updates

Author: evelyn-schmidt

Dockerfile

@@ -9,7 +9,7 @@ ADD scripts/fda_quality_thresholds.csv /opt/scripts/fda_quality_thresholds.csv
 ADD scripts/generate_reviews_files.py /opt/scripts/generate_reviews_files.py
 ADD scripts/bold_classII.py /opt/scripts/bold_classII.py
 ADD scripts/color_peptides51mer.py /opt/scripts/color_peptides51mer.py
-ADD scripts/setup_reivew.py /opt/scripts/setup_review.py
+ADD scripts/setup_review.py /opt/scripts/setup_review.py
 
 RUN chmod +r /opt/scripts/*
 

scripts/color_peptides51mer.py

@@ -115,7 +115,6 @@ def set_underline(peptide_sequence, mutant_peptide_pos, row_ID):
     frameshift = False
     classI_position = 0
 
-    print(row_ID)
     if '-' in mutant_peptide_pos:
         positions = mutant_peptide_pos.split("-")
         start_position = int(positions[0])
@@ -251,12 +250,12 @@ def main():
     # Create a universal ID by editing the peptide 51mer ID
     peptides_51mer.rename(columns={'ID': 'full ID'}, inplace=True)
     peptides_51mer['ID'] = peptides_51mer['full ID']
-    print()
 
     peptides_51mer['ID'] = peptides_51mer['ID'].apply(lambda x: '.'.join(x.split('.')[1:]))  # Removing before first period, periods will be removed 
 
     peptides_51mer['ID'] = peptides_51mer['ID'].apply(lambda x: '.'.join(x.split('.')[1:]))  # Removing before second period
     peptides_51mer['ID'] = peptides_51mer['ID'].apply(lambda x: '.'.join(x.split('.')[:3]) + '.' + '.'.join(x.split('.')[4:]))
+    
 
     for index, row in peptides_51mer.iterrows():
         for i, char in enumerate(row['ID'][::-1]):
@@ -306,7 +305,9 @@ def main():
         classII_peptide = merged_peptide_51mer.loc[merged_peptide_51mer['full ID'] == search_string, 'Best Peptide Class II'].values[0]
         #classI_sequence 
         classI_peptide = merged_peptide_51mer.loc[merged_peptide_51mer['full ID'] == search_string, 'Best Peptide Class I'].values[0]
-        # mutant pepetide position --- not working yet becasue of STUPID frameshift
+        
+        
+        # mutant pepetide position ---
         mutant_peptide_pos = str(merged_peptide_51mer.loc[merged_peptide_51mer['full ID'] == search_string, 'Pos'].values[0])
 
         # Find the tag containing the search string
@@ -326,9 +327,7 @@ def main():
 
             # actaully lets break class I and classII into two steps and handle the mutated nucleotide in class I function
             # it should be basically like at that position in the class I set 
-
-            print(row['full ID'])
-            print(mutant_peptide_pos)
+            
             set_underline(peptide_sequence, mutant_peptide_pos, row['full ID'])
 
             set_span_tags(peptide_sequence) # pass by reference
@@ -340,7 +339,10 @@ def main():
             modified_html = peptides_51mer_soup.prettify(formatter=None)
 
         else:
-            print("\nSearch string: ", search_string, " not found.\n")
+            print("\nNOT FOUND: ", search_string)
+            print("Mutant Peptide Position: ", mutant_peptide_pos)
+            print("ClassI: ", classI_peptide)
+            print("ClassII: ", classII_peptide, "\n")
 
     with open(args.o, "w", encoding = 'utf-8') as file:
         file.write(modified_html)

scripts/get_FDA_thresholds.py

@@ -36,9 +36,9 @@ def parse_arguments():
     parser.add_argument("--una_n_dna", help="file path for unaligned normal dna FDA report table")
     parser.add_argument("--una_t_dna", help="file path for unaligned tumor dna FDA report table")
     parser.add_argument("--una_t_rna", help="file path for unaligned tumor rna FDA report table")
-    parser.add_argument("--somalier", help="file path for Somalier results for sample tumor/normal sample relatedness")
+    parser.add_argument("--somalier", help="file path for Somalier results for sample tumor/normal sample relatedness (concordance.somalier.pairs.tsv)")
     parser.add_argument("--contam_n", help="file path for VerifyBamID results for contamination the normal sample")
-    parser.add_argument("--contam_t", help="file path for VerifyBamID results for contamination the tumor sample")
+    parser.add_argument("--contam_t", help="file path for VerifyBamID results for contamination the tumor dna sample")
 
     return(parser.parse_args())
 
@@ -362,7 +362,7 @@ def main():
 
 
     if args.WB:
-        qc.to_csv(args.WB + final_result + '/qc/fda_quality_thresholds_report.tsv', sep="\t", index=False)
+        qc.to_csv(args.WB + final_result + '/fda_quality_thresholds_report.tsv', sep="\t", index=False)
     else:
         qc.to_csv('fda_quality_thresholds_report.tsv', sep="\t", index=False)
 

scripts/get_neoantigen_qc.py

@@ -274,13 +274,16 @@ def main():
     else:
         qc_file = open('qc_file.txt', 'w')
 
-    
+    print()
+    print()
+
     qc_file.write(get_read_pairs(normal_dna, tumor_dna, tumor_rna))
     qc_file.write(get_relatedness(concordance))
     qc_file.write(get_contaimination(contamination_normal, contamination_tumor))
     qc_file.write(get_rna_alignment(rna_metrics))
     qc_file.write(check_strand(strandness_check,  yaml_file))
     qc_file.write(get_variant_count(final_variants))
+    qc_file.write("REMEMBER to visually inspect end bias plot (usually found in qc/tumor_rna/rna_metrics.pdf)")
 
     print()
     print("REMEMBER to visually inspect end bias plot (usually found in qc/tumor_rna/rna_metrics.pdf)")

scripts/setup_review.py

@@ -4,10 +4,9 @@
 # Define the command-line arguments
 parser = argparse.ArgumentParser(description='Sets up manuel review files')
 
+parser.add_argument('-samp', help='Name of the sample')
 parser.add_argument('-a', help='Path to ITB Reviewed Candidates')
 parser.add_argument('-c', help='Path to annotated_filtered.vcf-pass-51mer.fa.manufacturability.tsv')
-parser.add_argument('-samp', help='Name of the sample')
-parser.add_argument('-f', "--fin_results", help='Name of the final results folder')
 
 parser.add_argument('-classI', help='Path to classI all_epitopes.aggregated.tsv', required=True)
 parser.add_argument('-classII', help='Path to classII all_epitopes.aggregated.tsv', required=True)
@@ -24,8 +23,8 @@
 
 
 
-command1 = f"python scripts/generate_reviews_files.py -a {args.a} -c {args.c} -samp {args.samp}"
-command2 = f"python scripts/color_peptides51mer.py -p {args.samp}_Peptides_51-mer.xlsx -classI {args.classI} -classII {args.classII} -o {args.o}"
+command1 = f"python /opt/scripts/generate_reviews_files.py -a {args.a} -c {args.c} -samp {args.samp}"
+command2 = f"python /opt/scripts/color_peptides51mer.py -p {args.samp}_Peptides_51-mer.xlsx -classI {args.classI} -classII {args.classII} -o {args.o}"
 
 
 # Execute the first script