Merge pull request #74 from clinical-genomics-uppsala/clean_config_dir

feat: redo sample order extraction

config/sample_order.tsv

@@ -1,25 +1,2 @@
 Sample Order	Sample Name
-sample_001	D22-07608
-sample_002	D24-03890
-sample_003	D24-03891
-sample_004	D24-03892
-sample_005	D20-05240
-sample_006	D23-09349
-sample_007	D23-09384
-sample_008	D24-01401
-sample_009	D24-01640
-sample_010	D24-02504
-sample_011	D24-03945
-sample_012	D24-03888
-sample_013	D24-03946
-sample_014	D24-03889
-sample_015	D24-03952
-sample_016	D23-08138
-sample_017	D24-03982
-sample_018	D24-04023
-sample_019	D24-04029
-sample_020	D24-04028
-sample_021	D24-03986
-sample_022	D24-03987
-sample_023	D24-03985
-sample_024	D24-04082
+sample_001	NA12878-1

config/sample_replacement.tsv

@@ -1,24 +1 @@
-D22-07608	sample_001
-D24-03890	sample_002
-D24-03891	sample_003
-D24-03892	sample_004
-D20-05240	sample_005
-D23-09349	sample_006
-D23-09384	sample_007
-D24-01401	sample_008
-D24-01640	sample_009
-D24-02504	sample_010
-D24-03945	sample_011
-D24-03888	sample_012
-D24-03946	sample_013
-D24-03889	sample_014
-D24-03952	sample_015
-D23-08138	sample_016
-D24-03982	sample_017
-D24-04023	sample_018
-D24-04029	sample_019
-D24-04028	sample_020
-D24-03986	sample_021
-D24-03987	sample_022
-D24-03985	sample_023
-D24-04082	sample_024
+NA12878-1	sample_001

scripts/extract_samples_info.py

@@ -70,17 +70,13 @@ def get_sample_sheet_order(fastq_path):
 
     fq1_name = os.path.basename(fastq_path)
     # get the 's#' part of the illumina fastq file name
-    sample_order = fq1_name.split('_')[2]
+    fq_filename = fq1_name.split('_')[1:] # fq filename without sample id
+    sample_order = [i for i in fq_filename if i.startswith('S')][0]
     numeric_order = int(sample_order[1:])
 
     return numeric_order
 
 
-def format_sample_order(numeric_order):
-
-    return f"sample_{numeric_order:03}"
-
-
 def main(samples_file, units_file, order_file, replacement_file):
 
     try:
@@ -100,7 +96,7 @@ def main(samples_file, units_file, order_file, replacement_file):
     except ValueError:  # manually create cols with NAs when no trio present
         samples["trioid"] = ["NA"] * samples.shape[0]
         samples["trio_member"] = ["NA"] * samples.shape[0]
-    
+
     # get the trio member in english
     samples["trio_member"] = samples.apply(
         lambda x: translate_trio_member(x.trio_member, x.sex), axis=1)
@@ -124,8 +120,8 @@ def main(samples_file, units_file, order_file, replacement_file):
         ["sample_order", "sample"]].drop_duplicates().sort_values(
             by="sample_order")
 
-    sample_order_df["sample_order"] = sample_order_df["sample_order"].apply(
-        format_sample_order)
+    sample_order_df["sample_order"] = [
+        f"sample_{i:03}" for i in range(1, sample_order_df.shape[0] + 1)]
 
     sample_order_df = sample_order_df.rename(
         columns={"sample_order": "Sample Order", "sample": "Sample Name"})
@@ -152,4 +148,4 @@ def main(samples_file, units_file, order_file, replacement_file):
                         help='Path to the units file')
     args = parser.parse_args()
     main(args.samples_file, args.units_file, args.sample_order,
-         args.sample_replacement)
+         args.sample_replacement)