2d2c836edaff720e31ac3fab4433e15f744b7245
hiram
  Wed Jul 6 12:46:13 2022 -0700
improve the description vs. the organism strings in the hub.txt refs #29545

diff --git src/hg/makeDb/doc/asmHubs/mkGenomes.pl src/hg/makeDb/doc/asmHubs/mkGenomes.pl
index 77a242b..4a72ab7 100755
--- src/hg/makeDb/doc/asmHubs/mkGenomes.pl
+++ src/hg/makeDb/doc/asmHubs/mkGenomes.pl
@@ -1,46 +1,49 @@
 #!/usr/bin/env perl
 
 use strict;
 use warnings;
 use File::Basename;
 
+my %commonName;	# key is asmId, value is common name
+my @monthNumber = qw( Zero Jan. Feb. Mar. Apr. May Jun. Jul. Aug. Sep. Oct. Nov. Dec. );
+
 my $argc = scalar(@ARGV);
 if ($argc != 3) {
   printf STDERR "mkGenomes.pl blatHost blatPort [two column name list] > .../hub/genomes.txt\n";
   printf STDERR "e.g.: mkGenomes.pl dynablat-01 4040 vgp.primary.assemblies.tsv > .../vgp/genomes.txt\n";
   printf STDERR "e.g.: mkGenomes.pl hgwdev 4040 vgp.primary.assemblies.tsv > .../vgp/download.genomes.txt\n";
   printf STDERR "the name list is found in \$HOME/kent/src/hg/makeDb/doc/asmHubs/\n";
   printf STDERR "\nthe two columns are 1: asmId (accessionId_assemblyName)\n";
   printf STDERR "column 2: common name for species, columns separated by tab\n";
   printf STDERR "result will write a local asmId.genomes.txt file for each hub\n";
   printf STDERR "and a local asmId.hub.txt file for each hub\n";
   printf STDERR "and a local asmId.groups.txt file for each hub\n";
   printf STDERR "and the output to stdout will be the overall genomes.txt\n";
   printf STDERR "index file for all genomes in the given list\n";
   exit 255;
 }
 
 my $downloadHost = "hgwdev";
 my @blatHosts = qw( dynablat-01 dynablat-01 );
 my @blatPorts = qw( 4040 4040 );
 my $blatHostDomain = ".soe.ucsc.edu";
 my $groupsTxt = `cat ~/kent/src/hg/makeDb/doc/asmHubs/groups.txt`;
 
 ################### writing out hub.txt file, twice ##########################
-sub singleFileHub($$$$$$$$$$$) {
-  my ($fh1, $fh2, $accessionId, $orgName, $descr, $asmId, $defPos, $taxId, $trackDb, $accessionDir, $buildDir) = @_;
+sub singleFileHub($$$$$$$$$$$$) {
+  my ($fh1, $fh2, $accessionId, $orgName, $descr, $asmId, $asmDate, $defPos, $taxId, $trackDb, $accessionDir, $buildDir) = @_;
   my @fhN;
   push @fhN, $fh1;
   push @fhN, $fh2;
 
   my %liftOverChain;	# key is 'otherDb' name, value is bbi path
   my %liftOverGz;	# key is 'otherDb' name, value is lift.over.gz file path
   my $hasChainNets = `ls -d $buildDir/trackData/lastz.* 2> /dev/null | wc -l`;
   chomp $hasChainNets;
   if ($hasChainNets) {
     printf STDERR "# hasChainNets: %d\t%s\n", $hasChainNets, $asmId;
     open (CH, "ls -d $buildDir/trackData/lastz.*|") or die "can not ls -d $buildDir/trackData/lastz.*";
     while (my $line = <CH>) {
       chomp $line;
       my $otherDb = basename($line);
       $otherDb =~ s/lastz.//;
@@ -52,51 +55,56 @@
      my $loPath = "$buildDir/liftOver/${accessionId}To${OtherDb}.over.chain.gz";
       if (-s "${loPath}") {
     $liftOverGz{$otherDb} = "liftOver/${accessionId}To${OtherDb}.over.chain.gz";
       }
     }
     close (CH);
   }
   my $fileCount = 0;
   my @tdbLines;
   open (TD, "<$trackDb") or die "can not read trackDb: $trackDb";
   while (my $tdbLine = <TD>) {
      chomp $tdbLine;
      push @tdbLines, $tdbLine;
   }
   close (TD);
+  my $trimmedOrgName = $orgName;
+  $trimmedOrgName =~ s/$commonName{$asmId}//i;
+  $trimmedOrgName = $orgName if (length($trimmedOrgName) < 1);
+  my $assemblyName = $asmId;
+  $assemblyName =~ s/${accessionId}_//;
   foreach my $fh (@fhN) {
     printf $fh "hub %s genome assembly\n", $accessionId;
     printf $fh "shortLabel %s\n", $orgName;
     printf $fh "longLabel %s/%s/%s genome assembly\n", $orgName, $descr, $asmId;
     printf $fh "useOneFile on\n";
     printf $fh "email hclawson\@ucsc.edu\n";
     printf $fh "descriptionUrl html/%s.description.html\n", $asmId;
     printf $fh "\n";
     printf $fh "genome %s\n", $accessionId;
     printf $fh "taxId %s\n", $taxId if (length($taxId) > 1);
     printf $fh "groups groups.txt\n";
-    printf $fh "description %s\n", $orgName;
+    printf $fh "description %s %s\n", $assemblyName, $asmDate;
     printf $fh "twoBitPath %s.2bit\n", $accessionId;
     printf $fh "twoBitBptUrl %s.2bit.bpt\n", $accessionId;
     printf $fh "chromSizes %s.chrom.sizes.txt\n", $accessionId;
     if ( -s "${buildDir}/${asmId}.chromAlias.bb" ) {
       printf $fh "chromAliasBb %s.chromAlias.bb\n", $accessionId;
     } else {
       printf $fh "chromAlias %s.chromAlias.txt\n", $accessionId;
     }
-    printf $fh "organism %s\n", $orgName;
+    printf $fh "organism %s\n", $commonName{$asmId};
     printf $fh "defaultPos %s\n", $defPos;
     printf $fh "scientificName %s\n", $descr;
     printf $fh "htmlPath html/%s.description.html\n", $asmId;
     # until blat server host is ready for hgdownload, avoid these lines
     if ($blatHosts[$fileCount] ne $downloadHost) {
       printf $fh "blat %s%s %s dynamic $accessionDir/$accessionId\n", $blatHosts[$fileCount], $blatHostDomain, $blatPorts[$fileCount];
       printf $fh "transBlat %s%s %s dynamic $accessionDir/$accessionId\n", $blatHosts[$fileCount], $blatHostDomain, $blatPorts[$fileCount];
       printf $fh "isPcr %s%s %s dynamic $accessionDir/$accessionId\n", $blatHosts[$fileCount], $blatHostDomain, $blatPorts[$fileCount];
     }
     foreach my $otherDb (sort keys %liftOverGz) {
        printf $fh "liftOver.%s %s\n", $otherDb, $liftOverGz{$otherDb};
     }
     printf $fh "\n";
     foreach my $tdbLine (@tdbLines) {
       printf $fh "%s\n", $tdbLine;
@@ -105,31 +113,30 @@
   }
 }
 
 ##############################################################################
 my $home = $ENV{'HOME'};
 my $toolsDir = "$home/kent/src/hg/makeDb/doc/asmHubs";
 
 my $blatHost = shift;
 my $blatPort = shift;
 my $inputList = shift;
 my $orderList = $inputList;
 if ( ! -s "$orderList" ) {
   $orderList = $toolsDir/$inputList;
 }
 
-my %commonName;	# key is asmId, value is common name
 my @orderList;	# asmId of the assemblies in order from the *.list files
 # the order to read the different .list files:
 my $assemblyCount = 0;
 
 open (FH, "<${orderList}") or die "can not read ${orderList}";
 while (my $line = <FH>) {
   next if ($line =~ m/^#/);
   chomp $line;
   my ($asmId, $commonName) = split('\t', $line);
   if (!defined($commonName)) {
     printf STDERR "ERROR: missing tab sep common name:\n'%s'\n", $line;
     exit 255;
   }
   if (defined($commonName{$asmId})) {
     printf STDERR "ERROR: duplicate asmId: '%s'\n", $asmId;
@@ -175,55 +182,68 @@
   my $asmReport="$buildDir/download/${asmId}_assembly_report.txt";
   my $trackDb = "$buildDir/$asmId.trackDb.txt";
   if ( ! -s "${trackDb}" ) {
     printf STDERR "# %03d not built yet: %s\n", $orderKey, $asmId;
     printf STDERR "# '%s'\n", $trackDb;
     next;
   }
   if ( ! -s "${asmReport}" ) {
     printf STDERR "# %03d missing assembly_report: %s\n", $orderKey, $asmId;
     next;
   }
   ++$buildDone;
 printf STDERR "# %03d genomes.txt %s/%s\n", $buildDone, $accessionDir, $accessionId;
   my $taxId=`grep -i "taxid:" $asmReport | head -1 | awk '{printf \$(NF)}' | tr -d \$'\\r'`;
   chomp $taxId;
-  my $descr=`grep -i "organism name:" $asmReport | head -1 | sed -e 's#.*organism name: *##i; s# (.*\$##;'`;
+  my $descr=`grep -i "organism name:" $asmReport | head -1 | tr -d \$'\\r' | sed -e 's#.*organism name: *##i; s# (.*\$##;'`;
   chomp $descr;
-  my $orgName=`grep -i "organism name:" $asmReport | head -1 | sed -e 's#.* name: .* (##; s#).*##;'`;
+  my $orgName=`grep -i "organism name:" $asmReport | head -1 | tr -d \$'\\r' | sed -e 's#.* name: .* (##; s#).*##;'`;
   chomp $orgName;
+  my $asmDate=`grep -i "Date" $asmReport | head -1 | tr -d \$'\\r'`;
+  chomp $asmDate;
+  $asmDate =~ s/.*Date:\s+//;
+  my ($year, $month, $day) = split('-', $asmDate);
+  $asmDate = sprintf("%s %s", $monthNumber[$month], $year);
+
   if (defined($commonName{$asmId})) {
      $orgName = $commonName{$asmId};
   }
+  my $trimmedOrgName = $orgName;
+  $trimmedOrgName =~ s/$commonName{$asmId}//i;
+  $trimmedOrgName =~ s/^\s+//;
+  $trimmedOrgName =~ s/\s+$//;
+  $trimmedOrgName = $orgName if (length($trimmedOrgName) < 1);
+  my $assemblyName = $asmId;
+  $assemblyName =~ s/${accessionId}_//;
 
   printf "genome %s\n", $accessionId;
   printf "taxId %s\n", $taxId if (length($taxId) > 1);
   printf "trackDb ../%s/%s/trackDb.txt\n", $accessionDir, $accessionId;
   printf "groups groups.txt\n";
-  printf "description %s\n", $orgName;
+  printf "description %s %s\n", $assemblyName, $asmDate;
   printf "twoBitPath ../%s/%s/%s.2bit\n", $accessionDir, $accessionId, $accessionId;
   printf "twoBitBptUrl ../%s/%s/%s.2bit.bpt\n", $accessionDir, $accessionId, $accessionId;
   printf "chromSizes ../%s/%s/%s.chrom.sizes.txt\n", $accessionDir, $accessionId, $accessionId;
 
   # wait until code gets out for v429 release before using chromAlias.bb
   # for the chromInfoPage display of hgTracks
   if ( -s "${buildDir}/${asmId}.chromAlias.bb" ) {
     printf "chromAliasBb ../%s/%s/%s.chromAlias.bb\n", $accessionDir, $accessionId, $accessionId;
   } else {
     printf "chromAlias ../%s/%s/%s.chromAlias.txt\n", $accessionDir, $accessionId, $accessionId;
   }
-  printf "organism %s\n", $orgName;
+  printf "organism %s\n", $commonName{$asmId};
   my $chrName=`head -1 $buildDir/$asmId.chrom.sizes | awk '{print \$1}'`;
   chomp $chrName;
   my $bigChrom=`head -1 $buildDir/$asmId.chrom.sizes | awk '{print \$NF}'`;
   chomp $bigChrom;
   my $oneThird = int($bigChrom/3);
   my $tenK = $oneThird + 10000;
   $tenK = $bigChrom if ($tenK > $bigChrom);
   my $defPos="${chrName}:${oneThird}-${tenK}";
   if ( -s "$buildDir/defaultPos.txt" ) {
     $defPos=`cat "$buildDir/defaultPos.txt"`;
     chomp $defPos;
   }
   printf "defaultPos %s\n", $defPos;
   printf "orderKey %d\n", $buildDone;
   printf "scientificName %s\n", $descr;
@@ -243,49 +263,49 @@
   open (HT, ">$localHubTxt") or die "can not write to $localHubTxt";
   printf HT "hub %s genome assembly\n", $accessionId;
   printf HT "shortLabel %s\n", $orgName;
   printf HT "longLabel %s/%s/%s genome assembly\n", $orgName, $descr, $asmId;
   printf HT "genomesFile genomes.txt\n";
   printf HT "email hclawson\@ucsc.edu\n";
   printf HT "descriptionUrl html/%s.description.html\n", $asmId;
   close (HT);
 
   # try creating single file hub.txt, one for hgwdev, one for hgdownload
   my $downloadHubTxt = "$buildDir/${asmId}.download.hub.txt";
   open (DL, ">$downloadHubTxt") or die "can not write to $downloadHubTxt";
   $localHubTxt = "$buildDir/${asmId}.singleFile.hub.txt";
   open (HT, ">$localHubTxt") or die "can not write to $localHubTxt";
 
-  singleFileHub(\*HT, \*DL, $accessionId, $orgName, $descr, $asmId,
+  singleFileHub(\*HT, \*DL, $accessionId, $orgName, $descr, $asmId, $asmDate,
 	$defPos, $taxId, $trackDb, $accessionDir, $buildDir);
 
   my $localGenomesFile = "$buildDir/${asmId}.genomes.txt";
   open (GF, ">$localGenomesFile") or die "can not write to $localGenomesFile";
   printf GF "genome %s\n", $accessionId;
   printf GF "taxId %s\n", $taxId if (length($taxId) > 1);
   printf GF "trackDb trackDb.txt\n";
   printf GF "groups groups.txt\n";
-  printf GF "description %s\n", $orgName;
+  printf GF "description %s %s\n", $assemblyName, $asmDate;
   printf GF "twoBitPath %s.2bit\n", $accessionId;
   printf GF "twoBitBptUrl %s.2bit.bpt\n", $accessionId;
   printf GF "chromSizes %s.chrom.sizes.txt\n", $accessionId;
   if ( -s "${buildDir}/${asmId}.chromAlias.bb" ) {
     printf GF "chromAliasBb %s.chromAlias.bb\n", $accessionId;
   } else {
     printf GF "chromAlias %s.chromAlias.txt\n", $accessionId;
   }
-  printf GF "organism %s\n", $orgName;
+  printf GF "organism %s\n", $commonName{$asmId};
   printf GF "defaultPos %s\n", $defPos;
   printf GF "scientificName %s\n", $descr;
   printf GF "htmlPath html/%s.description.html\n", $asmId;
   # until blat server host is ready for hgdownload, avoid these lines
   if ($blatHost ne $downloadHost) {
     if ( -s "${destDir}/$accessionId.trans.gfidx" ) {
       printf GF "blat $blatHost$blatHostDomain $blatPort dynamic $accessionDir/$accessionId\n";
       printf GF "transBlat $blatHost$blatHostDomain $blatPort dynamic $accessionDir/$accessionId\n";
      printf GF "isPcr $blatHost$blatHostDomain $blatPort dynamic $accessionDir/$accessionId\n";
     }
   }
   close (GF);
 
   my $localGroups = "$buildDir/${asmId}.groups.txt";
   open (GR, ">$localGroups") or die "can not write to $localGroups";