VEuPathDB · jbrestel · Apr 5, 2026 · Apr 14, 2026 · Apr 14, 2026 · Apr 14, 2026
diff --git a/Main/bin/runGeneCNVAndPloidyQuery b/Main/bin/runGeneCNVAndPloidyQuery
@@ -7,45 +7,33 @@ use GUS::ObjRelP::DbiDatabase;
 use GUS::Supported::GusConfig;
 use CBIL::Util::PropertySet;
 
-my ($gusConfigFile,$organismAbbrev,$geneSourceIdOrthologFile,$chrsForCalcsFile);
-&GetOptions("organismAbbrev=s" => \$organismAbbrev,
+my ($gusConfigFile,$taxonId,$orthoGroupFile,$geneSourceIdOrthologFile,$chrsForCalcsFile);
+&GetOptions("taxonId=s" => \$taxonId,
+            "orthoGroupFile=s" => \$orthoGroupFile,
             "geneSourceIdOrthologFile=s" => \$geneSourceIdOrthologFile,
+            "gusConfigFile=s" => \$gusConfigFile,
             "chrsForCalcsFile=s" => \$chrsForCalcsFile);
-my $ploidy = 2;
-
-my $geneSourceSql = "with sequence as (
-                select gf.source_id as gene_source_id
-                , gf.na_feature_id
-                , ns.source_id as contig_source_id
-                , ns.source_id as sequence_source_id
-                , ns.TAXON_ID
-                from dots.genefeature gf
-                , DOTS.NASEQUENCE ns
-                , SRES.ONTOLOGYTERM ot
-                where gf.na_sequence_id = ns.na_sequence_id
-                and ot.name = 'chromosome'
-                and ns.SEQUENCE_ONTOLOGY_ID = ot.ONTOLOGY_TERM_ID
-                and ns.taxon_id = (select taxon_id from apidb.organism where abbrev = '$organismAbbrev')
-            ), orthologs as (
-                select gf.na_feature_id, sg.name
-                from dots.genefeature gf
-                , dots.SequenceSequenceGroup ssg
-                , dots.SequenceGroup sg
-                , core.TableInfo ti
-                where gf.na_feature_id = ssg.sequence_id
-                and ssg.sequence_group_id = sg.sequence_group_id
-                and ssg.source_table_id = ti.table_id
-                and ti.name = 'GeneFeature'
-            )
-            select s.gene_source_id
-            , o.name
-            from sequence s
-            , orthologs o
-            where s.na_feature_id = o.na_feature_id";
-
-my $chrsForCalcsSql = "select ns.source_id from dots.nasequence ns, sres.ontologyterm ot where ot.name = 'chromosome' and ot.ontology_term_id = ns.sequence_ontology_id and ns.taxon_id = (select taxon_id from apidb.organism where abbrev = '$organismAbbrev')";
-
-$gusConfigFile = $ENV{GUS_HOME}."/config/gus.config";
+
+my $proteinToGeneSql = "
+SELECT aas.source_id AS protein_source_id,
+       gf.source_id  AS gene_source_id
+FROM dots.AASequence aas
+JOIN dots.TranslatedAASequence tas ON aas.aa_sequence_id = tas.aa_sequence_id
+JOIN dots.TranslatedAAFeature taf ON taf.aa_sequence_id = tas.aa_sequence_id
+JOIN dots.Transcript t ON taf.na_feature_id = t.na_feature_id
+JOIN dots.GeneFeature gf ON t.parent_id = gf.na_feature_id
+WHERE aas.subclass_view = 'TranslatedAASequence'
+  AND aas.taxon_id = $taxonId
+  AND aas.taxon_id IN (
+      SELECT taxon_id
+      FROM apidb.organism
+      WHERE is_annotated_genome = 1
+  )
+";
+
+my $chrsForCalcsSql = "select ns.source_id from dots.nasequence ns, sres.ontologyterm ot where ot.name = 'chromosome' and ot.ontology_term_id = ns.sequence_ontology_id and ns.taxon_id = $taxonId";
+
+#$gusConfigFile = $ENV{GUS_HOME}."/config/gus.config";
 die "Config file $gusConfigFile does not exist" unless -e $gusConfigFile;
 
 my @properties = ();
@@ -59,19 +47,50 @@ my $db = GUS::ObjRelP::DbiDatabase-> new($gusConfig->{props}->{dbiDsn},
 
 my $dbh = $db->getQueryHandle();
 
-my $orthoMclStmt = $dbh->prepare($geneSourceSql);
-$orthoMclStmt->execute();
+my $proteinToGeneStmt = $dbh->prepare($proteinToGeneSql);
+$proteinToGeneStmt->execute();
+
+my %proteinToGene;
+while (my @row = $proteinToGeneStmt->fetchrow_array()){
+    $proteinToGene{$row[0]} = $row[1];
+}
 
-open(GENE,">$geneSourceIdOrthologFile");
-while (my @row = $orthoMclStmt->fetchrow_array()){
-    print GENE "$row[0]\t$row[1]\n";
+my %proteinToGroup;
+open(GROUPS, "<$orthoGroupFile") or die "Cannot open $orthoGroupFile: $!";
+while (my $line = <GROUPS>) {
+    chomp $line;
+    my ($groupId, $proteinList) = split(/:\s*/, $line, 2);
+    next unless defined $proteinList;
+    foreach my $protein (split(/\s+/, $proteinList)) {
+        $proteinToGroup{$protein} = $groupId;
+    }
+}
+close GROUPS;
+
+my @proteinsWithNoGroup;
+open(GENE, ">$geneSourceIdOrthologFile") or die "Cannot open $geneSourceIdOrthologFile: $!";
+while (my ($protein, $gene) = each %proteinToGene) {
+    my $group = $proteinToGroup{$protein};
+    unless ($group) {
+        (my $altProtein = $protein) =~ s/:/\_/g;
+        $group = $proteinToGroup{$altProtein};
+    }
+    if ($group) {
+        print GENE "$gene\t$group\n";
+    } else {
+        push @proteinsWithNoGroup, $protein;
+    }
 }
 close GENE;
 
+if (@proteinsWithNoGroup) {
+    print STDERR "The following proteins have no group assignment in $orthoGroupFile:\n" . join("\n", @proteinsWithNoGroup) . "\n";
+}
+
 my $chrsForCalcs = $dbh->prepare($chrsForCalcsSql);
 $chrsForCalcs->execute();
 
-open(CHRS,">$chrsForCalcsFile");
+open(CHRS, ">$chrsForCalcsFile") or die "Cannot open $chrsForCalcsFile: $!";
 while (my @row = $chrsForCalcs->fetchrow_array()){
     print CHRS "$row[0]\t\n";
 }

diff --git a/Main/lib/perl/WorkflowSteps/CopyDnaseqBigwigToWebSvc.pm b/Main/lib/perl/WorkflowSteps/CopyDnaseqBigwigToWebSvc.pm
@@ -0,0 +1,49 @@
+package ApiCommonWorkflow::Main::WorkflowSteps::CopyDnaseqBigwigToWebSvc;
+
+@ISA = (ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep);
+use strict;
+use warnings;
+use ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep;
+use ApiCommonWorkflow::Main::Util::OrganismInfo;
+
+sub run {
+    my ($self, $test, $undo) = @_;
+
+    my $copyFromDir = $self->getParamValue('copyFromDir');
+    my $organismAbbrev = $self->getParamValue('organismAbbrev');
+    my $relativeDir = $self->getParamValue('relativeDir');
+    my $experimentDatasetName = $self->getParamValue('experimentDatasetName');
+    my $gusConfigFile = $self->getParamValue('gusConfigFile');
+
+    my $workflowDataDir = $self->getWorkflowDataDir();
+    $gusConfigFile = "$workflowDataDir/$gusConfigFile";
+    my $websiteFilesDir = $self->getWebsiteFilesDir($test);
+
+    my $organismNameForFiles =
+        $self->getOrganismInfo($test, $organismAbbrev, $gusConfigFile)->getNameForFiles();
+
+    my $experimentCopyToDir = "$websiteFilesDir/$relativeDir/$organismNameForFiles/dnaseq/bigwig/$experimentDatasetName";
+    my $sourceDir = "$workflowDataDir/$copyFromDir";
+
+    $self->testInputFile('copyFromDir', $sourceDir);
+
+    if ($undo) {
+        $self->runCmd(0, "rm -rf $experimentCopyToDir");
+    } else {
+        $self->runCmd($test, "mkdir -p $experimentCopyToDir");
+
+        opendir(my $dh, $sourceDir) or die "Cannot open results directory '$sourceDir': $!";
+        my @samples = grep { !/^\./ && -d "$sourceDir/$_" } readdir($dh);
+        closedir($dh);
+
+        die "No sample subdirectories found in '$sourceDir'" unless @samples;
+
+        foreach my $sample (@samples) {
+            my $sampleCopyToDir = "$experimentCopyToDir/$sample";
+            $self->runCmd($test, "mkdir -p $sampleCopyToDir");
+            $self->runCmd($test, "cp $sourceDir/$sample/*.bw $sampleCopyToDir/");
+        }
+    }
+}
+
+1;
diff --git a/Main/lib/perl/WorkflowSteps/MakeDnaSeqLoadNextflowConfig.pm b/Main/lib/perl/WorkflowSteps/MakeDnaSeqLoadNextflowConfig.pm
@@ -0,0 +1,39 @@
+package ApiCommonWorkflow::Main::WorkflowSteps::MakeDnaSeqLoadNextflowConfig;
+
+@ISA = (ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep);
+
+use strict;
+use warnings;
+use ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep;
+
+sub run {
+    my ($self, $test, $undo) = @_;
+
+    my $indelDir          = $self->getParamValue("indelDir");
+    my $extDbRlsSpec      = $self->getParamValue("extDbRlsSpec");
+    my $genomeExtDbRlsSpec = $self->getParamValue("genomeExtDbRlsSpec");
+
+    my $configPath = $self->getWorkflowDataDir() . "/" . $self->getParamValue("nextflowConfigFile");
+
+    if ($undo) {
+        $self->runCmd(0, "rm -rf $configPath");
+    } else {
+        open(F, ">", $configPath) or die "$! :Can't open config file '$configPath' for writing";
+        print F
+"
+params {
+  indelDir          = \"$indelDir\"
+  extDbRlsSpec      = '\"$extDbRlsSpec\"'
+  genomeExtDbRlsSpec = '\"$genomeExtDbRlsSpec\"'
+}
+
+singularity {
+  enabled    = true
+  autoMounts = true
+}
+";
+        close(F);
+    }
+}
+
+1;
diff --git a/Main/lib/perl/WorkflowSteps/MakeDnaSeqNextflowConfig.pm b/Main/lib/perl/WorkflowSteps/MakeDnaSeqNextflowConfig.pm
@@ -0,0 +1,135 @@
+package ApiCommonWorkflow::Main::WorkflowSteps::MakeDnaSeqNextflowConfig;
+
+@ISA = (ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep);
+
+use strict;
+use warnings;
+use ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep;
+
+sub run {
+    my ($self, $test, $undo) = @_;
+
+    my $workingDirRelativePath = $self->getParamValue("workingDirRelativePath");
+
+    my $sampleSheetFile        = $self->getParamValue("sampleSheetFile");
+    my $genomeFile             = $self->getParamValue("genomeFile");
+    my $gtfFile                = $self->getParamValue("gtfFile");
+    my $footprintFile          = $self->getParamValue("footprintFile");
+    my $ploidy                 = $self->getParamValue("ploidy");
+    my $resultsDirectory       = $self->getParamValue("resultsDirectory");
+    my $geneSourceIdOrthologFile = $self->getParamValue("geneSourceIdOrthologFile");
+    my $chrsForCalcFile        = $self->getParamValue("chrsForCalcFile");
+
+    my $nextflowConfigFile = $self->getWorkflowDataDir() . "/" . $self->getParamValue("nextflowConfigFile");
+
+    # Translate local paths to cluster-side paths
+    my $digestedSampleSheet      = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $sampleSheetFile);
+    my $digestedGenomeFile       = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $genomeFile);
+    my $digestedGtfFile          = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $gtfFile);
+    my $digestedFootprintFile    = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $footprintFile);
+    my $digestedResultsDir       = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $resultsDirectory);
+    my $digestedOrthologFile     = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $geneSourceIdOrthologFile);
+    my $digestedChrsForCalcFile  = $self->relativePathToNextflowClusterPath($workingDirRelativePath, $chrsForCalcFile);
+
+    # Workflow config values
+    my $minCoverage             = $self->getConfig("minCoverage");
+    my $winLen                  = $self->getConfig("winLen");
+    my $bwaThreads              = $self->getConfig("bwaThreads");
+
+    my $executor        = $self->getClusterExecutor();
+    my $queue           = $self->getClusterQueue();
+    my $maxMemoryGigs   = eval { $self->getParamValue("maxMemoryGigs") };
+    my $genomeFastaFile = $self->getWorkflowDataDir() . "/" . eval { $self->getParamValue("genomeFastaFile") };
+
+    my $isLsf = lc($executor) eq 'lsf';
+
+    # Dynamic bwaMem memory: (genome_Gb * 3.3) + 2 GB, rounded up to next power of 2 for safety
+    my $bwaDefaultMemMb = 4 * 1024;  # fallback: 4 GB
+    if (defined($genomeFastaFile)) {
+        my $genomeSize = 0;
+        open(my $fh, "<", $genomeFastaFile) or die "Cannot open genome fasta '$genomeFastaFile': $!";
+        while (<$fh>) {
+            next if /^>/;
+            chomp;
+            $genomeSize += length($_);
+        }
+        close($fh);
+        my $genomeGb  = $genomeSize / 1_000_000_000;
+        my $rawGb     = ($genomeGb * 3.3) + 2;
+        my $safeGb    = $rawGb * 1.25;
+        my $memGb     = 1;
+        $memGb       *= 2 while $memGb < $safeGb;
+        $bwaDefaultMemMb = $memGb * 1024;
+    }
+    my $bwaRetryMemMb = $bwaDefaultMemMb * 2;
+
+    # runFreebayes process block
+    my $freebayesBlock = "  withName: 'runFreebayes' {\n";
+    $freebayesBlock   .= "    maxRetries = 1\n";
+    $freebayesBlock   .= "    errorStrategy = { task.exitStatus in 130..140 ? 'retry' : 'finish' }\n";
+    if ($isLsf) {
+        $freebayesBlock .= "    clusterOptions = {\n";
+        $freebayesBlock .= "      (task.attempt > 1 && task.exitStatus in 130..140)\n";
+        $freebayesBlock .= "        ? '-M 12000 -R \"rusage [mem=12000] span[hosts=1]\"'\n";
+        $freebayesBlock .= "        : '-M 4000 -R \"rusage [mem=4000] span[hosts=1]\"'\n";
+        $freebayesBlock .= "    }\n";
+    }
+    $freebayesBlock   .= "  }\n";
+
+    # bwaMem process block
+    my $bwaRetries = defined($maxMemoryGigs) ? 0 : 1;
+    my $bwaBlock   = "  withName: 'bwaMem' {\n";
+    $bwaBlock     .= "    maxRetries = $bwaRetries\n";
+    if (!defined($maxMemoryGigs)) {
+        $bwaBlock .= "    errorStrategy = { task.exitStatus in 130..140 ? 'retry' : 'finish' }\n";
+    }
+    if ($isLsf) {
+        if (defined($maxMemoryGigs)) {
+            my $memMb = int($maxMemoryGigs * 1024);
+            $bwaBlock .= "    clusterOptions = '-M $memMb -R \"rusage [mem=$memMb] span[hosts=1]\"'\n";
+        } else {
+            $bwaBlock .= "    clusterOptions = {\n";
+            $bwaBlock .= "      (task.attempt > 1 && task.exitStatus in 130..140)\n";
+            $bwaBlock .= "        ? '-M $bwaRetryMemMb -R \"rusage [mem=$bwaRetryMemMb] span[hosts=1]\"'\n";
+            $bwaBlock .= "        : '-M $bwaDefaultMemMb -R \"rusage [mem=$bwaDefaultMemMb] span[hosts=1]\"'\n";
+            $bwaBlock .= "    }\n";
+        }
+    }
+    $bwaBlock .= "  }\n";
+
+    if ($undo) {
+        $self->runCmd(0, "rm -rf $nextflowConfigFile");
+    } else {
+        open(F, ">", $nextflowConfigFile) or die "$! :Can't open config file '$nextflowConfigFile' for writing";
+        print F "
+params {
+  samplesheet              = \"$digestedSampleSheet\"
+  bwaThreads               = $bwaThreads
+  minCoverage              = $minCoverage
+  genomeFastaFile          = \"$digestedGenomeFile\"
+  gtfFile                  = \"$digestedGtfFile\"
+  footprintFile            = \"$digestedFootprintFile\"
+  winLen                   = $winLen
+  ploidy                   = $ploidy
+  outputDir                = \"$digestedResultsDir\"
+  geneSourceIdOrthologFile = \"$digestedOrthologFile\"
+  chrsForCalcFile          = \"$digestedChrsForCalcFile\"
+}
+
+process {
+  executor = '$executor'
+  queue    = '$queue'
+$freebayesBlock
+$bwaBlock
+}
+
+singularity {
+  enabled    = true
+  autoMounts = true
+}
+";
+        close(F);
+    }
+}
+
+1;
diff --git a/Main/lib/perl/WorkflowSteps/MakeDnaSeqSingleExperimentNextflowConfig.pm b/Main/lib/perl/WorkflowSteps/MakeDnaSeqSingleExperimentNextflowConfig.pm
@@ -35,10 +35,8 @@ sub run {
   my $varscanPValue = $self->getConfig("varscanPValue");
   my $varscanMinVarFreqSnp = $self->getConfig("varscanMinVarFreqSnp");
   my $varscanMinVarFreqCons = $self->getConfig("varscanMinVarFreqCons");
-  my $maxNumberOfReads = $self->getConfig("maxNumberOfReads");
   my $hisat2Index = $self->getConfig("hisat2Index");
   my $createIndex = $self->getConfig("createIndex");
-  my $trimmomaticAdaptorsFile = $self->getConfig("trimmomaticAdaptorsFile");  
   my $ebiFtpUser = $self->getConfig("ebiFtpUser");  
   my $ebiFtpPassword = $self->getConfig("ebiFtpPassword");  
 
@@ -93,11 +91,9 @@ params {
   hisat2Index = $hisat2Index
   createIndex = $createIndex
   outputDir = \"$clusterResultDir\"
-  trimmomaticAdaptorsFile = $trimmomaticAdaptorsFile
   varscanPValue = $varscanPValue
   varscanMinVarFreqSnp = $varscanMinVarFreqSnp
   varscanMinVarFreqCons = $varscanMinVarFreqCons
-  maxNumberOfReads = $maxNumberOfReads
   taxonId = \"$taxonId\"
   geneSourceIdOrthologFile = \"$geneSourceIdOrthologFile\"
   chrsForCalcFile = \"$chrsForCalcFile\"

diff --git a/Main/lib/perl/WorkflowSteps/MakeGtfForGuidedCufflinks.pm b/Main/lib/perl/WorkflowSteps/MakeGtfForGuidedCufflinks.pm
@@ -20,7 +20,7 @@ sub run {
     my $project = $self->getParamValue("project");
     my $genomeExtDbRlsSpec = $self->getParamValue("genomeExtDbRlsSpec");
     my $cdsOnly = $self->getBooleanParamValue("cdsOnly");
-my $gusConfigFile = $self->getGusConfigFile();
+    my $gusConfigFile = $self->getWorkflowDataDir() . "/" . $self->getParamValue('gusConfigFile');
 
     my $cmd = "makeGtf.pl --outputFile $workflowDataDir/$gtfDir/$outputFile --project $project --genomeExtDbRlsSpec '$genomeExtDbRlsSpec'  --gusConfigFile $gusConfigFile";