# HG changeset patch # User stef # Date 1425045376 18000 # Node ID aaa240cf978bfd3cddbe9ffa8e1da80549d51fe3 # Parent 61c0e184e50d9822d3ba1b11e4a2449412cabbce Uploaded diff -r 61c0e184e50d -r aaa240cf978b mkHtmlReportGalaxy.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mkHtmlReportGalaxy.pl Fri Feb 27 08:56:16 2015 -0500 @@ -0,0 +1,232 @@ +#!/usr/bin/perl -w + +use strict; +use Cwd; +use Spreadsheet::WriteExcel; + +$| = 1; +my $sample = shift || die "No input\n"; +my $dir = shift || "./"; +my $outdir = shift || "./"; +my $pat = shift || ""; +my $cwd = cwd(); +(my $runName = $cwd) =~ s/^.*\/(.*?)$/$1/; + +# QC +# Results +my @samples = (); +#open INDEX, ">$outdir/index.html"; +my $htmlHead = qq( + + + + + + +); +#print INDEX $htmlHead; +# opendir DIR, "$dir"; +# while (my $cd = readdir DIR) { +# if ($cd =~ /(.*$pat)\.qc\.targets\.txt$/) { +# my $sam = $1; +# # next if ($sam =~ /R[12]/); +# print STDERR $1 . "\n"; +# push @samples, $1; +# } +# } +# close DIR; + +#print INDEX ""; +#print INDEX ""; +#print INDEX "\n"; +#foreach my $sam (sort @samples) { +# print INDEX "\n"; + +#} +my %link = (); +my $excelBook0 = Spreadsheet::WriteExcel->new("$outdir/runQC.xls"); +my $excel0 = $excelBook0->add_worksheet("table1"); +my $excel0Ref = [[qw/sampleName runName totalReads pct100 ntbGenes/]]; + +print STDERR "Processing $sample\n"; +# next if ($sample =~ /R[12]/); + +my $readCnt = 0; +my $amp100 = 0; +my %ntbGenes = (); + +open OUT, ">$outdir/$sample.html"; +open OUT2, ">$outdir/$sample.tsv"; +my $excelBook = Spreadsheet::WriteExcel->new("$outdir/$sample.xls"); +my $excel1 = $excelBook->add_worksheet("table1"); +my $excel2 = $excelBook->add_worksheet("table2"); +print OUT $htmlHead; +my %QC = (); +open QC, "<$dir/$sample.qc.targets.txt"; +readline QC; +print STDERR "Reading in $sample.qc.targets.txt\n"; +while () { + chomp; + my @row = split(/\t/, $_); + my @id = split(/[\_\.\-:]/, $row[0]); + $row[-1] = 0 if ($row[-1] eq "NA"); + $readCnt += $row[-1]; # DP + if ($#id != 10) { + $id[0] =~ /(\D+)(\d+)/; + $id[0] = $2; + unshift @id, $1; + } + + if ($row[-1] >= 100) { + $amp100++ + } + else { + $ntbGenes{$row[0]}{dp} = $row[-1]; + $ntbGenes{$row[0]}{id} = [@id]; + } + + $QC{$row[0]}{QC} = [@id, @row];# if ($id[0]); + foreach my $c ($row[4] .. $row[5]) { + $link{$id[-3] . ":" . $c}{$row[0]} = "Assay"; + } + foreach my $c ($row[2] .. $row[4], $row[5] .. $row[3]) { + $link{$id[-3] . ":" . $c}{$row[0]} = "LSO"; + } +} +close QC; + +open RES, "<$dir/$sample.res.filtered.tsv" or die "Unable to open $dir/$sample\n"; +my %uniq = (); +my $colCnt = 0; +my $resHead = readline(RES); +chomp $resHead; +$resHead =~ s/^#//; +$resHead =~ s/\s+$//; +my %resCol = map { $_ => $colCnt++ } split(/\t/, $resHead); +my @keyColsN = qw/QUAL Gene_Name Codon_Change Amino_Acid_change vaf DP AD Tag CHROM POS ID REF ALT Context Effect_Impact Functional_Class Amino_Acid_length Gene_Coding Transcript_ID Exon_Rank/; +# my @keyColsN = qw/CHROM POS ID REF ALT QUAL DP AD vaf Context Effect_Impact Functional_Class Codon_Change Amino_Acid_change Amino_Acid_length Gene_Name Coding Transcript Exon Tag/; +my @keyColsI = map { $resCol{$_} } @keyColsN; +foreach my $i (0 .. $#keyColsN) { + print STDERR join(":", $i, $keyColsN[$i], $keyColsI[$i]) . "\n"; +} + +print STDERR "Processing results\n"; +while () { + chomp; + my @row = split(/\t/, $_); + my $cpos = join(":", @row[0, 1]); + if (exists $link{$cpos}) { +# my $key = join(":", @row[0 .. 4,6, 9,10,11,12,14 .. 21]); + my $key = join(":", @row[@keyColsI]); + #print STDERR join(":", @keyColsI) . "\n"; +# print STDERR join(":", @row) . "\n"; sleep 1; + if (not exists($uniq{$key})) { + foreach my $locus (keys(%{$link{$cpos}})) { + next if ($link{$cpos}{$locus} eq "LSO"); + push @{$QC{$locus}{RES}}, [@row, $link{$cpos}{$locus}]; + # print STDERR "Adding $key to $locus\n\n"; #sleep 1; + } + $uniq{$key} = 0; + } + else { + # print STDERR $key . " : Exists\n\n"; #sleep 1; + } + } +} +close RES; + +## Rplots that are not self-explanatory enough +#print OUT ""; +#print OUT ""; +#print OUT ""; +#print OUT ""; +#print OUT ""; +#print OUT ""; + +print OUT ""; +#print OUT ""; +#print OUT ""; +#print OUT ""; +#print OUT ""; +print OUT "
Download:runQC.xls
SampleBAMsnpindelreadCntAmp > 100
$samBAMBAI
"; +print OUT "
Download:TSVXLS
"; +print OUT "\n"; +# my @colnames = qw/depth chr pos id ref var qual DP AD vaf context impact effectClass codonChange AAChange RefSeqLength geneName RefSeqClass RefSeqID Exon Tag/; +my @colnames = ("depth", @keyColsN); +print OUT "" . join("", map { "" } ("Amplicon", "c","c2", "b", @colnames)) . ""; +print OUT2 join("\t", "Amplicon", @colnames) . "\n"; +my $excelAref = [["Amplicon", @colnames]]; +my $excelAref2 = [[qw/gene exon protein vaf func depth /]]; +my %rescnt = (); +foreach my $locus (sort keys(%QC)) { +# my @targets = keys(%{$QC{$locus}{QC}}); +# print OUT ""; + my $nres = 1; + $nres = scalar(@{$QC{$locus}{RES}}) if ($QC{$locus}{RES}); + + print OUT "\n"; + print OUT "\n"; + print OUT "\n"; + print OUT "\n"; + print OUT "\n"; #\n"; + print OUT2 join("\t", $locus, $QC{$locus}{QC}->[-1], @{$res}[@keyColsI]) . "\n"; + push @$excelAref, [$locus, $QC{$locus}{QC}->[-1], @{$res}[@keyColsI]]; + +# qw/QUAL Gene_Name Codon_Change Amino_Acid_change vaf DP AD Tag CHROM POS ID REF ALT Context Effect_Impact Functional_Class Amino_Acid_length Coding Transcript Exon/; + push @$excelAref2, [map {$_ || "NA"} @{$res}[map { $resCol{$_} } (qw/Gene_Name Exon_Rank Amino_Acid_change vaf Functional_Class/)], $QC{$locus}{QC}->[-1]]; +# push @$excelAref2, [map {$_ || "NA"} @{$res}[[qw/Gene_Name Exon_Rank Cdna_change Amino_Acid_change vaf Functional_Class/]], $QC{$locus}{QC}->[-1]]; + my $pl = $res->[$keyColsI[7]]; + my $ref = $res->[$keyColsI[11]]; + my $var = $res->[$keyColsI[12]]; +# print STDERR "$pl $ref $var\n"; sleep 1; + if (length($ref) == length($var)) { + $rescnt{$pl . "snp"}++; + } + else { + $rescnt{$pl . "indel"}++; + } +# $rescnt++; + } + print STDERR $locus . ":" . $nres . "\n"; + print STDERR $locus . ":" . join("-", @{$QC{$locus}{RES}}) . "\n"; + if (scalar(@{$QC{$locus}{RES}}) == 0) { #$nres == 0) { + print OUT2 join("\t", $locus, $QC{$locus}{QC}->[-1], ("-") x scalar(@keyColsI)) . "\n"; + push @$excelAref, [$locus, $QC{$locus}{QC}->[-1], ("-") x scalar(@keyColsI)]; + } + print OUT "\n"; +} +print OUT "
$_
$locuscc2b$QC{$locus}{QC}->[-1]"; + + foreach my $res (@{$QC{$locus}{RES}}) { + $res = [map {$_ || ""} @$res]; + print OUT "\n"; + print OUT join("\n", @{$res}[@keyColsI]); + print OUT "
\n"; +print OUT "\n"; +close OUT; +close OUT2; +$excel1->write_col(0,0, $excelAref); +$excel2->write_col(0,0, $excelAref2); +$excelBook->close(); +my @resCnt = map { $rescnt{$_} || 0 } qw/Falcosnp Falcoindel/; +my $pctGood = sprintf("%.2f", $amp100 / scalar(keys(%QC)) * 100); +#print INDEX "$sampleBAM$resCnt[0]$resCnt[1]$readCnt$pctGood\n"; +my $ntbsAmps = join(",", map { s/^(.*?)\.chr.*$/$1/; $_; } keys(%ntbGenes)); +push @{$excel0Ref}, [$sample, $runName, $readCnt, $pctGood, $ntbsAmps]; + +$excel0->write_col(0,0, $excel0Ref); +$excelBook0->close(); + +#print INDEX ""; +#print INDEX ""; +#print INDEX ""; +#print INDEX ""; +#print INDEX ""; +#close INDEX; + +