X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FMapping.java;h=4d90e3e0b6c042533ef42f020ccbb232c9b7094c;hb=1e507c915398542fe6e206e7a6f2620283243f1e;hp=01c51518c7438202fda7255ca30c4a4f29eade1c;hpb=797df64fa2a0a30773d0f48f5494d4155e5a8be3;p=jalview.git
diff --git a/src/jalview/datamodel/Mapping.java b/src/jalview/datamodel/Mapping.java
index 01c5151..4d90e3e 100644
--- a/src/jalview/datamodel/Mapping.java
+++ b/src/jalview/datamodel/Mapping.java
@@ -1,40 +1,299 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
- * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
* Jalview is free software: you can redistribute it and/or
* modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
- *
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
* Jalview is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR
* PURPOSE. See the GNU General Public License for more details.
*
- * You should have received a copy of the GNU General Public License along with Jalview. If not, see .
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see .
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.datamodel;
+import java.util.Iterator;
+import java.util.NoSuchElementException;
import java.util.Vector;
+import jalview.util.Comparison;
import jalview.util.MapList;
public class Mapping
{
/**
+ * An iterator that serves the aligned codon positions (with their protein
+ * products).
+ *
+ * @author gmcarstairs
+ *
+ */
+ public class AlignedCodonIterator implements Iterator
+ {
+ /*
+ * The gap character used in the aligned sequence
+ */
+ private final char gap;
+
+ /*
+ * The characters of the aligned sequence e.g. "-cGT-ACgTG-"
+ */
+ private final SequenceI alignedSeq;
+
+ /*
+ * the sequence start residue
+ */
+ private int start;
+
+ /*
+ * Next position (base 0) in the aligned sequence
+ */
+ private int alignedColumn = 0;
+
+ /*
+ * Count of bases up to and including alignedColumn position
+ */
+ private int alignedBases = 0;
+
+ /*
+ * [start, end] from ranges (base 1)
+ */
+ private Iterator fromRanges;
+
+ /*
+ * [start, end] to ranges (base 1)
+ */
+ private Iterator toRanges;
+
+ /*
+ * The current [start, end] (base 1) from range
+ */
+ private int[] currentFromRange = null;
+
+ /*
+ * The current [start, end] (base 1) to range
+ */
+ private int[] currentToRange = null;
+
+ /*
+ * The next 'from' position (base 1) to process
+ */
+ private int fromPosition = 0;
+
+ /*
+ * The next 'to' position (base 1) to process
+ */
+ private int toPosition = 0;
+
+ /**
+ * Constructor
+ *
+ * @param seq
+ * the aligned sequence
+ * @param gapChar
+ */
+ public AlignedCodonIterator(SequenceI seq, char gapChar)
+ {
+ this.alignedSeq = seq;
+ this.start = seq.getStart();
+ this.gap = gapChar;
+ fromRanges = map.getFromRanges().iterator();
+ toRanges = map.getToRanges().iterator();
+ if (fromRanges.hasNext())
+ {
+ currentFromRange = fromRanges.next();
+ fromPosition = currentFromRange[0];
+ }
+ if (toRanges.hasNext())
+ {
+ currentToRange = toRanges.next();
+ toPosition = currentToRange[0];
+ }
+ }
+
+ /**
+ * Returns true unless we have already traversed the whole mapping.
+ */
+ @Override
+ public boolean hasNext()
+ {
+ if (fromRanges.hasNext())
+ {
+ return true;
+ }
+ if (currentFromRange == null || fromPosition >= currentFromRange[1])
+ {
+ return false;
+ }
+ return true;
+ }
+
+ /**
+ * Returns the next codon's aligned positions, and translated value.
+ *
+ * @throws NoSuchElementException
+ * if hasNext() would have returned false
+ * @throws IncompleteCodonException
+ * if not enough mapped bases are left to make up a codon
+ */
+ @Override
+ public AlignedCodon next() throws IncompleteCodonException
+ {
+ if (!hasNext())
+ {
+ throw new NoSuchElementException();
+ }
+
+ int[] codon = getNextCodon();
+ int[] alignedCodon = getAlignedCodon(codon);
+
+ String peptide = getPeptide();
+ int peptideCol = toPosition - 1 - Mapping.this.to.getStart();
+ return new AlignedCodon(alignedCodon[0], alignedCodon[1],
+ alignedCodon[2], peptide, peptideCol);
+ }
+
+ /**
+ * Retrieve the translation as the 'mapped to' position in the mapped to
+ * sequence.
+ *
+ * @return
+ * @throws NoSuchElementException
+ * if the 'toRange' is exhausted (nothing to map to)
+ */
+ private String getPeptide()
+ {
+ // TODO should ideally handle toRatio other than 1 as well...
+ // i.e. code like getNextCodon()
+ if (toPosition <= currentToRange[1])
+ {
+ SequenceI seq = Mapping.this.to;
+ char pep = seq.getCharAt(toPosition - seq.getStart());
+ toPosition++;
+ return String.valueOf(pep);
+ }
+ if (!toRanges.hasNext())
+ {
+ throw new NoSuchElementException(
+ "Ran out of peptide at position " + toPosition);
+ }
+ currentToRange = toRanges.next();
+ toPosition = currentToRange[0];
+ return getPeptide();
+ }
+
+ /**
+ * Get the (base 1) dataset positions for the next codon in the mapping.
+ *
+ * @throws IncompleteCodonException
+ * if less than 3 remaining bases are mapped
+ */
+ private int[] getNextCodon()
+ {
+ int[] codon = new int[3];
+ int codonbase = 0;
+
+ while (codonbase < 3)
+ {
+ if (fromPosition <= currentFromRange[1])
+ {
+ /*
+ * Add next position from the current start-end range
+ */
+ codon[codonbase++] = fromPosition++;
+ }
+ else
+ {
+ /*
+ * Move to the next range - if there is one
+ */
+ if (!fromRanges.hasNext())
+ {
+ throw new IncompleteCodonException();
+ }
+ currentFromRange = fromRanges.next();
+ fromPosition = currentFromRange[0];
+ }
+ }
+ return codon;
+ }
+
+ /**
+ * Get the aligned column positions (base 0) for the given sequence
+ * positions (base 1), by counting ungapped characters in the aligned
+ * sequence.
+ *
+ * @param codon
+ * @return
+ */
+ private int[] getAlignedCodon(int[] codon)
+ {
+ int[] aligned = new int[codon.length];
+ for (int i = 0; i < codon.length; i++)
+ {
+ aligned[i] = getAlignedColumn(codon[i]);
+ }
+ return aligned;
+ }
+
+ /**
+ * Get the aligned column position (base 0) for the given sequence position
+ * (base 1).
+ *
+ * @param sequencePos
+ * @return
+ */
+ private int getAlignedColumn(int sequencePos)
+ {
+ /*
+ * allow for offset e.g. treat pos 8 as 2 if sequence starts at 7
+ */
+ int truePos = sequencePos - (start - 1);
+ int length = alignedSeq.getLength();
+ while (alignedBases < truePos && alignedColumn < length)
+ {
+ char c = alignedSeq.getCharAt(alignedColumn++);
+ if (c != gap && !Comparison.isGap(c))
+ {
+ alignedBases++;
+ }
+ }
+ return alignedColumn - 1;
+ }
+
+ @Override
+ public void remove()
+ {
+ // ignore
+ }
+
+ }
+
+ /*
* Contains the start-end pairs mapping from the associated sequence to the
- * sequence in the database coordinate system it also takes care of step
- * difference between coordinate systems
+ * sequence in the database coordinate system. It also takes care of step
+ * difference between coordinate systems.
*/
MapList map = null;
- /**
- * The seuqence that map maps the associated seuqence to (if any).
+ /*
+ * The sequence that map maps the associated sequence to (if any).
*/
SequenceI to = null;
+ /*
+ * optional sequence id for the 'from' ranges
+ */
+ private String mappedFromId;
+
public Mapping(MapList map)
{
super();
@@ -82,6 +341,7 @@ public class Mapping
map = new MapList(map2.map);
}
to = map2.to;
+ mappedFromId = map2.mappedFromId;
}
}
@@ -105,26 +365,54 @@ public class Mapping
/**
* Equals that compares both the to references and MapList mappings.
*
- * @param other
+ * @param o
* @return
+ * @see MapList#equals
*/
- public boolean equals(Mapping other)
+ @Override
+ public boolean equals(Object o)
{
- if (other == null)
+ if (o == null || !(o instanceof Mapping))
+ {
return false;
+ }
+ Mapping other = (Mapping) o;
if (other == this)
+ {
return true;
+ }
if (other.to != to)
+ {
return false;
+ }
if ((map != null && other.map == null)
|| (map == null && other.map != null))
+ {
return false;
- if (map.equals(other.map))
+ }
+ if ((map == null && other.map == null) || map.equals(other.map))
+ {
return true;
+ }
return false;
}
/**
+ * Returns a hashCode made from the sequence and maplist
+ */
+ @Override
+ public int hashCode()
+ {
+ int hashCode = (this.to == null ? 1 : this.to.hashCode());
+ if (this.map != null)
+ {
+ hashCode = hashCode * 31 + this.map.hashCode();
+ }
+
+ return hashCode;
+ }
+
+ /**
* get the 'initial' position in the associated sequence for a position in the
* mapped reference frame
*
@@ -145,23 +433,6 @@ public class Mapping
}
/**
- * gets boundary in direction of mapping
- *
- * @param position
- * in mapped reference frame
- * @return int{start, end} positions in associated sequence (in direction of
- * mapped word)
- */
- public int[] getWord(int mpos)
- {
- if (map != null)
- {
- return map.getToWord(mpos);
- }
- return null;
- }
-
- /**
* width of mapped unit in associated sequence
*
*/
@@ -215,8 +486,7 @@ public class Mapping
int[] mp = map.shiftFrom(pos);
if (mp != null)
{
- return new int[]
- { mp[0], mp[0] + mp[2] * (map.getToRatio() - 1) };
+ return new int[] { mp[0], mp[0] + mp[2] * (map.getToRatio() - 1) };
}
}
return null;
@@ -244,39 +514,19 @@ public class Mapping
SequenceFeature[] vf = new SequenceFeature[frange.length / 2];
for (int i = 0, v = 0; i < frange.length; i += 2, v++)
{
- vf[v] = new SequenceFeature(f);
- vf[v].setBegin(frange[i]);
- vf[v].setEnd(frange[i + 1]);
+ vf[v] = new SequenceFeature(f, frange[i], frange[i + 1],
+ f.getFeatureGroup(), f.getScore());
if (frange.length > 2)
+ {
vf[v].setDescription(f.getDescription() + "\nPart " + (v + 1));
+ }
}
return vf;
}
}
- if (false) // else
- {
- int[] word = getWord(f.getBegin());
- if (word[0] < word[1])
- {
- f.setBegin(word[0]);
- }
- else
- {
- f.setBegin(word[1]);
- }
- word = getWord(f.getEnd());
- if (word[0] > word[1])
- {
- f.setEnd(word[0]);
- }
- else
- {
- f.setEnd(word[1]);
- }
- }
+
// give up and just return the feature.
- return new SequenceFeature[]
- { f };
+ return new SequenceFeature[] { f };
}
/**
@@ -297,19 +547,22 @@ public class Mapping
from = (map.getToLowest() < from) ? from : map.getToLowest();
to = (map.getToHighest() > to) ? to : map.getToHighest();
if (from > to)
+ {
return null;
+ }
}
else
{
from = (map.getToHighest() > from) ? from : map.getToHighest();
to = (map.getToLowest() < to) ? to : map.getToLowest();
if (from < to)
+ {
return null;
+ }
}
return map.locateInFrom(from, to);
}
- return new int[]
- { from, to };
+ return new int[] { from, to };
}
/**
@@ -330,19 +583,22 @@ public class Mapping
from = (map.getFromLowest() < from) ? from : map.getFromLowest();
to = (map.getFromHighest() > to) ? to : map.getFromHighest();
if (from > to)
+ {
return null;
+ }
}
else
{
from = (map.getFromHighest() > from) ? from : map.getFromHighest();
to = (map.getFromLowest() < to) ? to : map.getFromLowest();
if (from < to)
+ {
return null;
+ }
}
return map.locateInTo(from, to);
}
- return new int[]
- { from, to };
+ return new int[] { from, to };
}
/**
@@ -370,13 +626,11 @@ public class Mapping
{
for (int m = 0; m < mpr.length; m += 2)
{
- toRange.addElement(new int[]
- { mpr[m], mpr[m + 1] });
+ toRange.addElement(new int[] { mpr[m], mpr[m + 1] });
int[] xpos = locateRange(mpr[m], mpr[m + 1]);
for (int x = 0; x < xpos.length; x += 2)
{
- fromRange.addElement(new int[]
- { xpos[x], xpos[x + 1] });
+ fromRange.addElement(new int[] { xpos[x], xpos[x + 1] });
}
}
}
@@ -396,30 +650,12 @@ public class Mapping
to[f * 2] = r[0];
to[f * 2 + 1] = r[1];
}
- copy.setMap(new MapList(from, to, map.getFromRatio(), map
- .getToRatio()));
+ copy.setMap(
+ new MapList(from, to, map.getFromRatio(), map.getToRatio()));
}
return copy;
}
- public static void main(String[] args)
- {
- /**
- * trite test of the intersectVisContigs method for a simple DNA -> Protein
- * exon map and a range of visContigs
- */
- MapList fk = new MapList(new int[]
- { 1, 6, 8, 13, 15, 23 }, new int[]
- { 1, 7 }, 3, 1);
- Mapping m = new Mapping(fk);
- Mapping m_1 = m.intersectVisContigs(new int[]
- { fk.getFromLowest(), fk.getFromHighest() });
- Mapping m_2 = m.intersectVisContigs(new int[]
- { 1, 7, 11, 20 });
- System.out.println("" + m_1.map.getFromRanges());
-
- }
-
/**
* get the sequence being mapped to - if any
*
@@ -440,16 +676,47 @@ public class Mapping
to = tto;
}
- /*
- * (non-Javadoc)
+ /**
+ * Returns an iterator which can serve up the aligned codon column positions
+ * and their corresponding peptide products
+ *
+ * @param seq
+ * an aligned (i.e. possibly gapped) sequence
+ * @param gapChar
+ * @return
+ */
+ public Iterator getCodonIterator(SequenceI seq,
+ char gapChar)
+ {
+ return new AlignedCodonIterator(seq, gapChar);
+ }
+
+ /**
+ * Readable representation for debugging only, not guaranteed not to change
+ */
+ @Override
+ public String toString()
+ {
+ return String.format("%s %s", this.map.toString(),
+ this.to == null ? "" : this.to.getName());
+ }
+
+ /**
+ * Returns the identifier for the 'from' range sequence, or null if not set
*
- * @see java.lang.Object#finalize()
+ * @return
+ */
+ public String getMappedFromId()
+ {
+ return mappedFromId;
+ }
+
+ /**
+ * Sets the identifier for the 'from' range sequence
*/
- protected void finalize() throws Throwable
+ public void setMappedFromId(String mappedFromId)
{
- map = null;
- to = null;
- super.finalize();
+ this.mappedFromId = mappedFromId;
}
}