in progress...

[jalview.git] / forester / java / src / org / forester / msa / MsaMethods.java

diff --git a/forester/java/src/org/forester/msa/MsaMethods.java b/forester/java/src/org/forester/msa/MsaMethods.java
index c94869e..2b47020 100644 (file)
--- a/forester/java/src/org/forester/msa/MsaMethods.java
+++ b/forester/java/src/org/forester/msa/MsaMethods.java
@@ -34,7 +34,7 @@ import java.util.SortedMap;
 import java.util.TreeMap;
 
 import org.forester.sequence.BasicSequence;
-import org.forester.sequence.Sequence;
+import org.forester.sequence.MolecularSequence;
 import org.forester.util.BasicDescriptiveStatistics;
 import org.forester.util.DescriptiveStatistics;
 
@@ -67,7 +67,7 @@ public final class MsaMethods {
                 ++new_length;
             }
         }
-        final List<Sequence> seqs = new ArrayList<Sequence>( msa.getNumberOfSequences() );
+        final List<MolecularSequence> seqs = new ArrayList<MolecularSequence>( msa.getNumberOfSequences() );
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
             final char[] mol_seq = new char[ new_length ];
             int new_col = 0;
@@ -76,7 +76,7 @@ public final class MsaMethods {
                 if ( !delete_cols[ col ] ) {
                     final char residue = msa.getResidueAt( row, col );
                     mol_seq[ new_col++ ] = ( residue );
-                    if ( residue != Sequence.GAP ) {
+                    if ( residue != MolecularSequence.GAP ) {
                         ++non_gap_cols_sum;
                     }
                 }
@@ -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 ) {
@@ -119,7 +156,7 @@ public final class MsaMethods {
         int gaps = 0;
         for( int seq = 0; seq < msa.getNumberOfSequences(); ++seq ) {
             for( int i = 0; i < msa.getLength(); ++i ) {
-                if ( msa.getResidueAt( seq, i ) == Sequence.GAP ) {
+                if ( msa.getResidueAt( seq, i ) == MolecularSequence.GAP ) {
                     gaps++;
                 }
             }
@@ -191,7 +228,7 @@ public final class MsaMethods {
     final public static DescriptiveStatistics calculateEffectiveLengthStatistics( final Msa msa ) {
         final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
-            final Sequence s = msa.getSequence( row );
+            final MolecularSequence s = msa.getSequence( row );
             stats.addValue( s.getLength() - s.getNumberOfGapResidues() );
         }
         return stats;
@@ -221,7 +258,7 @@ public final class MsaMethods {
     public static SortedMap<Character, Integer> calculateResidueDestributionPerColumn( final Msa msa, final int column ) {
         final SortedMap<Character, Integer> map = new TreeMap<Character, Integer>();
         for( final Character r : msa.getColumnAt( column ) ) {
-            if ( r != Sequence.GAP ) {
+            if ( r != MolecularSequence.GAP ) {
                 if ( !map.containsKey( r ) ) {
                     map.put( r, 1 );
                 }
@@ -238,7 +275,7 @@ public final class MsaMethods {
     }
 
     final public static Msa removeSequence( final Msa msa, final String to_remove_id ) {
-        final List<Sequence> seqs = new ArrayList<Sequence>();
+        final List<MolecularSequence> seqs = new ArrayList<MolecularSequence>();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
             if ( !to_remove_id.equals( msa.getIdentifier( row ) ) ) {
                 seqs.add( msa.getSequence( row ) );
@@ -251,7 +288,7 @@ public final class MsaMethods {
     }
 
     final public static Msa removeSequences( final Msa msa, final List<String> to_remove_ids ) {
-        final List<Sequence> seqs = new ArrayList<Sequence>();
+        final List<MolecularSequence> seqs = new ArrayList<MolecularSequence>();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
             if ( !to_remove_ids.contains( msa.getIdentifier( row ) ) ) {
                 seqs.add( msa.getSequence( row ) );
@@ -268,7 +305,7 @@ public final class MsaMethods {
         for( int seq = 0; seq < msa.getNumberOfSequences(); ++seq ) {
             int eff_length = 0;
             for( int i = 0; i < msa.getLength(); ++i ) {
-                if ( msa.getResidueAt( seq, i ) != Sequence.GAP ) {
+                if ( msa.getResidueAt( seq, i ) != MolecularSequence.GAP ) {
                     eff_length++;
                 }
             }
@@ -280,7 +317,7 @@ public final class MsaMethods {
     }
 
     final public static Msa removeSequencesByRow( final Msa msa, final List<Integer> to_remove_rows ) {
-        final List<Sequence> seqs = new ArrayList<Sequence>();
+        final List<MolecularSequence> seqs = new ArrayList<MolecularSequence>();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
             if ( !to_remove_rows.contains( row ) ) {
                 seqs.add( msa.getSequence( row ) );
@@ -296,7 +333,7 @@ public final class MsaMethods {
         final HashMap<Character, Integer> counts = new HashMap<Character, Integer>();
         for( int row = 0; row < msa.getNumberOfSequences(); ++row ) {
             final char c = msa.getResidueAt( row, col );
-            if ( c != Sequence.GAP ) {
+            if ( c != MolecularSequence.GAP ) {
                 if ( !counts.containsKey( c ) ) {
                     counts.put( c, 1 );
                 }
@@ -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 ) {