debian/changelog

-megan-ce (0.0+git20180524.24e70bf-1) UNRELEASED; urgency=medium
+megan-ce (0.0+git20180801.099e956-1) UNRELEASED; urgency=medium
 
   * Initial release (Closes: #<bug>)
+  TODO: Sort out issue with libsis-hdf5-java which is not (yet) ported to
+        hdf5 1.10
 
  -- Andreas Tille <tille@debian.org>  Fri, 19 May 2017 15:01:42 +0200

resources/files/interpro2go.info

-Sat Oct 24 08:42:50 CEST 2015
-Please also cite: Mitchell et al (2015) NAR 43 D213-D221. The Gene Ontology Consortium (2015) NAR 43 D1049-D1056.
-
+created: Fri Jun 22 10:41:30 CEST 2018
+Cite: Mitchell et al (2015) NAR 43 D213-221. The Gene Ontology Consortium (2015) NAR 43 D1049-1056.

resources/files/ncbi.info

-created: Thu Mar 22 13:23:29 SGT 2018
+created: Thu Jun 21 10:43:25 CEST 2018
 Cite: Benson et al (2005) NAR 33 D34–38.
\ No newline at end of file

src/megan/algorithms/ActiveMatches.java

@@ -47,7 +47,7 @@ public class ActiveMatches {
         for (int i = 0; i < readBlock.getNumberOfAvailableMatchBlocks(); i++) {
             final IMatchBlock matchBlock = readBlock.getMatchBlock(i);
             if (!matchBlock.isIgnore() && !TaxonomyData.isTaxonDisabled(matchBlock.getTaxonId()) && matchBlock.getBitScore() >= minScore && matchBlock.getExpected() <= maxExpected &&
-                    (minPercentIdentity == 0 || matchBlock.getPercentIdentity() >= minPercentIdentity)) {
+                    (matchBlock.getPercentIdentity() == 0 || matchBlock.getPercentIdentity() >= minPercentIdentity)) {
                 if (classificationName == null || matchBlock.getId(classificationName) > 0)
                     activeMatchesForClassification.set(i);
             }

src/megan/algorithms/AssignmentUsingIntervalUnionLCA.java

@@ -150,15 +150,15 @@ public class AssignmentUsingIntervalUnionLCA implements IAssignmentAlgorithm {
                             }
                         }
                         // determine the top-percent threshold on the current segment:
-                        float topPercenThreshold = 0;
+                        float topPercentThreshold = 0;
                         for (Float value : taxon2BestScore.values()) {
-                            topPercenThreshold = Math.max(topPercenThreshold, value);
+                            topPercentThreshold = Math.max(topPercentThreshold, value);
                         }
-                        topPercenThreshold = (100.0f - topPercent) / 100.0f * topPercenThreshold;
+                        topPercentThreshold = (100.0f - topPercent) / 100.0f * topPercentThreshold;
 
                         // add the segments for all taxa whose best match exceeds the threshold:
                         for (Integer taxonId : taxon2BestScore.keySet()) {
-                            if (taxon2BestScore.get(taxonId) >= topPercenThreshold) {
+                            if (taxon2BestScore.get(taxonId) >= topPercentThreshold) {
                                 IntervalList intervals = taxa2intervals.get(taxonId);
                                 if (intervals == null) {
                                     intervals = new IntervalList();

src/megan/algorithms/AssignmentUsingMultiGeneBestHit.java

@@ -31,8 +31,8 @@ import java.util.HashSet;
 import java.util.Set;
 
 /**
- * assignment using best hit
- * Created by huson on 1/22/16.
+ * assignment using multi-gene best hit
+ * Daniel Huson, 2017
  */
 public class AssignmentUsingMultiGeneBestHit implements IMultiAssignmentAlgorithm {
     private final IntervalTree<IMatchBlock> allMatches;

src/megan/algorithms/DataProcessor.java

@@ -67,7 +67,7 @@ public class DataProcessor {
             if (doc.isUseContaminantFilter() && doc.getDataTable().hasContaminants()) {
                 contaminantManager = new ContaminantManager();
                 contaminantManager.parseTaxonIdsString(doc.getDataTable().getContaminants());
-                System.err.println(String.format("Using contaminant filter for %,d taxa", contaminantManager.size()));
+                System.err.println(String.format("Using contaminants profile: %,d input, %,d total", contaminantManager.inputSize(), contaminantManager.size()));
             } else
                 contaminantManager = null;
 
@@ -94,16 +94,16 @@ public class DataProcessor {
 
             // step 0: set up classification algorithms
 
-            final double minCoveredPercent = doc.getMinPercentReadToCover();
+            final double minPercentReadToCover = doc.getMinPercentReadToCover();
             int numberOfReadsFailedCoveredThreshold = 0;
             final IntervalTree<Object> intervals;
-            if (minCoveredPercent > 0 && doc.isLongReads() || doc.getReadAssignmentMode() == Document.ReadAssignmentMode.alignedBases)
+            if (minPercentReadToCover > 0 && doc.isLongReads() || doc.getReadAssignmentMode() == Document.ReadAssignmentMode.alignedBases)
                 intervals = new IntervalTree<>();
             else
                 intervals = null;
 
-            if (minCoveredPercent > 0)
-                System.err.println(String.format("Minimum percentage of read to be covered: %.1f%%", minCoveredPercent));
+            if (minPercentReadToCover > 0)
+                System.err.println(String.format("Minimum percentage of read to be covered: %.1f%%", minPercentReadToCover));
 
             final boolean usingLongReadAlgorithm = (doc.getLcaAlgorithm() == Document.LCAAlgorithm.longReads);
 
@@ -195,7 +195,7 @@ public class DataProcessor {
                 final ReadBlockRMA6 mateReadBlock;
                 if (doMatePairs) {
                     try (RMA6File RMA6File = new RMA6File(doc.getMeganFile().getFileName(), "r")) {
-                        String[] matchClassificationNames = RMA6File.getHeaderSectionRMA6().getMatchClassNames();
+                        final String[] matchClassificationNames = RMA6File.getHeaderSectionRMA6().getMatchClassNames();
                         mateReadBlock = new ReadBlockRMA6(doc.getBlastMode(), true, matchClassificationNames);
                     }
                 } else
@@ -237,7 +237,7 @@ public class DataProcessor {
                         if (referenceCoverFilter != null)
                             referenceCoverFilter.applyFilter(readBlock, activeMatchesForTaxa);
 
-                        if (minCoveredPercent == 0 || ensureCovered(minCoveredPercent, readBlock, activeMatchesForTaxa, intervals)) {
+                        if (minPercentReadToCover == 0 || ensureCovered(minPercentReadToCover, readBlock, activeMatchesForTaxa, intervals)) {
                             if (doMatePairs && readBlock.getMateUId() > 0) {
                                 mateReader.seek(readBlock.getMateUId());
                                 mateReadBlock.read(mateReader, false, true, doc.getMinScore(), doc.getMaxExpected());
@@ -427,7 +427,7 @@ public class DataProcessor {
 
         for (int m = activeMatches.nextSetBit(0); m != -1; m = activeMatches.nextSetBit(m + 1)) {
             final IMatchBlock matchBlock = readBlock.getMatchBlock(m);
-            if (Math.abs(matchBlock.getAlignedQueryStart() - matchBlock.getAlignedQueryStart()) >= lengthToCover)
+            if (Math.abs(matchBlock.getAlignedQueryEnd() - matchBlock.getAlignedQueryStart()) >= lengthToCover)
                 return true;
             if (intervals != null) {
                 Interval<Object> interval = new Interval<>(matchBlock.getAlignedQueryStart(), matchBlock.getAlignedQueryEnd(), null);

src/megan/classification/commandtemplates/LoadMappingFileCommand.java

@@ -47,13 +47,13 @@ public class LoadMappingFileCommand extends CommandBase implements ICommand {
      */
     @Override
     public String getSyntax() {
-        return "load mapFile=<filename> mapType=<mapType> cName=<name> [parseTaxonNames={false|true}];";
+        return "load mapFile=<filename> mapType=<" + Basic.toString(IdMapper.MapType.values(), "|") + "> cName=<" + Basic.toString(ClassificationManager.getAllSupportedClassifications(), "|") + "> [parseTaxonNames={false|true}];";
     }
 
     /**
      * parses the given command and executes it
      *
-     * @param np
+     * @param npe
      * @throws java.io.IOException
      */
     @Override

src/megan/classification/data/ClassificationFullTree.java

@@ -24,7 +24,6 @@ import jloda.graph.NodeData;
 import jloda.graph.NodeSet;
 import jloda.phylo.PhyloTree;
 import jloda.util.Basic;
-import jloda.util.ProgramProperties;
 import jloda.util.ResourceManager;
 import megan.algorithms.LCAAddressing;
 import megan.classification.Classification;
@@ -122,7 +121,6 @@ public class ClassificationFullTree extends PhyloTree {
         }
         setInfo(getANode(IdMapper.LOW_COMPLEXITY_ID), IdMapper.LOW_COMPLEXITY_ID);
 
-        if (ProgramProperties.get("enable-contaminants", false)) {
             if (id2Node.get(IdMapper.CONTAMINANTS_ID) == null) {
                 Node v = newNode();
                 addId2Node(IdMapper.CONTAMINANTS_ID, v);
@@ -131,7 +129,6 @@ public class ClassificationFullTree extends PhyloTree {
                 newEdge(getRoot(), v);
             }
             setInfo(getANode(IdMapper.CONTAMINANTS_ID), IdMapper.CONTAMINANTS_ID);
-        }
 
         if (getName().equals(Classification.Taxonomy)) {
             // fix Domains:

src/megan/clusteranalysis/ClusterViewer.java

@@ -40,10 +40,8 @@ import jloda.util.ProgramProperties;
 import megan.classification.Classification;
 import megan.classification.ClassificationManager;
 import megan.clusteranalysis.gui.*;
-import megan.clusteranalysis.indices.CalculateEcologicalIndices;
-import megan.clusteranalysis.indices.JensenShannonDivergence;
-import megan.clusteranalysis.indices.PearsonDistance;
-import megan.clusteranalysis.indices.UniFrac;
+import megan.clusteranalysis.indices.BrayCurtisDissimilarity;
+import megan.clusteranalysis.indices.DistancesManager;
 import megan.clusteranalysis.tree.Distances;
 import megan.clusteranalysis.tree.Taxa;
 import megan.core.Director;
@@ -109,7 +107,7 @@ public class ClusterViewer extends JFrame implements IDirectableViewer, IViewerW
     private int numberOfNodesUsed = 0;
 
     private String dataType;
-    private String ecologicalIndex = CalculateEcologicalIndices.BRAYCURTIS;
+    private String ecologicalIndex = BrayCurtisDissimilarity.NAME;
 
     private boolean locked = false;
     private boolean uptodate = true;
@@ -506,17 +504,7 @@ public class ClusterViewer extends JFrame implements IDirectableViewer, IViewerW
             throw new IOException("Too few samples: " + taxa.size());
 
         distances = new Distances(taxa.size());
-
-        if (ecologicalIndex.equalsIgnoreCase(UniFrac.UnweightedTaxonomicUniFrac))
-            numberOfNodesUsed = UniFrac.apply(getParentViewer(), UniFrac.UnweightedTaxonomicUniFrac, 1, distances);
-        else if (ecologicalIndex.equalsIgnoreCase(UniFrac.WeightedTaxonomicUniFrac))
-            numberOfNodesUsed = UniFrac.apply(getParentViewer(), UniFrac.WeightedTaxonomicUniFrac, 1, distances);
-        else if (ecologicalIndex.equalsIgnoreCase(JensenShannonDivergence.SqrtJensenShannonDivergence))
-            numberOfNodesUsed = JensenShannonDivergence.apply(getParentViewer(), JensenShannonDivergence.SqrtJensenShannonDivergence, distances);
-        else if (ecologicalIndex.equalsIgnoreCase(PearsonDistance.PEARSON_DISTANCE))
-            numberOfNodesUsed = PearsonDistance.apply(doc, getParentViewer(), ecologicalIndex, distances);
-        else
-            numberOfNodesUsed = CalculateEcologicalIndices.apply(doc, getParentViewer(), ecologicalIndex, distances, !getEcologicalIndex().contains("Goodall"));
+        DistancesManager.apply(ecologicalIndex, getParentViewer(), distances);
 
         if (distances.replaceNaNByZero()) {
             NotificationsInSwing.showWarning(getFrame(), "Undefined distances detected, replaced by 0");

src/megan/clusteranalysis/GUIConfiguration.java

@@ -56,7 +56,7 @@ public class GUIConfiguration {
         menuConfig.defineMenu("Rotate", "Rotate Left;Rotate Right;Rotate Up;Rotate Down;");
         menuConfig.defineMenu("Expand/Contract", "Expand Horizontal;Contract Horizontal;Expand Vertical;Contract Vertical;");
 
-        menuConfig.defineMenu("Options", "Apply Triangulation Test...;|;PCoA Tab;UPGMA Tree Tab;NJ Tree Tab;Network Tab;Matrix Tab;|;Use JSD;Use Bray-Curtis;Use Euclidean;|;" + ProgramProperties.getIfEnabled("enable-unifrac", "Use Unweighted Uniform UniFrac;Use Weighted Uniform UniFrac;|;") + "Use Chi-Square;Use Kulczynski;Use Hellinger;|;Sync;");
+        menuConfig.defineMenu("Options", "Apply Triangulation Test...;|;PCoA Tab;UPGMA Tree Tab;NJ Tree Tab;Network Tab;Matrix Tab;|;Use JSD;Use Bray-Curtis;Use Euclidean;|;Use Unweighted Uniform UniFrac;Use Weighted Uniform UniFrac;|;Use Chi-Square;Use Kulczynski;Use Hellinger;Use Goodall;|;Sync;");
 
 
         menuConfig.defineMenu("PCoA", "PCoA Tab;|;PC1 vs PC2;PC1 vs PC3;PC2 vs PC3;PCi vs PCj...;|;PC1 PC2 PC3;PCi PCj PCk...;|;Show Axes;|;Show BiPlot;BiPlot Size...;|;Show TriPlot;TriPlot Size...;");

src/megan/clusteranalysis/commands/EcologicalIndexBrayCurtisCommand.java

@@ -21,7 +21,7 @@ package megan.clusteranalysis.commands;
 import jloda.gui.commands.ICheckBoxCommand;
 import jloda.util.parse.NexusStreamParser;
 import megan.clusteranalysis.ClusterViewer;
-import megan.clusteranalysis.indices.CalculateEcologicalIndices;
+import megan.clusteranalysis.indices.BrayCurtisDissimilarity;
 
 import javax.swing.*;
 import java.awt.event.ActionEvent;
@@ -38,7 +38,7 @@ public class EcologicalIndexBrayCurtisCommand extends CommandBase implements ICh
      */
     public boolean isSelected() {
         ClusterViewer viewer = getViewer();
-        return viewer.getEcologicalIndex().equalsIgnoreCase(CalculateEcologicalIndices.BRAYCURTIS);
+        return viewer.getEcologicalIndex().equalsIgnoreCase(BrayCurtisDissimilarity.NAME);
     }
 
     /**
@@ -56,7 +56,7 @@ public class EcologicalIndexBrayCurtisCommand extends CommandBase implements ICh
      * @return description
      */
     public String getDescription() {
-        return "Use Bray-Curtis ecological index";
+        return "Use Bray-Curtis ecological index (Bray and Curtis, 1957)";
     }
 
     /**
@@ -83,7 +83,7 @@ public class EcologicalIndexBrayCurtisCommand extends CommandBase implements ICh
      * @param ev
      */
     public void actionPerformed(ActionEvent ev) {
-        execute("set index=" + CalculateEcologicalIndices.BRAYCURTIS + ";");
+        execute("set index=" + BrayCurtisDissimilarity.NAME + ";");
     }
 
     /**

src/megan/clusteranalysis/commands/EcologicalIndexChiSquareCommand.java

@@ -21,7 +21,7 @@ package megan.clusteranalysis.commands;
 import jloda.gui.commands.ICheckBoxCommand;
 import jloda.util.parse.NexusStreamParser;
 import megan.clusteranalysis.ClusterViewer;
-import megan.clusteranalysis.indices.CalculateEcologicalIndices;
+import megan.clusteranalysis.indices.ChiSquareDistance;
 
 import javax.swing.*;
 import java.awt.event.ActionEvent;
@@ -38,7 +38,7 @@ public class EcologicalIndexChiSquareCommand extends CommandBase implements IChe
      */
     public boolean isSelected() {
         ClusterViewer viewer = getViewer();
-        return viewer.getEcologicalIndex().equalsIgnoreCase(CalculateEcologicalIndices.CHISSQUARE);
+        return viewer.getEcologicalIndex().equalsIgnoreCase(ChiSquareDistance.NAME);
     }
 
     /**
@@ -56,7 +56,7 @@ public class EcologicalIndexChiSquareCommand extends CommandBase implements IChe
      * @return description
      */
     public String getDescription() {
-        return "Use ChiSquare ecological index";
+        return "Use ChiSquare ecological index (Lebart et al, 1979)";
     }
 
     /**
@@ -83,7 +83,7 @@ public class EcologicalIndexChiSquareCommand extends CommandBase implements IChe
      * @param ev
      */
     public void actionPerformed(ActionEvent ev) {
-        execute("set index=" + CalculateEcologicalIndices.CHISSQUARE + ";");
+        execute("set index=" + ChiSquareDistance.NAME + ";");
     }
 
     /**

src/megan/clusteranalysis/commands/EcologicalIndexCommand.java

@@ -21,9 +21,7 @@ package megan.clusteranalysis.commands;
 import jloda.util.ProgramProperties;
 import jloda.util.parse.NexusStreamParser;
 import megan.clusteranalysis.ClusterViewer;
-import megan.clusteranalysis.indices.JensenShannonDivergence;
-import megan.clusteranalysis.indices.PearsonDistance;
-import megan.clusteranalysis.indices.UniFrac;
+import megan.clusteranalysis.indices.DistancesManager;
 
 import javax.swing.*;
 import java.awt.event.ActionEvent;
@@ -33,17 +31,6 @@ import java.awt.event.ActionEvent;
  * Daniel Huson, 6.2010
  */
 public abstract class EcologicalIndexCommand extends CommandBase {
-    private final String[] methods;
-
-    public EcologicalIndexCommand() {
-        if (ProgramProperties.get("enable-unifrac", false))
-            methods = new String[]{"Goodall", "Goodall-Normalized", "ChiSquare", "Kulczynski",
-                    "BrayCurtis", "Hellinger", "Euclidean", "Euclidean-Normalized", UniFrac.UnweightedTaxonomicUniFrac, UniFrac.WeightedTaxonomicUniFrac, PearsonDistance.PEARSON_DISTANCE, JensenShannonDivergence.SqrtJensenShannonDivergence};
-        else
-            methods = new String[]{"Goodall", "Goodall-Normalized", "ChiSquare", "Kulczynski",
-                    "BrayCurtis", "Hellinger", "Euclidean", "Euclidean-Normalized", PearsonDistance.PEARSON_DISTANCE, JensenShannonDivergence.SqrtJensenShannonDivergence};
-    }
-
     /**
      * parses the given command and executes it
      *
@@ -52,12 +39,12 @@ public abstract class EcologicalIndexCommand extends CommandBase {
      */
     public void apply(NexusStreamParser np) throws Exception {
         np.matchIgnoreCase("set index=");
-        String method = np.getWordMatchesIgnoringCase(methods);
+        String method = np.getWordMatchesIgnoringCase(DistancesManager.getAllNames());
         np.matchIgnoreCase(";");
 
         ClusterViewer viewer = getViewer();
         viewer.setEcologicalIndex(method);
-        execute("sync;");
+        executeImmediately("sync;");
     }
 
     /**
@@ -78,7 +65,7 @@ public abstract class EcologicalIndexCommand extends CommandBase {
         final ClusterViewer viewer = getViewer();
 
         final String method = (String) JOptionPane.showInputDialog(getViewer().getFrame(), "Set Ecological Index", "Set Ecological Index", JOptionPane.QUESTION_MESSAGE,
-                ProgramProperties.getProgramIcon(), methods, viewer.getEcologicalIndex());
+                ProgramProperties.getProgramIcon(), DistancesManager.getAllNames(), viewer.getEcologicalIndex());
         if (method != null)
             executeImmediately("set index=" + method + ";");
     }

src/megan/clusteranalysis/commands/EcologicalIndexEuclideanCommand.java

@@ -21,7 +21,7 @@ package megan.clusteranalysis.commands;
 import jloda.gui.commands.ICheckBoxCommand;
 import jloda.util.parse.NexusStreamParser;
 import megan.clusteranalysis.ClusterViewer;
-import megan.clusteranalysis.indices.CalculateEcologicalIndices;
+import megan.clusteranalysis.indices.EuclideanDistance;
 
 import javax.swing.*;
 import java.awt.event.ActionEvent;
@@ -38,7 +38,7 @@ public class EcologicalIndexEuclideanCommand extends CommandBase implements IChe
      */
     public boolean isSelected() {
         ClusterViewer viewer = getViewer();
-        return viewer.getEcologicalIndex().equalsIgnoreCase(CalculateEcologicalIndices.EUCLIDEAN);
+        return viewer.getEcologicalIndex().equalsIgnoreCase(EuclideanDistance.NAME);
     }
 
     /**
@@ -83,7 +83,7 @@ public class EcologicalIndexEuclideanCommand extends CommandBase implements IChe
      * @param ev
      */
     public void actionPerformed(ActionEvent ev) {
-        execute("set index=" + CalculateEcologicalIndices.EUCLIDEAN + ";");
+        execute("set index=" + EuclideanDistance.NAME + ";");
     }
 
     /**

src/megan/clusteranalysis/commands/EcologicalIndexGoodallCommand.java

@@ -21,7 +21,7 @@ package megan.clusteranalysis.commands;
 import jloda.gui.commands.ICheckBoxCommand;
 import jloda.util.parse.NexusStreamParser;
 import megan.clusteranalysis.ClusterViewer;
-import megan.clusteranalysis.indices.CalculateEcologicalIndices;
+import megan.clusteranalysis.indices.GoodallsDistance;
 
 import javax.swing.*;
 import java.awt.event.ActionEvent;
@@ -38,7 +38,7 @@ public class EcologicalIndexGoodallCommand extends CommandBase implements ICheck
      */
     public boolean isSelected() {
         ClusterViewer viewer = getViewer();
-        return viewer.getEcologicalIndex().equalsIgnoreCase(CalculateEcologicalIndices.GOODALL);
+        return viewer.getEcologicalIndex().equalsIgnoreCase(GoodallsDistance.NAME);
     }
 
     /**
@@ -56,7 +56,7 @@ public class EcologicalIndexGoodallCommand extends CommandBase implements ICheck
      * @return description
      */
     public String getDescription() {
-        return "Use Goodall's ecological index";
+        return "Use Goodall's ecological index (Goodall 1964, 1966)";
     }
 
     /**
@@ -83,7 +83,7 @@ public class EcologicalIndexGoodallCommand extends CommandBase implements ICheck
      * @param ev
      */
     public void actionPerformed(ActionEvent ev) {
-        execute("set index=" + CalculateEcologicalIndices.GOODALL + ";");
+        execute("set index=" + GoodallsDistance.NAME + ";");
     }
 
     /**