/*
- * Jalview - A Sequence Alignment Editor and Viewer
- * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle
- *
- * This program 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 2
+ * 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.
- *
- * This program 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.
- *
+ *
+ * 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 this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.datamodel;
-import java.util.*;
+import jalview.analysis.AlignSeq;
+import jalview.api.DBRefEntryI;
+import jalview.util.StringUtils;
-import jalview.analysis.*;
+import java.util.ArrayList;
+import java.util.Enumeration;
+import java.util.List;
+import java.util.Vector;
+
+import fr.orsay.lri.varna.models.rna.RNA;
/**
*
* @author $author$
* @version $Revision$
*/
-public class Sequence implements SequenceI
+public class Sequence extends ASequence implements SequenceI
{
SequenceI datasetSequence;
int end;
- Vector pdbIds;
+ Vector<PDBEntry> pdbIds;
String vamsasId;
+ DBRefEntryI sourceDBRef;
+
DBRefEntry[] dbrefs;
+ RNA rna;
+
/**
* This annotation is displayed below the alignment but the positions are tied
* to the residues of this sequence
+ *
+ * TODO: change to List<>
*/
- Vector annotation;
+ Vector<AlignmentAnnotation> annotation;
- /** array of seuqence features - may not be null for a valid sequence object */
+ /**
+ * The index of the sequence in a MSA
+ */
+ int index = -1;
+
+ /** array of sequence features - may not be null for a valid sequence object */
public SequenceFeature[] sequenceFeatures;
/**
* Creates a new Sequence object.
*
* @param name
- * display name string
+ * display name string
* @param sequence
- * string to form a possibly gapped sequence out of
+ * string to form a possibly gapped sequence out of
* @param start
- * first position of non-gap residue in the sequence
+ * first position of non-gap residue in the sequence
* @param end
- * last position of ungapped residues (nearly always only used
- * for display purposes)
+ * last position of ungapped residues (nearly always only used for
+ * display purposes)
*/
public Sequence(String name, String sequence, int start, int end)
{
- this.name = name;
- this.sequence = sequence.toCharArray();
- this.start = start;
- this.end = end;
- parseId();
- checkValidRange();
+ initSeqAndName(name, sequence.toCharArray(), start, end);
}
public Sequence(String name, char[] sequence, int start, int end)
{
- this.name = name;
- this.sequence = sequence;
- this.start = start;
- this.end = end;
+ initSeqAndName(name, sequence, start, end);
+ }
+
+ /**
+ * Stage 1 constructor - assign name, sequence, and set start and end fields.
+ * start and end are updated values from name2 if it ends with /start-end
+ *
+ * @param name2
+ * @param sequence2
+ * @param start2
+ * @param end2
+ */
+ protected void initSeqAndName(String name2, char[] sequence2, int start2,
+ int end2)
+ {
+ this.name = name2;
+ this.sequence = sequence2;
+ this.start = start2;
+ this.end = end2;
parseId();
checkValidRange();
}
.println("POSSIBLE IMPLEMENTATION ERROR: null sequence name passed to constructor.");
name = "";
}
- // Does sequence have the /start-end signiature?
+ // Does sequence have the /start-end signature?
if (limitrx.search(name))
{
name = limitrx.left();
void checkValidRange()
{
- if (end < 1)
+ // Note: JAL-774 :
+ // http://issues.jalview.org/browse/JAL-774?focusedCommentId=11239&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-11239
{
int endRes = 0;
for (int j = 0; j < sequence.length; j++)
endRes += start - 1;
}
- this.end = endRes;
+ if (end < endRes)
+ {
+ end = endRes;
+ }
}
}
* Creates a new Sequence object.
*
* @param name
- * DOCUMENT ME!
+ * DOCUMENT ME!
* @param sequence
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
public Sequence(String name, String sequence)
{
* reference.
*
* @param seq
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
public Sequence(SequenceI seq)
{
* annotation that is present in the given annotation array.
*
* @param seq
- * the sequence to be copied
+ * the sequence to be copied
* @param alAnnotation
- * an array of annotation including some associated with seq
+ * an array of annotation including some associated with seq
*/
public Sequence(SequenceI seq, AlignmentAnnotation[] alAnnotation)
{
- this(seq.getName(), seq.getSequence(), seq.getStart(), seq.getEnd());
+ initSeqFrom(seq, alAnnotation);
+
+ }
+
+ protected void initSeqFrom(SequenceI seq,
+ AlignmentAnnotation[] alAnnotation)
+ {
+ initSeqAndName(seq.getName(), seq.getSequence(), seq.getStart(),
+ seq.getEnd());
description = seq.getDescription();
+ sourceDBRef = seq.getSourceDBRef() == null ? null : new DBRefEntry(
+ seq.getSourceDBRef());
if (seq.getSequenceFeatures() != null)
{
SequenceFeature[] sf = seq.getSequenceFeatures();
}
}
setDatasetSequence(seq.getDatasetSequence());
- if (datasetSequence==null && seq.getDBRef() != null)
+ if (datasetSequence == null && seq.getDBRefs() != null)
{
// only copy DBRefs if we really are a dataset sequence
- DBRefEntry[] dbr = seq.getDBRef();
+ DBRefEntry[] dbr = seq.getDBRefs();
for (int i = 0; i < dbr.length; i++)
{
addDBRef(new DBRefEntry(dbr[i]));
}
}
}
- if (seq.getPDBId() != null)
+ if (seq.getAllPDBEntries() != null)
{
- Vector ids = seq.getPDBId();
+ Vector ids = seq.getAllPDBEntries();
Enumeration e = ids.elements();
while (e.hasMoreElements())
{
* DOCUMENT ME!
*
* @param v
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
+ @Override
public void setSequenceFeatures(SequenceFeature[] features)
{
sequenceFeatures = features;
}
+ @Override
public synchronized void addSequenceFeature(SequenceFeature sf)
{
if (sequenceFeatures == null)
sequenceFeatures = temp;
}
+ @Override
public void deleteFeature(SequenceFeature sf)
{
if (sequenceFeatures == null)
}
/**
- * DOCUMENT ME!
+ * Returns the sequence features (if any), looking first on the sequence, then
+ * on its dataset sequence, and so on until a non-null value is found (or
+ * none). This supports retrieval of sequence features stored on the sequence
+ * (as in the applet) or on the dataset sequence (as in the Desktop version).
*
- * @return DOCUMENT ME!
+ * @return
*/
+ @Override
public SequenceFeature[] getSequenceFeatures()
{
- return sequenceFeatures;
+ SequenceFeature[] features = sequenceFeatures;
+
+ SequenceI seq = this;
+ int count = 0; // failsafe against loop in sequence.datasetsequence...
+ while (features == null && seq.getDatasetSequence() != null
+ && count++ < 10)
+ {
+ seq = seq.getDatasetSequence();
+ features = ((Sequence) seq).sequenceFeatures;
+ }
+ return features;
}
+ @Override
public void addPDBId(PDBEntry entry)
{
if (pdbIds == null)
{
- pdbIds = new Vector();
+ pdbIds = new Vector<PDBEntry>();
}
- if (!pdbIds.contains(entry))
+ if (pdbIds.contains(entry))
+ {
+ updatePDBEntry(pdbIds.get(pdbIds.indexOf(entry)), entry);
+ }
+ else
{
pdbIds.addElement(entry);
}
}
+ private static void updatePDBEntry(PDBEntry oldEntry, PDBEntry newEntry)
+ {
+ if (newEntry.getFile() != null)
+ {
+ oldEntry.setFile(newEntry.getFile());
+ }
+ }
+
/**
* DOCUMENT ME!
*
* @param id
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
- public void setPDBId(Vector id)
+ @Override
+ public void setPDBId(Vector<PDBEntry> id)
{
pdbIds = id;
}
*
* @return DOCUMENT ME!
*/
- public Vector getPDBId()
+ @Override
+ public Vector<PDBEntry> getAllPDBEntries()
{
- return pdbIds;
+ return pdbIds == null ? new Vector<PDBEntry>() : pdbIds;
}
/**
*
* @return DOCUMENT ME!
*/
+ @Override
public String getDisplayId(boolean jvsuffix)
{
StringBuffer result = new StringBuffer(name);
* DOCUMENT ME!
*
* @param name
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
+ @Override
public void setName(String name)
{
this.name = name;
*
* @return DOCUMENT ME!
*/
+ @Override
public String getName()
{
return this.name;
* DOCUMENT ME!
*
* @param start
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
+ @Override
public void setStart(int start)
{
this.start = start;
*
* @return DOCUMENT ME!
*/
+ @Override
public int getStart()
{
return this.start;
* DOCUMENT ME!
*
* @param end
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
+ @Override
public void setEnd(int end)
{
this.end = end;
*
* @return DOCUMENT ME!
*/
+ @Override
public int getEnd()
{
return this.end;
*
* @return DOCUMENT ME!
*/
+ @Override
public int getLength()
{
return this.sequence.length;
* DOCUMENT ME!
*
* @param seq
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
+ @Override
public void setSequence(String seq)
{
this.sequence = seq.toCharArray();
checkValidRange();
}
+ @Override
public String getSequenceAsString()
{
return new String(sequence);
}
+ @Override
public String getSequenceAsString(int start, int end)
{
return new String(getSequence(start, end));
}
+ @Override
public char[] getSequence()
{
return sequence;
*
* @see jalview.datamodel.SequenceI#getSequence(int, int)
*/
+ @Override
public char[] getSequence(int start, int end)
{
if (start < 0)
+ {
start = 0;
+ }
// JBPNote - left to user to pad the result here (TODO:Decide on this
// policy)
if (start >= sequence.length)
return reply;
}
- /**
- * make a new Sequence object from start to end (including gaps) over this
- * seqeunce
- *
- * @param start
- * int
- * @param end
- * int
- * @return SequenceI
- */
+ @Override
public SequenceI getSubSequence(int start, int end)
{
if (start < 0)
* DOCUMENT ME!
*
* @param i
- * DOCUMENT ME!
+ * DOCUMENT ME!
*
* @return DOCUMENT ME!
*/
+ @Override
public char getCharAt(int i)
{
if (i < sequence.length)
* DOCUMENT ME!
*
* @param desc
- * DOCUMENT ME!
+ * DOCUMENT ME!
*/
+ @Override
public void setDescription(String desc)
{
this.description = desc;
*
* @return DOCUMENT ME!
*/
+ @Override
public String getDescription()
{
return this.description;
}
- /**
- * Return the alignment position for a sequence position
- *
- * @param pos
- * lying from start to end
+ /*
+ * (non-Javadoc)
*
- * @return aligned position of residue pos
+ * @see jalview.datamodel.SequenceI#findIndex(int)
*/
+ @Override
public int findIndex(int pos)
{
// returns the alignment position for a residue
int j = start;
int i = 0;
-
+ // Rely on end being at least as long as the length of the sequence.
while ((i < sequence.length) && (j <= end) && (j <= pos))
{
if (!jalview.util.Comparison.isGap(sequence[i]))
}
}
- /**
- * Returns the sequence position for an alignment position
- *
- * @param i
- * column index in alignment (from 1)
- *
- * @return residue number for residue (left of and) nearest ith column
- */
+ @Override
public int findPosition(int i)
{
int j = 0;
* @return int[SequenceI.getEnd()-SequenceI.getStart()+1] or null if no
* residues in SequenceI object
*/
+ @Override
public int[] gapMap()
{
String seq = jalview.analysis.AlignSeq.extractGaps(
return map;
}
- /*
- * (non-Javadoc)
- *
- * @see jalview.datamodel.SequenceI#findPositionMap()
- */
+
+ @Override
public int[] findPositionMap()
{
int map[] = new int[sequence.length];
}
return map;
}
- /*
- * (non-Javadoc)
- *
- * @see jalview.datamodel.SequenceI#deleteChars(int, int)
- */
- public void deleteChars(int i, int j)
+
+ @Override
+ public List<int[]> getInsertions()
{
- int newstart = start, newend = end;
- if (i >= sequence.length)
+ ArrayList<int[]> map = new ArrayList<int[]>();
+ int lastj = -1, j = 0;
+ int pos = start;
+ int seqlen = sequence.length;
+ while ((j < seqlen))
{
- return;
+ if (jalview.util.Comparison.isGap(sequence[j]))
+ {
+ if (lastj == -1)
+ {
+ lastj = j;
+ }
+ }
+ else
+ {
+ if (lastj != -1)
+ {
+ map.add(new int[] { lastj, j - 1 });
+ lastj = -1;
+ }
+ }
+ j++;
}
-
- char[] tmp;
-
- if (j >= sequence.length)
+ if (lastj != -1)
{
- tmp = new char[i];
- System.arraycopy(sequence, 0, tmp, 0, i);
+ map.add(new int[] { lastj, j - 1 });
+ lastj = -1;
}
- else
+ return map;
+ }
+
+ @Override
+ public void deleteChars(int i, int j)
+ {
+ int newstart = start, newend = end;
+ if (i >= sequence.length || i < 0)
{
- tmp = new char[sequence.length - j + i];
- System.arraycopy(sequence, 0, tmp, 0, i);
- System.arraycopy(sequence, j, tmp, i, sequence.length - j);
+ return;
}
+
+ char[] tmp = StringUtils.deleteChars(sequence, i, j);
boolean createNewDs = false;
+ // TODO: take a (second look) at the dataset creation validation method for
+ // the very large sequence case
+ int eindex = -1, sindex = -1;
+ boolean ecalc = false, scalc = false;
for (int s = i; s < j; s++)
{
if (jalview.schemes.ResidueProperties.aaIndex[sequence[s]] != 23)
}
else
{
- int sindex = findIndex(start) - 1;
+ if (!scalc)
+ {
+ sindex = findIndex(start) - 1;
+ scalc = true;
+ }
if (sindex == s)
{
// delete characters including start of sequence
else
{
// delete characters after start.
- int eindex = findIndex(end) - 1;
+ if (!ecalc)
+ {
+ eindex = findIndex(end) - 1;
+ ecalc = true;
+ }
if (eindex < j)
{
// delete characters at end of sequence
{
createNewDs = true;
newend--; // decrease end position by one for the deleted residue
- // and search further
+ // and search further
}
}
}
sequence = tmp;
}
- /**
- * DOCUMENT ME!
- *
- * @param i
- * DOCUMENT ME!
- * @param c
- * DOCUMENT ME!
- * @param chop
- * DOCUMENT ME!
- */
+ @Override
public void insertCharAt(int i, int length, char c)
{
char[] tmp = new char[sequence.length + length];
sequence = tmp;
}
+ @Override
public void insertCharAt(int i, char c)
{
insertCharAt(i, 1, c);
}
+ @Override
public String getVamsasId()
{
return vamsasId;
}
+ @Override
public void setVamsasId(String id)
{
vamsasId = id;
}
- public void setDBRef(DBRefEntry[] dbref)
+ @Override
+ public void setDBRefs(DBRefEntry[] dbref)
{
dbrefs = dbref;
}
- public DBRefEntry[] getDBRef()
+ @Override
+ public DBRefEntry[] getDBRefs()
{
- if (dbrefs==null && datasetSequence!=null && this!=datasetSequence)
+ if (dbrefs == null && datasetSequence != null
+ && this != datasetSequence)
{
- return datasetSequence.getDBRef();
+ return datasetSequence.getDBRefs();
}
return dbrefs;
}
+ @Override
public void addDBRef(DBRefEntry entry)
{
if (dbrefs == null)
dbrefs = temp;
}
+ @Override
public void setDatasetSequence(SequenceI seq)
{
datasetSequence = seq;
}
+ @Override
public SequenceI getDatasetSequence()
{
return datasetSequence;
}
+ @Override
public AlignmentAnnotation[] getAnnotation()
{
- if (annotation == null)
- {
- return null;
- }
-
- AlignmentAnnotation[] ret = new AlignmentAnnotation[annotation.size()];
- for (int r = 0; r < ret.length; r++)
- {
- ret[r] = (AlignmentAnnotation) annotation.elementAt(r);
- }
+ return annotation == null ? null : annotation
+ .toArray(new AlignmentAnnotation[annotation.size()]);
+ }
- return ret;
+ @Override
+ public boolean hasAnnotation(AlignmentAnnotation ann)
+ {
+ return annotation == null ? false : annotation.contains(ann);
}
+ @Override
public void addAlignmentAnnotation(AlignmentAnnotation annotation)
{
if (this.annotation == null)
{
- this.annotation = new Vector();
+ this.annotation = new Vector<AlignmentAnnotation>();
+ }
+ if (!this.annotation.contains(annotation))
+ {
+ this.annotation.addElement(annotation);
}
-
- this.annotation.addElement(annotation);
annotation.setSequenceRef(this);
}
+ @Override
public void removeAlignmentAnnotation(AlignmentAnnotation annotation)
{
if (this.annotation != null)
{
this.annotation.removeElement(annotation);
if (this.annotation.size() == 0)
+ {
this.annotation = null;
+ }
}
}
return true;
}
- /*
- * (non-Javadoc)
- *
- * @see jalview.datamodel.SequenceI#deriveSequence()
- */
+ @Override
public SequenceI deriveSequence()
{
SequenceI seq = new Sequence(this);
*
* @see jalview.datamodel.SequenceI#createDatasetSequence()
*/
+ @Override
public SequenceI createDatasetSequence()
{
if (datasetSequence == null)
datasetSequence.setDescription(getDescription());
setSequenceFeatures(null);
// move database references onto dataset sequence
- datasetSequence.setDBRef(getDBRef());
- setDBRef(null);
- datasetSequence.setPDBId(getPDBId());
+ datasetSequence.setDBRefs(getDBRefs());
+ setDBRefs(null);
+ datasetSequence.setPDBId(getAllPDBEntries());
setPDBId(null);
datasetSequence.updatePDBIds();
+ if (annotation != null)
+ {
+ for (AlignmentAnnotation aa : annotation)
+ {
+ AlignmentAnnotation _aa = new AlignmentAnnotation(aa);
+ _aa.sequenceRef = datasetSequence;
+ _aa.adjustForAlignment(); // uses annotation's own record of
+ // sequence-column mapping
+ datasetSequence.addAlignmentAnnotation(_aa);
+ }
+ }
}
return datasetSequence;
}
/*
* (non-Javadoc)
*
- * @see jalview.datamodel.SequenceI#setAlignmentAnnotation(AlignmmentAnnotation[]
- * annotations)
+ * @see
+ * jalview.datamodel.SequenceI#setAlignmentAnnotation(AlignmmentAnnotation[]
+ * annotations)
*/
+ @Override
public void setAlignmentAnnotation(AlignmentAnnotation[] annotations)
{
if (annotation != null)
for (int i = 0; i < annotations.length; i++)
{
if (annotations[i] != null)
+ {
addAlignmentAnnotation(annotations[i]);
+ }
}
}
}
- /*
- * (non-Javadoc)
- *
- * @see jalview.datamodel.SequenceI#getAnnotation(java.lang.String)
- */
+ @Override
public AlignmentAnnotation[] getAnnotation(String label)
{
if (annotation == null || annotation.size() == 0)
return anns;
}
+ @Override
public boolean updatePDBIds()
{
if (datasetSequence != null)
return false;
}
- /*
- * (non-Javadoc)
- *
- * @see jalview.datamodel.SequenceI#transferAnnotation(jalview.datamodel.SequenceI,
- * jalview.datamodel.Mapping)
- */
+ @Override
public void transferAnnotation(SequenceI entry, Mapping mp)
{
if (datasetSequence != null)
for (int si = 0; si < sfs.length; si++)
{
SequenceFeature sf[] = (mp != null) ? mp.locateFeature(sfs[si])
- : new SequenceFeature[]
- { new SequenceFeature(sfs[si]) };
+ : new SequenceFeature[] { new SequenceFeature(sfs[si]) };
if (sf != null && sf.length > 0)
{
for (int sfi = 0; sfi < sf.length; sfi++)
}
// transfer PDB entries
- if (entry.getPDBId() != null)
+ if (entry.getAllPDBEntries() != null)
{
- Enumeration e = entry.getPDBId().elements();
+ Enumeration e = entry.getAllPDBEntries().elements();
while (e.hasMoreElements())
{
PDBEntry pdb = (PDBEntry) e.nextElement();
}
}
// transfer database references
- DBRefEntry[] entryRefs = entry.getDBRef();
+ DBRefEntry[] entryRefs = entry.getDBRefs();
if (entryRefs != null)
{
for (int r = 0; r < entryRefs.length; r++)
}
}
+ /**
+ * @return The index (zero-based) on this sequence in the MSA. It returns
+ * {@code -1} if this information is not available.
+ */
+ @Override
+ public int getIndex()
+ {
+ return index;
+ }
+
+ /**
+ * Defines the position of this sequence in the MSA. Use the value {@code -1}
+ * if this information is undefined.
+ *
+ * @param The
+ * position for this sequence. This value is zero-based (zero for
+ * this first sequence)
+ */
+ @Override
+ public void setIndex(int value)
+ {
+ index = value;
+ }
+
+ @Override
+ public void setRNA(RNA r)
+ {
+ rna = r;
+ }
+
+ @Override
+ public RNA getRNA()
+ {
+ return rna;
+ }
+
+ @Override
+ public List<AlignmentAnnotation> getAlignmentAnnotations(String calcId,
+ String label)
+ {
+ List<AlignmentAnnotation> result = new ArrayList<AlignmentAnnotation>();
+ if (this.annotation != null)
+ {
+ for (AlignmentAnnotation ann : annotation)
+ {
+ if (ann.calcId != null && ann.calcId.equals(calcId)
+ && ann.label != null && ann.label.equals(label))
+ {
+ result.add(ann);
+ }
+ }
+ }
+ return result;
+ }
+
+ @Override
+ public String toString()
+ {
+ return getDisplayId(false);
+ }
+
+ @Override
+ public PDBEntry getPDBEntry(String pdbIdStr)
+ {
+ if (getDatasetSequence() == null
+ || getDatasetSequence().getAllPDBEntries() == null)
+ {
+ return null;
+ }
+ List<PDBEntry> entries = getDatasetSequence().getAllPDBEntries();
+ for (PDBEntry entry : entries)
+ {
+ if (entry.getId().equalsIgnoreCase(pdbIdStr))
+ {
+ return entry;
+ }
+ }
+ return null;
+ }
+
+ @Override
+ public void setSourceDBRef(DBRefEntryI dbRef)
+ {
+ this.sourceDBRef = dbRef;
+ }
+
+ @Override
+ public DBRefEntryI getSourceDBRef()
+ {
+ return this.sourceDBRef;
+ }
+
}