2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 package jalview.datamodel;
23 import jalview.datamodel.features.FeatureAttributeType;
24 import jalview.datamodel.features.FeatureAttributes;
25 import jalview.datamodel.features.FeatureLocationI;
26 import jalview.datamodel.features.FeatureSourceI;
27 import jalview.datamodel.features.FeatureSources;
28 import jalview.util.StringUtils;
30 import java.util.Comparator;
31 import java.util.HashMap;
33 import java.util.Map.Entry;
34 import java.util.SortedMap;
35 import java.util.TreeMap;
36 import java.util.Vector;
39 * A class that models a single contiguous feature on a sequence. If flag
40 * 'contactFeature' is true, the start and end positions are interpreted instead
41 * as two contact points.
43 public class SequenceFeature implements FeatureLocationI
46 * score value if none is set; preferably Float.Nan, but see
47 * JAL-2060 and JAL-2554 for a couple of blockers to that
49 private static final float NO_SCORE = 0f;
51 private static final String STATUS = "status";
53 private static final String STRAND = "STRAND";
55 // private key for Phase designed not to conflict with real GFF data
56 private static final String PHASE = "!Phase";
58 // private key for ENA location designed not to conflict with real GFF data
59 private static final String LOCATION = "!Location";
61 private static final String ROW_DATA = "<tr><td>%s</td><td>%s</td><td>%s</td></tr>";
64 * ATTRIBUTES is reserved for the GFF 'column 9' data, formatted as
65 * name1=value1;name2=value2,value3;...etc
67 private static final String ATTRIBUTES = "ATTRIBUTES";
70 * type, begin, end, featureGroup, score and contactFeature are final
71 * to ensure that the integrity of SequenceFeatures data store
72 * can't be broken by direct update of these fields
74 public final String type;
76 public final int begin;
80 public final String featureGroup;
82 public final float score;
84 private final boolean contactFeature;
86 public String description;
89 * a map of key-value pairs; may be populated from GFF 'column 9' data,
90 * other data sources (e.g. GenBank file), or programmatically
92 public Map<String, Object> otherDetails;
94 public Vector<String> links;
97 * the identifier (if known) for the FeatureSource held in FeatureSources,
98 * as a provider of metadata about feature attributes
100 private String source;
103 * Constructs a duplicate feature. Note: Uses makes a shallow copy of the
104 * otherDetails map, so the new and original SequenceFeature may reference the
105 * same objects in the map.
109 public SequenceFeature(SequenceFeature cpy)
111 this(cpy, cpy.getBegin(), cpy.getEnd(), cpy.getFeatureGroup(), cpy
124 public SequenceFeature(String theType, String theDesc, int theBegin,
125 int theEnd, String group)
127 this(theType, theDesc, theBegin, theEnd, NO_SCORE, group);
131 * Constructor including a score value
140 public SequenceFeature(String theType, String theDesc, int theBegin,
141 int theEnd, float theScore, String group)
144 this.description = theDesc;
145 this.begin = theBegin;
147 this.featureGroup = group;
148 this.score = theScore;
151 * for now, only "Disulfide/disulphide bond" is treated as a contact feature
153 this.contactFeature = "disulfide bond".equalsIgnoreCase(type)
154 || "disulphide bond".equalsIgnoreCase(type);
158 * A copy constructor that allows the value of final fields to be 'modified'
167 public SequenceFeature(SequenceFeature sf, String newType, int newBegin,
168 int newEnd, String newGroup, float newScore)
170 this(newType, sf.getDescription(), newBegin, newEnd, newScore,
173 this.source = sf.source;
175 if (sf.otherDetails != null)
177 otherDetails = new HashMap<>();
178 for (Entry<String, Object> entry : sf.otherDetails.entrySet())
180 otherDetails.put(entry.getKey(), entry.getValue());
183 if (sf.links != null && sf.links.size() > 0)
185 links = new Vector<>();
186 for (int i = 0, iSize = sf.links.size(); i < iSize; i++)
188 links.addElement(sf.links.elementAt(i));
194 * A copy constructor that allows the value of final fields to be 'modified'
202 public SequenceFeature(SequenceFeature sf, int newBegin, int newEnd,
203 String newGroup, float newScore)
205 this(sf, sf.getType(), newBegin, newEnd, newGroup, newScore);
209 * Two features are considered equal if they have the same type, group,
210 * description, start, end, phase, strand, and (if present) 'Name', ID' and
211 * 'Parent' attributes.
213 * Note we need to check Parent to distinguish the same exon occurring in
214 * different transcripts (in Ensembl GFF). This allows assembly of transcript
215 * sequences from their component exon regions.
218 public boolean equals(Object o)
220 return equals(o, false);
224 * Overloaded method allows the equality test to optionally ignore the
225 * 'Parent' attribute of a feature. This supports avoiding adding many
226 * superficially duplicate 'exon' or CDS features to genomic or protein
230 * @param ignoreParent
233 public boolean equals(Object o, boolean ignoreParent)
235 if (o == null || !(o instanceof SequenceFeature))
240 SequenceFeature sf = (SequenceFeature) o;
241 boolean sameScore = Float.isNaN(score) ? Float.isNaN(sf.score)
243 if (begin != sf.begin || end != sf.end || !sameScore)
248 if (getStrand() != sf.getStrand())
253 if (!(type + description + featureGroup + getPhase()).equals(
254 sf.type + sf.description + sf.featureGroup + sf.getPhase()))
258 if (!equalAttribute(getValue("ID"), sf.getValue("ID")))
262 if (!equalAttribute(getValue("Name"), sf.getValue("Name")))
268 if (!equalAttribute(getValue("Parent"), sf.getValue("Parent")))
277 * Returns true if both values are null, are both non-null and equal
283 protected static boolean equalAttribute(Object att1, Object att2)
285 if (att1 == null && att2 == null)
291 return att1.equals(att2);
293 return att2.equals(att1);
299 * @return DOCUMENT ME!
302 public int getBegin()
310 * @return DOCUMENT ME!
321 * @return DOCUMENT ME!
323 public String getType()
331 * @return DOCUMENT ME!
333 public String getDescription()
338 public void setDescription(String desc)
343 public String getFeatureGroup()
348 public void addLink(String labelLink)
352 links = new Vector<>();
355 if (!links.contains(labelLink))
357 links.insertElementAt(labelLink, 0);
361 public float getScore()
367 * Used for getting values which are not in the basic set. eg STRAND, PHASE
373 public Object getValue(String key)
375 if (otherDetails == null)
381 return otherDetails.get(key);
386 * Answers the value of the specified attribute as string, or null if no such
387 * value. If more than one attribute name is provided, tries to resolve as keys
388 * to nested maps. For example, if attribute "CSQ" holds a map of key-value
389 * pairs, then getValueAsString("CSQ", "Allele") returns the value of "Allele"
395 public String getValueAsString(String... key)
397 if (otherDetails == null)
401 Object value = otherDetails.get(key[0]);
402 if (key.length > 1 && value instanceof Map<?, ?>)
404 value = ((Map) value).get(key[1]);
406 return value == null ? null : value.toString();
410 * Returns a property value for the given key if known, else the specified
414 * @param defaultValue
417 public Object getValue(String key, Object defaultValue)
419 Object value = getValue(key);
420 return value == null ? defaultValue : value;
424 * Used for setting values which are not in the basic set. eg STRAND, FRAME
432 public void setValue(String key, Object value)
436 if (otherDetails == null)
438 otherDetails = new HashMap<>();
441 otherDetails.put(key, value);
442 recordAttribute(key, value);
447 * Notifies the addition of a feature attribute. This lets us keep track of
448 * which attributes are present on each feature type, and also the range of
449 * numerical-valued attributes.
454 protected void recordAttribute(String key, Object value)
456 String attDesc = null;
459 attDesc = FeatureSources.getInstance().getSource(source)
460 .getAttributeName(key);
463 FeatureAttributes.getInstance().addAttribute(this.type, attDesc, value,
468 * The following methods are added to maintain the castor Uniprot mapping file
471 public void setStatus(String status)
473 setValue(STATUS, status);
476 public String getStatus()
478 return (String) getValue(STATUS);
481 public void setAttributes(String attr)
483 setValue(ATTRIBUTES, attr);
486 public String getAttributes()
488 return (String) getValue(ATTRIBUTES);
492 * Return 1 for forward strand ('+' in GFF), -1 for reverse strand ('-' in
493 * GFF), and 0 for unknown or not (validly) specified
497 public int getStrand()
500 if (otherDetails != null)
502 Object str = otherDetails.get(STRAND);
507 else if ("+".equals(str))
516 * Set the value of strand
519 * should be "+" for forward, or "-" for reverse
521 public void setStrand(String strand)
523 setValue(STRAND, strand);
526 public void setPhase(String phase)
528 setValue(PHASE, phase);
531 public String getPhase()
533 return (String) getValue(PHASE);
537 * Sets the 'raw' ENA format location specifier e.g. join(12..45,89..121)
541 public void setEnaLocation(String loc)
543 setValue(LOCATION, loc);
547 * Gets the 'raw' ENA format location specifier e.g. join(12..45,89..121)
551 public String getEnaLocation()
553 return (String) getValue(LOCATION);
557 * Readable representation, for debug only, not guaranteed not to change
561 public String toString()
563 return String.format("%d %d %s %s", getBegin(), getEnd(), getType(),
568 * Overridden to ensure that whenever two objects are equal, they have the
572 public int hashCode()
574 String s = getType() + getDescription() + getFeatureGroup()
575 + getValue("ID") + getValue("Name") + getValue("Parent")
577 return s.hashCode() + getBegin() + getEnd() + (int) getScore()
582 * Answers true if the feature's start/end values represent two related
583 * positions, rather than ends of a range. Such features may be visualised or
584 * reported differently to features on a range.
587 public boolean isContactFeature()
589 return contactFeature;
593 * Answers true if the sequence has zero start and end position
597 public boolean isNonPositional()
599 return begin == 0 && end == 0;
603 * Answers an html-formatted report of feature details
607 public String getDetailsReport()
609 FeatureSourceI metadata = FeatureSources.getInstance()
612 StringBuilder sb = new StringBuilder(128);
614 sb.append("<table>");
615 sb.append(String.format(ROW_DATA, "Type", type, ""));
616 sb.append(String.format(ROW_DATA, "Start/end", begin == end ? begin
617 : begin + (isContactFeature() ? ":" : "-") + end, ""));
618 String desc = StringUtils.stripHtmlTags(description);
619 sb.append(String.format(ROW_DATA, "Description", desc, ""));
620 if (!Float.isNaN(score) && score != 0f)
622 sb.append(String.format(ROW_DATA, "Score", score, ""));
624 if (featureGroup != null)
626 sb.append(String.format(ROW_DATA, "Group", featureGroup, ""));
629 if (otherDetails != null)
631 TreeMap<String, Object> ordered = new TreeMap<>(
632 String.CASE_INSENSITIVE_ORDER);
633 ordered.putAll(otherDetails);
635 for (Entry<String, Object> entry : ordered.entrySet())
637 String key = entry.getKey();
638 if (ATTRIBUTES.equals(key))
640 continue; // to avoid double reporting
643 Object value = entry.getValue();
644 if (value instanceof Map<?, ?>)
647 * expand values in a Map attribute across separate lines
648 * copy to a TreeMap for alphabetical ordering
650 Map<String, Object> values = (Map<String, Object>) value;
651 SortedMap<String, Object> sm = new TreeMap<>(
652 String.CASE_INSENSITIVE_ORDER);
654 for (Entry<?, ?> e : sm.entrySet())
656 sb.append(String.format(ROW_DATA, key, e.getKey().toString(), e
657 .getValue().toString()));
662 // tried <td title="key"> but it failed to provide a tooltip :-(
663 String attDesc = null;
664 if (metadata != null)
666 attDesc = metadata.getAttributeName(key);
668 String s = entry.getValue().toString();
669 if (isValueInteresting(key, s, metadata))
671 sb.append(String.format(ROW_DATA, key, attDesc == null ? ""
677 sb.append("</table>");
679 String text = sb.toString();
684 * Answers true if we judge the value is worth displaying, by some heuristic
692 boolean isValueInteresting(String key, String value,
693 FeatureSourceI metadata)
696 * currently suppressing zero values as well as null or empty
698 if (value == null || "".equals(value) || ".".equals(value)
699 || "0".equals(value))
704 if (metadata == null)
709 FeatureAttributeType attType = metadata.getAttributeType(key);
711 && (attType == FeatureAttributeType.Float || attType
712 .equals(FeatureAttributeType.Integer)))
716 float fval = Float.valueOf(value);
721 } catch (NumberFormatException e)
727 return true; // default to interesting
731 * Sets the feature source identifier
735 public void setSource(String theSource)
741 class SFSortByEnd implements Comparator<SequenceFeature>
744 public int compare(SequenceFeature a, SequenceFeature b)
746 return a.getEnd() - b.getEnd();
750 class SFSortByBegin implements Comparator<SequenceFeature>
753 public int compare(SequenceFeature a, SequenceFeature b)
755 return a.getBegin() - b.getBegin();