iedb workflow

Main/lib/perl/WorkflowSteps/MakeEpitopeMappingNextflowConfig.pm

@@ -0,0 +1,56 @@
+package ApiCommonWorkflow::Main::WorkflowSteps::MakeEpitopeMappingNextflowConfig;
+
+@ISA = (ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep);
+
+use warnings;
+use strict;
+use ApiCommonWorkflow::Main::WorkflowSteps::WorkflowStep;
+
+
+sub run {
+    my ($self, $test, $undo) = @_;
+
+    my $workflowDataDir = $self->getWorkflowDataDir();
+    my $clusterWorkflowDataDir = $self->getClusterWorkflowDataDir();
+    my $results = join("/", $workflowDataDir, $self->getParamValue("clusterResultDir"));
+    my $refFasta = $self->getParamValue("refFasta");
+    my $peptidesTab = $self->getParamValue("peptidesTab");
+    my $peptideGeneFasta = $self->getParamValue("peptideGeneFasta");
+    my $taxon = $self->getParamValue("taxon");
+    my $peptideMatchResults = $self->getParamValue("peptideMatchResults");
+    my $peptidesFilteredBySpeciesFasta = $self->getParamValue("peptidesFilteredBySpeciesFasta");
+    my $peptideMatchBlastCombinedResults = $self->getParamValue("peptideMatchBlastCombinedResults");
+    my $chunkSize = $self->getParamValue("chunkSize");
+    my $configPath = join("/", $self->getWorkflowDataDir(), $self->getParamValue("configFileName"));
+
+
+   if ($undo) {
+    $self->runCmd(0,"rm -rf $configPath");
+  } else {  
+
+    open(F, ">", $configPath) or die "$! :Can't open config file '$configPath' for writing";
+ print F
+  " 
+ params {
+   refFasta = \"$refFasta\" 
+   peptidesTab = \"$peptidesTab\"
+   peptideGeneFasta = \"$peptideGeneFasta\"
+   taxon = $taxon
+   peptideMatchResults = \"$peptideMatchResults\"
+   peptidesFilteredBySpeciesFasta = \"$peptidesFilteredBySpeciesFasta\"
+   peptideMatchBlastCombinedResults = \"$peptideMatchBlastCombinedResults\"
+   chuckSize = $chunkSize
+   results = \"$results\"
+
+   }
+
+    singularity {
+    enabled = true
+    autoMounts = true
+   }
+  "
+
+  }
+
+}
+1;

Main/lib/xml/workflow/componentGlobalGraph.xml

@@ -72,4 +72,16 @@
   </subgraph>
 
 
+  <!-- TODO:  Replace this with call to new subgraph which will call loadDataset.xml AND mirror tab+protinFasta to cluster -->
+  <subgraph name="component_epitope_IEDB_RSRC" xmlFile="loadDataset.xml">
+    <paramValue name="datasetName">component_epitope_IEDB_RSRC</paramValue>
+    <paramValue name="datasetLoaderXmlFileName">$$globalDatasetLoaderXmlFile$$</paramValue>
+    <paramValue name="parentDataDir"/>
+    <paramValue name="gusConfigFile">$$gusConfigFile$$</paramValue>
+    <depends name="initUserGroupProject"/>
+  </subgraph>
+
+
+
+
 </workflowGraph>

Main/lib/xml/workflow/mapEpitopeNextflow.xml

@@ -0,0 +1,69 @@
+<sworkflowGraph name="">
+   <param name="parentDataDir"/>
+   <param name="name"/>
+   <param name="refFasta"/>
+   <param name="peptideGeneFasta"/>
+   <param name="taxon"/>
+
+   <constant name="dataDir">$$parentDataDir$$/$$$$</constant>
+   <constant name="analysisConfig">$$parentDataDir$$/$$$$/final/analysisConfig.xml</constant>
+
+
+   <subgraph name="loadDataset" xml="loadDataset.xml">
+      <paramValue name="datasetName">$$$$</paramValue> <!-- should be conponent name -->
+      <paramValue name="datasetLoaderXmlFileName">$$$$</paramValue>
+   <paramValue name="parentDataDir">$$parentDataDir$$</paramValue>
+
+   </subgraph>
+
+
+   <step name="mirrorToClusterData" stepClass="ReFlow::StepClasses::MirrorToComputeCluster" stepLoadTypes="toCluster">
+        <paramValue name="fileOrDirToMirror">$$parentDataDir$$/$$$$</paramValue>
+        <depends name="loadDataset"/>
+   </step>
+
+
+   <step name="makeSamplesOutputDir" stepClass="ReFlow::StepClasses::MakeDataDir">
+      <paramValue name="dataDir">$$dataDir$$</paramValue>
+      <depends name="loadDataset"/>
+   </step>
+
+   <step name="epitopeNextflowConfig" stepClass="ApiCommonWorkflow::Main::WorkflowSteps::MakeEpitopeMappingNextflowConfig">
+      <paramValue name="analysisDir">$$parentDataDir$$</paramValue>
+      <paramValue name="refFasta">$$parentDataDir$$</paramValue>
+      <paramValue name="peptidesTab">$$parentDataDir$$/peptidesTab</paramValue>
+      <paramValue name="peptideGeneFasta">$$parentDataDir$$</paramValue>
+      <paramValue name="taxon">$$$$</paramValue>
+      <paramValue name="peptideMatchResults">PeptideMatches.txt</paramValue>
+      <paramValue name="peptidesFilteredBySpeciesFasta">PeptidesFilteredBySpecies.fasta</paramValue>
+      <paramValue name="peptideMatchBlastCombinedResults">peptideMatchBlastCombinedResults.txt</paramValue>
+      <paramValue name="results">$$DataDir$$/results</paramValue>
+      <paramValue name="chunkSize">500</paramValue>
+      <paramValue name="configFileName">$$parentDataDir$$/$$$$/nextflow.config</paramValue>
+
+   </step>
+
+
+   <step name="mirrorToCluster" stepClass="ReFlow::StepClasses::MirrorToComputeCluster" stepLoadTypes="toCluster">
+	<paramValue name="fileOrDirToMirror">$$dataDir$$</paramValue>
+      	<depends name="epitopeNextflowConfig"/>
+   </step>
+
+   <step name="runEpitopeMapping" stepClass="ReFlow::StepClasses::RunAndMonitorNextflow">
+     	<paramValue name="workingDir">$$dataDir$$</paramValue>
+      	<paramValue name="resultsDir">$$dataDir$$/results</paramValue>
+      	<paramValue name="nextflowConfigFile">$$dataDir$$/nextflow.config</paramValue>
+      	<paramValue name="nextflowWorkflow">VEuPathDB/iedb-epitope-mapping-nextflow</paramValue>
+      	<paramValue name="isGitRepo">true</paramValue>
+      	<depends name="mirrorToCluster"/>
+   </step>
+
+   <step name="mirrorFromCluster" stepClass="ReFlow::StepClasses::MirrorFromComputeCluster" stepLoadTypes="fromCluster">
+    	<paramValue name="fileOrDirToMirror">$$dataDir$$/results</paramValue>
+   	<paramValue name="outputDir">$$dataDir$$/results</paramValue>
+    	<paramValue name="outputFiles">TODO</paramValue>
+    	<paramValue name="deleteAfterCopy">false</paramValue>
+    	<depends name="runEpitopeMapping"/>
+   </step> 
+
+</workflowGraph>

Main/lib/xml/workflowTemplates/project.xml

@@ -683,4 +683,19 @@ ec
     </subgraph>
   </datasetTemplate>
 -->
+    <datasetTemplate class="EpitopeMappingNextflow">
+       <prop name="organismAbbrev"/>
+       <prop name="name"/>
+       <prop name="version"/>
+
+       <subgraph name="${name}_${organismAbbrev}_epitope_sequences_IEDB" xml="mapEpitopeNextflow.xml">
+         <paramValue name="organismAbbrev">${organismAbbrev}</paramValue>
+         <paramValue name="name">EpitopeMapping</paramValue>
+         <paramValue name="version"></paramValue>
+
+       </subgraph>
+
+   </datasetTemplate>
+
+
 </workflowGraph>