picture

README.md

@@ -31,6 +31,8 @@ choppy install renluyao/WGS_germline_datapotal
 
 ![workflow](./pictures/workflow.png)
 
+![](./pictures/table.png)
+
 ### 1. 原始数据质量控制
 
 #### [Fastqc](<https://www.bioinformatics.babraham.ac.uk/projects/fastqc/>) v0.11.5

codescripts/D5_D6.py

@@ -29,14 +29,14 @@ snv_sister_diff = 0
 
 for row in sister_dat.itertuples():
 	# snv indel
-	if ',' in row.ALT:
-		alt = row.ALT.split(',')
+	if ',' in row[4]:
+		alt = row[4].split(',')
 		alt_len = [len(i) for i in alt]
 		alt_max = max(alt_len)
 	else:
-		alt_max = len(row.ALT)
+		alt_max = len(row[4])
 	alt = alt_max
-	ref = row.REF
+	ref = row[3]
 	if len(ref) == 1 and alt == 1:
 		cate = 'SNV'
 	elif len(ref) > alt:
@@ -62,12 +62,6 @@ for row in sister_dat.itertuples():
 			sister_count = "no"
 		else:
 			sister_count = "yes_diff"
-	if sister_count == 'yes_same':
-		sister_same += 1
-	elif sister_count == 'yes_diff':
-		sister_diff += 1
-	else:
-		pass
 	if cate == 'SNV':
 		if sister_count == 'yes_same':
 			snv_sister_same += 1
@@ -86,9 +80,11 @@ for row in sister_dat.itertuples():
 indel_sister = indel_sister_same/(indel_sister_same + indel_sister_diff)
 snv_sister = snv_sister_same/(snv_sister_same + snv_sister_diff)
 outcolumn =  'Project\tReproducibility_D5_D6\n'
-outResult = project_name + '\t' + str(sister)  + '\n'
+indel_outResult = project_name + '.INDEL' + '\t' + str(indel_sister)  + '\n'
+snv_outResult = project_name + '.SNV' + '\t' + str(snv_sister)  + '\n'
 output_file.write(outcolumn)
-output_file.write(outResult)
+output_file.write(indel_outResult)
+output_file.write(snv_outResult)