/*
* 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.
*
* 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 .
* The Jalview Authors are detailed in the 'AUTHORS' file.
*/
package jalview.datamodel;
import jalview.datamodel.features.FeatureLocationI;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Vector;
/**
* DOCUMENT ME!
*
* @author $author$
* @version $Revision$
*/
public class SequenceFeature implements FeatureLocationI
{
/*
* score value if none is set; preferably Float.Nan, but see
* JAL-2060 and JAL-2554 for a couple of blockers to that
*/
private static final float NO_SCORE = 0f;
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";
/*
* type, begin, end, featureGroup, score and contactFeature are final
* to ensure that the integrity of SequenceFeatures data store
* can't be broken by direct update of these fields
*/
public final String type;
public final int begin;
public final int end;
public final String featureGroup;
public final float score;
private final boolean contactFeature;
public String description;
/*
* 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 Vector links;
/**
* 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
*/
public SequenceFeature(SequenceFeature cpy)
{
this(cpy, cpy.getBegin(), cpy.getEnd(), cpy.getFeatureGroup(), cpy
.getScore());
}
/**
* Constructor
*
* @param theType
* @param theDesc
* @param theBegin
* @param theEnd
* @param group
*/
public SequenceFeature(String theType, String theDesc, int theBegin,
int theEnd, String group)
{
this(theType, theDesc, theBegin, theEnd, NO_SCORE, group);
}
/**
* Constructor including a score value
*
* @param theType
* @param theDesc
* @param theBegin
* @param theEnd
* @param theScore
* @param group
*/
public SequenceFeature(String theType, String theDesc, int theBegin,
int theEnd, float theScore, String group)
{
this.type = theType;
this.description = theDesc;
this.begin = theBegin;
this.end = theEnd;
this.featureGroup = group;
this.score = theScore;
/*
* for now, only "Disulfide/disulphide bond" is treated as a contact feature
*/
this.contactFeature = "disulfide bond".equalsIgnoreCase(type)
|| "disulphide bond".equalsIgnoreCase(type);
}
/**
* A copy constructor that allows the value of final fields to be 'modified'
*
* @param sf
* @param newType
* @param newBegin
* @param newEnd
* @param newGroup
* @param newScore
*/
public SequenceFeature(SequenceFeature sf, String newType, int newBegin,
int newEnd, String newGroup, float newScore)
{
this(newType, sf.getDescription(), newBegin, newEnd, newScore,
newGroup);
if (sf.otherDetails != null)
{
otherDetails = new HashMap();
for (Entry entry : sf.otherDetails.entrySet())
{
otherDetails.put(entry.getKey(), entry.getValue());
}
}
if (sf.links != null && sf.links.size() > 0)
{
links = new Vector();
for (int i = 0, iSize = sf.links.size(); i < iSize; i++)
{
links.addElement(sf.links.elementAt(i));
}
}
}
/**
* A copy constructor that allows the value of final fields to be 'modified'
*
* @param sf
* @param newBegin
* @param newEnd
* @param newGroup
* @param newScore
*/
public SequenceFeature(SequenceFeature sf, int newBegin, int newEnd,
String newGroup, float newScore)
{
this(sf, sf.getType(), newBegin, newEnd, newGroup, newScore);
}
/**
* 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 (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 (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;
}
/**
* DOCUMENT ME!
*
* @return DOCUMENT ME!
*/
@Override
public int getEnd()
{
return end;
}
/**
* DOCUMENT ME!
*
* @return DOCUMENT ME!
*/
public String getType()
{
return type;
}
/**
* DOCUMENT ME!
*
* @return DOCUMENT ME!
*/
public String getDescription()
{
return description;
}
public void setDescription(String desc)
{
description = desc;
}
public String getFeatureGroup()
{
return featureGroup;
}
public void addLink(String labelLink)
{
if (links == null)
{
links = new Vector();
}
if (!links.contains(labelLink))
{
links.insertElementAt(labelLink, 0);
}
}
public float getScore()
{
return score;
}
/**
* Used for getting values which are not in the basic set. eg STRAND, PHASE
* for GFF file
*
* @param key
* String
*/
public Object getValue(String key)
{
if (otherDetails == null)
{
return null;
}
else
{
return otherDetails.get(key);
}
}
/**
* 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
*
* @param key
* eg STRAND
* @param value
* eg +
*/
public void setValue(String key, Object value)
{
if (value != null)
{
if (otherDetails == null)
{
otherDetails = new HashMap();
}
otherDetails.put(key, value);
}
}
/*
* The following methods are added to maintain the castor Uniprot mapping file
* for the moment.
*/
public void setStatus(String status)
{
setValue(STATUS, status);
}
public String getStatus()
{
return (String) getValue(STATUS);
}
public void setAttributes(String attr)
{
setValue(ATTRIBUTES, attr);
}
public String getAttributes()
{
return (String) getValue(ATTRIBUTES);
}
/**
* 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()
{
return contactFeature;
}
/**
* Answers true if the sequence has zero start and end position
*
* @return
*/
public boolean isNonPositional()
{
return begin == 0 && end == 0;
}
}