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/mkAsmStats.pl src/hg/makeDb/doc/globalReference/mkAsmStats.pl new file mode 100755 index 0000000..8d0ce11 --- /dev/null +++ src/hg/makeDb/doc/globalReference/mkAsmStats.pl @@ -0,0 +1,270 @@ +#!/usr/bin/env perl + +use strict; +use warnings; +use File::stat; + +my $asmHubWorkDir = "globalReference"; + +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 $overallNucleotides = 0; +my $overallSeqCount = 0; +my $overallGapSize = 0; +my $overallGapCount = 0; + +my %ethnicGroup; # ksy is asmId, value is ethnicity +my %countryOfOrigin; # ksy is asmId, value is country of origin + +############################################################################## +# from Perl Cookbook Recipe 2.17, print out large numbers with comma delimiters: +############################################################################## +sub commify($) { + 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 statistics

+

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

+ +

+

See also: hub access

+

+ +

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() { + +my $commaNuc = commify($overallNucleotides); +my $commaSeqCount = commify($overallSeqCount); +my $commaGapSize = commify($overallGapSize); +my $commaGapCount = commify($overallGapCount); + +print <<"END" + + + + + + + + + +
countethnicity
link to genome browser
country of origin
and data download
NCBI assemblysequence
count
genome size
nucleotides
gap
count
unknown bases
(gap size sum)
masking
percent
TOTALS:assembly count $assemblyCount$commaSeqCount$commaNuc$commaGapCount$commaGapSize 
+END +} + +############################################################################## +### end the HTML output +############################################################################## +sub endHtml() { +print <<"END" + + + + + +END +} + +sub asmCounts($) { + my ($chromSizes) = @_; + my ($sequenceCount, $totalSize) = split('\s+', `ave -col=2 $chromSizes | egrep "^count|^total" | awk '{printf "%d\\n", \$NF}' | xargs echo`); + return ($sequenceCount, $totalSize); +} + +# my ($gapSize) = maskStats($faSizeTxt); +sub maskStats($) { + my ($faSizeFile) = @_; + my $gapSize = `grep 'sequences in 1 file' $faSizeFile | awk '{print \$3}'`; + chomp $gapSize; + $gapSize =~ s/\(//; + my $totalBases = `grep 'sequences in 1 file' $faSizeFile | awk '{print \$1}'`; + chomp $totalBases; + my $maskedBases = `grep 'sequences in 1 file' $faSizeFile | awk '{print \$9}'`; + chomp $maskedBases; + my $maskPerCent = 100.0 * $maskedBases / $totalBases; + return ($gapSize, $maskPerCent); +} + +# grep "sequences in 1 file" GCA_900324465.2_fAnaTes1.2.faSize.txt +# 555641398 bases (3606496 N's 552034902 real 433510637 upper 118524265 lower) in 50 sequences in 1 files + +sub gapStats($) { + my ($asmId) = @_; + my $gapBed = "$asmId/trackData/allGaps/$asmId.allGaps.bed.gz"; + my $gapCount = 0; + if ( -s "$gapBed" ) { + $gapCount = `zcat $gapBed | awk '{print \$3-\$2}' | ave stdin | grep '^count' | awk '{print \$2}'`; + } + chomp $gapCount; + return ($gapCount); +} + +# GCA_901709675.1_fSynAcu1.1/trackData/allGaps] zcat GCA_901709675.1_fSynAcu1.1.allGaps.bed.gz | awk '{print $3-$2,$0}' | ave stdin | grep "^count" | awk '{print $2}' + +############################################################################## +### tableContents() +############################################################################## +sub tableContents() { + + my $asmCount = 0; + foreach my $asmId (reverse(@orderList)) { +# next if ($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 $twoBit = "${asmId}/trackData/addMask/${asmId}.masked.2bit"; + my $faSizeTxt = "${asmId}/${asmId}.faSize.txt"; + if ( ! -s "$faSizeTxt" ) { + printf STDERR "twoBitToFa $twoBit stdout | faSize stdin > $faSizeTxt\n"; + print `twoBitToFa $twoBit stdout | faSize stdin > $faSizeTxt`; + } + my ($gapSize, $maskPerCent) = maskStats($faSizeTxt); + $overallGapSize += $gapSize; + my ($seqCount, $totalSize) = asmCounts($chromSizes); + $overallSeqCount += $seqCount; +# my $totalSize=`ave -col=2 $chromSizes | grep "^total" | awk '{printf "%d", \$NF}'`; + $overallNucleotides += $totalSize; + my $gapCount = gapStats($asmId); + $overallGapCount += $gapCount; + 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; + $asmDate = $line; + $asmDate =~ s/.*:\s+//; + } + } elsif ($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; + $taxId =~ s/.*:\s+//; + } + } + } + close (FH); + printf "%d%s\n", ++$asmCount, $asmHubWorkDir, $asmId, $ethnicGroup{$asmId}; + printf " %s\n", $asmHubWorkDir, $asmId, $countryOfOrigin{$asmId}; + printf " %s\n", $gcPrefix, $asmAcc, $asmId; + printf " %s\n", commify($seqCount); + printf " %s\n", commify($totalSize); + printf " %s\n", commify($gapCount); + printf " %s\n", commify($gapSize); + printf " %.2f\n", $maskPerCent; + printf "\n"; + } +} + +############################################################################## +### main() +############################################################################## + +my $home = $ENV{'HOME'}; +my $srcDir = "$home/kent/src/hg/makeDb/doc/$asmHubWorkDir"; + +open (FH, "<$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();