Merge pull request #13 from Center-for-Health-Data-Science/update_recount3

Several updates to the Recount3 subpackage

Author: ValeSora

bulkDGD/execs/dgd_get_recount3_data.py

@@ -262,6 +262,9 @@ def main():
     # Create a list to store the futures.
     futures = []
 
+    # Create a set to store the names of the output/log files.
+    output_names = set()
+
     # For each row of the data frame containing the samples' batches
     for num_batch, row in enumerate(df.itertuples(index = False), 1):
 
@@ -288,9 +291,29 @@ def main():
 
         #-------------------------------------------------------------#
 
+        # Get the overall name for the output/log files.
+        output_name = f"{project_name}_{samples_category}"
+
+        # Set a counter in case the name already exists and we need
+        # to name the files differently.
+        counter = 1
+
+        # If the name already exists
+        while output_name in output_names:
+
+            # Uniquify the name by adding a counter.
+            output_name = output_name + f"_{counter}"
+
+            # Update the counter.
+            counter += 1
+
+        # Add the new name to the list of names.
+        output_names.add(output_name)
+
+        #-------------------------------------------------------------#
+
         # Get the name of the output file.
-        output_csv_name = \
-            f"{project_name}_{samples_category}_{num_batch}.csv"
+        output_csv_name = f"{output_name}.csv"
 
         # Get the path to the output file.
         output_csv_path = os.path.join(wd, output_csv_name)
@@ -306,8 +329,7 @@ def main():
         #-------------------------------------------------------------#
 
         # Get the path to the log file and the file's extension.
-        log_file_name = \
-            f"{project_name}_{samples_category}_{num_batch}.log"
+        log_file_name = f"{output_name}.log"
 
         # Get the path to the log file.
         log_file_path = os.path.join(wd, log_file_name)

bulkDGD/recount3/data/gtex_tissues.txt

@@ -1,6 +1,6 @@
 # `data`
 
-Last updated: 29/03/2024
+Last updated: 22/07/2024
 
 ## `gtex_metadata_fileds`
 
@@ -23,43 +23,6 @@ AGE
 DTHHRDY
 ```
 
-## `gtex_tissues.txt`
-
-A plain text file containing the list of available GTEx tissues. `dgd_get_recount3_data` uses it to check whether the user-provided tissue is valid.
-
-Example:
-
-```
-# GTEx tissue types - STUDY_NA is not included
-
-# Adipose tissue
-ADIPOSE_TISSUE
-
-# Adrenal gland
-ADRENAL_GLAND
-
-# Blood
-BLOOD
-
-# Blood vessel
-BLOOD_VESSEL
-```
-
-## `sra_codes.txt`
-
-A plain text file containing the list of available SRA codes. `dgd_get_recount3_data` uses it to check whether the user-provided SRA code is valid.
-
-Example:
-
-``` 
-# SRA codes
-
-SRP107565
-SRP149665
-SRP017465
-SRP119165
-```
-
 ## `sra_metadata_fields.txt`
 
 A plain text file containing the fields (= columns) found in the files describing the metadata associated with SRA samples downloaded from the Recount3 platform. 
@@ -78,28 +41,6 @@ sample_acc
 experiment_acc
 ```
 
-## `tcga_cancer_types.txt`
-
-A plain text file containing the list of TCGA cancer types. `dgd_get_recount3_data` uses it to check whether the user-provided cancer type is valid.
-
-Example:
-
-```
-# TCGA cancer types (from https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/tcga-study-abbreviations, CNTL, FPPP, and MISC excluded)
-
-# Adrenocortical carcinoma
-ACC
-
-# Bladder Urothelial Carcinoma
-BLCA
-
-# Breast Invasive Carcinoma
-BRCA
-
-# Cervical squamous cell carcinoma and endocervical carcinoma
-CESC
-```
-
 ## `tcga_metadata_fields.txt`
 
 A plain text file containing the fields (= columns) found in the files describing the metadata associated with TCGA samples downloaded from the Recount3 platform.