename(columns={"Hugo_Symbol": "gene"}, inplace=True)
+                    df.to_csv(path, index=False)
+                except KeyError:
+                    pass
 
-        if "LeftGene" in df.columns:
-            for col in df.columns:
-                if "Gene" in col:
-                    split_cols = df[col].str.split(" ", expand=True)
-                    df[col] = split_cols[0]
-                    df[col[:-4] + "EnsemblID"] = split_cols[1].str.replace("(", "").str.replace(")", "")
+            if "LeftGene" in df.columns:
+                for col in df.columns:
+                    if "Gene" in col:
+                        split_cols = df[col].str.split(" ", expand=True)
+                        df[col] = split_cols[0]
+                        df[col[:-4] + "EnsemblID"] = split_cols[1].str.replace("(", "").str.replace(")", "")
 
-            df.to_csv(path, index=False)
+                df.to_csv(path, index=False)
+        else:
+            #TODO: add more cases for different releases, e.g. 24Q4 new file formats
+            pass
 
         try:
             formatted = self.parser["formatted"]
@@ -221,46 +301,90 @@ def format_depmap_data(self, df, path):
         formatted[path.split("/")[-1]] = path
 
 
-    def download_reformatted_data(self, depmap_release=''):
-        if not os.path.exists(self.manager_path + '/data/'):
-            os.makedirs(self.manager_path + '/data/')
+class SangerDepMap(Manager):
+    def __init__(self, cfig_path='auto'):
+        super().__init__(cfig_path)
 
-        if not os.path.exists(self.manager_path + '/data/depmap/'):
-            os.makedirs(self.manager_path + '/data/depmap/')
+    def sanger_download():
+        pass
 
-        if self.download_source == "dataverse":
-            urls, file_names = depmap_dataverse_download(
-                self.manager_path + '/data/depmap/', 
-                return_type= ["url", "name"]
-            )
 
-            depmap_urls = {
-                file: url for url, file in zip(urls, file_names)
-            }
+class DataverseCoessentiality(Manager):
+    def __init__(self, manager_path='auto', cfig_path='auto', verbose=False):
+        super().__init__(manager_path, cfig_path, verbose)
+        self.download_source = 'Dataverse'
+        self.reference = 'https://github.com/kundajelab/coessentiality'
+        self.verbose = verbose
+    
+    def download_raw_files(self):
+        if not os.path.exists(self.manager_path + '/data/'):
+            os.makedirs(self.manager_path + '/data/')
 
-            depmap_files = {}
-            for file in file_names:
-                f_key = file.split('.')[0]
-                f_key = f_key.replace('CCLE_','')
-                f_key = f_key.replace('CRISPR_','')
-                depmap_files[f_key] = file 
+        if not os.path.exists(self.manager_path + '/data/coessentiality/'):
+            os.makedirs(self.manager_path + '/data/coessentiality/')
+        
+        session = dataverse.CoessentialityDownloader()
+        urls, file_names = session.download(
+            self.manager_path + '/data/coessentiality/',
+            return_type= ["url", "name"]
+        )
 
-            formatted = {
-                f'{self.manager_path}/data/depmap/{file}': file for file in file_names 
-                if 'readme' not in file.lower()
-            }
+        self.urls = urls
+        self.file_names = file_names
 
-            self.parser["depmap_urls"] = depmap_urls
-            self.parser["depmap_files"] = depmap_files
-            self.parser["formatted"] = formatted
+    def _load_coessentiality_matrix(self):
+        data_dir = f'{self.manager_path}/data/coessentiality'
 
-        else:
-            raise RuntimeError("Set download source to 'dataverse' before running download_formated_data")
+        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')
+        
+        self.matrix = pl.from_dataframe(
+            pd.DataFrame((-1*np.log10(GLS_p)) * GLS_sign, columns = gene_names, index = gene_names).reset_index()
+        )
+
+    def _get_coessentiality_df(self, pvalue_threshold = 10**-3):
+        df = self.matrix.melt('gene_name')
+        df.columns = ['gene_1','gene_2','coessentiality']
+        df = df.filter(~(pl.col('gene_1') == pl.col('gene_2')))
+        df = df.filter(pl.col('coessentiality') > -np.log10(pvalue_threshold))
+        
+        self.df = df
+        self.pvalue_threshold = pvalue_threshold
 
-    @staticmethod
-    def write_config(cfig_path, parser):
+    def coessentiality_autoformat(self):
 
-        print("Writing config file")
-        with open(cfig_path, "w") as f:
-            parser.write(f)
-            f.close()
+        if self.verbose: print("Building Coessentiality Matrix ...", end=' ')
+        self._load_coessentiality_matrix()
+        self.matrix.to_pandas().to_csv(
+            f'{self.manager_path}/data/coessentiality/coessentiality_matrix.csv'
+        )
+        if self.verbose: print("Done!")
+        
+        if self.verbose: print("Building Coessentiality DataFrame ...", end=' ')
+        self._get_coessentiality_df()
+        self.df.to_pandas().to_csv(
+            f'{self.manager_path}/data/coessentiality/coessentiality_df.csv'
+        )
+        if self.verbose: print("Done!")
+        
+        self.parser['data_paths'] = {    
+            'coessentiality': 'data/coessentiality/'
+        }
+
+        self.parser['formatted'] = {    
+            'coessentiality_matrix.csv': f'{self.manager_path}/data/coessentiality/coessentiality_matrix.csv',
+            'coessentiality_df.csv': f'{self.manager_path}/data/coessentiality/coessentiality_df.csv'
+        }
+        
+        self.parser['depmap_files'] = {
+            'coessentiality': f'{self.manager_path}/data/coessentiality/coessentiality_df.csv',
+            'coessentiality_matrix': f'{self.manager_path}/data/coessentiality/coessentiality_matrix.csv',
+            # 'coessentiality_signs': f'{self.manager_path}/data/coessentiality/GLS_sign.npy',
+            # 'coessentiality_pvalues': f'{self.manager_path}/data/coessentiality/GLS_p.npy',
+            # 'gene_names': f'{self.manager_path}/data/coessentiality/genes.txt',
+            # 'pvalue_threshold': self.pvalue_threshold,
+        }
\ No newline at end of file
diff --git a/CanDI/setup/reset_config.py b/CanDI/setup/reset_config.py
index 39a3a9d..4325b8b 100644
--- a/CanDI/setup/reset_config.py
+++ b/CanDI/setup/reset_config.py
@@ -4,9 +4,24 @@
 from .manager import Manager
 
 
-def main():
+def write_cfig(cfig_path, parser):
+
+    write_file = Manager.write_config
+    write_file(cfig_path, parser)
+
 
-    cfig_path = os.path.dirname(os.path.realpath(__file__)) + "/data/config.ini"
+def main(cfig_path='auto'):
+    """
+    This function will reset the config file to only contain the default sections.
+    This is useful if you want to reset the config file to its original state.
+    """
+    if cfig_path == 'auto':
+        cfig_path = os.path.dirname(os.path.realpath(__file__)) + "/data/config.ini"
+    elif os.path.exists(cfig_path) == False:
+        raise FileNotFoundError("Config file not found")
+    elif os.path.exists(cfig_path) == True:
+        print("Using config file at: " + cfig_path)
+    
     parser = configparser.ConfigParser()
     parser.read(cfig_path)
 
@@ -21,10 +36,5 @@ def main():
     write_cfig(cfig_path, parser)
 
 
-def write_cfig(cfig_path, parser):
-
-    write_file = Manager.write_config
-    write_file(cfig_path, parser)
-
 if __name__ == "__main__":
     main()
diff --git a/CanDI/setup/uninstall.py b/CanDI/setup/uninstall.py
new file mode 100644
index 0000000..0037a56
--- /dev/null
+++ b/CanDI/setup/uninstall.py
@@ -0,0 +1,35 @@
+import os
+import sys
+import shutil
+import argparse
+from .manager import Manager
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--database", help="Specify the database to uninstall", default="depmap")
+    parser.add_argument("--directory", help="Specify the data parent directory", default='auto')
+    args = parser.parse_args()
+
+    if args.database == 'depmap':
+        print("Uninstalling CanDI: removing DepMap data")
+
+        m = Manager()
+
+        if args.directory == 'auto':
+            depmap_path = m.manager_path + "/data/depmap/"
+        elif os.path.exists(args.directory):
+            depmap_path = args.directory + "/data/depmap/"
+        else:
+            sys.exit("Exit: Invalid directory path!")
+
+        if not os.path.exists(depmap_path):
+            sys.exit("Exit: Directory does not contain DepMap data")
+        else:
+            os.listdir(depmap_path)
+            shutil.rmtree(depmap_path)
+    else:
+        raise ValueError("Invalid database. Currently only 'depmap' is supported")
+    
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/CanDI/structures/handlers.py b/CanDI/structures/handlers.py
index 4a6b9d5..bbfed65 100644
--- a/CanDI/structures/handlers.py
+++ b/CanDI/structures/handlers.py
@@ -1,9 +1,10 @@
 import operator
 import pandas as pd
 import numpy as np
-import collections
+from collections.abc import Iterable
 import six
 
+
 class BinaryFilter:
     """BinaryFilter class filters datasets based on a specific threshold.
     It's often useful to filter essentiality, expression, copy number etc.
@@ -146,7 +147,7 @@ def _get_variant(mut_dat, variant, item, all_except=False):
         assert item in mut_dat[variant].unique(), "{0} not found, options are: {1}".format(item, mut_dat[variant].unique())
 
 
-        if isinstance(item, collections.Iterable) and not isinstance(item, six.string_types):
+        if isinstance(item, Iterable) and not isinstance(item, six.string_types):
             method = lambda x,y: mut_dat.loc[mut_dat[x].isin(y)]
 
         else:
diff --git a/README.rst b/README.rst
index 8c26095..c1c8222 100644
--- a/README.rst
+++ b/README.rst
@@ -1,36 +1,21 @@
 CanDI - A global cancer data integrator
 =======================================
 
-|Documentation Status|
-|DOI|
-|Dataverse|
+|PyPI| |Downloads| |Documentation Status| |DOI| |Dataverse|
 
-Package Installation
---------------------
+Installation
+------------
 
-CanDI is now available on `PyPI <https://pypi.org/project/PyCanDI/>`_ and can be installed with pip:
+CanDI is now available on `PyPI <https://pypi.org/project/PyCanDI/>`_ and can be installed with pip. 
+Then, a command from CanDI will automatically download stable datasets from `Dataverse <https://doi.org/10.7910/DVN/JIAT0H>`_.
 
 .. code:: bash
 
+   # Package Installation
    pip install PyCanDI
 
-___
-For the latest version (development version) install from GitHub:
-
-.. code:: bash
-   
-   pip install git+https://github.com/GilbertLabUCSF/CanDI.git
-
-
-Prepare Datasets
-~~~~~~~~~~~~~~~~
-
-The python command from CanDI will automatically download and modify
-datasets.
-
-.. code:: bash
-
-   python CanDI/CanDI/setup/install.py
+   # Prepare Datasets
+   candi-install
 
 Downloaded and formatted datasets would organize this way:
 
@@ -52,7 +37,13 @@ Downloaded and formatted datasets would organize this way:
    └── locations
        └── merged_locations.csv
 
-Package Usage
+
+**Note**:
+   *Currently, DepMap API is not available for public use. Therefore, we are providing the preprocessed datasets for the users
+   based on DepMap 21Q4 release. DepMap API will be available in the future to download the latest datasets.*
+
+
+Usage
 -------------
 
 Import CanDI into python
@@ -79,9 +70,28 @@ CanDI Objects
 -  ``GeneCluster`` : Provides cross dataset indexing for a group of user
    defined genes.
 
+Citation
+--------
+
+If you use CanDI in your research, please cite the following paper:
+
+.. code:: bibtex
+
+   Yogodzinski C, Arab A, Pritchard JR, Goodarzi H, Gilbert LA. 
+   A global cancer data integrator reveals principles of synthetic lethality, sex disparity and immunotherapy. 
+   Genome Med. 2021;13(1):167. Published 2021 Oct 18. doi:10.1186/s13073-021-00987-8
+
+
+
+.. |PyPI| image:: https://img.shields.io/pypi/v/PyCanDI
+   :target: https://pypi.org/project/PyCanDI/
+   
 .. |Documentation Status| image:: https://readthedocs.org/projects/candi/badge/?version=latest
    :target: https://candi.readthedocs.io/en/latest/?badge=latest
 
+.. |Downloads| image:: https://static.pepy.tech/badge/pycandi
+   :target: https://pepy.tech/project/pycandi
+
 .. |DOI| image:: https://zenodo.org/badge/DOI/10.1186/s13073-021-00987-8.svg
    :target: https://doi.org/10.1186/s13073-021-00987-8
 
diff --git a/environment.yml b/environment.yml
index 3c3a84b..6570f0e 100644
--- a/environment.yml
+++ b/environment.yml
@@ -1,7 +1,13 @@
 name: candi
 dependencies:
- - python==3.9
+ - python>=3.11,<4.0
  - pandas
+ - numpy
+ - polars
  - configparser
  - requests
  - tqdm
+ - pip
+ - pip:
+   - pydeseq2
+   - adpbulk
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index 8504299..8c1dd7a 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,9 @@
 pandas
+numpy
+polars
+anndata
 configparser
 requests
 tqdm
-
+adpbulk
+pydeseq2
\ No newline at end of file
diff --git a/scripts/run_deseq.r b/scripts/run_deseq.r
deleted file mode 100644
index f4f1088..0000000
--- a/scripts/run_deseq.r
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/usr/bin/env Rscript
-library(DESeq2)
-
-args = commandArgs(trailingOnly=TRUE)
-
-#read data
-counts.mat <- read.csv(args[1])
-coldata <- read.csv(args[2])
-
-#name metadata columns
-colnames(coldata) <- c("sample.id", "condition")
-#convert datatype to factor
-coldata[,-1] <- as.factor(coldata[, -1])
-#Match sample ids to sample columns in counts matrix
-coldata$sample.id <- sub("-", ".", coldata$sample.id)
-
-#init dds object
-dds <- DESeqDataSetFromMatrix(countData=counts.mat, 
-                              colData=coldata, 
-                              design= ~condition,
-                              tidy = TRUE)
-
-dds <- estimateSizeFactors(dds)
-#Filter lowly expressed genes
-idx <- rowSums(counts(dds, normalized=TRUE) >= 5) >= 3
-dds <- dds[idx,]
-
-dds <- DESeq(dds) #run deseq
-res <- results(dds) #get results
-#Show results
-print(summary(res))
-print(head(res))
-
-write.csv(res, args[3]) #save results
-
diff --git a/setup.py b/setup.py
index c15190e..b5a85ff 100644
--- a/setup.py
+++ b/setup.py
@@ -10,10 +10,13 @@
     name='PyCanDI',
     description='A cancer data integration package',
     version=version,
-    packages=find_packages(),
+    
+    packages=find_packages(exclude=['tests', 'test_*']),
+    
     long_description=long_description,
     long_description_content_type='text/x-rst',
-    python_requires='>=3.9',
+
+    python_requires='>=3.11,<4.0',
     install_requires=[
         "pandas",
         "configparser",
@@ -21,14 +24,21 @@
         "tqdm",
     ],
     url = 'https://github.com/GilbertLabUCSF/CanDI',
+    
     entry_points={
         'console_scripts': [
             'candi-install = CanDI.setup.install:main',
+            'candi-uninstall = CanDI.setup.uninstall:main',
         ],
     },
+    
     classifiers=[
         'Intended Audience :: Science/Research',
         'License :: OSI Approved :: MIT License',
         'Programming Language :: Python :: 3',
     ],
+    
+    include_package_data=True,
+    setup_requires=['setuptools_scm'],
+
 )
diff --git a/tests/test_candi.py b/tests/test_candi.py
index dd64b59..74f1a08 100644
--- a/tests/test_candi.py
+++ b/tests/test_candi.py
@@ -2,6 +2,7 @@
 import pandas as pd
 import numpy as np
 from CanDI.structures.entity import Entity 
+from CanDI.setup.manager import Manager
 
 
 class testEntity(unittest.TestCase):
@@ -92,5 +93,6 @@ def test_canc_filters(self):
         self.assertIsInstance(over, pd.core.frame.DataFrame)
         self.assertIsInstance(under, pd.core.frame.DataFrame)
 
-
-
+class testManager(unittest.TestCase):
+    #TODO: Implement tests for Manager class
+    pass
\ No newline at end of file