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.
22 * This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk
26 import java.io.BufferedReader;
27 import java.io.FileReader;
28 import java.io.IOException;
29 import java.util.ArrayList;
30 import java.util.Enumeration;
31 import java.util.Hashtable;
32 import java.util.LinkedHashMap;
33 import java.util.List;
35 import java.util.Vector;
37 import com.stevesoft.pat.Regex;
39 import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
40 import fr.orsay.lri.varna.factories.RNAFactory;
41 import fr.orsay.lri.varna.models.rna.RNA;
42 import jalview.analysis.Rna;
43 import jalview.datamodel.AlignmentAnnotation;
44 import jalview.datamodel.AlignmentI;
45 import jalview.datamodel.Annotation;
46 import jalview.datamodel.DBRefEntry;
47 import jalview.datamodel.DBRefSource;
48 import jalview.datamodel.Mapping;
49 import jalview.datamodel.Sequence;
50 import jalview.datamodel.SequenceFeature;
51 import jalview.datamodel.SequenceI;
52 import jalview.schemes.ResidueProperties;
53 import jalview.util.Comparison;
54 import jalview.util.DBRefUtils;
55 import jalview.util.Format;
56 import jalview.util.MessageManager;
58 // import org.apache.log4j.*;
61 * This class is supposed to parse a Stockholm format file into Jalview There
62 * are TODOs in this class: we do not know what the database source and version
63 * is for the file when parsing the #GS= AC tag which associates accessions with
64 * sequences. Database references are also not parsed correctly: a separate
65 * reference string parser must be added to parse the database reference form
66 * into Jalview's local representation.
68 * @author bsb at sanger.ac.uk
69 * @author Natasha Shersnev (Dundee, UK) (Stockholm file writer)
70 * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as
72 * @author Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data)
73 * @version 0.3 + jalview mods
76 public class StockholmFile extends AlignFile
78 private static final String ANNOTATION = "annotation";
80 private static final char UNDERSCORE = '_';
82 // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using NOT_RNASS first.
83 public static final String RNASS_BRACKETS = "<>[](){}AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz";
85 // use the following regex to decide an annotations (whole) line is NOT an RNA
86 // SS (it contains only E,H,e,h and other non-brace/non-alpha chars)
87 private static final Regex NOT_RNASS = new Regex(
88 "^[^<>[\\](){}A-DF-Za-df-z]*$");
90 StringBuffer out; // output buffer
92 private AlignmentI al;
94 public StockholmFile()
99 * Creates a new StockholmFile object for output
101 public StockholmFile(AlignmentI al)
106 public StockholmFile(String inFile, DataSourceType type)
112 public StockholmFile(FileParse source) throws IOException
118 public void initData()
124 * Parse a file in Stockholm format into Jalview's data model using VARNA
126 * @throws IOException
127 * If there is an error with the input file
129 public void parse_with_VARNA(java.io.File inFile) throws IOException
131 FileReader fr = null;
132 fr = new FileReader(inFile);
134 BufferedReader r = new BufferedReader(fr);
135 List<RNA> result = null;
138 result = RNAFactory.loadSecStrStockholm(r);
139 } catch (ExceptionUnmatchedClosingParentheses umcp)
141 errormessage = "Unmatched parentheses in annotation. Aborting ("
142 + umcp.getMessage() + ")";
143 throw new IOException(umcp);
145 // DEBUG System.out.println("this is the secondary scructure:"
147 SequenceI[] seqs = new SequenceI[result.size()];
149 for (int i = 0; i < result.size(); i++)
151 // DEBUG System.err.println("Processing i'th sequence in Stockholm file")
152 RNA current = result.get(i);
154 String seq = current.getSeq();
155 String rna = current.getStructDBN(true);
156 // DEBUG System.out.println(seq);
157 // DEBUG System.err.println(rna);
159 int end = seq.length() - 1;
160 id = safeName(getDataName());
161 seqs[i] = new Sequence(id, seq, begin, end);
162 String[] annot = new String[rna.length()];
163 Annotation[] ann = new Annotation[rna.length()];
164 for (int j = 0; j < rna.length(); j++)
166 annot[j] = rna.substring(j, j + 1);
170 for (int k = 0; k < rna.length(); k++)
172 ann[k] = new Annotation(annot[k], "",
173 Rna.getRNASecStrucState(annot[k]).charAt(0), 0f);
176 AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.",
177 current.getID(), ann);
179 seqs[i].addAlignmentAnnotation(align);
180 seqs[i].setRNA(result.get(i));
181 this.annotations.addElement(align);
188 * Parse a file in Stockholm format into Jalview's data model. The file has to
189 * be passed at construction time
191 * @throws IOException
192 * If there is an error with the input file
195 public void parse() throws IOException
197 StringBuffer treeString = new StringBuffer();
198 String treeName = null;
199 // --------------- Variable Definitions -------------------
203 Hashtable seqAnn = new Hashtable(); // Sequence related annotations
204 LinkedHashMap<String, String> seqs = new LinkedHashMap<>();
205 Regex p, r, rend, s, x;
206 // Temporary line for processing RNA annotation
207 // String RNAannot = "";
209 // ------------------ Parsing File ----------------------
210 // First, we have to check that this file has STOCKHOLM format, i.e. the
211 // first line must match
213 r = new Regex("# STOCKHOLM ([\\d\\.]+)");
214 if (!r.search(nextLine()))
216 throw new IOException(MessageManager
217 .getString("exception.stockholm_invalid_format"));
221 version = r.stringMatched(1);
223 // logger.debug("Stockholm version: " + version);
226 // We define some Regexes here that will be used regularly later
227 rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
228 p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
230 s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
231 r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
232 x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
234 // Convert all bracket types to parentheses (necessary for passing to VARNA)
235 Regex openparen = new Regex("(<|\\[)", "(");
236 Regex closeparen = new Regex("(>|\\])", ")");
238 // // Detect if file is RNA by looking for bracket types
239 // Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
246 openparen.optimize();
247 closeparen.optimize();
249 while ((line = nextLine()) != null)
251 if (line.length() == 0)
255 if (rend.search(line))
257 // End of the alignment, pass stuff back
258 this.noSeqs = seqs.size();
260 String dbsource = null;
261 Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
262 Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
263 if (getAlignmentProperty("AC") != null)
265 String dbType = getAlignmentProperty("AC").toString();
266 if (pf.search(dbType))
268 // PFAM Alignment - so references are typically from Uniprot
271 else if (rf.search(dbType))
276 // logger.debug("Number of sequences: " + this.noSeqs);
277 for (Map.Entry<String, String> skey : seqs.entrySet())
279 // logger.debug("Processing sequence " + acc);
280 String acc = skey.getKey();
281 String seq = skey.getValue();
282 if (maxLength < seq.length())
284 maxLength = seq.length();
290 * Retrieve hash of annotations for this accession Associate
291 * Annotation with accession
293 Hashtable accAnnotations = null;
295 if (seqAnn != null && seqAnn.containsKey(acc))
297 accAnnotations = (Hashtable) seqAnn.remove(acc);
298 // TODO: add structures to sequence
301 // Split accession in id and from/to
304 sid = p.stringMatched(1);
305 start = Integer.parseInt(p.stringMatched(2));
306 end = Integer.parseInt(p.stringMatched(3));
308 // logger.debug(sid + ", " + start + ", " + end);
310 Sequence seqO = new Sequence(sid, seq, start, end);
311 // Add Description (if any)
312 if (accAnnotations != null && accAnnotations.containsKey("DE"))
314 String desc = (String) accAnnotations.get("DE");
315 seqO.setDescription((desc == null) ? "" : desc);
317 // Add DB References (if any)
318 if (accAnnotations != null && accAnnotations.containsKey("DR"))
320 String dbr = (String) accAnnotations.get("DR");
321 if (dbr != null && dbr.indexOf(";") > -1)
323 String src = dbr.substring(0, dbr.indexOf(";"));
324 String acn = dbr.substring(dbr.indexOf(";") + 1);
325 jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);
329 if (accAnnotations != null && accAnnotations.containsKey("AC"))
331 String dbr = (String) accAnnotations.get("AC");
334 // we could get very clever here - but for now - just try to
335 // guess accession type from type of sequence, source of alignment plus
338 guessDatabaseFor(seqO, dbr, dbsource);
340 // else - do what ? add the data anyway and prompt the user to
341 // specify what references these are ?
344 Hashtable features = null;
345 // We need to adjust the positions of all features to account for gaps
348 features = (Hashtable) accAnnotations.remove("features");
349 } catch (java.lang.NullPointerException e)
351 // loggerwarn("Getting Features for " + acc + ": " +
355 // if we have features
356 if (features != null)
358 int posmap[] = seqO.findPositionMap();
359 Enumeration i = features.keys();
360 while (i.hasMoreElements())
362 // TODO: parse out secondary structure annotation as annotation
364 // TODO: parse out scores as annotation row
365 // TODO: map coding region to core jalview feature types
366 String type = i.nextElement().toString();
367 Hashtable content = (Hashtable) features.remove(type);
369 // add alignment annotation for this feature
370 String key = type2id(type);
373 * have we added annotation rows for this type ?
375 boolean annotsAdded = false;
378 if (accAnnotations != null
379 && accAnnotations.containsKey(key))
381 Vector vv = (Vector) accAnnotations.get(key);
382 for (int ii = 0; ii < vv.size(); ii++)
385 AlignmentAnnotation an = (AlignmentAnnotation) vv
387 seqO.addAlignmentAnnotation(an);
393 Enumeration j = content.keys();
394 while (j.hasMoreElements())
396 String desc = j.nextElement().toString();
397 if (ANNOTATION.equals(desc) && annotsAdded)
399 // don't add features if we already added an annotation row
402 String ns = content.get(desc).toString();
403 char[] byChar = ns.toCharArray();
404 for (int k = 0; k < byChar.length; k++)
407 if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM
414 int new_pos = posmap[k]; // look up nearest seqeunce
415 // position to this column
416 SequenceFeature feat = new SequenceFeature(type, desc,
417 new_pos, new_pos, null);
419 seqO.addSequenceFeature(feat);
429 // logger.debug("Adding seq " + acc + " from " + start + " to " + end
431 this.seqs.addElement(seqO);
433 return; // finished parsing this segment of source
435 else if (!r.search(line))
437 // System.err.println("Found sequence line: " + line);
439 // Split sequence in sequence and accession parts
442 // logger.error("Could not parse sequence line: " + line);
443 throw new IOException(MessageManager.formatMessage(
444 "exception.couldnt_parse_sequence_line", new String[]
447 String ns = seqs.get(x.stringMatched(1));
452 ns += x.stringMatched(2);
454 seqs.put(x.stringMatched(1), ns);
458 String annType = r.stringMatched(1);
459 String annContent = r.stringMatched(2);
461 // System.err.println("type:" + annType + " content: " + annContent);
463 if (annType.equals("GF"))
466 * Generic per-File annotation, free text Magic features: #=GF NH
467 * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier
468 * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS
470 * Compulsory fields: ------------------
472 * AC Accession number: Accession number in form PFxxxxx.version or
473 * PBxxxxxx. ID Identification: One word name for family. DE
474 * Definition: Short description of family. AU Author: Authors of the
475 * entry. SE Source of seed: The source suggesting the seed members
476 * belong to one family. GA Gathering method: Search threshold to
477 * build the full alignment. TC Trusted Cutoff: Lowest sequence score
478 * and domain score of match in the full alignment. NC Noise Cutoff:
479 * Highest sequence score and domain score of match not in full
480 * alignment. TP Type: Type of family -- presently Family, Domain,
481 * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM
482 * Alignment Method The order ls and fs hits are aligned to the model
483 * to build the full align. // End of alignment.
485 * Optional fields: ----------------
487 * DC Database Comment: Comment about database reference. DR Database
488 * Reference: Reference to external database. RC Reference Comment:
489 * Comment about literature reference. RN Reference Number: Reference
490 * Number. RM Reference Medline: Eight digit medline UI number. RT
491 * Reference Title: Reference Title. RA Reference Author: Reference
492 * Author RL Reference Location: Journal location. PI Previous
493 * identifier: Record of all previous ID lines. KW Keywords: Keywords.
494 * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.
495 * NL Location: Location of nested domains - sequence ID, start and
498 * Obsolete fields: ----------- AL Alignment method of seed: The
499 * method used to align the seed members.
501 // Let's save the annotations, maybe we'll be able to do something
502 // with them later...
503 Regex an = new Regex("(\\w+)\\s*(.*)");
504 if (an.search(annContent))
506 if (an.stringMatched(1).equals("NH"))
508 treeString.append(an.stringMatched(2));
510 else if (an.stringMatched(1).equals("TN"))
512 if (treeString.length() > 0)
514 if (treeName == null)
516 treeName = "Tree " + (getTreeCount() + 1);
518 addNewickTree(treeName, treeString.toString());
520 treeName = an.stringMatched(2);
521 treeString = new StringBuffer();
523 // TODO: JAL-3532 - this is where GF comments and database references are lost
524 // suggest overriding this method for Stockholm files to catch and properly
525 // process CC, DR etc into multivalued properties
526 setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
529 else if (annType.equals("GS"))
531 // Generic per-Sequence annotation, free text
533 * Pfam uses these features: Feature Description ---------------------
534 * ----------- AC <accession> ACcession number DE <freetext>
535 * DEscription DR <db>; <accession>; Database Reference OS <organism>
536 * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)
537 * LO <look> Look (Color, etc.)
539 if (s.search(annContent))
541 String acc = s.stringMatched(1);
542 String type = s.stringMatched(2);
543 String content = s.stringMatched(3);
544 // TODO: store DR in a vector.
545 // TODO: store AC according to generic file db annotation.
547 if (seqAnn.containsKey(acc))
549 ann = (Hashtable) seqAnn.get(acc);
553 ann = new Hashtable();
555 ann.put(type, content);
556 seqAnn.put(acc, ann);
560 // throw new IOException("Error parsing " + line);
561 System.err.println(">> missing annotation: " + line);
564 else if (annType.equals("GC"))
566 // Generic per-Column annotation, exactly 1 char per column
567 // always need a label.
568 if (x.search(annContent))
570 // parse out and create alignment annotation directly.
571 parseAnnotationRow(annotations, x.stringMatched(1),
575 else if (annType.equals("GR"))
577 // Generic per-Sequence AND per-Column markup, exactly 1 char per
580 * Feature Description Markup letters ------- -----------
581 * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface
582 * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane
583 * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;
584 * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in
587 if (s.search(annContent))
589 String acc = s.stringMatched(1);
590 String type = s.stringMatched(2);
591 String oseq = s.stringMatched(3);
593 * copy of annotation field that may be processed into whitespace chunks
595 String seq = new String(oseq);
598 // Get an object with all the annotations for this sequence
599 if (seqAnn.containsKey(acc))
601 // logger.debug("Found annotations for " + acc);
602 ann = (Hashtable) seqAnn.get(acc);
606 // logger.debug("Creating new annotations holder for " + acc);
607 ann = new Hashtable();
608 seqAnn.put(acc, ann);
611 // // start of block for appending annotation lines for wrapped
613 // TODO test structure, call parseAnnotationRow with vector from
614 // hashtable for specific sequence
617 // Get an object with all the content for an annotation
618 if (ann.containsKey("features"))
620 // logger.debug("Found features for " + acc);
621 features = (Hashtable) ann.get("features");
625 // logger.debug("Creating new features holder for " + acc);
626 features = new Hashtable();
627 ann.put("features", features);
631 if (features.containsKey(this.id2type(type)))
633 // logger.debug("Found content for " + this.id2type(type));
634 content = (Hashtable) features
635 .get(this.id2type(type));
639 // logger.debug("Creating new content holder for " +
640 // this.id2type(type));
641 content = new Hashtable();
642 features.put(id2type(type), content);
644 String ns = (String) content.get(ANNOTATION);
650 // finally, append the annotation line
652 content.put(ANNOTATION, ns);
653 // // end of wrapped annotation block.
654 // // Now a new row is created with the current set of data
657 if (seqAnn.containsKey(acc))
659 strucAnn = (Hashtable) seqAnn.get(acc);
663 strucAnn = new Hashtable();
666 Vector<AlignmentAnnotation> newStruc = new Vector<>();
667 parseAnnotationRow(newStruc, type, ns);
668 for (AlignmentAnnotation alan : newStruc)
670 alan.visible = false;
672 // new annotation overwrites any existing annotation...
674 strucAnn.put(type, newStruc);
675 seqAnn.put(acc, strucAnn);
681 "Warning - couldn't parse sequence annotation row line:\n"
683 // throw new IOException("Error parsing " + line);
688 throw new IOException(MessageManager.formatMessage(
689 "exception.unknown_annotation_detected", new String[]
690 { annType, annContent }));
694 if (treeString.length() > 0)
696 if (treeName == null)
698 treeName = "Tree " + (1 + getTreeCount());
700 addNewickTree(treeName, treeString.toString());
705 * Demangle an accession string and guess the originating sequence database
706 * for a given sequence
709 * sequence to be annotated
711 * Accession string for sequence
713 * source database for alignment (PFAM or RFAM)
715 private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)
717 DBRefEntry dbrf = null;
718 List<DBRefEntry> dbrs = new ArrayList<>();
719 String seqdb = "Unknown", sdbac = "" + dbr;
720 int st = -1, en = -1, p;
721 if ((st = sdbac.indexOf("/")) > -1)
723 String num, range = sdbac.substring(st + 1);
724 sdbac = sdbac.substring(0, st);
725 if ((p = range.indexOf("-")) > -1)
728 if (p < range.length())
730 num = range.substring(p).trim();
733 en = Integer.parseInt(num);
734 } catch (NumberFormatException x)
736 // could warn here that index is invalid
745 num = range.substring(0, p).trim();
748 st = Integer.parseInt(num);
749 } catch (NumberFormatException x)
751 // could warn here that index is invalid
755 if (dbsource == null)
757 // make up an origin based on whether the sequence looks like it is nucleotide
759 dbsource = (seqO.isProtein()) ? "PFAM" : "RFAM";
761 if (dbsource.equals("PFAM"))
764 if (sdbac.indexOf(".") > -1)
766 // strip of last subdomain
767 sdbac = sdbac.substring(0, sdbac.indexOf("."));
768 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource,
775 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
784 seqdb = "EMBL"; // total guess - could be ENA, or something else these
786 if (sdbac.indexOf(".") > -1)
788 // strip off last subdomain
789 sdbac = sdbac.substring(0, sdbac.indexOf("."));
790 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource,
798 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
805 if (st != -1 && en != -1)
807 for (DBRefEntry d : dbrs)
809 jalview.util.MapList mp = new jalview.util.MapList(
811 { seqO.getStart(), seqO.getEnd() }, new int[] { st, en }, 1,
813 jalview.datamodel.Mapping mping = new Mapping(mp);
819 protected static AlignmentAnnotation parseAnnotationRow(
820 Vector<AlignmentAnnotation> annotation, String label,
823 String convert1, convert2 = null;
824 // String convert1 = OPEN_PAREN.replaceAll(annots);
825 // String convert2 = CLOSE_PAREN.replaceAll(convert1);
826 // annots = convert2;
829 if (label.contains("_cons"))
831 type = (label.indexOf("_cons") == label.length() - 5)
832 ? label.substring(0, label.length() - 5)
835 boolean ss = false, posterior = false;
836 type = id2type(type);
838 boolean isrnass = false;
840 if (type.equalsIgnoreCase("secondary structure"))
843 isrnass = !NOT_RNASS.search(annots); // sorry about the double negative
844 // here (it's easier for dealing with
845 // other non-alpha-non-brace chars)
847 if (type.equalsIgnoreCase("posterior probability"))
851 // decide on secondary structure or not.
852 Annotation[] els = new Annotation[annots.length()];
853 for (int i = 0; i < annots.length(); i++)
855 String pos = annots.substring(i, i + 1);
856 if (UNDERSCORE == pos.charAt(0))
861 ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
865 // if (" .-_".indexOf(pos) == -1)
867 if (isrnass && RNASS_BRACKETS.indexOf(pos) >= 0)
869 ann.secondaryStructure = Rna.getRNASecStrucState(pos).charAt(0);
870 ann.displayCharacter = "" + pos.charAt(0);
874 ann.secondaryStructure = ResidueProperties.getDssp3state(pos)
877 if (ann.secondaryStructure == pos.charAt(0))
879 ann.displayCharacter = ""; // null; // " ";
883 ann.displayCharacter = " " + ann.displayCharacter;
889 if (posterior && !ann.isWhitespace()
890 && !Comparison.isGap(pos.charAt(0)))
893 // symbol encodes values - 0..*==0..10
894 if (pos.charAt(0) == '*')
900 val = pos.charAt(0) - '0';
911 AlignmentAnnotation annot = null;
912 Enumeration<AlignmentAnnotation> e = annotation.elements();
913 while (e.hasMoreElements())
915 annot = e.nextElement();
916 if (annot.label.equals(type))
924 annot = new AlignmentAnnotation(type, type, els);
925 annotation.addElement(annot);
929 Annotation[] anns = new Annotation[annot.annotations.length
931 System.arraycopy(annot.annotations, 0, anns, 0,
932 annot.annotations.length);
933 System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
934 annot.annotations = anns;
935 // System.out.println("else: ");
940 private String dbref_to_ac_record(DBRefEntry ref)
942 return ref.getSource().toString() + " ; "
943 + ref.getAccessionId().toString();
946 public String print(SequenceI[] s, boolean jvSuffix)
948 out = new StringBuffer();
949 out.append("# STOCKHOLM 1.0");
952 // find max length of id
958 Hashtable<String, String> dataRef = null;
959 boolean isAA = s[in].isProtein();
960 while ((in < slen) && ((seq = s[in]) != null))
962 String tmp = printId(seq, jvSuffix);
963 max = Math.max(max, seq.getLength());
965 if (tmp.length() > maxid)
967 maxid = tmp.length();
969 List<DBRefEntry> seqrefs = seq.getDBRefs();
971 if (seqrefs != null && (ndb = seqrefs.size()) > 0)
975 dataRef = new Hashtable<>();
977 List<DBRefEntry> primrefs = seq.getPrimaryDBRefs();
978 if (primrefs.size() >= 1)
980 dataRef.put(tmp, dbref_to_ac_record(primrefs.get(0)));
984 for (int idb = 0; idb < seq.getDBRefs().size(); idb++)
986 DBRefEntry dbref = seq.getDBRefs().get(idb);
987 dataRef.put(tmp, dbref_to_ac_record(dbref));
988 // if we put in a uniprot or EMBL record then we're done:
989 if (isAA && DBRefSource.UNIPROT
990 .equals(DBRefUtils.getCanonicalName(dbref.getSource())))
994 if (!isAA && DBRefSource.EMBL
995 .equals(DBRefUtils.getCanonicalName(dbref.getSource())))
1007 // output database type
1008 if (al.getProperties() != null)
1010 if (!al.getProperties().isEmpty())
1012 Enumeration key = al.getProperties().keys();
1013 Enumeration val = al.getProperties().elements();
1014 while (key.hasMoreElements())
1016 out.append("#=GF " + key.nextElement() + " " + val.nextElement());
1017 out.append(newline);
1022 // output database accessions
1023 if (dataRef != null)
1025 Enumeration<String> en = dataRef.keys();
1026 while (en.hasMoreElements())
1028 Object idd = en.nextElement();
1029 String type = dataRef.remove(idd);
1030 out.append(new Format("%-" + (maxid - 2) + "s")
1031 .form("#=GS " + idd.toString() + " "));
1032 if (isAA && type.contains("UNIPROT")
1033 || (!isAA && type.contains("EMBL")))
1036 out.append(" AC " + type.substring(type.indexOf(";") + 1));
1040 out.append(" DR " + type + " ");
1042 out.append(newline);
1046 // output annotations
1047 while (i < slen && (seq = s[i]) != null)
1049 AlignmentAnnotation[] alAnot = seq.getAnnotation();
1053 for (int j = 0; j < alAnot.length; j++)
1055 if (alAnot[j].annotations != null)
1057 String key = type2id(alAnot[j].label);
1058 boolean isrna = alAnot[j].isValidStruc();
1062 // hardwire to secondary structure if there is RNA secondary
1063 // structure on the annotation
1071 // out.append("#=GR ");
1072 out.append(new Format("%-" + maxid + "s").form(
1073 "#=GR " + printId(s[i], jvSuffix) + " " + key + " "));
1074 ann = alAnot[j].annotations;
1076 for (int k = 0; k < ann.length; k++)
1078 sseq += outputCharacter(key, k, isrna, ann, s[i]);
1081 out.append(newline);
1087 out.append(new Format("%-" + maxid + "s")
1088 .form(printId(seq, jvSuffix) + " "));
1089 out.append(seq.getSequenceAsString());
1090 out.append(newline);
1094 // alignment annotation
1095 AlignmentAnnotation aa;
1096 AlignmentAnnotation[] an = al.getAlignmentAnnotation();
1099 for (int ia = 0, na = an.length; ia < na; ia++)
1102 if (aa.autoCalculated || !aa.visible || aa.sequenceRef != null)
1109 if (aa.label.equals("seq"))
1115 key = type2id(aa.label.toLowerCase());
1122 label = key + "_cons";
1129 label = label.replace(" ", "_");
1132 new Format("%-" + maxid + "s").form("#=GC " + label + " "));
1133 boolean isrna = aa.isValidStruc();
1134 for (int j = 0, nj = aa.annotations.length; j < nj; j++)
1136 sseq += outputCharacter(key, j, isrna, aa.annotations, null);
1139 out.append(newline);
1144 out.append(newline);
1146 return out.toString();
1151 * add an annotation character to the output row
1160 private char outputCharacter(String key, int k, boolean isrna,
1161 Annotation[] ann, SequenceI sequenceI)
1164 Annotation annot = ann[k];
1165 String ch = (annot == null)
1166 ? ((sequenceI == null) ? "-"
1167 : Character.toString(sequenceI.getCharAt(k)))
1168 : (annot.displayCharacter == null
1169 ? String.valueOf(annot.secondaryStructure)
1170 : annot.displayCharacter);
1175 if (key != null && key.equals("SS"))
1177 char ssannotchar = ' ';
1178 boolean charset = false;
1181 // sensible gap character
1187 // valid secondary structure AND no alternative label (e.g. ' B')
1188 if (annot.secondaryStructure > ' ' && ch.length() < 2)
1190 ssannotchar = annot.secondaryStructure;
1196 return (ssannotchar == ' ' && isrna) ? '.' : ssannotchar;
1200 if (ch.length() == 0)
1204 else if (ch.length() == 1)
1208 else if (ch.length() > 1)
1213 return (seq == ' ' && key != null && key.equals("SS") && isrna) ? '.'
1218 * make a friendly ID string.
1221 * @return truncated dataName to after last '/'
1223 private String safeName(String dataName)
1226 while ((b = dataName.indexOf("/")) > -1 && b < dataName.length())
1228 dataName = dataName.substring(b + 1).trim();
1231 int e = (dataName.length() - dataName.indexOf(".")) + 1;
1232 dataName = dataName.substring(1, e).trim();
1237 public String print()
1239 out = new StringBuffer();
1240 out.append("# STOCKHOLM 1.0");
1241 out.append(newline);
1242 print(getSeqsAsArray(), false);
1245 out.append(newline);
1246 return out.toString();
1249 private static Hashtable typeIds = null;
1253 if (typeIds == null)
1255 typeIds = new Hashtable();
1256 typeIds.put("SS", "Secondary Structure");
1257 typeIds.put("SA", "Surface Accessibility");
1258 typeIds.put("TM", "transmembrane");
1259 typeIds.put("PP", "Posterior Probability");
1260 typeIds.put("LI", "ligand binding");
1261 typeIds.put("AS", "active site");
1262 typeIds.put("IN", "intron");
1263 typeIds.put("IR", "interacting residue");
1264 typeIds.put("AC", "accession");
1265 typeIds.put("OS", "organism");
1266 typeIds.put("CL", "class");
1267 typeIds.put("DE", "description");
1268 typeIds.put("DR", "reference");
1269 typeIds.put("LO", "look");
1270 typeIds.put("RF", "Reference Positions");
1275 protected static String id2type(String id)
1277 if (typeIds.containsKey(id))
1279 return (String) typeIds.get(id);
1282 "Warning : Unknown Stockholm annotation type code " + id);
1286 protected static String type2id(String type)
1289 Enumeration e = typeIds.keys();
1290 while (e.hasMoreElements())
1292 Object ll = e.nextElement();
1293 if (typeIds.get(ll).toString().equalsIgnoreCase(type))
1304 "Warning : Unknown Stockholm annotation type: " + type);