LIMS: Changes to make samplesheet compatible with pipeline

1_TSO500.sh

@@ -73,7 +73,7 @@ set -u
 cp "$raw_data"/SampleSheet.csv .
 
 # remove header from samplesheet
-sed -n -e '/Sample_ID,Sample_Name/,$p' SampleSheet.csv >> SampleSheet_updated.csv
+sed -n -e '/Sample_ID,Sample_Plate/,$p' SampleSheet.csv >> SampleSheet_updated.csv
 
 # make a list of samples and get correct order of samples for each worksheet
 python "$pipeline_scripts"/filter_sample_list.py

scripts/filter_sample_list.py

@@ -3,6 +3,7 @@
 include dictionary to translate referral types
 
 """
+import csv
 
 #Open sample sheet
 samplesheet = open('SampleSheet_updated.csv','r')
@@ -28,62 +29,70 @@
 dna = set()
 rna = set()
 
+#Get column by header name instead of header position.
+read_samplesheet = csv.DictReader(samplesheet)
+
 #Go through samplesheet until you hit the header lines
-for line in samplesheet:
+for line in read_samplesheet:
 
-	#Remove new line character
-	line = line.strip()
-
-	#Skip if header line
-	if line.startswith('Sample'):
-
-		next
-
-	else:
-
-		#Split line into list
-		line = line.split(",")
-
-		#Get columns we need from sample sheet
-		sample_id = line[0]
-		worksheet = line[2]
-		sample_type = line[7]
-		description = line[9]
+	#Get columns we need from sample sheet
+	sample_id = line["Sample_ID"]
+	worksheet = line["Sample_Plate"]
+	sample_type = line["Sample_Type"]
+	description = line["Description"]
+
+	#Append Sample ID (first element in list) to sample list
+	samplelist.write(sample_id+"\n")
+
+	# Split the decription column up, as now additional referrals section
+	desc_parts = description.split(";")
+	desc_dict = {}
+	for part in desc_parts:
+		if "=" in part:
+			key, value = part.split("=", 1)
+			desc_dict[key] = value
+
+	#Get referral from Description (tenth element in list), split by ; and get third element
+	referral = desc_dict.get("referral", "null")
+
+	#if RNA, update referral based on dictionary
+	if sample_type == "RNA" and (referral in referral_dict):
+
+		referral = referral_dict[referral]
+
+	#Add worksheet to set
+	if sample_type == "DNA":
+		dna.add(worksheet)
 
-		#Append Sample ID (first element in list) to sample list
-		samplelist.write(sample_id+"\n")
+	elif sample_type == "RNA":
+		rna.add(worksheet)
 
-		#Get referral from Description (tenth element in list), split by ; and get third element
-		referral = description.split(";")[2]
-		referral = referral.split("=")[1]
+	#Write to samples correct order
+	samplescorrect = open('samples_correct_order_'+worksheet+"_"+sample_type+".csv",'a') 
 
-		#if RNA, update referral based on dictionary
-		if sample_type == "RNA" and (referral in referral_dict):
+	samplescorrect.write(sample_id+","+worksheet+","+sample_type+","+referral+"\n")
 
-			referral = referral_dict[referral]
-
-		#Add worksheet to set
-		if sample_type == "DNA":
-			dna.add(worksheet)
-
-		elif sample_type == "RNA":
-			rna.add(worksheet)
+	samplescorrect.close()
 
-		#Write to samples correct order
-		samplescorrect = open('samples_correct_order_'+worksheet+"_"+sample_type+".csv",'a') 
-
-		samplescorrect.write(sample_id+","+worksheet+","+sample_type+","+referral+"\n")
+	#Write any aml referral samples to additional csv
+	if referral == "aml":
+		samplesaml = open("samples_aml_to_myeloid_"+worksheet+"_"+sample_type+".csv",'a')
 
-		samplescorrect.close()
-
-		#Write any aml referral samples to additional csv
-		if referral == "aml":
-			samplesaml = open("samples_aml_to_myeloid_"+worksheet+"_"+sample_type+".csv",'a')
-
-			samplesaml.write(sample_id+",myeloid\n")
-
-			samplesaml.close()
-
+		samplesaml.write(sample_id+",myeloid\n")
+
+		samplesaml.close()
+
+	# Get additional referrals to make one csv per referral
+	additional_referrals = desc_dict.get("additional_referrals", "")
+	if additional_referrals:
+		for add_ref in additional_referrals.split(","):
+			add_ref = add_ref.strip()
+			if add_ref:
+				add_ref_file = open(
+					"samples_additional_referral_"+add_ref+"_"+worksheet+"_"+sample_type+".csv", 'a'	
+				)
+				add_ref_file.write(sample_id+","+add_ref+"\n")
+				add_ref_file.close()
 
 #Write out worksheets to file
 with open('worksheets_dna.txt','w') as f: