147dce6b6804f24a5396a7ccb0b3bee184d1f6a7 hiram Thu Jan 2 11:47:50 2020 -0800 set of files for hub build refs @24354 diff --git src/hg/makeDb/doc/globalReference/mkHubIndex.pl src/hg/makeDb/doc/globalReference/mkHubIndex.pl new file mode 100755 index 0000000..52db04b --- /dev/null +++ src/hg/makeDb/doc/globalReference/mkHubIndex.pl @@ -0,0 +1,254 @@ +#!/usr/bin/env perl + +use strict; +use warnings; + +my $Name = "GlobalReference"; +my $asmHubWorkDir = "globalReference"; +my $defaultAssembly = "GCA_001524155.4_NA19240_prelim_3.0"; + +my @orderList; # asmId of the assemblies in order from the *.list files +# the order to read the different .list files: +my @classList = qw( human ); +my %class; # key is asmId, value is from class list +my $assemblyCount = 0; + +my %coriellLink; # key is asmId, value is isolate ID to construct link +# https://www.coriell.org/0/Sections/Search/Sample_Detail.aspx?Ref= +my %ethnicGroup; # ksy is asmId, value is ethnicity +my %countryOfOrigin; # ksy is asmId, value is country of origin + +############################################################################## +# from Perl Cookbook Recipe 2.17, print out large numbers with comma delimiters: +############################################################################## +sub commify($) { + 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" + + + + + + +

Platinum Genomes Project assembly hub

+This assembly hub contains assemblies released +by the +Platinum Genomes Project. +

+ +

How to view the hub

+You can load this hub from our +Public Hubs +page or by clicking these links to any of our official websites: +

+ +

+To manually attach this hub to other genome browsers: +

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

+ +

+After adding the hub, you will be redirected to the gateway page. The +genome assemblies can be selected from the Platinum Genomes Hub Assembly dropdown menu. +

Data resource links

+NOTE: Click on the column headers to sort the table by that column +END +} + +############################################################################## +### start the table output +############################################################################## +sub startTable() { +print <<"END" + + + + + + + +END +} + +############################################################################## +### end the table output +############################################################################## +sub endTable() { + +print <<"END" + + +

ethnicity link to genome browser	country of origin and data download	NCBI assembly	bioSample	bioProject	assembly date, source link

+END +} + +############################################################################## +### end the HTML output +############################################################################## +sub endHtml() { +print <<"END" + + + + + +END +} + +############################################################################## +### tableContents() +############################################################################## +sub tableContents() { + open (CN, "|sort --ignore-case >commonNameOrder.list") or die "can not write to commonNameOrder.list"; + + foreach my $asmId (@orderList) { +# next if ($asmId =~ m/GCF_900963305.1_fEcheNa1.1/); + my $asmReport="${asmId}/download/${asmId}_assembly_report.txt"; + my ($gcPrefix, $asmAcc, $asmName) = split('_', $asmId, 3); + my $chromSizes="${asmId}/${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); + printf CN "%s\t%s\n", $commonName, $asmId; + printf "%s\n", $asmHubWorkDir, $asmId, $ethnicGroup{$asmId}; + printf " %s\n", $asmHubWorkDir, $asmId, $countryOfOrigin{$asmId}; + printf " %s\n", $gcPrefix, $asmAcc, $asmId; + printf " %s\n", $bioSample, $bioSample; + printf " %s\n", $bioProject, $bioProject; + printf " %s\n", $coriellLink{$asmId}, $asmDate; + printf "\n"; + } + close(CN); +} + +############################################################################## +### main() +############################################################################## + +my $home = $ENV{'HOME'}; +my $srcDir = "$home/kent/src/hg/makeDb/doc/$asmHubWorkDir"; + +open (FH, "<$srcDir/isolate.txt") or die "can not read $srcDir/isolate.txt"; +while (my $line = ) { + chomp $line; + my ($asmId, $isolate) = split('\t', $line); + $coriellLink{$asmId} = $isolate; +} +close (FH); + +open (FH, "<$srcDir/ethnicGroup.txt") or die "can not read $srcDir/ethnicGroup.txt"; +while (my $line = ) { + chomp $line; + my ($asmId, $ethnicGroup) = split('\t', $line); + my ($ethnic, $origin) = split(', ', $ethnicGroup); + $ethnicGroup{$asmId} = $ethnic; + $countryOfOrigin{$asmId} = $origin; +} +close (FH); + +foreach my $species (@classList) { + my $listFile = "$srcDir/${species}.list"; + open (FH, "<$listFile") or die "can not read $listFile"; + while (my $asmId = ) { + chomp $asmId; + push @orderList, $asmId; + $class{$asmId} = $species; + ++$assemblyCount; + } + close (FH); +} + +startHtml(); +startTable(); +tableContents(); +endTable(); +endHtml();

Platinum Genomes Project assembly hub

How to view the hub

See also: assembly statistics

Data resource links