adding paths to fda thresholds and adding condition to remove extra row from itb review files if it exist

Author: evelyn-schmidt

scripts/fda_quality_thresholds.csv

@@ -1,18 +1,18 @@
 Criteria,Threshold for pass/failure
-TOTAL_READS (tumor DNA),>250M
-TOTAL_READS (normal DNA),>100M
-TOTAL_READS (tumor RNA),>200M
-PCT_PF_READS_ALIGNED (tumor/normal DNA),>95%
-PCT_PF_READS_ALIGNED (tumor RNA),>85%
-PCT_USABLE_BASES_ON_TARGET  (tumor/normal DNA),>20%
-PCT_EXC_OFF_TARGET  (tumor/normal DNA),<60%
-PERCENT_DUPLICATION  (tumor/normal DNA),<40%
-MEAN_TARGET_COVERAGE (tumor DNA),>250x
-MEAN_TARGET_COVERAGE (normal DNA),>100x
-PCT_TARGET_BASES_20X  (tumor/normal DNA),>95%
-PCT_READS_ALIGNED_IN_PAIRS  (tumor/normal DNA),>95%
-MEAN_INSERT_SIZE (tumor/normal DNA),125 - 300bp
-PF_MISMATCH_RATE_1 (tumor/normal DNA),<0.75%
-PF_MISMATCH_RATE_2 (tumor/normal DNA),<1.00%
-Genotype Concordance (tumor/normal DNA),>95%
-Contamination Estimate (tumor/normal DNA),<7.5%
+TOTAL_READS (tumor DNA),>250M,/qc/fda_metrics/unaligned_sample/sample_table1.csv
+TOTAL_READS (normal DNA),>100M,/qc/fda_metrics/unaligned_sample/sample_table1.csv
+TOTAL_READS (tumor RNA),>200M,/qc/fda_metrics/unaligned_sample/sample_table1.csv
+PCT_PF_READS_ALIGNED (tumor/normal DNA),>95%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PCT_PF_READS_ALIGNED (tumor RNA),>85%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PCT_USABLE_BASES_ON_TARGET  (tumor/normal DNA),>20%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PCT_EXC_OFF_TARGET  (tumor/normal DNA),<60%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PERCENT_DUPLICATION  (tumor/normal DNA),<40%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+MEAN_TARGET_COVERAGE (tumor DNA),>250x,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+MEAN_TARGET_COVERAGE (normal DNA),>100x,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PCT_TARGET_BASES_20X  (tumor/normal DNA),>95%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PCT_READS_ALIGNED_IN_PAIRS  (tumor/normal DNA),>95%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+MEAN_INSERT_SIZE (tumor/normal DNA),125 - 300bp,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PF_MISMATCH_RATE_1 (tumor/normal DNA),<0.75%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+PF_MISMATCH_RATE_2 (tumor/normal DNA),<1.00%,/qc/fda_metrics/aligned_sample/aligned_sample_table2.csv
+Genotype Concordance (tumor/normal DNA),>95%,/qc/concordance/concordance.somalier.pairs.tsv
+Contamination Estimate (tumor/normal DNA),<7.5%,/qc/sample/normal.VerifyBamId.selfSM

scripts/generate_reviews_files.py

@@ -83,10 +83,23 @@ def main():
     reviewed_candidates = pd.read_excel(args.a)
 
 
-    reviewed_candidates.columns = reviewed_candidates.iloc[0]
-    reviewed_candidates = reviewed_candidates[1:] # there is a extra row before the col name row
-    reviewed_candidates = reviewed_candidates.reset_index(drop=True) # Reset the index of the dataframe
+    #reviewed_candidates.columns = reviewed_candidates.iloc[0]
+    #reviewed_candidates = reviewed_candidates[1:] # there is a extra row before the col name row
+    #reviewed_candidates = reviewed_candidates.reset_index(drop=True) # Reset the index of the dataframe
 
+    # Check if the first row is blank
+    if reviewed_candidates.iloc[0].isnull().all():
+        # Remove the first row if it's blank
+        reviewed_candidates = reviewed_candidates[1:]
+        # If there are still rows in the DataFrame, proceed with the operations
+        if not reviewed_candidates.empty:
+            # Set the columns to the values of the first row
+            reviewed_candidates.columns = reviewed_candidates.iloc[0]
+            # Skip the first row (which is now the column names)
+            reviewed_candidates = reviewed_candidates[1:]
+            # Reset the index of the DataFrame
+            reviewed_candidates = reviewed_candidates.reset_index(drop=True)
+
     reviewed_candidates = reviewed_candidates[reviewed_candidates.Evaluation != "Pending"]
     reviewed_candidates = reviewed_candidates[reviewed_candidates.Evaluation != "Reject"]