don't assume case-sensitivity for known gene confirmation status

clinicalfilter/inheritance.py

@@ -723,10 +723,10 @@ def passes_ddg2p_filter(self, variant):
         self.log_string = "non-reported DDG2P CNV"
         gene_type = self.known_gene["status"]
 
-        if "Both DD and IF" in gene_type:
+        if "both dd and if" in gene_type:
             self.log_string = "Both DD and IF DDG2P gene"
             return True
-        elif {"Confirmed DD Gene", "Probable DD gene"} & gene_type == set():
+        elif {"confirmed dd gene", "probable dd gene"} & gene_type == set():
             return False
 
         for inh in self.known_gene["inh"]:

clinicalfilter/load_files.py

@@ -61,7 +61,7 @@ def parse_gene_line(line, header):
 
     gene = {}
     gene['inh'] = {inheritance: set([mechanism])}
-    gene["status"] = set([status])
+    gene["status"] = set([status.lower()])
     gene["start"] = int(line[header["start"]])
     gene["end"] = int(line[header["stop"]])
     gene["chrom"] = line[header["chr"]]
@@ -96,7 +96,7 @@ def open_known_genes(path):
         return None
 
     # only include genes with sufficient DDG2P status
-    allowed = set(["Confirmed DD Gene", "Probable DD gene", "Both DD and IF"])
+    allowed = set(["confirmed dd gene", "probable dd gene", "both dd and if"])
 
     known = {}
     with io.open(path, "r", encoding="latin_1") as handle:

setup.py

@@ -20,7 +20,7 @@
 
 setup(
     name = "clinical-filter",
-    version = "0.4.2",
+    version = "0.4.6",
     author = "Jeremy McRae",
     author_email = "jeremy.mcrae@sanger.ac.uk",
     description="Clinical filtering for trios.",

tests/test_allosomal_inheritance.py

@@ -53,7 +53,7 @@ def setUp(self):
         self.variants = [var]
 
         # make sure we've got known genes data
-        self.known_gene = {"inh": ["Monoallelic"], "confirmed_status": ["Confirmed DD Gene"]}
+        self.known_gene = {"inh": ["Monoallelic"], "confirmed_status": ["confirmed dd gene"]}
 
         self.inh = Allosomal(self.variants, self.trio, self.known_gene, "TEST")
         self.inh.is_lof = var.child.is_lof()

tests/test_autosomal_inheritance.py

@@ -52,7 +52,7 @@ def setUp(self):
         self.variants = [var]
 
         # make sure we've got known genes data
-        self.known_gene = {"inh": ["Monoallelic"], "confirmed_status": ["Confirmed DD Gene"]}
+        self.known_gene = {"inh": ["Monoallelic"], "confirmed_status": ["confirmed dd gene"]}
 
         self.inh = Autosomal(self.variants, self.trio, self.known_gene, "TEST")
         self.inh.is_lof = var.child.is_lof()

tests/test_cnv_inheritance.py

@@ -46,7 +46,7 @@ def setUp(self):
         self.variant = self.create_variant(child_gender)
 
         # make sure we've got known genes data
-        self.known_gene = {"inh": {"Monoallelic": {"Loss of function"}}, "status": {"Confirmed DD Gene"}, "start": 5000, "end": 6000}
+        self.known_gene = {"inh": {"Monoallelic": {"Loss of function"}}, "status": {"confirmed dd gene"}, "start": 5000, "end": 6000}
 
         syndrome_regions = {("1", "1000", "2000"): 1}
 
@@ -314,7 +314,7 @@ def test_passes_ddg2p_filter(self):
 
         gene_inh = {"inh": {"Monoallelic": \
             {"Increased gene dosage"}}, "status": \
-            {"Confirmed DD Gene"}, "start": 5000, "end": 6000}
+            {"confirmed dd gene"}, "start": 5000, "end": 6000}
 
         gene = "TEST"
         inh = "Monoallelic"
@@ -335,12 +335,12 @@ def test_passes_ddg2p_filter(self):
         # check if the variant passes if the confirmed type is "Both DD and IF",
         # even if the variant wouldn't otherwise pass
         self.inh.gene = "TEST"
-        self.inh.known_gene["status"] = {"Both DD and IF"}
+        self.inh.known_gene["status"] = {"both dd and if"}
         self.inh.known_gene["inh"][inh] = {"Loss of function"}
         self.assertTrue(self.inh.passes_ddg2p_filter(cnv))
 
         # fail on genes that don't have a robust confirmed status
-        self.inh.known_gene["status"] = {"Possible DD Gene"}
+        self.inh.known_gene["status"] = {"possible dd gene"}
         self.assertFalse(self.inh.passes_ddg2p_filter(cnv))
 
     def test_passes_gene_inheritance_surrounding_disruptive_dup(self):
@@ -349,7 +349,7 @@ def test_passes_gene_inheritance_surrounding_disruptive_dup(self):
 
         gene_inh = {"inh": {"Monoallelic": \
             {"Loss of function"}}, "status": \
-            {"Confirmed DD Gene"}, "start": 5000, "end": 6000}
+            {"confirmed dd gene"}, "start": 5000, "end": 6000}
 
         # make a gene that is loss of function, with a monoallelic inheritance
         self.inh.known_gene = gene_inh
@@ -395,7 +395,7 @@ def test_check_passes_intragenic_dup(self):
         gene_inh = {"inh": {"Monoallelic": \
             {"Loss of Function"}, "X-linked dominant": \
             {"Loss of Function"}}, "status": \
-            {"Confirmed DD Gene"}, "start": 5000, "end": 6000}
+            {"confirmed dd gene"}, "start": 5000, "end": 6000}
 
         self.inh.known_gene = gene_inh
 
@@ -497,7 +497,7 @@ def test_check_compound_inheritance(self):
 
         gene_inh = {"inh": {"Biallelic": \
             {"Increased gene dosage"}}, "status": \
-            {"Confirmed DD Gene"}, "start": 5000, "end": 6000}
+            {"confirmed dd gene"}, "start": 5000, "end": 6000}
 
         self.inh.known_gene = gene_inh
         cnv = self.create_variant("female")
@@ -535,7 +535,7 @@ def test_check_compound_inheritance_hemizygous(self):
 
         gene_inh = {"inh": {"Hemizygous": \
             {"Increased gene dosage"}}, "status": \
-            {"Confirmed DD Gene"}, "start": 5000, "end": 6000}
+            {"confirmed dd gene"}, "start": 5000, "end": 6000}
 
         self.inh.known_gene = gene_inh
         cnv = self.create_variant("female")

tests/test_inheritance.py

@@ -50,7 +50,7 @@ def setUp(self):
         self.variants.append(self.create_variant(sex))
 
         # make sure we've got known genes data
-        self.known_gene = {"inh": ["Monoallelic"], "confirmed_status": ["Confirmed DD Gene"]}
+        self.known_gene = {"inh": ["Monoallelic"], "confirmed_status": ["confirmed dd gene"]}
 
         self.inh = Autosomal(self.variants, self.trio, self.known_gene, "TEST")
 
@@ -136,7 +136,7 @@ def test_get_candidate_variants_monoallelic(self):
         """ test that get_candidate_variants() works for a monoallelic variant
         """
 
-        inh = {"inh": ["Monoallelic"], "confirmed_status": ["Confirmed DD Gene"]}
+        inh = {"inh": ["Monoallelic"], "confirmed_status": ["confirmed dd gene"]}
         var = self.create_variant(position='150', cq='stop_gained',
             geno=['0/1', '0/0', '0/0'])
         self.inh = Autosomal([var], self.trio, inh, "TEST")
@@ -156,7 +156,7 @@ def test_get_candidate_variants_imprinted(self):
         """
 
         # check a variant where the imprinting route should work
-        inh = {"inh": ["Imprinted"], "confirmed_status": ["Confirmed DD Gene"]}
+        inh = {"inh": ["Imprinted"], "confirmed_status": ["confirmed dd gene"]}
         var = self.create_variant(position='150', cq='stop_gained',
             geno=['0/1', '0/1', '0/0'])
         self.inh = Autosomal([var], self.trio, inh, "TEST")
@@ -204,7 +204,7 @@ def test_get_candidate_variants_compound_het(self):
         """ test that get_candidate_variants() works for biallelic variants
         """
 
-        inh = {"inh": ["Biallelic"], "confirmed_status": ["Confirmed DD Gene"]}
+        inh = {"inh": ["Biallelic"], "confirmed_status": ["confirmed dd gene"]}
         var1 = self.create_variant(position='150', cq='stop_gained',
             geno=['0/1', '0/1', '0/0'])
         var2 = self.create_variant(position='151', cq='stop_gained',
@@ -275,7 +275,7 @@ def test_check_compound_hets(self):
         # set the inheritance type, the compound het type ("compound_het"
         # for autosomal variants, and start autosomal inheritance)
         # known_genes = "Biallelic"
-        known_gene = {"inh": ["Biallelic"], "confirmed_status": ["Confirmed DD Gene"]}
+        known_gene = {"inh": ["Biallelic"], "confirmed_status": ["confirmed dd gene"]}
         self.inh = Autosomal([var1, var2, var3], self.trio, known_gene, "TEST")
 
         variants = [(), ()]

tests/test_load_files.py

@@ -69,12 +69,12 @@ def test_parse_gene_line(self):
         header = {'gene': 0, 'chr': 1, 'start': 2, 'stop': 3, 'type': 4,
             'mode': 5, 'mech': 6}
 
-        line = ['TEST', 'chr1', '1000', '2000', 'Confirmed DD Gene',
+        line = ['TEST', 'chr1', '1000', '2000', 'confirmed dd gene',
             'Biallelic', 'Loss-of-function']
 
         self.assertEqual(parse_gene_line(line, header), ('TEST', {
             'chrom': 'chr1', 'start': 1000, 'end': 2000,
-            'status': set(['Confirmed DD Gene']),
+            'status': set(['confirmed dd gene']),
             'inh': {'Biallelic': set(['Loss-of-function'])}}))
 
     def test_parse_gene_line_both_mechanism(self):
@@ -83,12 +83,12 @@ def test_parse_gene_line_both_mechanism(self):
 
         header = {'gene': 0, 'chr': 1, 'start': 2, 'stop': 3, 'type': 4,
             'mode': 5, 'mech': 6}
-        line = ['TEST', 'chr1', '1000', '2000', 'Confirmed DD Gene',
+        line = ['TEST', 'chr1', '1000', '2000', 'confirmed dd gene',
             'Both', 'Loss-of-function']
 
         self.assertEqual(parse_gene_line(line, header), ('TEST', {
             'chrom': 'chr1', 'start': 1000, 'end': 2000,
-            'status': set(['Confirmed DD Gene']),
+            'status': set(['confirmed dd gene']),
             'inh': {'Biallelic': set(['Loss-of-function']),
                 'Monoallelic': set(['Loss-of-function']),
                 'Both': set(['Loss-of-function'])}}))
@@ -98,7 +98,7 @@ def test_open_known_genes(self):
         '''
 
         header = ['gene', 'chr', 'start', 'stop', 'type', 'mode', 'mech']
-        line = ['TEST', '1', '1000', '2000', 'Confirmed DD Gene',
+        line = ['TEST', '1', '1000', '2000', 'confirmed dd gene',
             'Monoallelic', 'Loss-of-function']
 
         self.temp.write(('\t'.join(header) + '\n').encode('utf8'))
@@ -107,7 +107,7 @@ def test_open_known_genes(self):
 
         self.assertEqual(open_known_genes(self.temp.name),
             {'TEST': {'chrom': '1', 'start': 1000, 'end': 2000,
-                'status': set(['Confirmed DD Gene']),
+                'status': set(['confirmed dd gene']),
                 'inh': {'Monoallelic': set(['Loss-of-function'])}}
             })
 
@@ -116,9 +116,9 @@ def test_open_known_genes_multimodes(self):
         '''
 
         header = ['gene', 'chr', 'start', 'stop', 'type', 'mode', 'mech']
-        line1 = ['TEST', '1', '1000', '2000', 'Confirmed DD Gene',
+        line1 = ['TEST', '1', '1000', '2000', 'confirmed dd gene',
             'Monoallelic', 'Loss-of-function']
-        line2 = ['TEST', '1', '1000', '2000', 'Confirmed DD Gene',
+        line2 = ['TEST', '1', '1000', '2000', 'confirmed dd gene',
             'Biallelic', 'Loss-of-function']
 
         self.temp.write(('\t'.join(header) + '\n').encode('utf8'))
@@ -128,7 +128,7 @@ def test_open_known_genes_multimodes(self):
 
         self.assertEqual(open_known_genes(self.temp.name),
             {'TEST': {'chrom': '1', 'start': 1000, 'end': 2000,
-                'status': set(['Confirmed DD Gene']),
+                'status': set(['confirmed dd gene']),
                 'inh': {'Monoallelic': set(['Loss-of-function']),
                      'Biallelic': set(['Loss-of-function'])}}
             })
@@ -138,9 +138,9 @@ def test_open_known_genes_multimechs(self):
         '''
 
         header = ['gene', 'chr', 'start', 'stop', 'type', 'mode', 'mech']
-        line1 = ['TEST', '1', '1000', '2000', 'Confirmed DD Gene',
+        line1 = ['TEST', '1', '1000', '2000', 'confirmed dd gene',
             'Monoallelic', 'Loss-of-function']
-        line2 = ['TEST', '1', '1000', '2000', 'Confirmed DD Gene',
+        line2 = ['TEST', '1', '1000', '2000', 'confirmed dd gene',
             'Monoallelic', 'Activating']
 
         self.temp.write(('\t'.join(header) + '\n').encode('utf8'))
@@ -150,7 +150,7 @@ def test_open_known_genes_multimechs(self):
 
         self.assertEqual(open_known_genes(self.temp.name),
             {'TEST': {'chrom': '1', 'start': 1000, 'end': 2000,
-                'status': set(['Confirmed DD Gene']),
+                'status': set(['confirmed dd gene']),
                 'inh': {'Monoallelic': set(['Loss-of-function', 'Activating'])}}
             })
 
@@ -159,9 +159,9 @@ def test_open_known_genes_multigenes(self):
         '''
 
         header = ['gene', 'chr', 'start', 'stop', 'type', 'mode', 'mech']
-        line1 = ['TEST', '1', '1000', '2000', 'Confirmed DD Gene',
+        line1 = ['TEST', '1', '1000', '2000', 'confirmed dd gene',
             'Monoallelic', 'Loss-of-function']
-        line2 = ['TEST2', '1', '3000', '4000', 'Confirmed DD Gene',
+        line2 = ['TEST2', '1', '3000', '4000', 'confirmed dd gene',
             'Monoallelic', 'Loss-of-function']
 
         self.temp.write(('\t'.join(header) + '\n').encode('utf8'))
@@ -171,10 +171,10 @@ def test_open_known_genes_multigenes(self):
 
         self.assertEqual(open_known_genes(self.temp.name),
             {'TEST': {'chrom': '1', 'start': 1000, 'end': 2000,
-                'status': set(['Confirmed DD Gene']),
+                'status': set(['confirmed dd gene']),
                 'inh': {'Monoallelic': set(['Loss-of-function'])}},
             'TEST2': {'chrom': '1', 'start': 3000, 'end': 4000,
-                'status': set(['Confirmed DD Gene']),
+                'status': set(['confirmed dd gene']),
                 'inh': {'Monoallelic': set(['Loss-of-function'])}}
             })
 
@@ -183,9 +183,9 @@ def test_open_known_genes_wrong_status(self):
         '''
 
         header = ['gene', 'chr', 'start', 'stop', 'type', 'mode', 'mech']
-        line1 = ['TEST', '1', '1000', '2000', 'Possible DD Gene',
+        line1 = ['TEST', '1', '1000', '2000', 'possible dd gene',
             'Monoallelic', 'Loss-of-function']
-        line2 = ['TEST2', '1', '3000', '4000', 'Confirmed DD Gene',
+        line2 = ['TEST2', '1', '3000', '4000', 'confirmed dd gene',
             'Monoallelic', 'Loss-of-function']
 
         self.temp.write(('\t'.join(header) + '\n').encode('utf8'))
@@ -195,7 +195,7 @@ def test_open_known_genes_wrong_status(self):
 
         self.assertEqual(open_known_genes(self.temp.name),
             {'TEST2': {'chrom': '1', 'start': 3000, 'end': 4000,
-                'status': set(['Confirmed DD Gene']),
+                'status': set(['confirmed dd gene']),
                 'inh': {'Monoallelic': set(['Loss-of-function'])}}
             })
 

tests/test_load_vcfs.py

@@ -66,7 +66,7 @@ def setUp(self):
             "EUR_AF", "MAX_AF", "SAS_AF", "UK10K_cohort_AF"]
         self.known_genes = {"ATRX": {"inheritance": {"Hemizygous": \
             {"Loss of function"}}, "start": 1, "chrom": "1", \
-            "confirmed_status": {"Confirmed DD Gene"}, "end": 20000000}}
+            "confirmed_status": {"confirmed dd gene"}, "end": 20000000}}
 
         self.vcf_loader = LoadVCFs(total_trios, maf_tags, self.known_genes, set(), None, None, )
 

tests/test_variant_info.py

@@ -41,7 +41,7 @@ def setUp(self):
         # here are the default filtering criteria, as loaded into python
         known = {"ATRX": {"inheritance": {"Hemizygous": \
             {"Loss of function"}}, "start": "10000000", "chrom": "1", \
-            "confirmed_status": {"Confirmed DD Gene"}, "end": "20000000"}}
+            "confirmed_status": {"confirmed dd gene"}, "end": "20000000"}}
 
         self.pops = ["AFR_AF", "AMR_AF", "ASN_AF", "DDD_AF", "EAS_AF",
             "ESP_AF", "EUR_AF", "MAX_AF", "SAS_AF", "UK10K_cohort_AF"]