2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.1)
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 of the License, or (at your option) any later version.
11 * Jalview is distributed in the hope that it will be useful, but
12 * WITHOUT ANY WARRANTY; without even the implied warranty
13 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
14 * PURPOSE. See the GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
17 * The Jalview Authors are detailed in the 'AUTHORS' file.
20 * This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk
24 import jalview.datamodel.AlignmentI;
25 import jalview.datamodel.AlignmentAnnotation;
26 import jalview.datamodel.AlignmentI;
27 import jalview.datamodel.Annotation;
28 import jalview.datamodel.DBRefEntry;
29 import jalview.datamodel.Mapping;
30 import jalview.datamodel.Sequence;
31 import jalview.datamodel.SequenceFeature;
32 import jalview.datamodel.SequenceI;
33 import jalview.util.Format;
35 import java.io.BufferedReader;
36 import java.io.FileReader;
37 import java.io.IOException;
38 import java.util.ArrayList;
39 import java.util.Enumeration;
40 import java.util.Hashtable;
41 import java.util.List;
42 import java.util.StringTokenizer;
43 import java.util.Vector;
45 import com.stevesoft.pat.Regex;
47 import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
48 import fr.orsay.lri.varna.factories.RNAFactory;
49 import fr.orsay.lri.varna.models.rna.RNA;
51 // import org.apache.log4j.*;
54 * This class is supposed to parse a Stockholm format file into Jalview There
55 * are TODOs in this class: we do not know what the database source and version
56 * is for the file when parsing the #GS= AC tag which associates accessions with
57 * sequences. Database references are also not parsed correctly: a separate
58 * reference string parser must be added to parse the database reference form
59 * into Jalview's local representation.
61 * @author bsb at sanger.ac.uk
62 * @author Natasha Shersnev (Dundee, UK) (Stockholm file writer)
63 * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as stockholm)
64 * @author Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data)
65 * @version 0.3 + jalview mods
68 public class StockholmFile extends AlignFile
70 // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");
71 protected ArrayList<RNA> result;
72 StringBuffer out; // output buffer
76 public StockholmFile()
81 * Creates a new StockholmFile object for output.
83 public StockholmFile(AlignmentI al)
88 public StockholmFile(String inFile, String type) throws IOException
93 public StockholmFile(FileParse source) throws IOException
98 public void initData()
103 * Parse a file in Stockholm format into Jalview's data model using VARNA
105 * @throws IOException
106 * If there is an error with the input file
108 public void parse_with_VARNA(java.io.File inFile) throws IOException
110 FileReader fr = null;
111 fr = new FileReader(inFile);
113 BufferedReader r = new BufferedReader(fr);
117 result = RNAFactory.loadSecStrStockholm(r);
118 } catch (ExceptionUnmatchedClosingParentheses umcp)
120 errormessage = "Unmatched parentheses in annotation. Aborting ("
121 + umcp.getMessage() + ")";
122 throw new IOException(umcp);
124 // DEBUG System.out.println("this is the secondary scructure:"
126 SequenceI[] seqs = new SequenceI[result.size()];
128 for (int i = 0; i < result.size(); i++)
130 // DEBUG System.err.println("Processing i'th sequence in Stockholm file")
131 RNA current = result.get(i);
133 String seq = current.getSeq();
134 String rna = current.getStructDBN(true);
135 // DEBUG System.out.println(seq);
136 // DEBUG System.err.println(rna);
138 int end = seq.length() - 1;
139 id = safeName(getDataName());
140 seqs[i] = new Sequence(id, seq, begin, end);
141 String[] annot = new String[rna.length()];
142 Annotation[] ann = new Annotation[rna.length()];
143 for (int j = 0; j < rna.length(); j++)
145 annot[j] = rna.substring(j, j + 1);
149 for (int k = 0; k < rna.length(); k++)
151 ann[k] = new Annotation(annot[k], "",
152 jalview.schemes.ResidueProperties.getRNASecStrucState(
153 annot[k]).charAt(0), 0f);
156 AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.",
157 current.getID(), ann);
159 seqs[i].addAlignmentAnnotation(align);
160 seqs[i].setRNA(result.get(i));
161 this.annotations.addElement(align);
169 * Parse a file in Stockholm format into Jalview's data model. The file has to
170 * be passed at construction time
172 * @throws IOException
173 * If there is an error with the input file
175 public void parse() throws IOException
177 StringBuffer treeString = new StringBuffer();
178 String treeName = null;
179 // --------------- Variable Definitions -------------------
183 Hashtable seqAnn = new Hashtable(); // Sequence related annotations
184 Hashtable seqs = new Hashtable();
185 Regex p, r, rend, s, x;
186 // Temporary line for processing RNA annotation
187 // String RNAannot = "";
189 // ------------------ Parsing File ----------------------
190 // First, we have to check that this file has STOCKHOLM format, i.e. the
191 // first line must match
194 r = new Regex("# STOCKHOLM ([\\d\\.]+)");
195 if (!r.search(nextLine()))
197 throw new IOException(
198 "This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");
202 version = r.stringMatched(1);
204 // logger.debug("Stockholm version: " + version);
207 // We define some Regexes here that will be used regularily later
208 rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
209 p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
211 s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
212 r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
213 x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
215 // Convert all bracket types to parentheses (necessary for passing to VARNA)
216 Regex openparen = new Regex("(<|\\[)", "(");
217 Regex closeparen = new Regex("(>|\\])", ")");
219 // Detect if file is RNA by looking for bracket types
220 Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
227 openparen.optimize();
228 closeparen.optimize();
230 while ((line = nextLine()) != null)
232 if (line.length() == 0)
236 if (rend.search(line))
238 // End of the alignment, pass stuff back
239 this.noSeqs = seqs.size();
241 String seqdb,dbsource = null;
242 Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
243 Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
244 if (getAlignmentProperty("AC") != null)
246 String dbType = getAlignmentProperty("AC").toString();
247 if (pf.search(dbType))
249 // PFAM Alignment - so references are typically from Uniprot
252 else if (rf.search(dbType))
257 // logger.debug("Number of sequences: " + this.noSeqs);
258 Enumeration accs = seqs.keys();
259 while (accs.hasMoreElements())
261 String acc = (String) accs.nextElement();
262 // logger.debug("Processing sequence " + acc);
263 String seq = (String) seqs.remove(acc);
264 if (maxLength < seq.length())
266 maxLength = seq.length();
272 * Retrieve hash of annotations for this accession Associate
273 * Annotation with accession
275 Hashtable accAnnotations = null;
277 if (seqAnn != null && seqAnn.containsKey(acc))
279 accAnnotations = (Hashtable) seqAnn.remove(acc);
280 //TODO: add structures to sequence
283 // Split accession in id and from/to
286 sid = p.stringMatched(1);
287 start = Integer.parseInt(p.stringMatched(2));
288 end = Integer.parseInt(p.stringMatched(3));
290 // logger.debug(sid + ", " + start + ", " + end);
292 Sequence seqO = new Sequence(sid, seq, start, end);
293 // Add Description (if any)
294 if (accAnnotations != null && accAnnotations.containsKey("DE"))
296 String desc = (String) accAnnotations.get("DE");
297 seqO.setDescription((desc == null) ? "" : desc);
299 // Add DB References (if any)
300 if (accAnnotations != null && accAnnotations.containsKey("DR"))
302 String dbr = (String) accAnnotations.get("DR");
303 if (dbr != null && dbr.indexOf(";") > -1)
305 String src = dbr.substring(0, dbr.indexOf(";"));
306 String acn = dbr.substring(dbr.indexOf(";") + 1);
307 jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);
311 if (accAnnotations != null && accAnnotations.containsKey("AC"))
313 if (dbsource != null)
315 String dbr = (String) accAnnotations.get("AC");
318 // we could get very clever here - but for now - just try to guess accession type from source of alignment plus structure of accession
319 guessDatabaseFor(seqO, dbr, dbsource);
323 // else - do what ? add the data anyway and prompt the user to specify what references these are ?
326 Hashtable features = null;
327 // We need to adjust the positions of all features to account for gaps
330 features = (Hashtable) accAnnotations.remove("features");
331 } catch (java.lang.NullPointerException e)
333 // loggerwarn("Getting Features for " + acc + ": " +
337 // if we have features
338 if (features != null)
340 int posmap[] = seqO.findPositionMap();
341 Enumeration i = features.keys();
342 while (i.hasMoreElements())
344 // TODO: parse out secondary structure annotation as annotation
346 // TODO: parse out scores as annotation row
347 // TODO: map coding region to core jalview feature types
348 String type = i.nextElement().toString();
349 Hashtable content = (Hashtable) features.remove(type);
351 // add alignment annotation for this feature
352 String key = type2id(type);
355 if (accAnnotations != null
356 && accAnnotations.containsKey(key))
358 Vector vv = (Vector) accAnnotations.get(key);
359 for (int ii = 0; ii < vv.size(); ii++)
361 AlignmentAnnotation an = (AlignmentAnnotation) vv
363 seqO.addAlignmentAnnotation(an);
368 Enumeration j = content.keys();
369 while (j.hasMoreElements())
371 String desc = j.nextElement().toString();
372 String ns = content.get(desc).toString();
373 char[] byChar = ns.toCharArray();
374 for (int k = 0; k < byChar.length; k++)
377 if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM
384 int new_pos = posmap[k]; // look up nearest seqeunce
385 // position to this column
386 SequenceFeature feat = new SequenceFeature(type, desc,
387 new_pos, new_pos, 0f, null);
389 seqO.addSequenceFeature(feat);
399 // logger.debug("Adding seq " + acc + " from " + start + " to " + end
401 this.seqs.addElement(seqO);
403 return; // finished parsing this segment of source
405 else if (!r.search(line))
407 // System.err.println("Found sequence line: " + line);
409 // Split sequence in sequence and accession parts
412 // logger.error("Could not parse sequence line: " + line);
413 throw new IOException("Could not parse sequence line: " + line);
415 String ns = (String) seqs.get(x.stringMatched(1));
420 ns += x.stringMatched(2);
422 seqs.put(x.stringMatched(1), ns);
426 String annType = r.stringMatched(1);
427 String annContent = r.stringMatched(2);
429 // System.err.println("type:" + annType + " content: " + annContent);
431 if (annType.equals("GF"))
434 * Generic per-File annotation, free text Magic features: #=GF NH
435 * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier
436 * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS
438 * Compulsory fields: ------------------
440 * AC Accession number: Accession number in form PFxxxxx.version or
441 * PBxxxxxx. ID Identification: One word name for family. DE
442 * Definition: Short description of family. AU Author: Authors of the
443 * entry. SE Source of seed: The source suggesting the seed members
444 * belong to one family. GA Gathering method: Search threshold to
445 * build the full alignment. TC Trusted Cutoff: Lowest sequence score
446 * and domain score of match in the full alignment. NC Noise Cutoff:
447 * Highest sequence score and domain score of match not in full
448 * alignment. TP Type: Type of family -- presently Family, Domain,
449 * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM
450 * Alignment Method The order ls and fs hits are aligned to the model
451 * to build the full align. // End of alignment.
453 * Optional fields: ----------------
455 * DC Database Comment: Comment about database reference. DR Database
456 * Reference: Reference to external database. RC Reference Comment:
457 * Comment about literature reference. RN Reference Number: Reference
458 * Number. RM Reference Medline: Eight digit medline UI number. RT
459 * Reference Title: Reference Title. RA Reference Author: Reference
460 * Author RL Reference Location: Journal location. PI Previous
461 * identifier: Record of all previous ID lines. KW Keywords: Keywords.
462 * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.
463 * NL Location: Location of nested domains - sequence ID, start and
466 * Obsolete fields: ----------- AL Alignment method of seed: The
467 * method used to align the seed members.
469 // Let's save the annotations, maybe we'll be able to do something
470 // with them later...
471 Regex an = new Regex("(\\w+)\\s*(.*)");
472 if (an.search(annContent))
474 if (an.stringMatched(1).equals("NH"))
476 treeString.append(an.stringMatched(2));
478 else if (an.stringMatched(1).equals("TN"))
480 if (treeString.length() > 0)
482 if (treeName == null)
484 treeName = "Tree " + (getTreeCount() + 1);
486 addNewickTree(treeName, treeString.toString());
488 treeName = an.stringMatched(2);
489 treeString = new StringBuffer();
491 setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
494 else if (annType.equals("GS"))
496 // Generic per-Sequence annotation, free text
498 * Pfam uses these features: Feature Description ---------------------
499 * ----------- AC <accession> ACcession number DE <freetext>
500 * DEscription DR <db>; <accession>; Database Reference OS <organism>
501 * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)
502 * LO <look> Look (Color, etc.)
504 if (s.search(annContent))
506 String acc = s.stringMatched(1);
507 String type = s.stringMatched(2);
508 String content = s.stringMatched(3);
509 // TODO: store DR in a vector.
510 // TODO: store AC according to generic file db annotation.
512 if (seqAnn.containsKey(acc))
514 ann = (Hashtable) seqAnn.get(acc);
518 ann = new Hashtable();
520 ann.put(type, content);
521 seqAnn.put(acc, ann);
525 throw new IOException("Error parsing " + line);
528 else if (annType.equals("GC"))
530 // Generic per-Column annotation, exactly 1 char per column
531 // always need a label.
532 if (x.search(annContent))
534 // parse out and create alignment annotation directly.
535 parseAnnotationRow(annotations, x.stringMatched(1),
539 else if (annType.equals("GR"))
541 // Generic per-Sequence AND per-Column markup, exactly 1 char per
544 * Feature Description Markup letters ------- -----------
545 * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface
546 * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane
547 * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;
548 * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in
551 if (s.search(annContent))
553 String acc = s.stringMatched(1);
554 String type = s.stringMatched(2);
555 String seq = new String(s.stringMatched(3));
556 String description = null;
557 // Check for additional information about the current annotation
558 // We use a simple string tokenizer here for speed
559 StringTokenizer sep = new StringTokenizer(seq, " \t");
560 description = sep.nextToken();
561 if (sep.hasMoreTokens())
563 seq = sep.nextToken();
568 description = new String();
570 // sequence id with from-to fields
573 // Get an object with all the annotations for this sequence
574 if (seqAnn.containsKey(acc))
576 // logger.debug("Found annotations for " + acc);
577 ann = (Hashtable) seqAnn.get(acc);
581 // logger.debug("Creating new annotations holder for " + acc);
582 ann = new Hashtable();
583 seqAnn.put(acc, ann);
585 // TODO test structure, call parseAnnotationRow with vector from
586 // hashtable for specific sequence
588 // Get an object with all the content for an annotation
589 if (ann.containsKey("features"))
591 // logger.debug("Found features for " + acc);
592 features = (Hashtable) ann.get("features");
596 // logger.debug("Creating new features holder for " + acc);
597 features = new Hashtable();
598 ann.put("features", features);
602 if (features.containsKey(this.id2type(type)))
604 // logger.debug("Found content for " + this.id2type(type));
605 content = (Hashtable) features.get(this.id2type(type));
609 // logger.debug("Creating new content holder for " +
610 // this.id2type(type));
611 content = new Hashtable();
612 features.put(this.id2type(type), content);
614 String ns = (String) content.get(description);
620 content.put(description, ns);
622 // if(type.equals("SS")){
624 if (seqAnn.containsKey(acc))
626 strucAnn = (Hashtable) seqAnn.get(acc);
630 strucAnn = new Hashtable();
633 Vector newStruc=new Vector();
634 parseAnnotationRow(newStruc, type,ns);
636 strucAnn.put(type, newStruc);
637 seqAnn.put(acc, strucAnn);
643 .println("Warning - couldn't parse sequence annotation row line:\n"
645 // throw new IOException("Error parsing " + line);
650 throw new IOException("Unknown annotation detected: " + annType
655 if (treeString.length() > 0)
657 if (treeName == null)
659 treeName = "Tree " + (1 + getTreeCount());
661 addNewickTree(treeName, treeString.toString());
666 * Demangle an accession string and guess the originating sequence database for a given sequence
667 * @param seqO sequence to be annotated
668 * @param dbr Accession string for sequence
669 * @param dbsource source database for alignment (PFAM or RFAM)
671 private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)
673 DBRefEntry dbrf=null;
674 List<DBRefEntry> dbrs=new ArrayList<DBRefEntry>();
675 String seqdb="Unknown",sdbac=""+dbr;
677 if ((st=sdbac.indexOf("/"))>-1)
679 String num,range=sdbac.substring(st+1);
680 sdbac = sdbac.substring(0,st);
681 if ((p=range.indexOf("-"))>-1)
684 if (p<range.length())
686 num = range.substring(p).trim();
688 en = Integer.parseInt(num);
689 } catch (NumberFormatException x)
691 // could warn here that index is invalid
698 num=range.substring(0,p).trim();
700 st = Integer.parseInt(num);
701 } catch (NumberFormatException x)
703 // could warn here that index is invalid
707 if (dbsource.equals("PFAM")) {
709 if (sdbac.indexOf(".")>-1)
711 // strip of last subdomain
712 sdbac = sdbac.substring(0,sdbac.indexOf("."));
713 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);
719 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);
725 seqdb = "EMBL"; // total guess - could be ENA, or something else these days
726 if (sdbac.indexOf(".")>-1)
728 // strip off last subdomain
729 sdbac = sdbac.substring(0,sdbac.indexOf("."));
730 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);
737 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);
743 if (st!=-1 && en!=-1)
745 for (DBRefEntry d:dbrs)
747 jalview.util.MapList mp = new jalview.util.MapList(new int[] { seqO.getStart(),seqO.getEnd()},new int[] { st,en},1,1);
748 jalview.datamodel.Mapping mping = new Mapping(mp);
754 protected static AlignmentAnnotation parseAnnotationRow(
755 Vector annotation, String label, String annots)
757 String convert1, convert2 = null;
759 // Convert all bracket types to parentheses
760 Regex openparen = new Regex("(<|\\[)", "(");
761 Regex closeparen = new Regex("(>|\\])", ")");
763 // Detect if file is RNA by looking for bracket types
764 Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
766 convert1 = openparen.replaceAll(annots);
767 convert2 = closeparen.replaceAll(convert1);
771 if (label.contains("_cons"))
773 type = (label.indexOf("_cons") == label.length() - 5) ? label
774 .substring(0, label.length() - 5) : label;
777 type = id2type(type);
778 if (type.equals("secondary structure"))
782 // decide on secondary structure or not.
783 Annotation[] els = new Annotation[annots.length()];
784 for (int i = 0; i < annots.length(); i++)
786 String pos = annots.substring(i, i + 1);
788 ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
792 if (detectbrackets.search(pos))
794 ann.secondaryStructure = jalview.schemes.ResidueProperties
795 .getRNASecStrucState(pos).charAt(0);
799 ann.secondaryStructure = jalview.schemes.ResidueProperties
800 .getDssp3state(pos).charAt(0);
803 if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')
805 ann.displayCharacter = ""; // null; // " ";
809 ann.displayCharacter = " " + ann.displayCharacter;
815 AlignmentAnnotation annot = null;
816 Enumeration e = annotation.elements();
817 while (e.hasMoreElements())
819 annot = (AlignmentAnnotation) e.nextElement();
820 if (annot.label.equals(type))
826 annot = new AlignmentAnnotation(type, type, els);
827 annotation.addElement(annot);
831 Annotation[] anns = new Annotation[annot.annotations.length
833 System.arraycopy(annot.annotations, 0, anns, 0,
834 annot.annotations.length);
835 System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
836 annot.annotations = anns;
837 // System.out.println("else: ");
842 public String print(SequenceI[] s)
844 // find max length of id
848 Hashtable dataRef = null;
849 while ((in < s.length) && (s[in] != null))
851 String tmp = printId(s[in]);
852 if (s[in].getSequence().length > max)
854 max = s[in].getSequence().length;
857 if (tmp.length() > maxid)
859 maxid = tmp.length();
861 if (s[in].getDBRef() != null)
863 for (int idb = 0; idb < s[in].getDBRef().length; idb++)
866 dataRef = new Hashtable();
868 String datAs1 = s[in].getDBRef()[idb].getSource().toString()
870 + s[in].getDBRef()[idb].getAccessionId().toString();
871 dataRef.put(tmp, datAs1);
879 // output database type
880 if (al.getProperties() != null)
882 if (!al.getProperties().isEmpty())
884 Enumeration key = al.getProperties().keys();
885 Enumeration val = al.getProperties().elements();
886 while (key.hasMoreElements())
888 out.append("#=GF " + key.nextElement() + " " + val.nextElement());
894 // output database accessions
897 Enumeration en = dataRef.keys();
898 while (en.hasMoreElements())
900 Object idd = en.nextElement();
901 String type = (String) dataRef.remove(idd);
902 out.append(new Format("%-" + (maxid - 2) + "s").form("#=GS "
903 + idd.toString() + " "));
904 if (type.contains("PFAM") || type.contains("RFAM"))
907 out.append(" AC " + type.substring(type.indexOf(";") + 1));
911 out.append(" DR " + type + " ");
917 // output annotations
918 while (i < s.length && s[i] != null)
920 if (s[i].getDatasetSequence() != null)
922 SequenceI ds = s[i].getDatasetSequence();
923 AlignmentAnnotation[] alAnot;
926 alAnot = s[i].getAnnotation();
930 for (int j = 0; j < alAnot.length; j++)
932 if (ds.getSequenceFeatures() != null)
934 feature = ds.getSequenceFeatures()[0].type;
936 String key = type2id(feature);
941 // out.append("#=GR ");
942 out.append(new Format("%-" + maxid + "s").form("#=GR "
943 + printId(s[i]) + " " + key + " "));
944 ann = alAnot[j].annotations;
946 for (int k = 0; k < ann.length; k++)
949 String ch = (annot == null) ? Character.toString(s[i]
950 .getCharAt(k)) : annot.displayCharacter;
951 if (ch.length() == 0)
953 if (key.equals("SS"))
955 char ll = annot.secondaryStructure;
956 seq = (Character.toString(ll).equals(" ")) ? seq + "C"
964 else if (ch.length() == 1)
968 else if (ch.length() > 1)
979 out.append(new Format("%-" + maxid + "s").form(printId(s[i]) + " "));
980 out.append(s[i].getSequenceAsString());
985 // alignment annotation
986 AlignmentAnnotation aa;
987 if (al.getAlignmentAnnotation() != null)
989 for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++)
991 aa = al.getAlignmentAnnotation()[ia];
992 if (aa.autoCalculated || !aa.visible)
999 if (aa.label.equals("seq"))
1002 label = type2id(aa.label.toLowerCase()) + "_cons";
1007 out.append(new Format("%-" + maxid + "s").form("#=GC " + label
1009 for (int j = 0; j < aa.annotations.length; j++)
1011 String ch = (aa.annotations[j] == null) ? "-"
1012 : aa.annotations[j].displayCharacter;
1013 if (ch.length() == 0)
1015 char ll = aa.annotations[j].secondaryStructure;
1016 if (Character.toString(ll).equals(" "))
1021 else if (ch.length() == 1)
1025 else if (ch.length() > 1)
1027 seq += ch.charAt(1);
1031 out.append(newline);
1034 return out.toString();
1037 public String print()
1039 out = new StringBuffer();
1040 out.append("# STOCKHOLM 1.0");
1041 out.append(newline);
1042 print(getSeqsAsArray());
1045 out.append(newline);
1046 return out.toString();
1049 private static Hashtable typeIds = null;
1052 if (typeIds == null)
1054 typeIds = new Hashtable();
1055 typeIds.put("SS", "secondary structure");
1056 typeIds.put("SA", "surface accessibility");
1057 typeIds.put("TM", "transmembrane");
1058 typeIds.put("PP", "posterior probability");
1059 typeIds.put("LI", "ligand binding");
1060 typeIds.put("AS", "active site");
1061 typeIds.put("IN", "intron");
1062 typeIds.put("IR", "interacting residue");
1063 typeIds.put("AC", "accession");
1064 typeIds.put("OS", "organism");
1065 typeIds.put("CL", "class");
1066 typeIds.put("DE", "description");
1067 typeIds.put("DR", "reference");
1068 typeIds.put("LO", "look");
1069 typeIds.put("RF", "reference positions");
1074 protected static String id2type(String id)
1076 if (typeIds.containsKey(id))
1078 return (String) typeIds.get(id);
1080 System.err.println("Warning : Unknown Stockholm annotation type code "
1085 protected static String type2id(String type)
1088 Enumeration e = typeIds.keys();
1089 while (e.hasMoreElements())
1091 Object ll = e.nextElement();
1092 if (typeIds.get(ll).toString().equals(type))
1100 return (String) key;
1102 System.err.println("Warning : Unknown Stockholm annotation type: "
1107 * make a friendly ID string.
1110 * @return truncated dataName to after last '/'
1112 private String safeName(String dataName)
1115 while ((b = dataName.indexOf("/")) > -1 && b < dataName.length())
1117 dataName = dataName.substring(b + 1).trim();
1120 int e = (dataName.length() - dataName.indexOf(".")) + 1;
1121 dataName = dataName.substring(1, e).trim();