Merge pull request #1185 from dondi/maika-database

#1120 #1164 Fix for updating data

Author: dondi

database/network-database/constants.py

@@ -13,15 +13,4 @@ class Constants:
     PROTEIN_DATA_FILEPATH = DATA_DIRECTORY + "/protein_data.tsv"
     GENE_REGULATORY_NETWORK_DATA_FILEPATH = DATA_DIRECTORY + "/gene_regulatory_network_data.tsv"
     PROTEIN_PROTEIN_INTERACTIONS_DATA_FILEPATH = DATA_DIRECTORY + "/protein_protein_interactions_data.tsv"
-    SOURCE_DATA_FILEPATH = DATA_DIRECTORY + "/source_data.tsv"
-
-    # missing and update file paths
-    MISSING_DATA_DIRECTORY = DATA_DIRECTORY + "/missing_data"
-    UPDATE_DATA_DIRECTORY = DATA_DIRECTORY + "/update_data"
-    MISSING_GRN_GENE_DATA_FILEPATH =  MISSING_DATA_DIRECTORY + "/missing_grn_gene_data.tsv"
-    UPDATE_GRN_GENE_DATA_FILEPATH = UPDATE_DATA_DIRECTORY + "/update_grn_gene_data.tsv"
-    MISSING_PPI_GENE_DATA_FILEPATH = MISSING_DATA_DIRECTORY + "/missing_ppi_gene_data.tsv"
-    UPDATE_PPI_GENE_DATA_FILEPATH = UPDATE_DATA_DIRECTORY + "/update_ppi_gene_data.tsv"
-    MISSING_PROTEIN_DATA_FILEPATH = MISSING_DATA_DIRECTORY + "/missing_protein_data.tsv"
-    UPDATE_PROTEIN_DATA_FILEPATH = UPDATE_DATA_DIRECTORY + "/update_protein_data.tsv"
-    UPDATE_PROTEIN_NAME_DATA_FILEPATH = UPDATE_DATA_DIRECTORY + "/update_protein_name_data.tsv"
+    SOURCE_DATA_FILEPATH = DATA_DIRECTORY + "/source_data.tsv"

database/network-database/database_services/README.md

@@ -4,6 +4,4 @@ This folder contains all services for database operations. **Note:** This folder
 
 ## File Descriptions  
 
-- **`filter.py`** – Retrieves data from the database and identifies new or updated records.  
-- **`populator.py`** – Handles inserting new data into the database.  
-- **`updater.py`** – Defines the process for updating existing records when necessary.  
+- **`populator.py`** – Handles inserting new data into the database. 

database/network-database/database_services/filter.py

@@ -32,7 +32,7 @@ def process_file(self, conn, cursor, data_filepath, copy_statement):
         """
 
         # Determine if we need to drop the last column (PPI network type)
-        if self.network_mode == Constants.PPI_NETWORK_MODE and data_filepath == Constants.MISSING_PPI_GENE_DATA_FILEPATH:
+        if self.network_mode == Constants.PPI_NETWORK_MODE and data_filepath == Constants.GENE_DATA_FILEPATH:
             print("Dropping the regulator column from the input data...")
             processed_rows = []
 
@@ -72,12 +72,11 @@ class GeneDataPopulator(DataPopulator):
     def __init__(self, db_url, network_mode):
         super().__init__(db_url)
         self.network_mode = network_mode
+        self.filepath = Constants.GENE_DATA_FILEPATH
         if network_mode == Constants.GRN_NETWORK_MODE:
             self.database_namespace = Constants.GRN_DATABASE_NAMESPACE
-            self.filepath = Constants.MISSING_GRN_GENE_DATA_FILEPATH
         elif network_mode == Constants.PPI_NETWORK_MODE:
             self.database_namespace = Constants.PPI_DATABASE_NAMESPACE
-            self.filepath = Constants.MISSING_PPI_GENE_DATA_FILEPATH
         else:
             raise ValueError(f"Unknown network type: {network_mode}")
 
@@ -92,7 +91,7 @@ def get_copy_statement(self):
 class ProteinDataPopulator(DataPopulator):
     def __init__(self, db_url):
         super().__init__(db_url)
-        self.filepath = Constants.MISSING_PROTEIN_DATA_FILEPATH
+        self.filepath = Constants.PROTEIN_DATA_FILEPATH
 
     def get_copy_statement(self):
         return f"COPY {Constants.PPI_DATABASE_NAMESPACE}.protein (standard_name, gene_systematic_name, length, molecular_weight, PI, taxon_id, time_stamp, source) FROM stdin WITH CSV DELIMITER E'\\t' HEADER;"