diff options
author | zsloan | 2021-10-12 20:56:31 +0000 |
---|---|---|
committer | zsloan | 2021-10-12 20:56:31 +0000 |
commit | 6e211182354fb4d6941e3a44ec1ec9d378b0e4ef (patch) | |
tree | 60d9aaf382eefbb47cdbab9c74d98481cf0983de /tests/unit/db | |
parent | b815236123ff8e144bd84f349357a1852df95651 (diff) | |
parent | 77c274b79c3ec01de60e90db3299763cb58f715b (diff) | |
download | genenetwork3-6e211182354fb4d6941e3a44ec1ec9d378b0e4ef.tar.gz |
Merge branch 'main' of https://github.com/genenetwork/genenetwork3 into bug/fix_rqtl_covariates
Diffstat (limited to 'tests/unit/db')
-rw-r--r-- | tests/unit/db/data/genotypes/genotype_sample1.geno | 23 | ||||
-rw-r--r-- | tests/unit/db/test_datasets.py | 42 | ||||
-rw-r--r-- | tests/unit/db/test_genotypes.py | 170 | ||||
-rw-r--r-- | tests/unit/db/test_traits.py | 16 |
4 files changed, 224 insertions, 27 deletions
diff --git a/tests/unit/db/data/genotypes/genotype_sample1.geno b/tests/unit/db/data/genotypes/genotype_sample1.geno new file mode 100644 index 0000000..2a55964 --- /dev/null +++ b/tests/unit/db/data/genotypes/genotype_sample1.geno @@ -0,0 +1,23 @@ +# File name: genotype_sample for testing + +# Metadata: Please retain this header information with file. + + +@name: BXD +@type: riset +@mat: B +@pat: D +@het:H +@unk: U + + + + + + +Chr Locus cM Mb BXD1 BXD2 BXD5 BXD6 BXD8 BXD9 +1 rs31443144 1.50 3.010274 B B D D D B +1 rs6269442 1.50 3.492195 B B D D H Y +1 rs32285189 1.63 3.511204 B U D D D B +2 rs31443144 1.50 3.010274 B B D D D B +2 rs6269442 1.50 3.492195 B B D D H Y
\ No newline at end of file diff --git a/tests/unit/db/test_datasets.py b/tests/unit/db/test_datasets.py index 38de0e2..39f4af9 100644 --- a/tests/unit/db/test_datasets.py +++ b/tests/unit/db/test_datasets.py @@ -3,10 +3,10 @@ from unittest import mock, TestCase from gn3.db.datasets import ( retrieve_dataset_name, - retrieve_riset_fields, - retrieve_geno_riset_fields, - retrieve_publish_riset_fields, - retrieve_probeset_riset_fields) + retrieve_group_fields, + retrieve_geno_group_fields, + retrieve_publish_group_fields, + retrieve_probeset_group_fields) class TestDatasetsDBFunctions(TestCase): """Test cases for datasets functions.""" @@ -40,9 +40,9 @@ class TestDatasetsDBFunctions(TestCase): table=table, cols=columns), {"threshold": thresh, "name": dataset_name}) - def test_retrieve_probeset_riset_fields(self): + def test_retrieve_probeset_group_fields(self): """ - Test that the `riset` and `riset_id` fields are retrieved appropriately + Test that the `group` and `group_id` fields are retrieved appropriately for the 'ProbeSet' trait type. """ for trait_name, expected in [ @@ -52,7 +52,7 @@ class TestDatasetsDBFunctions(TestCase): with db_mock.cursor() as cursor: cursor.execute.return_value = () self.assertEqual( - retrieve_probeset_riset_fields(trait_name, db_mock), + retrieve_probeset_group_fields(trait_name, db_mock), expected) cursor.execute.assert_called_once_with( ( @@ -63,34 +63,34 @@ class TestDatasetsDBFunctions(TestCase): " AND ProbeSetFreeze.Name = %(name)s"), {"name": trait_name}) - def test_retrieve_riset_fields(self): + def test_retrieve_group_fields(self): """ - Test that the riset fields are set up correctly for the different trait + Test that the group fields are set up correctly for the different trait types. """ for trait_type, trait_name, dataset_info, expected in [ ["Publish", "pubTraitName01", {"dataset_name": "pubDBName01"}, - {"dataset_name": "pubDBName01", "riset": ""}], + {"dataset_name": "pubDBName01", "group": ""}], ["ProbeSet", "prbTraitName01", {"dataset_name": "prbDBName01"}, - {"dataset_name": "prbDBName01", "riset": ""}], + {"dataset_name": "prbDBName01", "group": ""}], ["Geno", "genoTraitName01", {"dataset_name": "genoDBName01"}, - {"dataset_name": "genoDBName01", "riset": ""}], - ["Temp", "tempTraitName01", {}, {"riset": ""}], + {"dataset_name": "genoDBName01", "group": ""}], + ["Temp", "tempTraitName01", {}, {"group": ""}], ]: db_mock = mock.MagicMock() with self.subTest( trait_type=trait_type, trait_name=trait_name, dataset_info=dataset_info): with db_mock.cursor() as cursor: - cursor.execute.return_value = ("riset_name", 0) + cursor.execute.return_value = ("group_name", 0) self.assertEqual( - retrieve_riset_fields( + retrieve_group_fields( trait_type, trait_name, dataset_info, db_mock), expected) - def test_retrieve_publish_riset_fields(self): + def test_retrieve_publish_group_fields(self): """ - Test that the `riset` and `riset_id` fields are retrieved appropriately + Test that the `group` and `group_id` fields are retrieved appropriately for the 'Publish' trait type. """ for trait_name, expected in [ @@ -100,7 +100,7 @@ class TestDatasetsDBFunctions(TestCase): with db_mock.cursor() as cursor: cursor.execute.return_value = () self.assertEqual( - retrieve_publish_riset_fields(trait_name, db_mock), + retrieve_publish_group_fields(trait_name, db_mock), expected) cursor.execute.assert_called_once_with( ( @@ -110,9 +110,9 @@ class TestDatasetsDBFunctions(TestCase): " AND PublishFreeze.Name = %(name)s"), {"name": trait_name}) - def test_retrieve_geno_riset_fields(self): + def test_retrieve_geno_group_fields(self): """ - Test that the `riset` and `riset_id` fields are retrieved appropriately + Test that the `group` and `group_id` fields are retrieved appropriately for the 'Geno' trait type. """ for trait_name, expected in [ @@ -122,7 +122,7 @@ class TestDatasetsDBFunctions(TestCase): with db_mock.cursor() as cursor: cursor.execute.return_value = () self.assertEqual( - retrieve_geno_riset_fields(trait_name, db_mock), + retrieve_geno_group_fields(trait_name, db_mock), expected) cursor.execute.assert_called_once_with( ( diff --git a/tests/unit/db/test_genotypes.py b/tests/unit/db/test_genotypes.py new file mode 100644 index 0000000..c125224 --- /dev/null +++ b/tests/unit/db/test_genotypes.py @@ -0,0 +1,170 @@ +"""Tests gn3.db.genotypes""" +from unittest import TestCase +from gn3.db.genotypes import ( + parse_genotype_file, + parse_genotype_labels, + parse_genotype_header, + parse_genotype_marker, + build_genotype_chromosomes) + +class TestGenotypes(TestCase): + """Tests for functions in `gn3.db.genotypes`.""" + + def test_parse_genotype_labels(self): + """Test that the genotype labels are parsed correctly.""" + self.assertEqual( + parse_genotype_labels([ + "@name: test_group\t", "@filler: test_filler ", + "@type:test_type", "@mat:test_mat \t", "@pat:test_pat ", + "@het: test_het ", "@unk: test_unk", "@other: test_other", + "@brrr: test_brrr "]), + (("group", "test_group"), ("filler", "test_filler"), + ("type", "test_type"), ("mat", "test_mat"), ("pat", "test_pat"), + ("het", "test_het"), ("unk", "test_unk"))) + + def test_parse_genotype_header(self): + """Test that the genotype header is parsed correctly.""" + for header, expected in [ + [("Chr\tLocus\tcM\tMb\tBXD1\tBXD2\tBXD5\tBXD6\tBXD8\tBXD9\t" + "BXD11\tBXD12\tBXD13\tBXD14\tBXD15\tBXD16\tBXD18\tBXD19"), + (("Mbmap", True), ("cm_column", 2), ("mb_column", 3), + ("prgy", + ("BXD1", "BXD2", "BXD5", "BXD6", "BXD8", "BXD9", "BXD11", + "BXD12", "BXD13", "BXD14", "BXD15", "BXD16", "BXD18", + "BXD19")), + ("nprgy", 14))], + [("Chr\tLocus\tcM\tBXD1\tBXD2\tBXD5\tBXD6\tBXD8\tBXD9\tBXD11" + "\tBXD12\tBXD13\tBXD14\tBXD15\tBXD16\tBXD18"), + (("Mbmap", False), ("cm_column", 2), ("mb_column", None), + ("prgy", + ("BXD1", "BXD2", "BXD5", "BXD6", "BXD8", "BXD9", "BXD11", + "BXD12", "BXD13", "BXD14", "BXD15", "BXD16", "BXD18")), + ("nprgy", 13))]]: + with self.subTest(header=header): + self.assertEqual(parse_genotype_header(header), expected) + + def test_parse_genotype_data_line(self): + """Test parsing of data lines.""" + for line, geno_obj, parlist, expected in [ + ["1\trs31443144\t1.50\t3.010274\tB\tB\tD\tD\tD\tB\tB\tD\tB\tB", + {"mat": "test_mat", "pat": "test_pat", "het": "test_het", + "unk": "test_unk", "cm_column": 2, "Mbmap": True, + "mb_column": 3}, + tuple(), + (("chr", "1"), ("name", "rs31443144"), ("cM", 2.0), + ("Mb", 3.0), + ("genotype", + ("U", "U", "U", "U", "U", "U", "U", "U", "U", "U")))], + ["1\trs31443144\t1.50\t3.010274\tB\tB\tD\tD\tD\tB\tB\tD\tB\tB", + {"mat": "test_mat", "pat": "test_pat", "het": "test_het", + "unk": "test_unk", "cm_column": 2, "Mbmap": True, + "mb_column": 3}, + ("some", "parlist", "content"), + (("chr", "1"), ("name", "rs31443144"), ("cM", 2.0), + ("Mb", 3.0), + ("genotype", + (-1, 1, "U", "U", "U", "U", "U", "U", "U", "U")))], + ["1\trs31443144\t1.50\t3.010274\tB\tB\tD\tH\tD\tB\tU\tD\tB\tB", + {"mat": "B", "pat": "D", "het": "H", "unk": "U", + "cm_column": 2, "Mbmap": True, "mb_column": 3}, + tuple(), + (("chr", "1"), ("name", "rs31443144"), ("cM", 2.0), + ("Mb", 3.0), + ("genotype", (-1, -1, 1, 0, 1, -1, "U", 1, -1, -1)))]]: + with self.subTest(line=line): + self.assertEqual( + parse_genotype_marker(line, geno_obj, parlist), + expected) + + def test_build_genotype_chromosomes(self): + """ + Given `markers` and `geno_obj`, test that `build_genotype_chromosomes` + builds a sequence of chromosomes with the given markers ordered + according to the `chr` value.""" + for markers, geno_obj, expected in [ + [[(("chr", "1"), ("name", "rs31443144"), ("cM", 2.0), + ("Mb", 3.0), + ("genotype", (-1, -1, 1, 0, 1, -1, "U", 1, -1, -1))), + (("chr", "2"), ("name", "rs31443144"), ("cM", 2.0), + ("Mb", 3.0), + ("genotype", (-1, -1, 1, 0, 1, -1, "U", 1, -1, -1)))], + {"mat": "B", "pat": "D", "het": "H", "unk": "U", + "cm_column": 2, "Mbmap": True, "mb_column": 3}, + ((("name", "1"), ("mb_exists", True), ("cm_column", 2), + ("mb_column", 3), + ("loci", + ({"chr": "1", "name": "rs31443144", "cM": 2.0, "Mb": 3.0, + "genotype": (-1, -1, 1, 0, 1, -1, "U", 1, -1, -1)},))), + (("name", "2"), ("mb_exists", True), ("cm_column", 2), + ("mb_column", 3), + ("loci", + ({"chr": "2", "name": "rs31443144", "cM": 2.0, "Mb": 3.0, + "genotype": (-1, -1, 1, 0, 1, -1, "U", 1, -1, -1)},))))], + [[(("chr", "1"), ("name", "rs31443144"), ("cM", 2.0), + ("Mb", None), + ("genotype", (-1, 1, 1, 0, 1, -1, "U", 1, -1, -1)))], + {"mat": "B", "pat": "D", "het": "H", "unk": "U", + "cm_column": 2, "Mbmap": False, "mb_column": None}, + ((("name", "1"), ("mb_exists", False), ("cm_column", 2), + ("mb_column", None), + ("loci", + ({"chr": "1", "name": "rs31443144", "cM": 2.0, "Mb": None, + "genotype": (-1, 1, 1, 0, 1, -1, "U", 1, -1, -1)},))),)]]: + with self.subTest(markers=markers): + self.assertEqual( + build_genotype_chromosomes(geno_obj, markers), + expected) + + def test_parse_genotype_file(self): + """Test the parsing of genotype files. """ + self.assertEqual( + parse_genotype_file( + "tests/unit/db/data/genotypes/genotype_sample1.geno"), + {"group": "BXD", + "type": "riset", + "mat": "B", + "pat": "D", + "het": "H", + "unk": "U", + "Mbmap": True, + "cm_column": 2, + "mb_column": 3, + "prgy": ("BXD1", "BXD2", "BXD5", "BXD6", "BXD8", "BXD9"), + "nprgy": 6, + "chromosomes": ( + {"name": "1", + "mb_exists": True, + "cm_column": 2, + "mb_column": 3, + "loci": ( + {"chr": "1", + "name": "rs31443144", + "cM": 2.0, + "Mb": 3.0, + "genotype": (-1, -1, 1, 1, 1, -1) + }, + {"chr": "1", + "name": "rs6269442", + "cM": 2.0, + "Mb": 3.0, + "genotype": (-1, -1, 1, 1, 0, "U")}, + {"chr": "1", + "name": "rs32285189", + "cM": 2.0, + "Mb": 3.0, + "genotype": (-1, "U", 1, 1, 1, -1)})}, + {"name": "2", + "mb_exists": True, + "cm_column": 2, + "mb_column": 3, + "loci": ( + {"chr": "2", + "name": "rs31443144", + "cM": 2.0, + "Mb": 3.0, + "genotype": (-1, -1, 1, 1, 1, -1)}, + {"chr": "2", + "name": "rs6269442", + "cM": 2.0, + "Mb": 3.0, + "genotype": (-1, -1, 1, 1, 0, "U")})})}) diff --git a/tests/unit/db/test_traits.py b/tests/unit/db/test_traits.py index ee98893..8af8e82 100644 --- a/tests/unit/db/test_traits.py +++ b/tests/unit/db/test_traits.py @@ -166,15 +166,19 @@ class TestTraitsDBFunctions(TestCase): the right calls. """ + # pylint: disable=C0103 db_mock = mock.MagicMock() STRAIN_ID_SQL: str = "UPDATE Strain SET Name = %s WHERE Id = %s" - PUBLISH_DATA_SQL: str = ("UPDATE PublishData SET value = %s " - "WHERE StrainId = %s AND Id = %s") - PUBLISH_SE_SQL: str = ("UPDATE PublishSE SET error = %s " - "WHERE StrainId = %s AND DataId = %s") - N_STRAIN_SQL: str = ("UPDATE NStrain SET count = %s " - "WHERE StrainId = %s AND DataId = %s") + PUBLISH_DATA_SQL: str = ( + "UPDATE PublishData SET value = %s " + "WHERE StrainId = %s AND Id = %s") + PUBLISH_SE_SQL: str = ( + "UPDATE PublishSE SET error = %s " + "WHERE StrainId = %s AND DataId = %s") + N_STRAIN_SQL: str = ( + "UPDATE NStrain SET count = %s " + "WHERE StrainId = %s AND DataId = %s") with db_mock.cursor() as cursor: type(cursor).rowcount = 1 |