ddi-fw 0.0.4__tar.gz → 0.0.6__tar.gz

{ddi_fw-0.0.4 → ddi_fw-0.0.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.2
 Name: ddi_fw
-Version: 0.0.4
+Version: 0.0.6
 Summary: Do not use :)
 Home-page: UNKNOWN
 Author: Kıvanç Bayraktar

{ddi_fw-0.0.4 → ddi_fw-0.0.6}/ddi_fw/datasets/core.py

@@ -9,7 +9,7 @@ from ddi_fw.datasets.idf_helper import IDF
 
 from ddi_fw.utils.zip_helper import ZipHelper
 from .feature_vector_generation import SimilarityMatrixGenerator, VectorGenerator
-from ner.ner import CTakesNER
+from ddi_fw.ner.ner import CTakesNER
 from ddi_fw.utils import create_folder_if_not_exists
 from stopwatch import Stopwatch, profile
 

ddi_fw-0.0.6/ddi_fw/datasets/custom/__init__.py

@@ -0,0 +1 @@
+from .base import CustomDataset

ddi_fw-0.0.6/ddi_fw/datasets/custom/base.py

@@ -0,0 +1,148 @@
+import pathlib
+import numpy as np
+
+import pandas as pd
+from ..idf_helper import IDF
+
+from ddi_fw.utils.zip_helper import ZipHelper
+from .. import BaseDataset
+from ..db_utils import create_connection
+
+HERE = pathlib.Path(__file__).resolve().parent
+
+'''
+uses drugbank_db.zip
+'''
+
+
+class CustomDataset(BaseDataset):
+    def __init__(self,  index_path, chemical_property_columns=['enzyme',
+                                             'target',
+                                             'pathway',
+                                             'smile'],
+                 drugbank_ids=[],
+                 embedding_columns=['indication'],
+                #  ner_columns = ['tui_description','cui_description', 'entities_description'],
+                 ner_columns = ['tui','cui', 'entities'],
+                 threshold_method='idf',
+                 threshold_val=0
+                 ):
+        super().__init__(chemical_property_columns, embedding_columns, ner_columns, threshold_method, threshold_val)
+
+        # self.embedding_columns = embedding_columns
+        # self.columns = columns
+
+        self.drugbank_ids = drugbank_ids
+
+        zip_helper = ZipHelper()
+        # zip_helper.extract(input_path=str(HERE.joinpath('drugbank_db.zip')), output_path=str(HERE))
+        zip_helper.extract(input_path=str(HERE), output_path=str(HERE))
+        # kwargs = {'index_path': str(HERE.joinpath('indexes'))}
+
+        # db = HERE.joinpath('event.db')
+        db = HERE.joinpath('drugbank.db')
+        conn = create_connection(db)
+        self.drugs_df = self.__select_all_drugs_as_dataframe__(conn)
+        # dataframe'de olan ilaçlar arasındaki etkileşimleri bulmak için
+        # self.drugbank_ids = self.drugs_df['id'].to_list()  ???
+        self.ddis_df = self.__select_all_events__(conn)
+
+        # self.index_path = kwargs.get('index_path')
+        self.index_path = index_path
+
+    def __select_all_events__(self, conn):
+        param = tuple(self.drugbank_ids)
+        cur = conn.cursor()
+        query = f'''
+            select
+                _Interactions."index",
+                drug_1_id,
+                drug_1,
+                drug_2_id,
+                drug_2,
+                mechanism_action, 
+                interaction, 
+                masked_interaction
+            from _Interactions '''
+        if len(self.drugbank_ids) > 0:
+            query = query + \
+                (f''' where drug_1_id in {format(param)} and drug_2_id in {format(param)}''')
+
+        cur.execute(query)
+
+        rows = cur.fetchall()
+
+        headers = ['index', 'id1', 'name1', 'id2', 'name2',
+                   'event_category', 'interaction', 'masked_interaction']
+        df = pd.DataFrame(columns=headers, data=rows)
+        return df
+
+    # TODO tuis_description, entities_description, belli bir eşik değeri altında olanı ignore etmek lazım
+    def __select_all_drugs_as_dataframe__(self, conn):
+        param = tuple(self.drugbank_ids)
+        query = f'''
+            select 
+            _Drugs."index",
+            drugbank_id,
+            _Drugs.name,
+            description,
+            synthesis_reference,
+            indication,
+            pharmacodynamics,
+            mechanism_of_action,
+            toxicity,
+            metabolism,
+            absorption,
+            half_life,
+            protein_binding,
+            route_of_elimination,
+            volume_of_distribution,
+            clearance,
+            smiles,
+            smiles_morgan_fingerprint,
+            enzymes_polypeptides,
+            targets_polypeptides,
+            pathways,
+            tuis_description,
+            cuis_description,
+            entities_description
+                    
+            from _Drugs '''
+
+        if len(self.drugbank_ids) > 0:
+            query = query + f'''where 
+                drugbank_id in {format(param)} and
+                targets_polypeptides is not null and 
+                enzymes_polypeptides is not null and 
+                pathways is not null and 
+                smiles_morgan_fingerprint is not null'''
+        cur = conn.cursor()
+        cur.execute(query)
+
+        # pathway is absent
+
+        rows = cur.fetchall()
+        headers = ['index', 'id', 'name', 'description', 'synthesis_reference', 'indication', 'pharmacodynamics', 'mechanism_of_action', 'toxicity', 'metabolism', 'absorption', 'half_life',
+                   'protein_binding', 'route_of_elimination', 'volume_of_distribution', 'clearance', 'smiles_notation', 'smile', 'enzyme', 'target', 'pathway',
+                   'tui_description', 'cui_description', 'entities_description']
+        df = pd.DataFrame(columns=headers, data=rows)
+        df['smile'] = df['smile'].apply(lambda x:
+                                        np.fromstring(
+                                            x.replace(
+                                                '\n', '')
+                                            .replace('[', '')
+                                            .replace(']', '')
+                                            .replace('  ', ' '), sep=','))
+        df['enzyme'] = df['enzyme'].apply(
+            lambda x: x.split('|') if x is not None else [])
+        df['target'] = df['target'].apply(
+            lambda x: x.split('|') if x is not None else [])
+        df['pathway'] = df['pathway'].apply(
+            lambda x: x.split('|') if x is not None else [])
+        df['tui_description'] = df['tui_description'].apply(
+            lambda x: x.split('|') if x is not None else [])
+        df['cui_description'] = df['cui_description'].apply(
+            lambda x: x.split('|') if x is not None else [])
+        df['entities_description'] = df['entities_description'].apply(
+            lambda x: x.split('|') if x is not None else [])
+        return df

ddi_fw-0.0.6/ddi_fw/datasets/ddi_mdl/base.py

@@ -0,0 +1,63 @@
+import pathlib
+
+import pandas as pd
+from .. import BaseDataset
+from ..db_utils import create_connection
+
+HERE = pathlib.Path(__file__).resolve().parent
+
+
+class DDIMDLDataset(BaseDataset):
+    def __init__(self,  chemical_property_columns=['enzyme',
+                                                   'target',
+                                                   'pathway',
+                                                   'smile'],
+                 embedding_columns=[],
+                 ner_columns=[],
+                 **kwargs):
+
+        super().__init__(chemical_property_columns, embedding_columns,
+                         ner_columns, **kwargs)
+
+        # kwargs = {'index_path': str(HERE.joinpath('indexes'))}
+        kwargs['index_path']= str(HERE.joinpath('indexes'))
+
+        db = HERE.joinpath('event.db')
+        conn = create_connection(db)
+        print("db prep")
+        self.drugs_df = self.__select_all_drugs_as_dataframe__(conn)
+        self.ddis_df = self.__select_all_events__(conn)
+        print("db bitti")
+        self.index_path = kwargs.get('index_path')
+
+    def __select_all_drugs_as_dataframe__(self, conn):
+        headers = ['index', 'id', 'name',
+                   'target', 'enzyme', 'pathway', 'smile']
+        cur = conn.cursor()
+        cur.execute(
+            '''select "index", id, name, target, enzyme, pathway, smile from drug''')
+        rows = cur.fetchall()
+        df = pd.DataFrame(columns=headers, data=rows)
+        df['enzyme'] = df['enzyme'].apply(lambda x: x.split('|'))
+        df['target'] = df['target'].apply(lambda x: x.split('|'))
+        df['pathway'] = df['pathway'].apply(lambda x: x.split('|'))
+        df['smile'] = df['smile'].apply(lambda x: x.split('|'))
+        return df
+
+    def __select_all_events__(self, conn):
+        """
+        Query all rows in the event table
+        :param conn: the Connection object
+        :return:
+        """
+        cur = conn.cursor()
+        cur.execute('''
+                select ex."index", d1.id, d1.name, d2.id, d2.name,  mechanism || ' ' ||action from extraction ex
+                join drug d1 on  d1.name = ex.drugA
+                join drug d2 on  d2.name = ex.drugB
+        ''')
+
+        rows = cur.fetchall()
+
+        headers = ["index", "id1", "name1", "id2", "name2", "event_category"]
+        return pd.DataFrame(columns=headers, data=rows)

ddi_fw-0.0.6/ddi_fw/datasets/mdf_sa_ddi/__init__.py

@@ -0,0 +1,3 @@
+from .base import MDFSADDIDataset
+
+__all__ = ['MDFSADDIDataset']

ddi_fw-0.0.6/ddi_fw/datasets/mdf_sa_ddi/base.py

@@ -0,0 +1,138 @@
+import os
+import pathlib
+import sqlite3
+from sqlite3 import Error
+import pandas as pd
+
+from ddi_fw.utils import ZipHelper
+
+from ..core import BaseDataset
+# from ..db_utils import create_connection, select_all_drugs_as_dataframe, select_events_with_category
+
+HERE = pathlib.Path(__file__).resolve().parent
+
+
+class MDFSADDIDataset(BaseDataset):
+    def __init__(self, chemical_property_columns=['enzyme',
+                                                  'target',
+                                                  'smile'],
+                 embedding_columns=[],
+                 ner_columns=[],
+                 **kwargs):
+
+        super().__init__(chemical_property_columns, embedding_columns,
+                         ner_columns, **kwargs)
+
+        db_zip_path = HERE.joinpath('mdf-sa-ddi.zip')
+        db_path = HERE.joinpath('mdf-sa-ddi.db')
+        if not os.path.exists(db_zip_path):
+            self.__to_db__(db_path)
+        else:
+            ZipHelper().extract(
+                input_path=str(HERE), output_path=str(HERE))
+            conn = create_connection(db_path)
+            self.drugs_df = select_all_drugs_as_dataframe(conn)
+            self.ddis_df = select_all_events_as_dataframe(conn)
+        kwargs = {'index_path': str(HERE.joinpath('indexes'))}
+
+        self.index_path = kwargs.get('index_path')
+
+    def __to_db__(self, db_path):
+        conn = create_connection(db_path)
+        drugs_path = HERE.joinpath('drug_information_del_noDDIxiaoyu50.csv')
+        ddis_path = HERE.joinpath('df_extraction_cleanxiaoyu50.csv')
+        self.drugs_df = pd.read_csv(drugs_path)
+        self.ddis_df = pd.read_csv(ddis_path)
+        self.drugs_df.drop(columns="Unnamed: 0", inplace=True)
+        self.ddis_df.drop(columns="Unnamed: 0", inplace=True)
+
+        self.ddis_df.rename(
+            columns={"drugA": "name1", "drugB": "name2"}, inplace=True)
+        self.ddis_df['event_category'] = self.ddis_df['mechanism'] + \
+            ' ' + self.ddis_df['action']
+
+        reverse_ddis_df = pd.DataFrame()
+        reverse_ddis_df['id1'] = self.ddis_df['id2']
+        reverse_ddis_df['name1'] = self.ddis_df['name2']
+        reverse_ddis_df['id2'] = self.ddis_df['id1']
+        reverse_ddis_df['name2'] = self.ddis_df['name1']
+        reverse_ddis_df['event_category'] = self.ddis_df['event_category']
+
+        self.ddis_df = pd.concat(
+            [self.ddis_df, reverse_ddis_df], ignore_index=True)
+
+        drug_name_id_pairs = {}
+        for idx, row in self.drugs_df.iterrows():
+            drug_name_id_pairs[row['name']] = row['id']
+
+        # id1,id2
+
+        def lambda_fnc1(column):
+            return drug_name_id_pairs[column]
+        # def lambda_fnc2(row):
+        #     x  = self.drugs_df[self.drugs_df['name'] == row['name2']]
+        #     return x['id']
+
+        self.ddis_df['id1'] = self.ddis_df['name1'].apply(
+            lambda_fnc1)  # , axis=1
+        self.ddis_df['id2'] = self.ddis_df['name2'].apply(
+            lambda_fnc1)  # , axis=1
+        self.drugs_df.to_sql('drug', conn, if_exists='replace', index=False)
+        self.ddis_df.to_sql('event', conn, if_exists='replace', index=False)
+        ZipHelper().zip_single_file(
+            file_path=db_path, output_path=HERE, name='mdf-sa-ddi')
+
+
+def create_connection(db_file=r"mdf-sa-ddi.db"):
+    """ create a database connection to the SQLite database
+        specified by db_file
+    :param db_file: database file
+    :return: Connection object or None
+    """
+    conn = None
+    try:
+        conn = sqlite3.connect(db_file)
+    except Error as e:
+        print(e)
+
+    return conn
+
+
+def select_all_drugs(conn):
+    cur = conn.cursor()
+    cur.execute(
+        '''select "index", id, name, target, enzyme, smile from drug''')
+    rows = cur.fetchall()
+    return rows
+
+
+def select_all_drugs_as_dataframe(conn):
+    headers = ['index', 'id', 'name', 'target', 'enzyme', 'smile']
+    rows = select_all_drugs(conn)
+    df = pd.DataFrame(columns=headers, data=rows)
+    df['enzyme'] = df['enzyme'].apply(lambda x: x.split('|'))
+    df['target'] = df['target'].apply(lambda x: x.split('|'))
+    df['smile'] = df['smile'].apply(lambda x: x.split('|'))
+    return df
+
+
+def select_all_events(conn):
+    """
+    Query all rows in the event table
+    :param conn: the Connection object
+    :return:
+    """
+    cur = conn.cursor()
+    cur.execute('''
+                select event."index", id1, name1, id2, name2, mechanism, action, event_category from event
+                ''')
+
+    rows = cur.fetchall()
+    return rows
+
+
+def select_all_events_as_dataframe(conn):
+    headers = ["index", "id1", "name1", "id2",
+               "name2", "mechanism", "action", "event_category"]
+    rows = select_all_events(conn)
+    return pd.DataFrame(columns=headers, data=rows)

{ddi_fw-0.0.4 → ddi_fw-0.0.6}/ddi_fw/drugbank/drugbank_processor.py

@@ -11,7 +11,7 @@ from rdkit import Chem
 from rdkit.Chem import AllChem
 import numpy as np
 from ddi_fw.drugbank.event_extractor import EventExtractor
-from ner.ner import CTakesNER
+from ddi_fw.ner.ner import CTakesNER
 
 from ddi_fw.utils import ZipHelper
 # from event_extractor import EventExtractor

{ddi_fw-0.0.4 → ddi_fw-0.0.6}/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 1.2
 Name: ddi-fw
-Version: 0.0.4
+Version: 0.0.6
 Summary: Do not use :)
 Home-page: UNKNOWN
 Author: Kıvanç Bayraktar

{ddi_fw-0.0.4 → ddi_fw-0.0.6}/ddi_fw.egg-info/SOURCES.txt

@@ -11,6 +11,11 @@ ddi_fw/datasets/embedding_generator.py
 ddi_fw/datasets/embedding_generator_new.py
 ddi_fw/datasets/feature_vector_generation.py
 ddi_fw/datasets/idf_helper.py
+ddi_fw/datasets/custom/__init__.py
+ddi_fw/datasets/custom/base.py
+ddi_fw/datasets/ddi_mdl/base.py
+ddi_fw/datasets/mdf_sa_ddi/__init__.py
+ddi_fw/datasets/mdf_sa_ddi/base.py
 ddi_fw/drugbank/__init__.py
 ddi_fw/drugbank/drugbank_parser.py
 ddi_fw/drugbank/drugbank_processor.py

{ddi_fw-0.0.4 → ddi_fw-0.0.6}/ddi_fw.egg-info/top_level.txt

@@ -1,4 +1,7 @@
 ddi_fw/datasets
+ddi_fw/datasets/custom
+ddi_fw/datasets/ddi_mdl
+ddi_fw/datasets/mdf_sa_ddi
 ddi_fw/drugbank
 ddi_fw/experiments
 ddi_fw/ner

ddi_fw-0.0.6/setup.py

@@ -0,0 +1,17 @@
+from setuptools import setup, find_packages
+setup(
+    name='ddi_fw',
+    version='0.0.6',
+    author='Kıvanç Bayraktar',
+    author_email='bayraktarkivanc@gmail.com',
+    description='Do not use :)',
+    # packages=find_packages(),
+    packages=['ddi_fw/datasets', 'ddi_fw/datasets/mdf_sa_ddi', 'ddi_fw/datasets/ddi_mdl',
+              'ddi_fw/datasets/custom', 'ddi_fw/drugbank',  'ddi_fw/experiments', 'ddi_fw/ner', 'ddi_fw/utils'],
+    classifiers=[
+        'Programming Language :: Python :: 3',
+        'License :: OSI Approved :: MIT License',
+        'Operating System :: OS Independent',
+    ],
+    python_requires='>=3.6',
+)

ddi_fw-0.0.4/setup.py

@@ -1,16 +0,0 @@
-from setuptools import setup, find_packages
-setup(
-name='ddi_fw',
-version='0.0.4',
-author='Kıvanç Bayraktar',
-author_email='bayraktarkivanc@gmail.com',
-description='Do not use :)',
-# packages=find_packages(),
-packages=['ddi_fw/datasets','ddi_fw/drugbank','ddi_fw/experiments','ddi_fw/ner','ddi_fw/utils'],
-classifiers=[
-'Programming Language :: Python :: 3',
-'License :: OSI Approved :: MIT License',
-'Operating System :: OS Independent',
-],
-python_requires='>=3.6',
-)