Draft: Add WGS read reconstruction for ROI

src/main/java/nl/wur/bif/pantools/analysis/region_analysis/ExtractFunctionsCLI.java

@@ -2,14 +2,18 @@ package nl.wur.bif.pantools.analysis.region_analysis;
 
 import nl.wur.bif.pantools.Pantools;
 import nl.wur.bif.pantools.utils.BeanUtils;
+import nl.wur.bif.pantools.utils.FileUtils;
+import nl.wur.bif.pantools.utils.Globals;
 import nl.wur.bif.pantools.utils.GraphUtils;
 import nl.wur.bif.pantools.utils.cli.mixins.SelectGenomes;
+import nl.wur.bif.pantools.utils.cli.mixins.ThreadNumber;
 import nl.wur.bif.pantools.utils.cli.validation.Constraints.OutputDirectory;
 import picocli.CommandLine.*;
 
 import java.nio.file.Path;
 import java.util.concurrent.Callable;
 
+import static nl.wur.bif.pantools.utils.Globals.THREADS;
 import static nl.wur.bif.pantools.utils.Globals.setGenomeSelectionOptions;
 
 /**
@@ -20,6 +24,7 @@ import static nl.wur.bif.pantools.utils.Globals.setGenomeSelectionOptions;
 @OutputDirectory(directory = "outputPath")
 public class ExtractFunctionsCLI implements Callable<Integer> {
     @Spec Model.CommandSpec spec;
+    @Mixin private ThreadNumber threadNumber;
     @ArgGroup private SelectGenomes selectGenomes;
 
     @ParentCommand
@@ -75,6 +80,19 @@ public class ExtractFunctionsCLI implements Callable<Integer> {
     )
     private boolean writeRepeats;
 
+    @Option(names = {"--reads-file"},
+            description = "Tab-delimited file with library names and corresponding read files. Default: none"
+    )
+    private Path readsFile;
+
+    @Option(names = {"--filter-high-frequency"},
+            defaultValue = "true",
+            negatable = true,
+            fallbackValue = "true",
+            description = "Filter out high-frequency k-mers for read reconstruction. Default: true"
+    )
+    private boolean filterHighFrequency;
+
     //TODO: add --write-blast option to visualize BLASTP and BLASTN results
 
     private String[] functions;
@@ -103,20 +121,21 @@ public class ExtractFunctionsCLI implements Callable<Integer> {
             GraphUtils.validateRepeats(); // check that repeats are present
         }
 
-        // determine whether to use the fast option
-        boolean fast = !writeGfa && !writeUnitigs;
+        // always use fast option, except when writing GFA or unitigs, or using read files
+        boolean fast = !writeGfa && !writeUnitigs && readsFile == null;
         if (!fast) {
             Pantools.logger.warn("Using a slow method for extraction.");
         }
 
         final RegionExtractor regionExtractor = new RegionExtractor(outputPath);
-        regionExtractor.extractFunctions(functions, flanking, writeAnnotations, writeGfa, writeHomology, writeUnitigs, writeRepeats, fast);
+        regionExtractor.extractFunctions(functions, flanking, writeAnnotations, writeGfa, writeHomology, writeUnitigs, writeRepeats, FileUtils.parseReadsFile(readsFile), filterHighFrequency, fast);
 
         return 0;
     }
 
     private void setGlobalParameters() {
         setGenomeSelectionOptions(selectGenomes);
+        THREADS = threadNumber.getnThreads();
     }
 
     private void crossValidate() {
@@ -126,6 +145,11 @@ public class ExtractFunctionsCLI implements Callable<Integer> {
                 throw new ParameterException(spec.commandLine(), "Functions must be GO, InterPro, Pfam or TIGRFAM");
             }
         }
+
+        // Assert that K is smaller than 64 when using reads (because of storing 2bit version of k-mers in long)
+        if (readsFile != null && Globals.K_SIZE > 63) {
+            throw new ParameterException(spec.commandLine(), "K should be smaller than 63 when using reads");
+        }
     }
 
     public Pantools getPantools() {