2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
3 * Copyright (C) 2014 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 jalview.datamodel.AlignmentI;
27 import jalview.datamodel.AlignmentAnnotation;
28 import jalview.datamodel.AlignmentI;
29 import jalview.datamodel.Annotation;
30 import jalview.datamodel.DBRefEntry;
31 import jalview.datamodel.Mapping;
32 import jalview.datamodel.Sequence;
33 import jalview.datamodel.SequenceFeature;
34 import jalview.datamodel.SequenceI;
35 import jalview.util.Format;
37 import java.io.BufferedReader;
38 import java.io.FileReader;
39 import java.io.IOException;
40 import java.util.ArrayList;
41 import java.util.Enumeration;
42 import java.util.Hashtable;
43 import java.util.List;
44 import java.util.StringTokenizer;
45 import java.util.Vector;
47 import com.stevesoft.pat.Regex;
49 import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
50 import fr.orsay.lri.varna.factories.RNAFactory;
51 import fr.orsay.lri.varna.models.rna.RNA;
53 // import org.apache.log4j.*;
56 * This class is supposed to parse a Stockholm format file into Jalview There
57 * are TODOs in this class: we do not know what the database source and version
58 * is for the file when parsing the #GS= AC tag which associates accessions with
59 * sequences. Database references are also not parsed correctly: a separate
60 * reference string parser must be added to parse the database reference form
61 * into Jalview's local representation.
63 * @author bsb at sanger.ac.uk
64 * @author Natasha Shersnev (Dundee, UK) (Stockholm file writer)
65 * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as stockholm)
66 * @author Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data)
67 * @version 0.3 + jalview mods
70 public class StockholmFile extends AlignFile
72 // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");
73 protected ArrayList<RNA> result;
74 StringBuffer out; // output buffer
78 public StockholmFile()
83 * Creates a new StockholmFile object for output.
85 public StockholmFile(AlignmentI al)
90 public StockholmFile(String inFile, String type) throws IOException
95 public StockholmFile(FileParse source) throws IOException
100 public void initData()
105 * Parse a file in Stockholm format into Jalview's data model using VARNA
107 * @throws IOException
108 * If there is an error with the input file
110 public void parse_with_VARNA(java.io.File inFile) throws IOException
112 FileReader fr = null;
113 fr = new FileReader(inFile);
115 BufferedReader r = new BufferedReader(fr);
119 result = RNAFactory.loadSecStrStockholm(r);
120 } catch (ExceptionUnmatchedClosingParentheses umcp)
122 errormessage = "Unmatched parentheses in annotation. Aborting ("
123 + umcp.getMessage() + ")";
124 throw new IOException(umcp);
126 // DEBUG System.out.println("this is the secondary scructure:"
128 SequenceI[] seqs = new SequenceI[result.size()];
130 for (int i = 0; i < result.size(); i++)
132 // DEBUG System.err.println("Processing i'th sequence in Stockholm file")
133 RNA current = result.get(i);
135 String seq = current.getSeq();
136 String rna = current.getStructDBN(true);
137 // DEBUG System.out.println(seq);
138 // DEBUG System.err.println(rna);
140 int end = seq.length() - 1;
141 id = safeName(getDataName());
142 seqs[i] = new Sequence(id, seq, begin, end);
143 String[] annot = new String[rna.length()];
144 Annotation[] ann = new Annotation[rna.length()];
145 for (int j = 0; j < rna.length(); j++)
147 annot[j] = rna.substring(j, j + 1);
151 for (int k = 0; k < rna.length(); k++)
153 ann[k] = new Annotation(annot[k], "",
154 jalview.schemes.ResidueProperties.getRNASecStrucState(
155 annot[k]).charAt(0), 0f);
158 AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.",
159 current.getID(), ann);
161 seqs[i].addAlignmentAnnotation(align);
162 seqs[i].setRNA(result.get(i));
163 this.annotations.addElement(align);
171 * Parse a file in Stockholm format into Jalview's data model. The file has to
172 * be passed at construction time
174 * @throws IOException
175 * If there is an error with the input file
177 public void parse() throws IOException
179 StringBuffer treeString = new StringBuffer();
180 String treeName = null;
181 // --------------- Variable Definitions -------------------
185 Hashtable seqAnn = new Hashtable(); // Sequence related annotations
186 Hashtable seqs = new Hashtable();
187 Regex p, r, rend, s, x;
188 // Temporary line for processing RNA annotation
189 // String RNAannot = "";
191 // ------------------ Parsing File ----------------------
192 // First, we have to check that this file has STOCKHOLM format, i.e. the
193 // first line must match
196 r = new Regex("# STOCKHOLM ([\\d\\.]+)");
197 if (!r.search(nextLine()))
199 throw new IOException(
200 "This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");
204 version = r.stringMatched(1);
206 // logger.debug("Stockholm version: " + version);
209 // We define some Regexes here that will be used regularily later
210 rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
211 p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
213 s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
214 r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
215 x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
217 // Convert all bracket types to parentheses (necessary for passing to VARNA)
218 Regex openparen = new Regex("(<|\\[)", "(");
219 Regex closeparen = new Regex("(>|\\])", ")");
221 // Detect if file is RNA by looking for bracket types
222 Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
229 openparen.optimize();
230 closeparen.optimize();
232 while ((line = nextLine()) != null)
234 if (line.length() == 0)
238 if (rend.search(line))
240 // End of the alignment, pass stuff back
241 this.noSeqs = seqs.size();
243 String seqdb,dbsource = null;
244 Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
245 Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
246 if (getAlignmentProperty("AC") != null)
248 String dbType = getAlignmentProperty("AC").toString();
249 if (pf.search(dbType))
251 // PFAM Alignment - so references are typically from Uniprot
254 else if (rf.search(dbType))
259 // logger.debug("Number of sequences: " + this.noSeqs);
260 Enumeration accs = seqs.keys();
261 while (accs.hasMoreElements())
263 String acc = (String) accs.nextElement();
264 // logger.debug("Processing sequence " + acc);
265 String seq = (String) seqs.remove(acc);
266 if (maxLength < seq.length())
268 maxLength = seq.length();
274 * Retrieve hash of annotations for this accession Associate
275 * Annotation with accession
277 Hashtable accAnnotations = null;
279 if (seqAnn != null && seqAnn.containsKey(acc))
281 accAnnotations = (Hashtable) seqAnn.remove(acc);
282 //TODO: add structures to sequence
285 // Split accession in id and from/to
288 sid = p.stringMatched(1);
289 start = Integer.parseInt(p.stringMatched(2));
290 end = Integer.parseInt(p.stringMatched(3));
292 // logger.debug(sid + ", " + start + ", " + end);
294 Sequence seqO = new Sequence(sid, seq, start, end);
295 // Add Description (if any)
296 if (accAnnotations != null && accAnnotations.containsKey("DE"))
298 String desc = (String) accAnnotations.get("DE");
299 seqO.setDescription((desc == null) ? "" : desc);
301 // Add DB References (if any)
302 if (accAnnotations != null && accAnnotations.containsKey("DR"))
304 String dbr = (String) accAnnotations.get("DR");
305 if (dbr != null && dbr.indexOf(";") > -1)
307 String src = dbr.substring(0, dbr.indexOf(";"));
308 String acn = dbr.substring(dbr.indexOf(";") + 1);
309 jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);
313 if (accAnnotations != null && accAnnotations.containsKey("AC"))
315 if (dbsource != null)
317 String dbr = (String) accAnnotations.get("AC");
320 // we could get very clever here - but for now - just try to guess accession type from source of alignment plus structure of accession
321 guessDatabaseFor(seqO, dbr, dbsource);
325 // else - do what ? add the data anyway and prompt the user to specify what references these are ?
328 Hashtable features = null;
329 // We need to adjust the positions of all features to account for gaps
332 features = (Hashtable) accAnnotations.remove("features");
333 } catch (java.lang.NullPointerException e)
335 // loggerwarn("Getting Features for " + acc + ": " +
339 // if we have features
340 if (features != null)
342 int posmap[] = seqO.findPositionMap();
343 Enumeration i = features.keys();
344 while (i.hasMoreElements())
346 // TODO: parse out secondary structure annotation as annotation
348 // TODO: parse out scores as annotation row
349 // TODO: map coding region to core jalview feature types
350 String type = i.nextElement().toString();
351 Hashtable content = (Hashtable) features.remove(type);
353 // add alignment annotation for this feature
354 String key = type2id(type);
357 if (accAnnotations != null
358 && accAnnotations.containsKey(key))
360 Vector vv = (Vector) accAnnotations.get(key);
361 for (int ii = 0; ii < vv.size(); ii++)
363 AlignmentAnnotation an = (AlignmentAnnotation) vv
365 seqO.addAlignmentAnnotation(an);
370 Enumeration j = content.keys();
371 while (j.hasMoreElements())
373 String desc = j.nextElement().toString();
374 String ns = content.get(desc).toString();
375 char[] byChar = ns.toCharArray();
376 for (int k = 0; k < byChar.length; k++)
379 if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM
386 int new_pos = posmap[k]; // look up nearest seqeunce
387 // position to this column
388 SequenceFeature feat = new SequenceFeature(type, desc,
389 new_pos, new_pos, 0f, null);
391 seqO.addSequenceFeature(feat);
401 // logger.debug("Adding seq " + acc + " from " + start + " to " + end
403 this.seqs.addElement(seqO);
405 return; // finished parsing this segment of source
407 else if (!r.search(line))
409 // System.err.println("Found sequence line: " + line);
411 // Split sequence in sequence and accession parts
414 // logger.error("Could not parse sequence line: " + line);
415 throw new IOException("Could not parse sequence line: " + line);
417 String ns = (String) seqs.get(x.stringMatched(1));
422 ns += x.stringMatched(2);
424 seqs.put(x.stringMatched(1), ns);
428 String annType = r.stringMatched(1);
429 String annContent = r.stringMatched(2);
431 // System.err.println("type:" + annType + " content: " + annContent);
433 if (annType.equals("GF"))
436 * Generic per-File annotation, free text Magic features: #=GF NH
437 * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier
438 * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS
440 * Compulsory fields: ------------------
442 * AC Accession number: Accession number in form PFxxxxx.version or
443 * PBxxxxxx. ID Identification: One word name for family. DE
444 * Definition: Short description of family. AU Author: Authors of the
445 * entry. SE Source of seed: The source suggesting the seed members
446 * belong to one family. GA Gathering method: Search threshold to
447 * build the full alignment. TC Trusted Cutoff: Lowest sequence score
448 * and domain score of match in the full alignment. NC Noise Cutoff:
449 * Highest sequence score and domain score of match not in full
450 * alignment. TP Type: Type of family -- presently Family, Domain,
451 * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM
452 * Alignment Method The order ls and fs hits are aligned to the model
453 * to build the full align. // End of alignment.
455 * Optional fields: ----------------
457 * DC Database Comment: Comment about database reference. DR Database
458 * Reference: Reference to external database. RC Reference Comment:
459 * Comment about literature reference. RN Reference Number: Reference
460 * Number. RM Reference Medline: Eight digit medline UI number. RT
461 * Reference Title: Reference Title. RA Reference Author: Reference
462 * Author RL Reference Location: Journal location. PI Previous
463 * identifier: Record of all previous ID lines. KW Keywords: Keywords.
464 * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.
465 * NL Location: Location of nested domains - sequence ID, start and
468 * Obsolete fields: ----------- AL Alignment method of seed: The
469 * method used to align the seed members.
471 // Let's save the annotations, maybe we'll be able to do something
472 // with them later...
473 Regex an = new Regex("(\\w+)\\s*(.*)");
474 if (an.search(annContent))
476 if (an.stringMatched(1).equals("NH"))
478 treeString.append(an.stringMatched(2));
480 else if (an.stringMatched(1).equals("TN"))
482 if (treeString.length() > 0)
484 if (treeName == null)
486 treeName = "Tree " + (getTreeCount() + 1);
488 addNewickTree(treeName, treeString.toString());
490 treeName = an.stringMatched(2);
491 treeString = new StringBuffer();
493 setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
496 else if (annType.equals("GS"))
498 // Generic per-Sequence annotation, free text
500 * Pfam uses these features: Feature Description ---------------------
501 * ----------- AC <accession> ACcession number DE <freetext>
502 * DEscription DR <db>; <accession>; Database Reference OS <organism>
503 * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)
504 * LO <look> Look (Color, etc.)
506 if (s.search(annContent))
508 String acc = s.stringMatched(1);
509 String type = s.stringMatched(2);
510 String content = s.stringMatched(3);
511 // TODO: store DR in a vector.
512 // TODO: store AC according to generic file db annotation.
514 if (seqAnn.containsKey(acc))
516 ann = (Hashtable) seqAnn.get(acc);
520 ann = new Hashtable();
522 ann.put(type, content);
523 seqAnn.put(acc, ann);
527 throw new IOException("Error parsing " + line);
530 else if (annType.equals("GC"))
532 // Generic per-Column annotation, exactly 1 char per column
533 // always need a label.
534 if (x.search(annContent))
536 // parse out and create alignment annotation directly.
537 parseAnnotationRow(annotations, x.stringMatched(1),
541 else if (annType.equals("GR"))
543 // Generic per-Sequence AND per-Column markup, exactly 1 char per
546 * Feature Description Markup letters ------- -----------
547 * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface
548 * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane
549 * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;
550 * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in
553 if (s.search(annContent))
555 String acc = s.stringMatched(1);
556 String type = s.stringMatched(2);
557 String seq = new String(s.stringMatched(3));
558 String description = null;
559 // Check for additional information about the current annotation
560 // We use a simple string tokenizer here for speed
561 StringTokenizer sep = new StringTokenizer(seq, " \t");
562 description = sep.nextToken();
563 if (sep.hasMoreTokens())
565 seq = sep.nextToken();
570 description = new String();
572 // sequence id with from-to fields
575 // Get an object with all the annotations for this sequence
576 if (seqAnn.containsKey(acc))
578 // logger.debug("Found annotations for " + acc);
579 ann = (Hashtable) seqAnn.get(acc);
583 // logger.debug("Creating new annotations holder for " + acc);
584 ann = new Hashtable();
585 seqAnn.put(acc, ann);
587 // TODO test structure, call parseAnnotationRow with vector from
588 // hashtable for specific sequence
590 // Get an object with all the content for an annotation
591 if (ann.containsKey("features"))
593 // logger.debug("Found features for " + acc);
594 features = (Hashtable) ann.get("features");
598 // logger.debug("Creating new features holder for " + acc);
599 features = new Hashtable();
600 ann.put("features", features);
604 if (features.containsKey(this.id2type(type)))
606 // logger.debug("Found content for " + this.id2type(type));
607 content = (Hashtable) features.get(this.id2type(type));
611 // logger.debug("Creating new content holder for " +
612 // this.id2type(type));
613 content = new Hashtable();
614 features.put(this.id2type(type), content);
616 String ns = (String) content.get(description);
622 content.put(description, ns);
624 // if(type.equals("SS")){
626 if (seqAnn.containsKey(acc))
628 strucAnn = (Hashtable) seqAnn.get(acc);
632 strucAnn = new Hashtable();
635 Vector newStruc=new Vector();
636 parseAnnotationRow(newStruc, type,ns);
638 strucAnn.put(type, newStruc);
639 seqAnn.put(acc, strucAnn);
645 .println("Warning - couldn't parse sequence annotation row line:\n"
647 // throw new IOException("Error parsing " + line);
652 throw new IOException("Unknown annotation detected: " + annType
657 if (treeString.length() > 0)
659 if (treeName == null)
661 treeName = "Tree " + (1 + getTreeCount());
663 addNewickTree(treeName, treeString.toString());
668 * Demangle an accession string and guess the originating sequence database for a given sequence
669 * @param seqO sequence to be annotated
670 * @param dbr Accession string for sequence
671 * @param dbsource source database for alignment (PFAM or RFAM)
673 private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)
675 DBRefEntry dbrf=null;
676 List<DBRefEntry> dbrs=new ArrayList<DBRefEntry>();
677 String seqdb="Unknown",sdbac=""+dbr;
679 if ((st=sdbac.indexOf("/"))>-1)
681 String num,range=sdbac.substring(st+1);
682 sdbac = sdbac.substring(0,st);
683 if ((p=range.indexOf("-"))>-1)
686 if (p<range.length())
688 num = range.substring(p).trim();
690 en = Integer.parseInt(num);
691 } catch (NumberFormatException x)
693 // could warn here that index is invalid
700 num=range.substring(0,p).trim();
702 st = Integer.parseInt(num);
703 } catch (NumberFormatException x)
705 // could warn here that index is invalid
709 if (dbsource.equals("PFAM")) {
711 if (sdbac.indexOf(".")>-1)
713 // strip of last subdomain
714 sdbac = sdbac.substring(0,sdbac.indexOf("."));
715 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);
721 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);
727 seqdb = "EMBL"; // total guess - could be ENA, or something else these days
728 if (sdbac.indexOf(".")>-1)
730 // strip off last subdomain
731 sdbac = sdbac.substring(0,sdbac.indexOf("."));
732 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);
739 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);
745 if (st!=-1 && en!=-1)
747 for (DBRefEntry d:dbrs)
749 jalview.util.MapList mp = new jalview.util.MapList(new int[] { seqO.getStart(),seqO.getEnd()},new int[] { st,en},1,1);
750 jalview.datamodel.Mapping mping = new Mapping(mp);
756 protected static AlignmentAnnotation parseAnnotationRow(
757 Vector annotation, String label, String annots)
759 String convert1, convert2 = null;
761 // Convert all bracket types to parentheses
762 Regex openparen = new Regex("(<|\\[)", "(");
763 Regex closeparen = new Regex("(>|\\])", ")");
765 // Detect if file is RNA by looking for bracket types
766 Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
768 convert1 = openparen.replaceAll(annots);
769 convert2 = closeparen.replaceAll(convert1);
773 if (label.contains("_cons"))
775 type = (label.indexOf("_cons") == label.length() - 5) ? label
776 .substring(0, label.length() - 5) : label;
779 type = id2type(type);
780 if (type.equals("secondary structure"))
784 // decide on secondary structure or not.
785 Annotation[] els = new Annotation[annots.length()];
786 for (int i = 0; i < annots.length(); i++)
788 String pos = annots.substring(i, i + 1);
790 ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
794 if (detectbrackets.search(pos))
796 ann.secondaryStructure = jalview.schemes.ResidueProperties
797 .getRNASecStrucState(pos).charAt(0);
801 ann.secondaryStructure = jalview.schemes.ResidueProperties
802 .getDssp3state(pos).charAt(0);
805 if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')
807 ann.displayCharacter = ""; // null; // " ";
811 ann.displayCharacter = " " + ann.displayCharacter;
817 AlignmentAnnotation annot = null;
818 Enumeration e = annotation.elements();
819 while (e.hasMoreElements())
821 annot = (AlignmentAnnotation) e.nextElement();
822 if (annot.label.equals(type))
828 annot = new AlignmentAnnotation(type, type, els);
829 annotation.addElement(annot);
833 Annotation[] anns = new Annotation[annot.annotations.length
835 System.arraycopy(annot.annotations, 0, anns, 0,
836 annot.annotations.length);
837 System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
838 annot.annotations = anns;
839 // System.out.println("else: ");
844 public String print(SequenceI[] s)
846 // find max length of id
850 Hashtable dataRef = null;
851 while ((in < s.length) && (s[in] != null))
853 String tmp = printId(s[in]);
854 if (s[in].getSequence().length > max)
856 max = s[in].getSequence().length;
859 if (tmp.length() > maxid)
861 maxid = tmp.length();
863 if (s[in].getDBRef() != null)
865 for (int idb = 0; idb < s[in].getDBRef().length; idb++)
868 dataRef = new Hashtable();
870 String datAs1 = s[in].getDBRef()[idb].getSource().toString()
872 + s[in].getDBRef()[idb].getAccessionId().toString();
873 dataRef.put(tmp, datAs1);
881 // output database type
882 if (al.getProperties() != null)
884 if (!al.getProperties().isEmpty())
886 Enumeration key = al.getProperties().keys();
887 Enumeration val = al.getProperties().elements();
888 while (key.hasMoreElements())
890 out.append("#=GF " + key.nextElement() + " " + val.nextElement());
896 // output database accessions
899 Enumeration en = dataRef.keys();
900 while (en.hasMoreElements())
902 Object idd = en.nextElement();
903 String type = (String) dataRef.remove(idd);
904 out.append(new Format("%-" + (maxid - 2) + "s").form("#=GS "
905 + idd.toString() + " "));
906 if (type.contains("PFAM") || type.contains("RFAM"))
909 out.append(" AC " + type.substring(type.indexOf(";") + 1));
913 out.append(" DR " + type + " ");
919 // output annotations
920 while (i < s.length && s[i] != null)
922 if (s[i].getDatasetSequence() != null)
924 SequenceI ds = s[i].getDatasetSequence();
925 AlignmentAnnotation[] alAnot;
928 alAnot = s[i].getAnnotation();
932 for (int j = 0; j < alAnot.length; j++)
934 if (ds.getSequenceFeatures() != null)
936 feature = ds.getSequenceFeatures()[0].type;
938 String key = type2id(feature);
943 // out.append("#=GR ");
944 out.append(new Format("%-" + maxid + "s").form("#=GR "
945 + printId(s[i]) + " " + key + " "));
946 ann = alAnot[j].annotations;
948 for (int k = 0; k < ann.length; k++)
951 String ch = (annot == null) ? Character.toString(s[i]
952 .getCharAt(k)) : annot.displayCharacter;
953 if (ch.length() == 0)
955 if (key.equals("SS"))
957 char ll = annot.secondaryStructure;
958 seq = (Character.toString(ll).equals(" ")) ? seq + "C"
966 else if (ch.length() == 1)
970 else if (ch.length() > 1)
981 out.append(new Format("%-" + maxid + "s").form(printId(s[i]) + " "));
982 out.append(s[i].getSequenceAsString());
987 // alignment annotation
988 AlignmentAnnotation aa;
989 if (al.getAlignmentAnnotation() != null)
991 for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++)
993 aa = al.getAlignmentAnnotation()[ia];
994 if (aa.autoCalculated || !aa.visible)
1001 if (aa.label.equals("seq"))
1004 label = type2id(aa.label.toLowerCase()) + "_cons";
1009 out.append(new Format("%-" + maxid + "s").form("#=GC " + label
1011 for (int j = 0; j < aa.annotations.length; j++)
1013 String ch = (aa.annotations[j] == null) ? "-"
1014 : aa.annotations[j].displayCharacter;
1015 if (ch.length() == 0)
1017 char ll = aa.annotations[j].secondaryStructure;
1018 if (Character.toString(ll).equals(" "))
1023 else if (ch.length() == 1)
1027 else if (ch.length() > 1)
1029 seq += ch.charAt(1);
1033 out.append(newline);
1036 return out.toString();
1039 public String print()
1041 out = new StringBuffer();
1042 out.append("# STOCKHOLM 1.0");
1043 out.append(newline);
1044 print(getSeqsAsArray());
1047 out.append(newline);
1048 return out.toString();
1051 private static Hashtable typeIds = null;
1054 if (typeIds == null)
1056 typeIds = new Hashtable();
1057 typeIds.put("SS", "secondary structure");
1058 typeIds.put("SA", "surface accessibility");
1059 typeIds.put("TM", "transmembrane");
1060 typeIds.put("PP", "posterior probability");
1061 typeIds.put("LI", "ligand binding");
1062 typeIds.put("AS", "active site");
1063 typeIds.put("IN", "intron");
1064 typeIds.put("IR", "interacting residue");
1065 typeIds.put("AC", "accession");
1066 typeIds.put("OS", "organism");
1067 typeIds.put("CL", "class");
1068 typeIds.put("DE", "description");
1069 typeIds.put("DR", "reference");
1070 typeIds.put("LO", "look");
1071 typeIds.put("RF", "reference positions");
1076 protected static String id2type(String id)
1078 if (typeIds.containsKey(id))
1080 return (String) typeIds.get(id);
1082 System.err.println("Warning : Unknown Stockholm annotation type code "
1087 protected static String type2id(String type)
1090 Enumeration e = typeIds.keys();
1091 while (e.hasMoreElements())
1093 Object ll = e.nextElement();
1094 if (typeIds.get(ll).toString().equals(type))
1102 return (String) key;
1104 System.err.println("Warning : Unknown Stockholm annotation type: "
1109 * make a friendly ID string.
1112 * @return truncated dataName to after last '/'
1114 private String safeName(String dataName)
1117 while ((b = dataName.indexOf("/")) > -1 && b < dataName.length())
1119 dataName = dataName.substring(b + 1).trim();
1122 int e = (dataName.length() - dataName.indexOf(".")) + 1;
1123 dataName = dataName.substring(1, e).trim();