X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FSequenceFeature.java;h=8eacb68d1c7eb1822b171d6f6b3acb6f191a386b;hb=3917b8cc08f85090d44dfa599c715a2ec7ef5b41;hp=61748c94e593a4e98139b16494443166ff89738e;hpb=59d682209891099d46b960509907c79e3fb276fe;p=jalview.git
diff --git a/src/jalview/datamodel/SequenceFeature.java b/src/jalview/datamodel/SequenceFeature.java
index 61748c9..8eacb68 100755
--- a/src/jalview/datamodel/SequenceFeature.java
+++ b/src/jalview/datamodel/SequenceFeature.java
@@ -1,23 +1,30 @@
/*
- * 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 java.util.*;
+import jalview.datamodel.features.FeatureLocationI;
+
+import java.util.HashMap;
+import java.util.Map;
+import java.util.Vector;
/**
* DOCUMENT ME!
@@ -25,8 +32,24 @@ import java.util.*;
* @author $author$
* @version $Revision$
*/
-public class SequenceFeature
+public class SequenceFeature implements FeatureLocationI
{
+ private static final String STATUS = "status";
+
+ private static final String STRAND = "STRAND";
+
+ // private key for Phase designed not to conflict with real GFF data
+ private static final String PHASE = "!Phase";
+
+ // private key for ENA location designed not to conflict with real GFF data
+ private static final String LOCATION = "!Location";
+
+ /*
+ * ATTRIBUTES is reserved for the GFF 'column 9' data, formatted as
+ * name1=value1;name2=value2,value3;...etc
+ */
+ private static final String ATTRIBUTES = "ATTRIBUTES";
+
public int begin;
public int end;
@@ -37,9 +60,13 @@ public class SequenceFeature
public String description;
- public Hashtable otherDetails;
+ /*
+ * a map of key-value pairs; may be populated from GFF 'column 9' data,
+ * other data sources (e.g. GenBank file), or programmatically
+ */
+ public Map otherDetails;
- public java.util.Vector links;
+ public Vector links;
// Feature group can be set from a features file
// as a group of features between STARTGROUP and ENDGROUP markers
@@ -50,9 +77,9 @@ public class SequenceFeature
}
/**
- * Constructs a duplicate feature. Note: Uses clone on the otherDetails so
- * only shallow copies are made of additional properties and method will
- * silently fail if unclonable objects are found in the hash.
+ * Constructs a duplicate feature. Note: Uses makes a shallow copy of the
+ * otherDetails map, so the new and original SequenceFeature may reference the
+ * same objects in the map.
*
* @param cpy
*/
@@ -79,15 +106,16 @@ public class SequenceFeature
{
try
{
- otherDetails = (Hashtable) cpy.otherDetails.clone();
+ otherDetails = (Map) ((HashMap) cpy.otherDetails)
+ .clone();
} catch (Exception e)
{
- // Uncloneable objects in the otherDetails - don't complain
+ // ignore
}
}
if (cpy.links != null && cpy.links.size() > 0)
{
- links = new Vector();
+ links = new Vector();
for (int i = 0, iSize = cpy.links.size(); i < iSize; i++)
{
links.addElement(cpy.links.elementAt(i));
@@ -96,49 +124,153 @@ public class SequenceFeature
}
}
+ /**
+ * Constructor including a Status value
+ *
+ * @param type
+ * @param desc
+ * @param status
+ * @param begin
+ * @param end
+ * @param featureGroup
+ */
public SequenceFeature(String type, String desc, String status,
int begin, int end, String featureGroup)
{
+ this(type, desc, begin, end, featureGroup);
+ setStatus(status);
+ }
+
+ /**
+ * Constructor
+ *
+ * @param type
+ * @param desc
+ * @param begin
+ * @param end
+ * @param featureGroup
+ */
+ SequenceFeature(String type, String desc, int begin, int end,
+ String featureGroup)
+ {
this.type = type;
this.description = desc;
- setValue("status", status);
this.begin = begin;
this.end = end;
this.featureGroup = featureGroup;
}
+ /**
+ * Constructor including a score value
+ *
+ * @param type
+ * @param desc
+ * @param begin
+ * @param end
+ * @param score
+ * @param featureGroup
+ */
public SequenceFeature(String type, String desc, int begin, int end,
float score, String featureGroup)
{
- this.type = type;
- this.description = desc;
- this.begin = begin;
- this.end = end;
+ this(type, desc, begin, end, featureGroup);
this.score = score;
- this.featureGroup = featureGroup;
}
- public boolean equals(SequenceFeature sf)
+ /**
+ * Two features are considered equal if they have the same type, group,
+ * description, start, end, phase, strand, and (if present) 'Name', ID' and
+ * 'Parent' attributes.
+ *
+ * Note we need to check Parent to distinguish the same exon occurring in
+ * different transcripts (in Ensembl GFF). This allows assembly of transcript
+ * sequences from their component exon regions.
+ */
+ @Override
+ public boolean equals(Object o)
+ {
+ return equals(o, false);
+ }
+
+ /**
+ * Overloaded method allows the equality test to optionally ignore the
+ * 'Parent' attribute of a feature. This supports avoiding adding many
+ * superficially duplicate 'exon' or CDS features to genomic or protein
+ * sequence.
+ *
+ * @param o
+ * @param ignoreParent
+ * @return
+ */
+ public boolean equals(Object o, boolean ignoreParent)
{
- if (begin != sf.begin || end != sf.end || score != sf.score)
+ if (o == null || !(o instanceof SequenceFeature))
+ {
+ return false;
+ }
+
+ SequenceFeature sf = (SequenceFeature) o;
+ boolean sameScore = Float.isNaN(score) ? Float.isNaN(sf.score)
+ : score == sf.score;
+ if (begin != sf.begin || end != sf.end || !sameScore)
{
return false;
}
- if (!(type + description + featureGroup).equals(sf.type
- + sf.description + sf.featureGroup))
+ if (getStrand() != sf.getStrand())
{
return false;
}
+ if (!(type + description + featureGroup + getPhase()).equals(sf.type
+ + sf.description + sf.featureGroup + sf.getPhase()))
+ {
+ return false;
+ }
+ if (!equalAttribute(getValue("ID"), sf.getValue("ID")))
+ {
+ return false;
+ }
+ if (!equalAttribute(getValue("Name"), sf.getValue("Name")))
+ {
+ return false;
+ }
+ if (!ignoreParent)
+ {
+ if (!equalAttribute(getValue("Parent"), sf.getValue("Parent")))
+ {
+ return false;
+ }
+ }
return true;
}
/**
+ * Returns true if both values are null, are both non-null and equal
+ *
+ * @param att1
+ * @param att2
+ * @return
+ */
+ protected static boolean equalAttribute(Object att1, Object att2)
+ {
+ if (att1 == null && att2 == null)
+ {
+ return true;
+ }
+ if (att1 != null)
+ {
+ return att1.equals(att2);
+ }
+ return att2.equals(att1);
+ }
+
+ /**
* DOCUMENT ME!
*
* @return DOCUMENT ME!
*/
+ @Override
public int getBegin()
{
return begin;
@@ -154,6 +286,7 @@ public class SequenceFeature
*
* @return DOCUMENT ME!
*/
+ @Override
public int getEnd()
{
return end;
@@ -208,10 +341,13 @@ public class SequenceFeature
{
if (links == null)
{
- links = new java.util.Vector();
+ links = new Vector();
}
- links.insertElementAt(labelLink, 0);
+ if (!links.contains(labelLink))
+ {
+ links.insertElementAt(labelLink, 0);
+ }
}
public float getScore()
@@ -225,7 +361,7 @@ public class SequenceFeature
}
/**
- * Used for getting values which are not in the basic set. eg STRAND, FRAME
+ * Used for getting values which are not in the basic set. eg STRAND, PHASE
* for GFF file
*
* @param key
@@ -244,6 +380,20 @@ public class SequenceFeature
}
/**
+ * Returns a property value for the given key if known, else the specified
+ * default value
+ *
+ * @param key
+ * @param defaultValue
+ * @return
+ */
+ public Object getValue(String key, Object defaultValue)
+ {
+ Object value = getValue(key);
+ return value == null ? defaultValue : value;
+ }
+
+ /**
* Used for setting values which are not in the basic set. eg STRAND, FRAME
* for GFF file
*
@@ -258,7 +408,7 @@ public class SequenceFeature
{
if (otherDetails == null)
{
- otherDetails = new Hashtable();
+ otherDetails = new HashMap();
}
otherDetails.put(key, value);
@@ -271,18 +421,22 @@ public class SequenceFeature
*/
public void setStatus(String status)
{
- setValue("status", status);
+ setValue(STATUS, status);
}
public String getStatus()
{
- if (otherDetails != null)
- {
- String stat = (String) otherDetails.get("status");
- if (stat != null)
- return new String(stat);
- }
- return null;
+ return (String) getValue(STATUS);
+ }
+
+ public void setAttributes(String attr)
+ {
+ setValue(ATTRIBUTES, attr);
+ }
+
+ public String getAttributes()
+ {
+ return (String) getValue(ATTRIBUTES);
}
public void setPosition(int pos)
@@ -296,4 +450,120 @@ public class SequenceFeature
return begin;
}
+ /**
+ * Return 1 for forward strand ('+' in GFF), -1 for reverse strand ('-' in
+ * GFF), and 0 for unknown or not (validly) specified
+ *
+ * @return
+ */
+ public int getStrand()
+ {
+ int strand = 0;
+ if (otherDetails != null)
+ {
+ Object str = otherDetails.get(STRAND);
+ if ("-".equals(str))
+ {
+ strand = -1;
+ }
+ else if ("+".equals(str))
+ {
+ strand = 1;
+ }
+ }
+ return strand;
+ }
+
+ /**
+ * Set the value of strand
+ *
+ * @param strand
+ * should be "+" for forward, or "-" for reverse
+ */
+ public void setStrand(String strand)
+ {
+ setValue(STRAND, strand);
+ }
+
+ public void setPhase(String phase)
+ {
+ setValue(PHASE, phase);
+ }
+
+ public String getPhase()
+ {
+ return (String) getValue(PHASE);
+ }
+
+ /**
+ * Sets the 'raw' ENA format location specifier e.g. join(12..45,89..121)
+ *
+ * @param loc
+ */
+ public void setEnaLocation(String loc)
+ {
+ setValue(LOCATION, loc);
+ }
+
+ /**
+ * Gets the 'raw' ENA format location specifier e.g. join(12..45,89..121)
+ *
+ * @param loc
+ */
+ public String getEnaLocation()
+ {
+ return (String) getValue(LOCATION);
+ }
+
+ /**
+ * Readable representation, for debug only, not guaranteed not to change
+ * between versions
+ */
+ @Override
+ public String toString()
+ {
+ return String.format("%d %d %s %s", getBegin(), getEnd(), getType(),
+ getDescription());
+ }
+
+ /**
+ * Overridden to ensure that whenever two objects are equal, they have the
+ * same hashCode
+ */
+ @Override
+ public int hashCode()
+ {
+ String s = getType() + getDescription() + getFeatureGroup()
+ + getValue("ID") + getValue("Name") + getValue("Parent")
+ + getPhase();
+ return s.hashCode() + getBegin() + getEnd() + (int) getScore()
+ + getStrand();
+ }
+
+ /**
+ * Answers true if the feature's start/end values represent two related
+ * positions, rather than ends of a range. Such features may be visualised or
+ * reported differently to features on a range.
+ */
+ @Override
+ public boolean isContactFeature()
+ {
+ // TODO abstract one day to a FeatureType class
+ if ("disulfide bond".equalsIgnoreCase(type)
+ || "disulphide bond".equalsIgnoreCase(type))
+ {
+ return true;
+ }
+ return false;
+ }
+
+ /**
+ * Answers true if the sequence has zero start and end position
+ *
+ * @return
+ */
+ public boolean isNonPositional()
+ {
+ return begin == 0 && end == 0;
+ }
}