bd7ad41f40025e2d8d08ea6a001507b935a8ff5d
hiram
  Mon Jul 21 17:39:50 2025 -0700
adding archaea as a new group refs #29545

diff --git src/hg/makeDb/doc/asmHubs/hubIndex.pl src/hg/makeDb/doc/asmHubs/hubIndex.pl
index d7806abcb53..c64c5aa33c9 100755
--- src/hg/makeDb/doc/asmHubs/hubIndex.pl
+++ src/hg/makeDb/doc/asmHubs/hubIndex.pl
@@ -45,104 +45,108 @@
  "VGP" => 1,
  "CCGP" => 1,
  "HPRC" => 1,
  "BRC" => 1,
  "birds" => 1,
  "fish" => 1,
  "globalReference" => 1,
  "mammals" => 1,
  "primates" => 1,
  "vertebrate" => 1,
  "invertebrate" => 1,
  "fungi" => 1,
  "legacy" => 1,
  "plants" => 1,
  "viral" => 1,
+ "archaea" => 1,
  "bacteria" => 1,
 );
 
 my %titles = (
  "VGP" => "Vertebrate Genomes Project collection",
  "CCGP" => "The California Conservation Genomics Project",
  "HPRC" => "Human Pangenome Reference Consortium",
  "BRC" => "BRC Analytics - Bioinformatics Research Center",
  "birds" => "NCBI bird genomes",
  "fish" => "NCBI fish genomes",
  "globalReference" => "Global Human Reference genomes, January 2020",
  "mammals" => "NCBI mammal genomes",
  "primates" => "NCBI primate genomes",
  "vertebrate" => "NCBI other vertebrate genomes",
  "invertebrate" => "NCBI invertebrate genomes",
  "fungi" => "NCBI fungi genomes",
  "legacy" => "NCBI genomes legacy/superseded by newer versions",
  "plants" => "NCBI plant genomes",
  "viral" => "NCBI virus genomes",
+ "archaea" => "NCBI archaea genomes",
  "bacteria" => "NCBI bacteria genomes",
  "gtexAnalysis" => "Genotype-Tissue Expression (GTEx) Project analysis results track hub, V6 October 2015",
  "gtex" => "Genotype-Tissue Expression (GTEx) RNA-seq signal track hub, V6 October 2015",
  "mouseStrains" => "16 mouse strain assembly and track hub, May 2017",
  "neuroDiffCrispr" => "Structurally conserved primate cerebral cortex lincRNAs track hub, December 2018",
 );
 
 my %otherTopLevels = (
   "GCA" => 1,
   "GCF" => 1,
   "gtex" => 1,
   "gtexAnalysis" => 1,
   "mouseStrains" => 1,
   "neuroDiffCrispr" => 1,
   "UCSC_GI.assemblyHubList.txt" => 1,
   "index.html" => 1,
 );
 
 my @orderOutHubs = (
  "primates",
  "mammals",
  "birds",
  "fish",
  "vertebrate",
  "invertebrate",
  "fungi",
  "plants",
  "viral",
+ "archaea",
  "bacteria",
  "VGP",
  "CCGP",
  "HPRC",
  "BRC",
  "globalReference",
  "mouseStrains",
  "legacy",
 );
 
 my @orderOutTracks = (
  "gtexAnalysis",
  "gtex",
  "neuroDiffCrispr",
 );
 
 my %indexPage = (
  "primates" => "index.html",
  "mammals" => "index.html",
  "birds" => "index.html",
  "fish" => "index.html",
  "vertebrate" => "index.html",
  "invertebrate" => "index.html",
  "fungi" => "index.html",
  "legacy" => "index.html",
  "plants" => "index.html",
  "viral" => "index.html",
+ "archaea" => "index.html",
  "bacteria" => "index.html",
  "VGP" => "index.html",
  "CCGP" => "index.html",
  "HPRC" => "index.html",
  "BRC" => "index.html",
  "mouseStrains" => "hubIndex.html",
  "globalReference" => "index.html",
  "gtexAnalysis" => "index.html",
  "gtex" => "index.html",
  "neuroDiffCrispr" => "index.html",
 );
 
 # verify all known directories and files, alert for any new ones
 open (FH, "ls -d /mirrordata/hubs/*|") or die "can not ls -d /mirrordata/hubs/*";
 while (my $dirPath = <FH>) {
@@ -151,31 +155,31 @@
   if (! (defined($expectedList{$fileDirName}) || defined($otherTopLevels{$fileDirName})) ) {
     printf STDERR "# something new: %s\n", $fileDirName;
   }
 }
 
 close (FH);
 
 ### Determine genome counts:
 my %genomeCounts;
 
 my $asmListJson = "/mirrordata/hubs/VGP/assemblyList.json";
 my $genomeCount = `cat $asmListJson | python -mjson.tool | grep -c '"asmId":'`;
 chomp $genomeCount;
 $genomeCounts{"VGP"} = $genomeCount;
 
-my @checkList = ('primates', 'mammals', 'birds', 'fish', 'vertebrate', 'legacy', 'plants', "invertebrate", "fungi", 'viral', 'bacteria', 'CCGP', 'HPRC', 'BRC', 'globalReference');
+my @checkList = ('primates', 'mammals', 'birds', 'fish', 'vertebrate', 'legacy', 'plants', "invertebrate", "fungi", 'viral', 'archaea', 'bacteria', 'CCGP', 'HPRC', 'BRC', 'globalReference');
 
 foreach my $hubSet (@checkList) {
   $asmListJson = "/mirrordata/hubs/$hubSet/assemblyList.json";
   if ( -s "${asmListJson}" ) {
     $genomeCount = `cat $asmListJson | python -mjson.tool | grep -c '"asmId":'`;
     chomp $genomeCount;
     $genomeCounts{$hubSet} = $genomeCount;
   } else {
     printf STDERR "# ERROR: can not find assemblyList.json:\n%s\n", $asmListJson;
   }
 }
 
 my $hubCount = 0;
 
 printf "<table border='1'>\n";