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 (o instanceof SequenceFeature
221 && equals((SequenceFeature) o, false));
225 * Overloaded method allows the equality test to optionally ignore the
226 * 'Parent' attribute of a feature. This supports avoiding adding many
227 * superficially duplicate 'exon' or CDS features to genomic or protein
231 * @param ignoreParent
234 public boolean equals(SequenceFeature sf, boolean ignoreParent)
236 return (begin == sf.begin && end == sf.end
237 && getStrand() == sf.getStrand()
238 && (Float.isNaN(score) ? Float.isNaN(sf.score)
240 && (type + description + featureGroup + getPhase())
241 .equals(sf.type + sf.description + sf.featureGroup
243 && equalAttribute(getValue("ID"), sf.getValue("ID"))
244 && equalAttribute(getValue("Name"), sf.getValue("Name"))
245 && (ignoreParent || equalAttribute(getValue("Parent"),
246 sf.getValue("Parent"))));
250 * Returns true if both values are null, are both non-null and equal
256 protected static boolean equalAttribute(Object att1, Object att2)
258 if (att1 == null && att2 == null)
264 return att1.equals(att2);
266 return att2.equals(att1);
272 * @return DOCUMENT ME!
275 public int getBegin()
283 * @return DOCUMENT ME!
294 * @return DOCUMENT ME!
296 public String getType()
304 * @return DOCUMENT ME!
306 public String getDescription()
311 public void setDescription(String desc)
316 public String getFeatureGroup()
321 public void addLink(String labelLink)
325 links = new Vector<>();
328 if (!links.contains(labelLink))
330 links.insertElementAt(labelLink, 0);
334 public float getScore()
340 * Used for getting values which are not in the basic set. eg STRAND, PHASE
346 public Object getValue(String key)
348 if (otherDetails == null)
354 return otherDetails.get(key);
359 * Answers the value of the specified attribute as string, or null if no such
360 * value. If more than one attribute name is provided, tries to resolve as keys
361 * to nested maps. For example, if attribute "CSQ" holds a map of key-value
362 * pairs, then getValueAsString("CSQ", "Allele") returns the value of "Allele"
368 public String getValueAsString(String... key)
370 if (otherDetails == null)
374 Object value = otherDetails.get(key[0]);
375 if (key.length > 1 && value instanceof Map<?, ?>)
377 value = ((Map) value).get(key[1]);
379 return value == null ? null : value.toString();
383 * Returns a property value for the given key if known, else the specified
387 * @param defaultValue
390 public Object getValue(String key, Object defaultValue)
392 Object value = getValue(key);
393 return value == null ? defaultValue : value;
397 * Used for setting values which are not in the basic set. eg STRAND, FRAME
405 public void setValue(String key, Object value)
409 if (otherDetails == null)
411 otherDetails = new HashMap<>();
414 otherDetails.put(key, value);
415 recordAttribute(key, value);
420 * Notifies the addition of a feature attribute. This lets us keep track of
421 * which attributes are present on each feature type, and also the range of
422 * numerical-valued attributes.
427 protected void recordAttribute(String key, Object value)
429 String attDesc = null;
432 attDesc = FeatureSources.getInstance().getSource(source)
433 .getAttributeName(key);
436 FeatureAttributes.getInstance().addAttribute(this.type, attDesc, value,
441 * The following methods are added to maintain the castor Uniprot mapping file
444 public void setStatus(String status)
446 setValue(STATUS, status);
449 public String getStatus()
451 return (String) getValue(STATUS);
454 public void setAttributes(String attr)
456 setValue(ATTRIBUTES, attr);
459 public String getAttributes()
461 return (String) getValue(ATTRIBUTES);
465 * Return 1 for forward strand ('+' in GFF), -1 for reverse strand ('-' in
466 * GFF), and 0 for unknown or not (validly) specified
470 public int getStrand()
473 if (otherDetails != null)
475 Object str = otherDetails.get(STRAND);
480 else if ("+".equals(str))
489 * Set the value of strand
492 * should be "+" for forward, or "-" for reverse
494 public void setStrand(String strand)
496 setValue(STRAND, strand);
499 public void setPhase(String phase)
501 setValue(PHASE, phase);
504 public String getPhase()
506 return (String) getValue(PHASE);
510 * Sets the 'raw' ENA format location specifier e.g. join(12..45,89..121)
514 public void setEnaLocation(String loc)
516 setValue(LOCATION, loc);
520 * Gets the 'raw' ENA format location specifier e.g. join(12..45,89..121)
524 public String getEnaLocation()
526 return (String) getValue(LOCATION);
530 * Readable representation, for debug only, not guaranteed not to change
534 public String toString()
536 return String.format("%d %d %s %s", getBegin(), getEnd(), getType(),
541 * Overridden to ensure that whenever two objects are equal, they have the
545 public int hashCode()
547 String s = getType() + getDescription() + getFeatureGroup()
548 + getValue("ID") + getValue("Name") + getValue("Parent")
550 return s.hashCode() + getBegin() + getEnd() + (int) getScore()
555 * Answers true if the feature's start/end values represent two related
556 * positions, rather than ends of a range. Such features may be visualised or
557 * reported differently to features on a range.
560 public boolean isContactFeature()
562 return contactFeature;
566 * Answers true if the sequence has zero start and end position
570 public boolean isNonPositional()
572 return begin == 0 && end == 0;
576 * Answers an html-formatted report of feature details
580 public String getDetailsReport()
582 FeatureSourceI metadata = FeatureSources.getInstance()
585 StringBuilder sb = new StringBuilder(128);
587 sb.append("<table>");
588 sb.append(String.format(ROW_DATA, "Type", type, ""));
589 sb.append(String.format(ROW_DATA, "Start/end", begin == end ? begin
590 : begin + (isContactFeature() ? ":" : "-") + end, ""));
591 String desc = StringUtils.stripHtmlTags(description);
592 sb.append(String.format(ROW_DATA, "Description", desc, ""));
593 if (!Float.isNaN(score) && score != 0f)
595 sb.append(String.format(ROW_DATA, "Score", score, ""));
597 if (featureGroup != null)
599 sb.append(String.format(ROW_DATA, "Group", featureGroup, ""));
602 if (otherDetails != null)
604 TreeMap<String, Object> ordered = new TreeMap<>(
605 String.CASE_INSENSITIVE_ORDER);
606 ordered.putAll(otherDetails);
608 for (Entry<String, Object> entry : ordered.entrySet())
610 String key = entry.getKey();
611 if (ATTRIBUTES.equals(key))
613 continue; // to avoid double reporting
616 Object value = entry.getValue();
617 if (value instanceof Map<?, ?>)
620 * expand values in a Map attribute across separate lines
621 * copy to a TreeMap for alphabetical ordering
623 Map<String, Object> values = (Map<String, Object>) value;
624 SortedMap<String, Object> sm = new TreeMap<>(
625 String.CASE_INSENSITIVE_ORDER);
627 for (Entry<?, ?> e : sm.entrySet())
629 sb.append(String.format(ROW_DATA, key, e.getKey().toString(), e
630 .getValue().toString()));
635 // tried <td title="key"> but it failed to provide a tooltip :-(
636 String attDesc = null;
637 if (metadata != null)
639 attDesc = metadata.getAttributeName(key);
641 String s = entry.getValue().toString();
642 if (isValueInteresting(key, s, metadata))
644 sb.append(String.format(ROW_DATA, key, attDesc == null ? ""
650 sb.append("</table>");
652 String text = sb.toString();
657 * Answers true if we judge the value is worth displaying, by some heuristic
665 boolean isValueInteresting(String key, String value,
666 FeatureSourceI metadata)
669 * currently suppressing zero values as well as null or empty
671 if (value == null || "".equals(value) || ".".equals(value)
672 || "0".equals(value))
677 if (metadata == null)
682 FeatureAttributeType attType = metadata.getAttributeType(key);
684 && (attType == FeatureAttributeType.Float || attType
685 .equals(FeatureAttributeType.Integer)))
689 float fval = Float.valueOf(value);
694 } catch (NumberFormatException e)
700 return true; // default to interesting
704 * Sets the feature source identifier
708 public void setSource(String theSource)
716 class SFSortByEnd implements Comparator<SequenceFeature>
719 public int compare(SequenceFeature a, SequenceFeature b)
721 return a.getEnd() - b.getEnd();
725 class SFSortByBegin implements Comparator<SequenceFeature>
728 public int compare(SequenceFeature a, SequenceFeature b)
730 return a.getBegin() - b.getBegin();