X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fmsa%2FMsaMethods.java;h=2b470203d611294f1de19114e5226e0102d17208;hb=0b49b8e750b34d28a5989facdd8a7959870de996;hp=edca9b7cd9ebf9985280f815d821d32a6cd236b0;hpb=6b3ec0cd978bd692dfae1de3e076963283fdf322;p=jalview.git

diff --git a/forester/java/src/org/forester/msa/MsaMethods.java b/forester/java/src/org/forester/msa/MsaMethods.java
index edca9b7..2b47020 100644
--- a/forester/java/src/org/forester/msa/MsaMethods.java
+++ b/forester/java/src/org/forester/msa/MsaMethods.java
@@ -107,6 +107,43 @@ public final class MsaMethods {
         _ignored_seqs_ids = new ArrayList<String>();
     }
 
+    public static final DescriptiveStatistics calcNumberOfGapsStats( final Msa msa ) {
+        final int[] gaps = calcNumberOfGapsInMsa( msa );
+        final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
+        for( final int gap : gaps ) {
+            stats.addValue(  gap );
+        }
+        return stats;
+    }
+
+    public static final int[] calcNumberOfGapsInMsa( final Msa msa ) {
+        final int seqs = msa.getNumberOfSequences();
+        final int[]  gaps= new int[ seqs ];
+        for( int i = 0; i < seqs; ++i ) {
+            gaps[ i ] =  calcNumberOfGaps( msa.getSequence( i ) );
+        }
+        return gaps;
+    }
+    
+    
+
+    public final static int calcNumberOfGaps( final MolecularSequence seq  ) {
+        int gaps = 0;
+        boolean was_gap = false;
+        for( int i = 0; i < seq.getLength(); ++i ) {
+            if ( seq.isGapAt( i ) ) {
+               if ( !was_gap ) {
+                   ++gaps;
+                   was_gap = true;
+               }
+            }
+            else {
+                was_gap = false;
+            }
+        }
+        return gaps;
+    }
+
     public static DescriptiveStatistics calcBasicGapinessStatistics( final Msa msa ) {
         final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
         for( int i = 0; i < msa.getLength(); ++i ) {
@@ -324,8 +361,8 @@ public final class MsaMethods {
 
     final private static HashMap<Character, Integer> calcResidueDistribution6( final Msa msa, final int col ) {
         // Residues are classified into one of tex2html_wrap199 types:
-        // aliphatic [AVLIMC], aromatic [FWYH], polar [STNQ], positive [KR], negative [DE], 
-        // special conformations [GP] and gaps. This convention follows that 
+        // aliphatic [AVLIMC], aromatic [FWYH], polar [STNQ], positive [KR], negative [DE],
+        // special conformations [GP] and gaps. This convention follows that
         // of Mirny & Shakhnovich (1999, J Mol Biol 291:177-196).
         final HashMap<Character, Integer> counts = new HashMap<Character, Integer>();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
@@ -370,8 +407,8 @@ public final class MsaMethods {
 
     final private static HashMap<Character, Integer> calcResidueDistribution7( final Msa msa, final int col ) {
         // Residues are classified into one of tex2html_wrap199 types:
-        // aliphatic [AVLIMC], aromatic [FWYH], polar [STNQ], positive [KR], negative [DE], 
-        // special conformations [GP] and gaps. This convention follows that 
+        // aliphatic [AVLIMC], aromatic [FWYH], polar [STNQ], positive [KR], negative [DE],
+        // special conformations [GP] and gaps. This convention follows that
         // of Mirny & Shakhnovich (1999, J Mol Biol 291:177-196).
         final HashMap<Character, Integer> counts = new HashMap<Character, Integer>();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {