X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FAlignedCodonFrame.java;h=627f0a6a6ba112e3178ed909e80432ca8a551b10;hb=4d7f98a6dd54d9863ba449ec79dcd95d25ed863d;hp=313c9bba2499162776c7193acbb172bcf547fe0e;hpb=a8f483d04205bb8273ee311c12968b7e86d205fa;p=jalview.git
diff --git a/src/jalview/datamodel/AlignedCodonFrame.java b/src/jalview/datamodel/AlignedCodonFrame.java
index 313c9bb..627f0a6 100644
--- a/src/jalview/datamodel/AlignedCodonFrame.java
+++ b/src/jalview/datamodel/AlignedCodonFrame.java
@@ -1,150 +1,59 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
+ * 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.Enumeration;
-import java.util.Vector;
-
import jalview.util.MapList;
+import jalview.util.MappingUtils;
+
+import java.util.ArrayList;
+import java.util.List;
/**
* Stores mapping between the columns of a protein alignment and a DNA alignment
* and a list of individual codon to amino acid mappings between sequences.
*/
-
public class AlignedCodonFrame
{
- /**
- * array of nucleotide positions for aligned codons at column of aligned
- * proteins.
- */
- public int[][] codons = null;
-
- /**
- * width of protein sequence alignement implicit assertion that codons.length
- * >= aaWidth
- */
- public int aaWidth = 0;
-
- /**
- * initialise codon frame with a nominal alignment width
- *
- * @param aWidth
- */
- public AlignedCodonFrame(int aWidth)
- {
- if (aWidth <= 0)
- {
- codons = null;
- return;
- }
- codons = new int[aWidth][];
- for (int res = 0; res < aWidth; res++)
- codons[res] = null;
- }
-
- /**
- * ensure that codons array is at least as wide as aslen residues
- *
- * @param aslen
- * @return (possibly newly expanded) codon array
- */
- public int[][] checkCodonFrameWidth(int aslen)
- {
- if (codons.length <= aslen + 1)
- {
- // probably never have to do this ?
- int[][] c = new int[codons.length + 10][];
- for (int i = 0; i < codons.length; i++)
- {
- c[i] = codons[i];
- codons[i] = null;
- }
- codons = c;
- }
- return codons;
- }
/**
- * @return width of aligned translated amino acid residues
+ * tied array of na Sequence objects.
*/
- public int getaaWidth()
- {
- return aaWidth;
- }
+ private SequenceI[] dnaSeqs = null;
/**
- * TODO: not an ideal solution - we reference the aligned amino acid sequences
- * in order to make insertions on them Better would be dnaAlignment and
- * aaAlignment reference....
+ * tied array of Mappings to protein sequence Objects and SequenceI[]
+ * aaSeqs=null; MapLists where each maps from the corresponding dnaSeqs
+ * element to corresponding aaSeqs element
*/
- Vector a_aaSeqs = new Vector();
+ private Mapping[] dnaToProt = null;
/**
- * increase aaWidth by one and insert a new aligned codon position space at
- * aspos.
- *
- * @param aspos
+ * Constructor
*/
- public void insertAAGap(int aspos, char gapCharacter)
- {
- // this aa appears before the aligned codons at aspos - so shift them in
- // each pair of mapped sequences
- aaWidth++;
- if (a_aaSeqs != null)
- {
- // we actually have to modify the aligned sequences here, so use the
- // a_aaSeqs vector
- Enumeration sq = a_aaSeqs.elements();
- while (sq.hasMoreElements())
- {
- ((SequenceI) sq.nextElement()).insertCharAt(aspos, gapCharacter);
- }
- }
- checkCodonFrameWidth(aspos);
- if (aspos < aaWidth)
- {
- aaWidth++;
- System.arraycopy(codons, aspos, codons, aspos + 1, codons.length - aspos - 1);
- codons[aspos] = null; // clear so new codon position can be marked.
- }
- }
-
- public void setAaWidth(int aapos)
+ public AlignedCodonFrame()
{
- aaWidth = aapos;
}
/**
- * tied array of na Sequence objects.
- */
- SequenceI[] dnaSeqs = null;
-
- /**
- * tied array of Mappings to protein sequence Objects and SequenceI[]
- * aaSeqs=null; MapLists where eac maps from the corresponding dnaSeqs element
- * to corresponding aaSeqs element
- */
- Mapping[] dnaToProt = null;
-
- /**
- * add a mapping between the dataset sequences for the associated dna and
+ * Adds a mapping between the dataset sequences for the associated dna and
* protein sequence objects
*
* @param dnaseq
@@ -176,7 +85,6 @@ public class AlignedCodonFrame
// aaseq.transferAnnotation(dnaseq, new Mapping(map.getInverse()));
mp.to = (aaseq.getDatasetSequence() == null) ? aaseq : aaseq
.getDatasetSequence();
- a_aaSeqs.addElement(aaseq);
dnaToProt[nlen] = mp;
}
@@ -188,7 +96,9 @@ public class AlignedCodonFrame
public SequenceI[] getAaSeqs()
{
if (dnaToProt == null)
+ {
return null;
+ }
SequenceI[] sqs = new SequenceI[dnaToProt.length];
for (int sz = 0; sz < dnaToProt.length; sz++)
{
@@ -200,7 +110,9 @@ public class AlignedCodonFrame
public MapList[] getdnaToProt()
{
if (dnaToProt == null)
+ {
return null;
+ }
MapList[] sqs = new MapList[dnaToProt.length];
for (int sz = 0; sz < dnaToProt.length; sz++)
{
@@ -215,9 +127,37 @@ public class AlignedCodonFrame
}
/**
+ * Returns the first mapping found which is to or from the given sequence, or
+ * null.
+ *
+ * @param seq
+ * @return
+ */
+ public Mapping getMappingForSequence(SequenceI seq)
+ {
+ if (dnaSeqs == null)
+ {
+ return null;
+ }
+ SequenceI seqDs = seq.getDatasetSequence();
+ seqDs = seqDs != null ? seqDs : seq;
+
+ for (int ds = 0; ds < dnaSeqs.length; ds++)
+ {
+ if (dnaSeqs[ds] == seqDs || dnaToProt[ds].to == seqDs)
+ {
+ return dnaToProt[ds];
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Return the corresponding aligned or dataset aa sequence for given dna
+ * sequence, null if not found.
*
* @param sequenceRef
- * @return null or corresponding aaSeq entry for dnaSeq entry
+ * @return
*/
public SequenceI getAaForDnaSeq(SequenceI dnaSeqRef)
{
@@ -229,7 +169,9 @@ public class AlignedCodonFrame
for (int ds = 0; ds < dnaSeqs.length; ds++)
{
if (dnaSeqs[ds] == dnaSeqRef || dnaSeqs[ds] == dnads)
+ {
return dnaToProt[ds].to;
+ }
}
return null;
}
@@ -249,7 +191,9 @@ public class AlignedCodonFrame
for (int as = 0; as < dnaToProt.length; as++)
{
if (dnaToProt[as].to == aaSeqRef || dnaToProt[as].to == aads)
+ {
return dnaSeqs[as];
+ }
}
return null;
}
@@ -316,4 +260,203 @@ public class AlignedCodonFrame
}
}
}
+
+ /**
+ * Returns the DNA codon positions (base 1) for the given position (base 1) in
+ * a mapped protein sequence, or null if no mapping is found.
+ *
+ * Intended for use in aligning cDNA to match aligned protein. Only the first
+ * mapping found is returned, so not suitable for use if multiple protein
+ * sequences are mapped to the same cDNA (but aligning cDNA as protein is
+ * ill-defined for this case anyway).
+ *
+ * @param seq
+ * the DNA dataset sequence
+ * @param aaPos
+ * residue position (base 1) in a protein sequence
+ * @return
+ */
+ public int[] getDnaPosition(SequenceI seq, int aaPos)
+ {
+ /*
+ * Adapted from markMappedRegion().
+ */
+ MapList ml = null;
+ for (int i = 0; i < dnaToProt.length; i++)
+ {
+ if (dnaSeqs[i] == seq)
+ {
+ ml = getdnaToProt()[i];
+ break;
+ }
+ }
+ return ml == null ? null : ml.locateInFrom(aaPos, aaPos);
+ }
+
+ /**
+ * Convenience method to return the first aligned sequence in the given
+ * alignment whose dataset has a mapping with the given dataset sequence.
+ *
+ * @param seq
+ *
+ * @param al
+ * @return
+ */
+ public SequenceI findAlignedSequence(SequenceI seq, AlignmentI al)
+ {
+ /*
+ * Search mapped protein ('to') sequences first.
+ */
+ if (this.dnaToProt != null)
+ {
+ for (int i = 0; i < dnaToProt.length; i++)
+ {
+ if (this.dnaSeqs[i] == seq)
+ {
+ for (SequenceI sourceAligned : al.getSequences())
+ {
+ if (this.dnaToProt[i].to == sourceAligned.getDatasetSequence())
+ {
+ return sourceAligned;
+ }
+ }
+ }
+ }
+ }
+
+ /*
+ * Then try mapped dna sequences.
+ */
+ if (this.dnaToProt != null)
+ {
+ for (int i = 0; i < dnaToProt.length; i++)
+ {
+ if (this.dnaToProt[i].to == seq)
+ {
+ for (SequenceI sourceAligned : al.getSequences())
+ {
+ if (this.dnaSeqs[i] == sourceAligned.getDatasetSequence())
+ {
+ return sourceAligned;
+ }
+ }
+ }
+ }
+ }
+
+ return null;
+ }
+
+ /**
+ * Returns the region in the 'mappedFrom' sequence's dataset that is mapped to
+ * position 'pos' (base 1) in the 'mappedTo' sequence's dataset. The region is
+ * a set of start/end position pairs.
+ *
+ * @param mappedFrom
+ * @param mappedTo
+ * @param pos
+ * @return
+ */
+ public int[] getMappedRegion(SequenceI mappedFrom, SequenceI mappedTo,
+ int pos)
+ {
+ SequenceI targetDs = mappedFrom.getDatasetSequence() == null ? mappedFrom
+ : mappedFrom.getDatasetSequence();
+ SequenceI sourceDs = mappedTo.getDatasetSequence() == null ? mappedTo
+ : mappedTo.getDatasetSequence();
+ if (targetDs == null || sourceDs == null || dnaToProt == null)
+ {
+ return null;
+ }
+ for (int mi = 0; mi < dnaToProt.length; mi++)
+ {
+ if (dnaSeqs[mi] == targetDs && dnaToProt[mi].to == sourceDs)
+ {
+ int[] codon = dnaToProt[mi].map.locateInFrom(pos, pos);
+ if (codon != null)
+ {
+ return codon;
+ }
+ }
+ }
+ return null;
+ }
+
+ /**
+ * Returns the DNA codon for the given position (base 1) in a mapped protein
+ * sequence, or null if no mapping is found.
+ *
+ * @param protein
+ * the peptide dataset sequence
+ * @param aaPos
+ * residue position (base 1) in the peptide sequence
+ * @return
+ */
+ public char[] getMappedCodon(SequenceI protein, int aaPos)
+ {
+ if (dnaToProt == null)
+ {
+ return null;
+ }
+ MapList ml = null;
+ char[] dnaSeq = null;
+ for (int i = 0; i < dnaToProt.length; i++)
+ {
+ if (dnaToProt[i].to == protein)
+ {
+ ml = getdnaToProt()[i];
+ dnaSeq = dnaSeqs[i].getSequence();
+ break;
+ }
+ }
+ if (ml == null)
+ {
+ return null;
+ }
+ int[] codonPos = ml.locateInFrom(aaPos, aaPos);
+ if (codonPos == null)
+ {
+ return null;
+ }
+
+ /*
+ * Read off the mapped nucleotides (converting to position base 0)
+ */
+ codonPos = MappingUtils.flattenRanges(codonPos);
+ return new char[] { dnaSeq[codonPos[0] - 1], dnaSeq[codonPos[1] - 1],
+ dnaSeq[codonPos[2] - 1] };
+ }
+
+ /**
+ * Returns any mappings found which are to (or from) the given sequence, and
+ * to distinct sequences.
+ *
+ * @param seq
+ * @return
+ */
+ public List getMappingsForSequence(SequenceI seq)
+ {
+ List result = new ArrayList();
+ if (dnaSeqs == null)
+ {
+ return result;
+ }
+ List related = new ArrayList();
+ SequenceI seqDs = seq.getDatasetSequence();
+ seqDs = seqDs != null ? seqDs : seq;
+
+ for (int ds = 0; ds < dnaSeqs.length; ds++)
+ {
+ final Mapping mapping = dnaToProt[ds];
+ if (dnaSeqs[ds] == seqDs || mapping.to == seqDs)
+ {
+ if (!related.contains(mapping.to))
+ {
+ result.add(mapping);
+ related.add(mapping.to);
+ }
+ }
+ }
+ return result;
+ }
}