54d2ab3bc67708e54ef4ce54b0bd94927e1ff18b
jnavarr5
  Tue Nov 25 16:57:38 2025 -0800
Curling the URL like Hiram recommended. Using the file from /hive was not the most up-to-date, refs #36712 #33200

diff --git src/utils/qa/pairLastzWrapper.py src/utils/qa/pairLastzWrapper.py
index 8fd0ec94a9c..be1dca0a050 100755
--- src/utils/qa/pairLastzWrapper.py
+++ src/utils/qa/pairLastzWrapper.py
@@ -66,31 +66,31 @@
     except subprocess.CalledProcessError:
       sys.stdout = sys.__stdout__
       print('# can not find '+destDir)
       quit()
     cdDir = str(cdDir)[1:-1]
     gcName = cdDir.split('//')[1][:-1]
     return gcName
 
 
 def getClade(assembly):
     """Input assembly and return clade of assembly"""
     if assembly[0:3]=='GCA' or assembly[0:3]=='GCF':
         chromSizes_1="/hive/data/genomes/asmHubs/"+assembly[0:3]+"/"+assembly[4:7]+"/"+assembly[7:10]+"/"+assembly[10:13]+"/"+assembly+"/"+assembly+".chrom.sizes.txt"
         assembly=goto(assembly)
         assembly_version = "_".join(assembly.split('_', 2)[:2]) # Get the assembly ID, e.g. GCF_016772045.1
-        find_gcNum=bash(f"grep {assembly_version} /hive/data/genomes/asmHubs/UCSC_GI.assemblyHubList.txt")[0] #Bash returns a list, so get the first item
+        find_gcNum=bash(f"curl -s https://hgdownload.soe.ucsc.edu/hubs/UCSC_GI.assemblyHubList.txt | grep {assembly_version}")[0] #Bash returns a list, so get the first item
 
         try:
                clade=find_gcNum.split('\t')[5] # Value is tab-separated, the clade is the last item
         except IndexError:
                print('# can not find '+assembly+', the assembly might be suppressed')
                quit()
         if clade in validClades:
             return clade
         for singular, plural in validClades.items():
             if clade in plural:
                 return singular # check to see if 'mammals' or 'mammal(L)' is given. If so return 'mammal'
 
         else: clade='other'
     else:
         chromSizes_1="/hive/data/genomes/"+assembly+"/chrom.sizes"