fork/cellxgene
1
0
Fork 0
mirror of https://github.com/chanzuckerberg/cellxgene.git synced 2026-10-08 17:58:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Convert HGNC ids to their symbol (#1972)

Browse Source 
There are entries in some var indexes like HGNC:18790. We'd like to convert that to its symbol, NSG1.
This commit is contained in:
Marcus Kinsella
2020-11-06 09:27:49 -08:00
committed by GitHub
parent 39a1124c35
commit e892e64685
2 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/converters/schema/gene_symbol.py
+3
View File
@@ -109,6 +109,9 @@ class HGNCSymbolChecker:
if record[field] is not np.nan: if record[field] is not np.nan:
for symbol in record[field].split("|"): for symbol in record[field].split("|"):
yield format_symbol(symbol)[0] yield format_symbol(symbol)[0]
# Sometimes something like HGNC:1234 appears in datasets, which we
# want to fix as well.
yield record["hgnc_id"]
hgnc_records = pd.read_csv(hgnc_dataset_path, sep="\t", header=0, low_memory=False).to_dict("records") hgnc_records = pd.read_csv(hgnc_dataset_path, sep="\t", header=0, low_memory=False).to_dict("records")
server/test/unit/converters/schema/test_gene_symbol.py
+5
View File
@@ -41,6 +41,11 @@ class TestHGNCSymbolChecker(unittest.TestCase):
self.assertEqual(self.hgnc_checker.upgrade_symbol("NOTASYMBOL"), "NOTASYMBOL") self.assertEqual(self.hgnc_checker.upgrade_symbol("NOTASYMBOL"), "NOTASYMBOL")
self.assertEqual(self.hgnc_checker.upgrade_symbol("notasymbol"), "notasymbol") self.assertEqual(self.hgnc_checker.upgrade_symbol("notasymbol"), "notasymbol")
# Upgrade HGNC ids unless you can't find it
self.assertEqual(self.hgnc_checker.upgrade_symbol("HGNC:286"), "ADRB2")
self.assertEqual(self.hgnc_checker.upgrade_symbol("HGNC:4812"), "HAP1")
self.assertEqual(self.hgnc_checker.upgrade_symbol("HGNC:123456"), "HGNC:123456")
def test_check_symbol(self): def test_check_symbol(self):
self.assertEqual(self.hgnc_checker.check_symbol("SEPT1"), gene_symbol.SymbolStatus.UPGRADABLE) self.assertEqual(self.hgnc_checker.check_symbol("SEPT1"), gene_symbol.SymbolStatus.UPGRADABLE)
self.assertEqual(self.hgnc_checker.check_symbol("DIFF6"), gene_symbol.SymbolStatus.AMBIGUOUS) self.assertEqual(self.hgnc_checker.check_symbol("DIFF6"), gene_symbol.SymbolStatus.AMBIGUOUS)