d0aad7f66c2fee0fa9366c3b3caf4d761750c055 braney Tue Aug 17 10:27:07 2021 -0700 first version of Gencode genes (knownGene version) for mm39 diff --git src/hg/utils/automation/doHgNearBlastp.pl src/hg/utils/automation/doHgNearBlastp.pl index 3234c87..c87c626 100755 --- src/hg/utils/automation/doHgNearBlastp.pl +++ src/hg/utils/automation/doHgNearBlastp.pl @@ -276,31 +276,31 @@ $blastPath/bin/formatdb -i $qFasta -t $qDb -n $qDb _EOF_ ; close($fh); &HgAutomate::run("chmod a+x $bossScript"); &HgAutomate::nfsNoodge("$bossScript"); &HgAutomate::run("$HgAutomate::runSSH $distrHost nice $bossScript"); } # formatSequence # Make a matrix of clade-pair -e (max E-value) threshold: my ($mammal, $fish, $fly, $worm, $yeast) = (0..5); my %dbToClade = ( hg => $mammal, mm => $mammal, rn => $mammal, tmpFoo => $mammal, danRer => $fish, dm => $fly, ce => $worm, - sacCer => $yeast, ); + sacCer => $yeast, knownGeneV => $mammal, knownGeneVM => $mammal, ); my @cladeEs; # Different species within clade (not self alignments -- see $selfE): $cladeEs[$mammal][$mammal] = $cladeEs[$fish][$fish] = $cladeEs[$fly][$fly] = $cladeEs[$worm][$worm] = $cladeEs[$yeast][$yeast] = 0.001; # Cross-clade: $cladeEs[$mammal][$fish] = $cladeEs[$fish][$mammal] = 0.005; $cladeEs[$mammal][$fly] = $cladeEs[$fly][$mammal] = 0.01; $cladeEs[$mammal][$worm] = $cladeEs[$worm][$mammal] = 0.01; $cladeEs[$mammal][$yeast] = $cladeEs[$yeast][$mammal] = 0.01; $cladeEs[$fish][$fly] = $cladeEs[$fly][$fish] = 0.01; $cladeEs[$fish][$worm] = $cladeEs[$worm][$fish] = 0.01; $cladeEs[$fish][$yeast] = $cladeEs[$yeast][$fish] = 0.01; $cladeEs[$fly][$worm] = $cladeEs[$worm][$fly] = 0.01; $cladeEs[$fly][$yeast] = $cladeEs[$yeast][$fly] = 0.01; $cladeEs[$worm][$yeast] = $cladeEs[$yeast][$worm] = 0.01; @@ -361,31 +361,32 @@ &HgAutomate::nfsNoodge("$bossScript"); &HgAutomate::run("$HgAutomate::runSSH $clusterHub $bossScript"); } # runPairwiseBlastp sub dbToPrefix { # Condense database name to a 2-character prefix for the *BlastTab table. my ($db) = @_; my $prefix; return $targetAbbrev if ($targetAbbrev && $db eq $tDb); if ($db =~ /^(\w\w)\d+$/) { $prefix = $1; } elsif ($db =~ /^(\w)\w\w(\w)\w\w\d+$/) { $prefix = $1 . lc($2); } else { - die "Error: dbToPrefix: expecting database name, got $db"; + # just use the whole db name + $prefix = $db; } return $prefix; } sub loadPairwise { my ($tDb, $qDb, $tablePrefix, $max, $filePattern) = @_; $filePattern = 'out/*.tab' if (! defined $filePattern); my $tableName = $tablePrefix . 'BlastTab'; my $bestOnly = ($max > 1) ? '-bestOnly' : ''; my $runDir = "$buildDir/run.$tDb.$qDb"; my $bossScript = "$buildDir/run.$tDb.$qDb/loadPairwise.csh"; my $fh = HgAutomate::mustOpen(">$bossScript"); print $fh <<_EOF_ #!/bin/csh -efx