Merge pull request #8 from simpsonlab/fix_lineage_notes

Fix lineage notes

README.md

@@ -5,9 +5,12 @@
 The `ncov_parser` package provides a suite of tools to parse the files generated
 in the Nextflow workflow and provide a QC summary file.  The package requires
 several files including:
-* <sample>.variants.tsv/<sample>.pass.vcf
+* <sample>.variants.tsv
+* <sample>.variants.norm.vcf
+* <sample>.pass.vcf
 * <sample>.per_base_coverage.bed
 * <sample>.primertrimmed.consensus.fa
+* <sample>.consensus.fasta
 * alleles.tsv
 
 An optional metadata file with qPCR ct and collection date values can be

data/test_lineages.csv

@@ -0,0 +1,4 @@
+taxon,lineage,conflict,ambiguity_score,scorpio_call,scorpio_support,scorpio_conflict,version,pangolin_version,pangoLEARN_version,pango_version,status,note
+sampleA,B.1.1.7,0.0,1.0,cB.1.1.7,0.782600,0.130400,PLEARN-v1.2.6,3.0.3,2021-05-27,v1.2.6,passed_qc,scorpio call: Alt alleles 18; Ref alleles 3; Amb alleles 0
+sampleB,B.1.1.7,0.0,1.0,cB.1.1.7,0.652200,0.130400,PLEARN-v1.2.6,3.0.3,2021-05-27,v1.2.6,passed_qc,scorpio call: Alt alleles 15; Ref alleles 3; Amb alleles 3
+sampleC,B.1.1.7,0.0,1.0,cB.1.1.7,0.782600,0.130400,PLEARN-v1.2.6,3.0.3,2021-05-27,v1.2.6,passed_qc,scorpio call: Alt alleles 18; Ref alleles 3; Amb alleles 0

ncov/parser/Lineage.py

@@ -41,7 +41,12 @@ def get_notes(self, row):
         if n is None or n == "":
             return "none"
         else:
-            return n.replace(" ", "_")
+            n_dict = n.split(' ')
+            alt = re.sub(';', '', n_dict[4])
+            ref = re.sub(';', '', n_dict[7])
+            amb = n_dict[-1]
+            return '/'.join([alt, ref, amb])
+            #return n.replace(" ", "_")
 
     def create_lineage_dictionary(self):
         """

setup.py

@@ -8,7 +8,7 @@
 
 setuptools.setup(
     name="ncov_parser",
-    version="0.6.5",
+    version="0.6.6",
     author="Richard J. de Borja",
     author_email="[email protected]",
     description="A nCoV package for parsing analysis files",

tests/test_Lineage.py

@@ -5,14 +5,15 @@
 import unittest
 import ncov.parser
 
-test_lineage = ncov.parser.Lineage(file='data/sample_lineages.csv')
+test_lineage = ncov.parser.Lineage(file='data/test_lineages.csv')
 
 
 class LineageTest(unittest.TestCase):
     def test_create_lineage_dictionary(self):
         lineage_dict = test_lineage.create_lineage_dictionary()
-        self.assertEqual(lineage_dict['sampleA']['lineage'], 'B.1.1.43')
-        self.assertEqual(lineage_dict['sampleB']['lineage'], 'B.1.36')
+        self.assertEqual(lineage_dict['sampleA']['lineage'], 'B.1.1.7')
+        self.assertEqual(lineage_dict['sampleA']['notes'], '18/3/0')
+        self.assertEqual(lineage_dict['sampleB']['lineage'], 'B.1.1.7')
         self.assertEqual(lineage_dict['sampleC']['lineage'], 'B.1.1.7')
     def test_get_sample_name(self):
         sample_row = {'taxon' : 'sampleA/ARTIC/nanopolish',