895c7fceea79e43c9abf53a85b76ce7542cec328
hiram
  Thu Apr 7 13:26:38 2022 -0700
allow otherAligners directory in data downloads and gff3 gene file refs #29203

diff --git src/hg/utils/automation/asmHubGatewayPage.pl src/hg/utils/automation/asmHubGatewayPage.pl
index 84bda67..f27e55d 100755
--- src/hg/utils/automation/asmHubGatewayPage.pl
+++ src/hg/utils/automation/asmHubGatewayPage.pl
@@ -318,54 +318,62 @@
 <b>Assembly date:</b> %s<br>
 <b>Assembly type:</b> %s<br>
 <b>Assembly level:</b> %s<br>
 <b>Biosample:</b> <a href=\"https://www.ncbi.nlm.nih.gov/biosample/?term=%s\" target=\"_blank\">%s</a><br>
 <b>Assembly accession ID:</b> <a href=\"https://www.ncbi.nlm.nih.gov/assembly/%s\" target=\"_blank\">%s</a><br>
 <b>Assembly FTP location:</b> <a href='ftp://ftp.ncbi.nlm.nih.gov/genomes/all/%s' target='_blank'>%s</a><br>
 \n", $commonName, $orgName, $taxId, $taxId, $submitter, $asmDate, $descrAsmType,
   $asmLevel, $bioSample, $bioSample, $asmAccession, $asmAccession, $newStyleUrl, $newStyleUrl;
 
 chromSizes($chromSizes);
 
 printf "</p>\n<hr>
 <h4>Data file downloads</h4>
 <p>
 <ul>
-<li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.fa.gz' target=_blank>$asmAccession.fa.gz</a> fasta sequence with original assembly sequence names</li>
-<li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.2bit' target=_blank>$asmAccession.2bit</a> UCSC 2bit sequence file with original assembly sequence names</li>
+<li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.fa.gz' target=_blank>$asmAccession.fa.gz</a> fasta sequence with NCBI GenBank sequence names</li>
+<li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.2bit' target=_blank>$asmAccession.2bit</a> UCSC 2bit sequence file with NCBI GenBank sequence names</li>
 <li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.chromAlias.txt' target=_blank>$asmAccession.chromAlias.txt</a> chromAlias file to relate chromosome names</li>
 ";
 
 if ( -s "$buildDir/$asmId.chrNames.fa.gz") {
 printf "<li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.chrNames.fa.gz' target=_blank>$asmAccession.chrNames.fa.gz</a> fasta sequence with <b>chrN</b> sequence names</li>\n";
 }
 
 if ( -s "$buildDir/$asmId.chrNames.2bit") {
 printf "<li><a href='https://$sourceServer/hubs/$localDataUrl/$asmAccession.chrNames.2bit' target=_blank>$asmAccession.chrNames.2bit</a> UCSC 2bit sequence file with <b>chrN</b> sequence names</li>\n";
 }
 
 if ( -d "$genesDir" ) {
- open (GD, "ls $genesDir/*.gtf.gz 2> /dev/null|") or die "can not ls $genesDir/*.gtf.gz";
+ open (GD, "ls $genesDir/*.gtf.gz $genesDir/*.gff3.gz 2> /dev/null|") or die "can not ls $genesDir/*.gtf.gz";
  while (my $gtfFile = <GD>) {
     chomp $gtfFile;
     my $gtf = basename($gtfFile);
+    if ($gtf =~ m/gff3.gz/) {
+      printf "<li><a href='https://$sourceServer/hubs/$localDataUrl/genes/$gtf' target=_blank>$gtf</a> gene GFF3 file</li>\n";
+    } else {
       printf "<li><a href='https://$sourceServer/hubs/$localDataUrl/genes/$gtf' target=_blank>$gtf</a> gene GTF file</li>\n";
     }
  }
+ close (GD);
+}
+
+if ( -d "${buildDir}/otherAligners" ) {
+  printf "<li><a href='https://$sourceServer/hubs/$localDataUrl/otherAligners/' target=_blank>pre-computed indices</a> for alignment programs: bowtie2, bwa-mem2, hisat2, minimap2</li>\n";
+}
 
-printf "
-<li>explore the hub directory at: <a href='https://$sourceServer/hubs/$localDataUrl/' target=_blank>$sourceServer/hubs/$localDataUrl/</a></li>
+printf "<li>explore the hub directory at: <a href='https://$sourceServer/hubs/$localDataUrl/' target=_blank>$sourceServer/hubs/$localDataUrl/</a></li>
 </ul>
 ";
 printf "</p>\n<hr>
 <h4>Copy this entire assembly hub for local use</h4>
 <p>
 This download is only for the purpose of using this assembly hub in
 your institution which may have firewall access restrictions to this
 data.<br>
 
 To download this assembly data, use this <b>rsync</b> command:
 <pre>
   rsync -a -P \\
     rsync://$sourceServer/hubs/$localDataUrl/ \\
       ./$accessionId/
 </pre>
@@ -398,31 +406,31 @@
 if ($genomeSize < 4294967297) {
   printf "<hr>
 <h4>blat service</h4>
 <p>
 There is blat service available for this genome assembly.  When viewing this
 assembly in the genome browser, access the blat service via the
 <em><b>Tools -> Blat</b></em> blue navigation bar menu item.
 </p>
 <p>
 For local command line blat service, access
 the blat service via the <b>gfClient</b> command line operation.<br>
 See also: <a href='http://hgdownload.soe.ucsc.edu/admin/exe/linux.x86_64/' target=_blank>
 hgdownload.soe.ucsc.edu/admin/exe/linux.x86_64/</a> to download command line
 binaries.<br>
 <br>
-To operate this locally, you will need the <b>%s.2bit</b> file from:
+To operate this locally, you will need the <b>$accessionId.2bit</b> file from:
 <pre>
   https://$sourceServer/hubs/$localDataUrl/
 </pre>
 Which can be obtained with rsync via:
 <pre>
   rsync -a -P \
     rsync://hgdownload.soe.ucsc.edu/hubs/$accessionDir/$accessionId.2bit ./
 </pre>
 With that <b>$accessionId.2bit</b> file in your working directory where you run
 this command, for example, a DNA query with your DNA sequence in
 the file: <b>someDna.fa</b>
 with result in the file: <b>$accessionId.someDna.psl</b>
 <pre>
 gfClient -t=dna -q=dna -genome=$accessionId -genomeDataDir=$accessionDir \
     dynablat-01.soe.ucsc.edu 4040 ./ someDna.fa $accessionId.someDna.psl