653a69b696a8534261a8ff0dcbf1ef3af7d7c816
hiram
  Wed Mar 15 21:45:32 2023 -0700
adding link to HPRC collection no redmine

diff --git src/hg/makeDb/doc/asmHubs/hubIndex.pl src/hg/makeDb/doc/asmHubs/hubIndex.pl
index fe7e099..97f0e19 100755
--- src/hg/makeDb/doc/asmHubs/hubIndex.pl
+++ src/hg/makeDb/doc/asmHubs/hubIndex.pl
@@ -23,57 +23,59 @@
 <!--#set var="ROOT" value=".." -->
 
 <!--#include virtual="$ROOT/inc/gbPageStartHardcoded.html" -->
 
 <h1>GenArk: UCSC Genome Archive</h1>
 
 '
 }
 
 #############################################################################
 sub endHtml() {
 printf '
 </div><!-- closing gbsPage from gbPageStartHardcoded.html -->
 </div><!-- closing container-fluid from gbPageStartHardcoded.html -->
 <!--#include virtual="$ROOT/inc/gbFooterHardcoded.html"-->
-<script type="text/javascript" src="<!--#echo var="ROOT" -->/js/sorttable.js"></script>
-<script type="text/javascript" src="<!--#echo var="ROOT" -->/js/analytics.js"></script>
+<script src="<!--#echo var="ROOT" -->/js/sorttable.js"></script>
+<script src="<!--#echo var="ROOT" -->/js/analytics.js"></script>
 </body></html>
 '
 }
 
 #############################################################################
 startHtml;
 
 my %expectedList = (
  "VGP" => 1,
+ "HPRC" => 1,
  "birds" => 1,
  "fish" => 1,
  "globalReference" => 1,
  "mammals" => 1,
  "primates" => 1,
  "vertebrate" => 1,
  "invertebrate" => 1,
  "fungi" => 1,
  "legacy" => 1,
  "plants" => 1,
  "viral" => 1,
  "bacteria" => 1,
 );
 
 my %titles = (
  "VGP" => "Vertebrate Genomes Project collection",
+ "HPRC" => "Human Pangenome Reference Consortium",
  "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 "NCBI genomes legacy/superseded by newer versions",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",
  "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",
@@ -91,115 +93,122 @@
   "index.html" => 1,
 );
 
 my @orderOutHubs = (
  "primates",
  "mammals",
  "birds",
  "fish",
  "vertebrate",
  "invertebrate",
  "fungi",
  "plants",
  "viral",
  "bacteria",
  "VGP",
+ "HPRC",
  "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",
  "bacteria" => "index.html",
  "VGP" => "index.html",
+ "HPRC" => "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>) {
   chomp $dirPath;
   my $fileDirName = basename($dirPath);
   if (! (defined($expectedList{$fileDirName}) || defined($otherTopLevels{$fileDirName})) ) {
     printf STDERR "# something new: %s\n", $fileDirName;
   }
 }
 
 close (FH);
 
 ### Determine genome counts:
 my %genomeCounts;
 
 my $genomeCount = `grep -h ^genome /mirrordata/hubs/VGP/*enomes.txt | wc -l`;
 chomp $genomeCount;
 $genomeCounts{"VGP"} = $genomeCount;
 
-my @checkList = ('primates', 'mammals', 'birds', 'fish', 'vertebrate', 'legacy', 'plants', "invertebrate", "fungi", 'viral', 'bacteria', 'globalReference');
+my @checkList = ('primates', 'mammals', 'birds', 'fish', 'vertebrate', 'legacy', 'plants', "invertebrate", "fungi", 'viral', 'bacteria', 'HPRC', 'globalReference');
 
 foreach my $hubSet (@checkList) {
   $genomeCount = `grep -h ^genome /mirrordata/hubs/$hubSet/genomes.txt | wc -l`;
   chomp $genomeCount;
   $genomeCounts{$hubSet} = $genomeCount;
 }
 
 my $hubCount = 0;
 
 printf "<table class='sortable' border='1'>\n";
 printf "<thead><tr>\n";
 printf "  <th>hub&nbsp;gateway</th>\n";
 printf "  <th>description</th>\n";
 printf "</tr></thead><tbody>\n";
 
 # construct table
 foreach my $orderUp (@orderOutHubs) {
   printf "<tr>\n";
   ++$hubCount;
+  if ($orderUp eq "VGP") {
+     printf "    <th colspan=2>collections below are subsets of the assemblies above</th>\n";
+     printf "</tr>\n";
+     printf "<tr>\n";
+  }
   if ($orderUp eq "fish") {
      printf "    <td><a href='%s/%s' target=_blank>fishes</a></td>\n", $orderUp, $indexPage{$orderUp};
   } else {
      printf "    <td><a href='%s/%s' target=_blank>%s</a></td>\n", $orderUp, $indexPage{$orderUp}, $orderUp;
   }
   if (defined($genomeCounts{$orderUp})) {
     printf "    <td>%s (%d assemblies)</td>\n", $titles{$orderUp}, $genomeCounts{$orderUp};
   } else {
     printf "    <td>%s</td>\n", $titles{$orderUp};
   }
   printf "</tr>\n";
 }
 
 printf "</tbody></table>\n";
 
 my $totalAsmHubs = `grep -v "^#" /mirrordata/hubs/UCSC_GI.assemblyHubList.txt | wc -l`;
 chomp $totalAsmHubs;
 printf "<p>\n";
-printf "Please note: text file <a href='UCSC_GI.assemblyHubList.txt' target=_blank>listing</a> of %d NCBI/VGP genome assembly hubs\n", $totalAsmHubs;
+printf "Please note: text file <a href='UCSC_GI.assemblyHubList.txt' target=_blank>listing</a> of %d genome assembly hubs\n", $totalAsmHubs;
 printf "</p>\n";
 
 printf "<p>\n";
 printf "Please note, the <em>invertebrate</em> category contains more than just <em>invertebrate</em> animals.  Until these clades are sorted out, with extra categories created, you will also find parasites, protozoa, and other single celled eukaryotes in the <em>invertebrate</em> grouping.\n";
 printf "</p>\n";
 
 printf "<p>\n";
 printf "Please use the <a href='https://genome.ucsc.edu/assemblyRequest.html?all' target=_blank>Assembly Request</a> page to find and request GenBank assemblies that have not yet been included in the collections here.\n";
 printf "</p>\n";
 
 endHtml;