a7652d074beefd4f023287d09ec32bc2bbf43796 hiram Fri Jan 24 10:26:32 2020 -0800 now using common scripts to build hubs refs #24748 diff --git src/hg/makeDb/doc/primateAsmHub/mkHubIndex.pl src/hg/makeDb/doc/primateAsmHub/mkHubIndex.pl deleted file mode 100755 index f1528d3..0000000 --- src/hg/makeDb/doc/primateAsmHub/mkHubIndex.pl +++ /dev/null @@ -1,244 +0,0 @@ -#!/usr/bin/env perl - -use strict; -use warnings; - -my $home = $ENV{'HOME'}; -my $srcDocDir = "primateAsmHub"; -my $asmHubDocDir = "$home/kent/src/hg/makeDb/doc/$srcDocDir"; -my $Name = "Primate"; -my $asmHubName = "primates"; -my $defaultAssembly = "GCF_000001405.39_GRCh38.p13"; - -my $srcDir = "$home/kent/src/hg/makeDb/doc/$srcDocDir"; -my $commonNameOrder = "primates.commonName.asmId.orderList.tsv"; - -my @orderList; # asmId of the assemblies in order from the *.list files -# the order to read the different .list files: -my $assemblyCount = 0; - -############################################################################## -# from Perl Cookbook Recipe 2.17, print out large numbers with comma delimiters: -############################################################################## -sub commify($) { - my $text = reverse $_[0]; - $text =~ s/(\d\d\d)(?=\d)(?!\d*\.)/$1,/g; - return scalar reverse $text -} - -############################################################################## -### start the HTML output -############################################################################## -sub startHtml() { - -my $timeStamp = `date "+%F"`; -chomp $timeStamp; - -# - -print <<"END" - - - - - - -

$Name Genomes assembly hubs

-

-Assemblies from NCBI/Genbank/Refseq sources, subset of $asmHubName only. -

- -

How to view the hub

-

-Individual assemblies are attached to the genome browser via the -link to genome browser in the table below. To attach all -of these assemblies in one set for this hub, select the ${Name}s assembly -hub from our -Public Hubs -page or by clicking these assembly links to any of our official websites: -

-

- -

-To manually attach all the assemblies in this hub to other genome browsers: -

    -
  1. - From the blue navigation bar, go to - My Data -> Track Hubs
    2. -
  2. - Then select the My Hubs tab and enter this URL into the textbox: -
    https://hgdownload.soe.ucsc.edu/hubs/$asmHubName/hub.txt
    3. -
  3. - Once you have added the URL to the entry form, press the Add Hub - button to add the hub.
    4. -
-

- -

-After adding the hub, you will be redirected to the gateway page. The -genome assemblies can be selected from the -${Name}s Hub Assembly dropdown menu. -Instead of adding all the assemblies in one collected group, use the individual -link to genome browser in the table below. -

-

See also: assembly statistics


-

Data resource links

-NOTE: Click on the column headers to sort the table by that column
-The link to genome browser will attach only that single assembly to -the genome browser. -END -} # sub startHtml() - -############################################################################## -### start the table output -############################################################################## -sub startTable() { -print <<"END" - - - - - - - - -END -} # sub startTable() - -############################################################################## -### end the table output -############################################################################## -sub endTable() { - -print <<"END" - - -
countcommon name
link to genome browser		scientific name
and data download		NCBI assemblybioSamplebioProjectassembly date,
source link
-END -} # sub endTable() - -############################################################################## -### end the HTML output -############################################################################## -sub endHtml() { -print <<"END" - - - - - -END -} # sub endHtml() - -############################################################################## -### tableContents() -############################################################################## -sub tableContents() { - my $rowCount = 0; - foreach my $asmId (@orderList) { - my $accessionDir = substr($asmId, 0 ,3); - $accessionDir .= "/" . substr($asmId, 4 ,3); - $accessionDir .= "/" . substr($asmId, 7 ,3); - $accessionDir .= "/" . substr($asmId, 10 ,3); - $accessionDir .= "/" . $asmId; - my $ncbiFtpLink = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/$accessionDir/"; - my $buildDir = "/hive/data/genomes/asmHubs/refseqBuild/$accessionDir"; - my $asmReport="$buildDir/download/${asmId}_assembly_report.txt"; - my ($gcPrefix, $asmAcc, $asmName) = split('_', $asmId, 3); - my $chromSizes="${buildDir}/${asmId}.chrom.sizes"; - my $sciName = "notFound"; - my $commonName = "notFound"; - my $bioSample = "notFound"; - my $bioProject = "notFound"; - my $taxId = "notFound"; - my $asmDate = "notFound"; - my $itemsFound = 0; - open (FH, "<$asmReport") or die "can not read $asmReport"; - while (my $line = ) { - last if ($itemsFound > 5); - chomp $line; - $line =~ s/ //g;; - $line =~ s/\s+$//g;; - if ($line =~ m/Date:/) { - if ($asmDate =~ m/notFound/) { - ++$itemsFound; - $line =~ s/.*:\s+//; - my @a = split('-', $line); - $asmDate = sprintf("%04d-%02d-%02d", $a[0], $a[1], $a[2]); - } - } elsif ($line =~ m/BioSample:/) { - if ($bioSample =~ m/notFound/) { - ++$itemsFound; - $bioSample = $line; - $bioSample =~ s/.*:\s+//; - } - } elsif ($line =~ m/BioProject:/) { - if ($bioProject =~ m/notFound/) { - ++$itemsFound; - $bioProject = $line; - $bioProject =~ s/.*:\s+//; - } - } elsif ($line =~ m/Organism name:/) { - if ($sciName =~ m/notFound/) { - ++$itemsFound; - $commonName = $line; - $sciName = $line; - $commonName =~ s/.*\(//; - $commonName =~ s/\)//; - $sciName =~ s/.*:\s+//; - $sciName =~ s/\s+\(.*//; - } - } elsif ($line =~ m/Taxid:/) { - if ($taxId =~ m/notFound/) { - ++$itemsFound; - $taxId = $line; - $taxId =~ s/.*:\s+//; - } - } - } - close (FH); - my $hubUrl = "https://hgdownload.soe.ucsc.edu/hubs/$accessionDir"; - printf "%d\n", ++$rowCount; - printf "%s\n", $hubUrl, $asmId, $asmId, $commonName; - printf " %s\n", $hubUrl, $sciName; - printf " %s\n", $gcPrefix, $asmAcc, $asmId; - if ( $bioSample ne "notFound" ) { - printf " %s\n", $bioSample, $bioSample; - } else { - printf " n/a\n"; - } - printf " %s\n", $bioProject, $bioProject; - printf " %s\n", $ncbiFtpLink, $asmDate; - printf "\n"; - } -} # sub tableContents() - -############################################################################## -### main() -############################################################################## - -open (FH, "<$srcDir/${commonNameOrder}") or die "can not read ${commonNameOrder}"; -while (my $line = ) { - chomp $line; - my ($commonName, $asmId) = split('\t', $line); - push @orderList, $asmId; - ++$assemblyCount; -} -close (FH); - -startHtml(); -startTable(); -tableContents(); -endTable(); -endHtml();