2feb808479d0767a519a687c3948b1a21f1e8431 hiram Fri Jan 3 13:31:23 2020 -0800 initial set of files to create symlinks and index pages refs #20137 diff --git src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl new file mode 100755 index 0000000..cb3d393 --- /dev/null +++ src/hg/makeDb/doc/primateAsmHub/mkAsmStats.pl @@ -0,0 +1,258 @@ +#!/usr/bin/env perl + +use strict; +use warnings; +use File::stat; + +my $home = $ENV{'HOME'}; +my $srcDocDir = "primateAsmHub"; +my $asmHubDocDir = "$home/kent/src/hg/makeDb/doc/$srcDocDir"; +my $asmHubName = "primates"; + +my $commonNameList = "primates.asmId.commonName.tsv"; +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; +my $overallNucleotides = 0; +my $overallSeqCount = 0; +my $overallGapSize = 0; +my $overallGapCount = 0; + +############################################################################## +# from Perl Cookbook Recipe 2.17, print out large numbers with comma delimiters: +############################################################################## +sub commify($) { + 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" +<!DOCTYPE HTML 4.01 Transitional> +<!--#set var="TITLE" value="Primate genomes assembly hubs" --> +<!--#set var="ROOT" value="../.." --> + +<!--#include virtual="\$ROOT/inc/gbPageStartHardcoded.html" --> + +<h1>Primate Genomes assembly hubs</h1> +<p> +Assemblies from NCBI/Genbank/Refseq sources +</p> + +<p> +<h3>See also: <a href='index.html' target=_blank>hub access</a></h3> +</p> + +<h3>Data resource links</h3> +NOTE: <em>Click on the column headers to sort the table by that column</em> +END +} + +############################################################################## +### start the table output +############################################################################## +sub startTable() { +print <<"END" +<table class="sortable" border="1"> +<thead><tr><th>count</th> + <th>common name<br>link to genome browser</th> + <th>scientific name<br>and data download</th> + <th>NCBI assembly</th> + <th>sequence<br>count</th><th>genome size<br>nucleotides</th> + <th>gap<br>count</th><th>unknown bases<br>(gap size sum)</th><th>masking<br>percent</th> +</tr></thead><tbody> +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" + +</tbody> +<tfoot><tr><th>TOTALS:</th><td align=center colspan=3>assembly count $assemblyCount</td> + <td align=right>$commaSeqCount</td> + <td align=right>$commaNuc</td> + <td align=right>$commaGapCount</td> + <td align=right>$commaGapSize</td> + <td colspan=1> </td> + </tr></tfoot> +</table> +END +} + +############################################################################## +### end the HTML output +############################################################################## +sub endHtml() { +print <<"END" +</div><!-- closing gbsPage from gbPageStartHardcoded.html --> +</div><!-- closing container-fluid from gbPageStartHardcoded.html --> +<!--#include virtual="\$ROOT/inc/gbFooterHardcoded.html"--> +<script type="text/javascript" src="/js/sorttable.js"></script> +</body></html> +END +} + +sub asmCounts($) { + 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 ($buildDir, $asmId) = @_; + my $gapBed = "$buildDir/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)) { + my $buildDir = "/hive/data/genomes/asmHubs/refseqBuild/" . substr($asmId, 0 ,3); + $buildDir .= "/" . substr($asmId, 4 ,3); + $buildDir .= "/" . substr($asmId, 7 ,3); + $buildDir .= "/" . substr($asmId, 10 ,3); + $buildDir .= "/" . $asmId; + my $asmReport="$buildDir/download/${asmId}_assembly_report.txt"; + my ($gcPrefix, $asmAcc, $asmName) = split('_', $asmId, 3); + my $chromSizes = "${buildDir}/${asmId}.chrom.sizes"; + my $twoBit = "${buildDir}/trackData/addMask/${asmId}.masked.2bit"; + my $faSizeTxt = "${buildDir}/${asmId}.faSize.txt"; + if ( ! -s "$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 $gapCount = gapStats($buildDir, $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 $line = <FH>) { + last if ($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; + $taxId =~ s/.*:\s+//; + } + } + } + close (FH); + printf "<tr><th>%d</th><td align=center><a href='https://genome.ucsc.edu/cgi-bin/hgGateway?hubUrl=https://hgdownload.soe.ucsc.edu/hubs/%s/hub.txt&genome=%s&position=lastDbPos' target=_blank>%s</a></td>\n", ++$asmCount, $asmHubName, $asmId, $commonName; + printf " <td align=center><a href='https://hgdownload.soe.ucsc.edu/hubs/%s/genomes/%s/' target=_blank>%s</a></td>\n", $asmHubName, $asmId, $sciName; + printf " <td align=left><a href='https://www.ncbi.nlm.nih.gov/assembly/%s_%s/' target=_blank>%s</a></td>\n", $gcPrefix, $asmAcc, $asmId; + printf " <td align=right>%s</td>\n", commify($seqCount); + printf " <td align=right>%s</td>\n", commify($totalSize); + printf " <td align=right>%s</td>\n", commify($gapCount); + printf " <td align=right>%s</td>\n", commify($gapSize); + printf " <td align=right>%.2f</td>\n", $maskPerCent; + printf "</tr>\n"; + } +} + +############################################################################## +### main() +############################################################################## + +open (FH, "<$asmHubDocDir/${commonNameOrder}") or die "can not read ${commonNameOrder}"; +while (my $line = <FH>) { + chomp $line; + my ($commonName, $asmId) = split('\t', $line); + push @orderList, $asmId; + ++$assemblyCount; +} +close (FH); + +startHtml(); +startTable(); +tableContents(); +endTable(); +endHtml();