22a67b8eddff877e9265906cfbc4df5a41c3e0db lrnassar Mon Aug 5 12:01:54 2019 -0700 Pointing hard-coded links to hgdownload refs #23734 diff --git src/hg/makeDb/doc/VGP/mkAsmStats.pl src/hg/makeDb/doc/VGP/mkAsmStats.pl index 979c3a4..ab72eb9 100755 --- src/hg/makeDb/doc/VGP/mkAsmStats.pl +++ src/hg/makeDb/doc/VGP/mkAsmStats.pl @@ -1,266 +1,266 @@ #!/usr/bin/env perl use strict; use warnings; use File::stat; my @orderList; # asmId of the assemblies in order from the *.list files # the order to read the different .list files: my @classList = qw( mammal bird reptile amphibian fish ); my %class; # key is asmId, value is from class list my $assemblyCount = 0; my $overallNucleotides = 0; my $overallSeqCount = 0; my $overallGapSize = 0; my $overallGapCount = 0; my %betterName; # key is asmId, value is common name ############################################################################## # from Perl Cookbook Recipe 2.17, print out large numbers with comma delimiters: ############################################################################## sub commify($) { 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"

VGP - Vertebrate Genomes Project assembly statistics

VGP logo

This assembly hub contains assemblies released by the Vertebrate 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"
countcommon name
view in browser		 scientific name NCBI assembly sequence
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 = `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 $asmId (@orderList) { # next if ($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); $commonName = $betterName{$asmId} if (exists($betterName{$asmId})); - printf "%d%s\n", ++$asmCount, $asmId, $commonName; + printf "%d%s\n", ++$asmCount, $asmId, $commonName; printf " %s\n", $sciName; 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/VGP"; open (FH, "<$srcDir/commonNames.txt") or die "can not read $srcDir/commonNames.txt"; while (my $line = ) { chomp $line; my ($asmId, $name) = split('\t', $line); $betterName{$asmId} = $name; } 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();