X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequenceI.java;h=163a4a043fe239144a5092a9e1329aefa35fac74;hb=480d7b96f089281a3caf77d2a4e5adec09dc5bfa;hp=57d25690511e4f037ac598fc33ec9ac96798eb68;hpb=28787d9646cca5dd77190930f59b7ff32cf995b4;p=jalview.git
diff --git a/src/jalview/datamodel/SequenceI.java b/src/jalview/datamodel/SequenceI.java
index 57d2569..163a4a0 100755
--- a/src/jalview/datamodel/SequenceI.java
+++ b/src/jalview/datamodel/SequenceI.java
@@ -1,34 +1,40 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
- * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, 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 jalview.datamodel.features.SequenceFeaturesI;
+import java.util.List;
import java.util.Vector;
import fr.orsay.lri.varna.models.rna.RNA;
/**
- * DOCUMENT ME!
+ * Methods for manipulating a sequence, its metadata and related annotation in
+ * an alignment or dataset.
*
* @author $author$
* @version $Revision$
*/
-public interface SequenceI
+public interface SequenceI extends ASequenceI
{
/**
* Set the display name for the sequence
@@ -100,21 +106,21 @@ public interface SequenceI
public String getSequenceAsString();
/**
- * get a range on the seuqence as a string
+ * get a range on the sequence as a string
*
* @param start
- * DOCUMENT ME!
+ * position relative to start of sequence including gaps (from 0)
* @param end
- * DOCUMENT ME!
+ * position relative to start of sequence including gaps (from 0)
*
- * @return DOCUMENT ME!
+ * @return String containing all gap and symbols in specified range
*/
public String getSequenceAsString(int start, int end);
/**
- * DOCUMENT ME!
+ * Get the sequence as a character array
*
- * @return DOCUMENT ME!
+ * @return seqeunce and any gaps
*/
public char[] getSequence();
@@ -131,23 +137,26 @@ public interface SequenceI
public char[] getSequence(int start, int end);
/**
- * create a new sequence object from start to end of this sequence
+ * create a new sequence object with a subsequence of this one but sharing the
+ * same dataset sequence
*
* @param start
- * int
+ * int index for start position (base 0, inclusive)
* @param end
- * int
+ * int index for end position (base 0, exclusive)
+ *
* @return SequenceI
+ * @note implementations may use getSequence to get the sequence data
*/
public SequenceI getSubSequence(int start, int end);
/**
- * DOCUMENT ME!
+ * get the i'th character in this sequence's local reference frame (ie from
+ * 0-number of characters lying from start-end)
*
* @param i
- * DOCUMENT ME!
- *
- * @return DOCUMENT ME!
+ * index
+ * @return character or ' '
*/
public char getCharAt(int i);
@@ -167,8 +176,7 @@ public interface SequenceI
public String getDescription();
/**
- * Return the alignment column for a sequence position * Return the alignment
- * position for a sequence position
+ * Return the alignment column (from 1..) for a sequence position
*
* @param pos
* lying from start to end
@@ -186,13 +194,37 @@ public interface SequenceI
* Returns the sequence position for an alignment position
*
* @param i
- * column index in alignment (from 1)
+ * column index in alignment (from 0..
+ * Example:
+ * >Seq/8-13
+ * ABC--DE-F
+ * findPositions(1, 4) returns Range(9, 9) // B only
+ * findPositions(3, 4) returns null // all gaps
+ * findPositions(2, 6) returns Range(10, 12) // CDE
+ * findPositions(3, 7) returns Range(11,12) // DE
+ *
+ *
+ * @param fromCol
+ * first aligned column position (base 0, inclusive)
+ * @param toCol
+ * last aligned column position (base 0, inclusive)
+ *
+ * @return
+ */
+ public Range findPositions(int fromCol, int toCol);
+
+ /**
* Returns an int array where indices correspond to each residue in the
* sequence and the element value gives its position in the alignment
*
@@ -211,13 +243,22 @@ public interface SequenceI
public int[] findPositionMap();
/**
+ * Answers true if the sequence is composed of amino acid characters. Note
+ * that implementations may use heuristic methods which are not guaranteed to
+ * give the biologically 'right' answer.
+ *
+ * @return
+ */
+ public boolean isProtein();
+
+ /**
* Delete a range of aligned sequence columns, creating a new dataset sequence
* if necessary and adjusting start and end positions accordingly.
*
* @param i
- * first column in range to delete
+ * first column in range to delete (inclusive)
* @param j
- * last column in range to delete
+ * last column in range to delete (exclusive)
*/
public void deleteChars(int i, int j);
@@ -225,36 +266,47 @@ public interface SequenceI
* DOCUMENT ME!
*
* @param i
- * DOCUMENT ME!
+ * alignment column number
* @param c
- * DOCUMENT ME!
+ * character to insert
*/
public void insertCharAt(int i, char c);
/**
- * DOCUMENT ME!
+ * insert given character at alignment column position
*
- * @param i
- * DOCUMENT ME!
- * @param c
- * DOCUMENT ME!
+ * @param position
+ * alignment column number
+ * @param count
+ * length of insert
+ * @param ch
+ * character to insert
*/
- public void insertCharAt(int i, int length, char c);
+ public void insertCharAt(int position, int count, char ch);
/**
- * DOCUMENT ME!
+ * Answers a list of all sequence features associated with this sequence. The
+ * list may be held by the sequence's dataset sequence if that is defined.
*
- * @return DOCUMENT ME!
+ * @return hard reference to array
*/
- public SequenceFeature[] getSequenceFeatures();
+ public List getSequenceFeatures();
/**
- * DOCUMENT ME!
+ * Answers the object holding features for the sequence
*
- * @param v
- * DOCUMENT ME!
+ * @return
+ */
+ SequenceFeaturesI getFeatures();
+
+ /**
+ * Replaces the sequence features associated with this sequence with the given
+ * features. If this sequence has a dataset sequence, then this method will
+ * update the dataset sequence's features instead.
+ *
+ * @param features
*/
- public void setSequenceFeatures(SequenceFeature[] features);
+ public void setSequenceFeatures(List features);
/**
* DOCUMENT ME!
@@ -262,21 +314,28 @@ public interface SequenceI
* @param id
* DOCUMENT ME!
*/
- public void setPDBId(Vector ids);
+ public void setPDBId(Vector ids);
/**
- * DOCUMENT ME!
+ * Returns a list
*
* @return DOCUMENT ME!
*/
- public Vector getPDBId();
+ public Vector getAllPDBEntries();
/**
- * add entry to the vector of PDBIds, if it isn't in the list already
+ * Adds the entry to the *normalised* list of PDBIds.
+ *
+ * If a PDBEntry is passed with the same entry.getID() string as one already
+ * in the list, or one is added that appears to be the same but has a chain ID
+ * appended, then the existing PDBEntry will be updated with the new
+ * attributes instead, unless the entries have distinct chain codes or
+ * associated structure files.
*
* @param entry
+ * @return true if the entry was added, false if updated
*/
- public void addPDBId(PDBEntry entry);
+ public boolean addPDBId(PDBEntry entry);
/**
* update the list of PDBEntrys to include any DBRefEntrys citing structural
@@ -290,9 +349,17 @@ public interface SequenceI
public void setVamsasId(String id);
- public void setDBRef(DBRefEntry[] dbs);
+ /**
+ * set the array of Database references for the sequence.
+ *
+ * @param dbs
+ * @deprecated - use is discouraged since side-effects may occur if DBRefEntry
+ * set are not normalised.
+ */
+ @Deprecated
+ public void setDBRefs(DBRefEntry[] dbs);
- public DBRefEntry[] getDBRef();
+ public DBRefEntry[] getDBRefs();
/**
* add the given entry to the list of DBRefs for this sequence, or replace a
@@ -302,7 +369,14 @@ public interface SequenceI
*/
public void addDBRef(DBRefEntry entry);
- public void addSequenceFeature(SequenceFeature sf);
+ /**
+ * Adds the given sequence feature and returns true, or returns false if it is
+ * already present on the sequence, or if the feature type is null.
+ *
+ * @param sf
+ * @return
+ */
+ public boolean addSequenceFeature(SequenceFeature sf);
public void deleteFeature(SequenceFeature sf);
@@ -310,8 +384,22 @@ public interface SequenceI
public SequenceI getDatasetSequence();
+ /**
+ * Returns a new array containing this sequence's annotations, or null.
+ */
public AlignmentAnnotation[] getAnnotation();
+ /**
+ * Returns true if this sequence has the given annotation (by object
+ * identity).
+ */
+ public boolean hasAnnotation(AlignmentAnnotation ann);
+
+ /**
+ * Add the given annotation, if not already added, and set its sequence ref to
+ * be this sequence. Does nothing if this sequence's annotations already
+ * include this annotation (by identical object reference).
+ */
public void addAlignmentAnnotation(AlignmentAnnotation annotation);
public void removeAlignmentAnnotation(AlignmentAnnotation annotation);
@@ -340,9 +428,21 @@ public interface SequenceI
public AlignmentAnnotation[] getAnnotation(String label);
/**
+ * Returns a (possibly empty) list of any annotations that match on given
+ * calcId (source) and label (type). Null values do not match.
+ *
+ * @param calcId
+ * @param label
+ */
+ public List getAlignmentAnnotations(String calcId,
+ String label);
+
+ /**
* create a new dataset sequence (if necessary) for this sequence and sets
* this sequence to refer to it. This call will move any features or
- * references on the sequence onto the dataset.
+ * references on the sequence onto the dataset. It will also make a duplicate
+ * of existing annotation rows for the dataset sequence, rather than relocate
+ * them in order to preserve external references (since 2.8.2).
*
* @return dataset sequence for this sequence
*/
@@ -350,7 +450,9 @@ public interface SequenceI
/**
* Transfer any database references or annotation from entry under a sequence
- * mapping.
+ * mapping.
+ * Note: DOES NOT transfer sequence associated alignment annotation
+ *
*
* @param entry
* @param mp
@@ -368,17 +470,53 @@ public interface SequenceI
* @return The index of the sequence in the alignment
*/
public int getIndex();
-
+
/**
* @return The RNA of the sequence in the alignment
*/
-
+
public RNA getRNA();
-
+
/**
- * @param rna The RNA.
+ * @param rna
+ * The RNA.
*/
public void setRNA(RNA rna);
-
+ /**
+ *
+ * @return list of insertions (gap characters) in sequence
+ */
+ public List getInsertions();
+
+ /**
+ * Given a pdbId String, return the equivalent PDBEntry if available in the
+ * given sequence
+ *
+ * @param pdbId
+ * @return
+ */
+ public PDBEntry getPDBEntry(String pdbId);
+
+ /**
+ * Get all primary database/accessions for this sequence's data. These
+ * DBRefEntry are expected to resolve to a valid record in the associated
+ * external database, either directly or via a provided 1:1 Mapping.
+ *
+ * @return just the primary references (if any) for this sequence, or an empty
+ * list
+ */
+ public List getPrimaryDBRefs();
+
+ /**
+ * Returns a (possibly empty) list of sequence features that overlap the range
+ * from-to (inclusive), optionally restricted to one or more specified feature
+ * types
+ *
+ * @param from
+ * @param to
+ * @param types
+ * @return
+ */
+ List findFeatures(int from, int to, String... types);
}