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.AlignmentAnnotation;
27 import jalview.datamodel.AlignmentI;
28 import jalview.datamodel.Annotation;
29 import jalview.datamodel.DBRefEntry;
30 import jalview.datamodel.Mapping;
31 import jalview.datamodel.Sequence;
32 import jalview.datamodel.SequenceFeature;
33 import jalview.datamodel.SequenceI;
34 import jalview.util.Format;
35 import jalview.util.MessageManager;
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.LinkedHashMap;
44 import java.util.List;
46 import java.util.StringTokenizer;
47 import java.util.Vector;
49 import com.stevesoft.pat.Regex;
51 import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
52 import fr.orsay.lri.varna.factories.RNAFactory;
53 import fr.orsay.lri.varna.models.rna.RNA;
55 // import org.apache.log4j.*;
58 * This class is supposed to parse a Stockholm format file into Jalview There
59 * are TODOs in this class: we do not know what the database source and version
60 * is for the file when parsing the #GS= AC tag which associates accessions with
61 * sequences. Database references are also not parsed correctly: a separate
62 * reference string parser must be added to parse the database reference form
63 * into Jalview's local representation.
65 * @author bsb at sanger.ac.uk
66 * @author Natasha Shersnev (Dundee, UK) (Stockholm file writer)
67 * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as
69 * @author Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data)
70 * @version 0.3 + jalview mods
73 public class StockholmFile extends AlignFile
75 // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");
76 protected ArrayList<RNA> result;
78 StringBuffer out; // output buffer
82 public StockholmFile()
87 * Creates a new StockholmFile object for output.
89 public StockholmFile(AlignmentI al)
94 public StockholmFile(String inFile, String type) throws IOException
99 public StockholmFile(FileParse source) throws IOException
104 public void initData()
110 * Parse a file in Stockholm format into Jalview's data model using VARNA
112 * @throws IOException
113 * If there is an error with the input file
115 public void parse_with_VARNA(java.io.File inFile) throws IOException
117 FileReader fr = null;
118 fr = new FileReader(inFile);
120 BufferedReader r = new BufferedReader(fr);
124 result = RNAFactory.loadSecStrStockholm(r);
125 } catch (ExceptionUnmatchedClosingParentheses umcp)
127 errormessage = "Unmatched parentheses in annotation. Aborting ("
128 + umcp.getMessage() + ")";
129 throw new IOException(umcp);
131 // DEBUG System.out.println("this is the secondary scructure:"
133 SequenceI[] seqs = new SequenceI[result.size()];
135 for (int i = 0; i < result.size(); i++)
137 // DEBUG System.err.println("Processing i'th sequence in Stockholm file")
138 RNA current = result.get(i);
140 String seq = current.getSeq();
141 String rna = current.getStructDBN(true);
142 // DEBUG System.out.println(seq);
143 // DEBUG System.err.println(rna);
145 int end = seq.length() - 1;
146 id = safeName(getDataName());
147 seqs[i] = new Sequence(id, seq, begin, end);
148 String[] annot = new String[rna.length()];
149 Annotation[] ann = new Annotation[rna.length()];
150 for (int j = 0; j < rna.length(); j++)
152 annot[j] = rna.substring(j, j + 1);
156 for (int k = 0; k < rna.length(); k++)
158 ann[k] = new Annotation(annot[k], "",
159 jalview.schemes.ResidueProperties.getRNASecStrucState(
160 annot[k]).charAt(0), 0f);
163 AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.",
164 current.getID(), ann);
166 seqs[i].addAlignmentAnnotation(align);
167 seqs[i].setRNA(result.get(i));
168 this.annotations.addElement(align);
175 * Parse a file in Stockholm format into Jalview's data model. The file has to
176 * be passed at construction time
178 * @throws IOException
179 * If there is an error with the input file
181 public void parse() throws IOException
183 StringBuffer treeString = new StringBuffer();
184 String treeName = null;
185 // --------------- Variable Definitions -------------------
189 Hashtable seqAnn = new Hashtable(); // Sequence related annotations
190 LinkedHashMap<String, String> seqs = new LinkedHashMap<String, String>();
191 Regex p, r, rend, s, x;
192 // Temporary line for processing RNA annotation
193 // String RNAannot = "";
195 // ------------------ Parsing File ----------------------
196 // First, we have to check that this file has STOCKHOLM format, i.e. the
197 // first line must match
199 r = new Regex("# STOCKHOLM ([\\d\\.]+)");
200 if (!r.search(nextLine()))
202 throw new IOException(MessageManager.getString("exception.stockholm_invalid_format"));
206 version = r.stringMatched(1);
208 // logger.debug("Stockholm version: " + version);
211 // We define some Regexes here that will be used regularily later
212 rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
213 p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
215 s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
216 r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
217 x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
219 // Convert all bracket types to parentheses (necessary for passing to VARNA)
220 Regex openparen = new Regex("(<|\\[)", "(");
221 Regex closeparen = new Regex("(>|\\])", ")");
223 // Detect if file is RNA by looking for bracket types
224 Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
231 openparen.optimize();
232 closeparen.optimize();
234 while ((line = nextLine()) != null)
236 if (line.length() == 0)
240 if (rend.search(line))
242 // End of the alignment, pass stuff back
243 this.noSeqs = seqs.size();
245 String seqdb, dbsource = null;
246 Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
247 Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
248 if (getAlignmentProperty("AC") != null)
250 String dbType = getAlignmentProperty("AC").toString();
251 if (pf.search(dbType))
253 // PFAM Alignment - so references are typically from Uniprot
256 else if (rf.search(dbType))
261 // logger.debug("Number of sequences: " + this.noSeqs);
262 for (Map.Entry<String, String> skey : seqs.entrySet())
264 // logger.debug("Processing sequence " + acc);
265 String acc = skey.getKey();
266 String seq = skey.getValue();
267 if (maxLength < seq.length())
269 maxLength = seq.length();
275 * Retrieve hash of annotations for this accession Associate
276 * Annotation with accession
278 Hashtable accAnnotations = null;
280 if (seqAnn != null && seqAnn.containsKey(acc))
282 accAnnotations = (Hashtable) seqAnn.remove(acc);
283 // TODO: add structures to sequence
286 // Split accession in id and from/to
289 sid = p.stringMatched(1);
290 start = Integer.parseInt(p.stringMatched(2));
291 end = Integer.parseInt(p.stringMatched(3));
293 // logger.debug(sid + ", " + start + ", " + end);
295 Sequence seqO = new Sequence(sid, seq, start, end);
296 // Add Description (if any)
297 if (accAnnotations != null && accAnnotations.containsKey("DE"))
299 String desc = (String) accAnnotations.get("DE");
300 seqO.setDescription((desc == null) ? "" : desc);
302 // Add DB References (if any)
303 if (accAnnotations != null && accAnnotations.containsKey("DR"))
305 String dbr = (String) accAnnotations.get("DR");
306 if (dbr != null && dbr.indexOf(";") > -1)
308 String src = dbr.substring(0, dbr.indexOf(";"));
309 String acn = dbr.substring(dbr.indexOf(";") + 1);
310 jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);
314 if (accAnnotations != null && accAnnotations.containsKey("AC"))
316 if (dbsource != null)
318 String dbr = (String) accAnnotations.get("AC");
321 // we could get very clever here - but for now - just try to
322 // guess accession type from source of alignment plus structure
324 guessDatabaseFor(seqO, dbr, dbsource);
328 // else - do what ? add the data anyway and prompt the user to
329 // specify what references these are ?
332 Hashtable features = null;
333 // We need to adjust the positions of all features to account for gaps
336 features = (Hashtable) accAnnotations.remove("features");
337 } catch (java.lang.NullPointerException e)
339 // loggerwarn("Getting Features for " + acc + ": " +
343 // if we have features
344 if (features != null)
346 int posmap[] = seqO.findPositionMap();
347 Enumeration i = features.keys();
348 while (i.hasMoreElements())
350 // TODO: parse out secondary structure annotation as annotation
352 // TODO: parse out scores as annotation row
353 // TODO: map coding region to core jalview feature types
354 String type = i.nextElement().toString();
355 Hashtable content = (Hashtable) features.remove(type);
357 // add alignment annotation for this feature
358 String key = type2id(type);
361 if (accAnnotations != null
362 && accAnnotations.containsKey(key))
364 Vector vv = (Vector) accAnnotations.get(key);
365 for (int ii = 0; ii < vv.size(); ii++)
367 AlignmentAnnotation an = (AlignmentAnnotation) vv
369 seqO.addAlignmentAnnotation(an);
375 Enumeration j = content.keys();
376 while (j.hasMoreElements())
378 String desc = j.nextElement().toString();
379 String ns = content.get(desc).toString();
380 char[] byChar = ns.toCharArray();
381 for (int k = 0; k < byChar.length; k++)
384 if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM
391 int new_pos = posmap[k]; // look up nearest seqeunce
392 // position to this column
393 SequenceFeature feat = new SequenceFeature(type, desc,
394 new_pos, new_pos, 0f, null);
396 seqO.addSequenceFeature(feat);
406 // logger.debug("Adding seq " + acc + " from " + start + " to " + end
408 this.seqs.addElement(seqO);
410 return; // finished parsing this segment of source
412 else if (!r.search(line))
414 // System.err.println("Found sequence line: " + line);
416 // Split sequence in sequence and accession parts
419 // logger.error("Could not parse sequence line: " + line);
420 throw new IOException(MessageManager.formatMessage("exception.couldnt_parse_sequence_line", new String[]{line}));
422 String ns = (String) seqs.get(x.stringMatched(1));
427 ns += x.stringMatched(2);
429 seqs.put(x.stringMatched(1), ns);
433 String annType = r.stringMatched(1);
434 String annContent = r.stringMatched(2);
436 // System.err.println("type:" + annType + " content: " + annContent);
438 if (annType.equals("GF"))
441 * Generic per-File annotation, free text Magic features: #=GF NH
442 * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier
443 * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS
445 * Compulsory fields: ------------------
447 * AC Accession number: Accession number in form PFxxxxx.version or
448 * PBxxxxxx. ID Identification: One word name for family. DE
449 * Definition: Short description of family. AU Author: Authors of the
450 * entry. SE Source of seed: The source suggesting the seed members
451 * belong to one family. GA Gathering method: Search threshold to
452 * build the full alignment. TC Trusted Cutoff: Lowest sequence score
453 * and domain score of match in the full alignment. NC Noise Cutoff:
454 * Highest sequence score and domain score of match not in full
455 * alignment. TP Type: Type of family -- presently Family, Domain,
456 * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM
457 * Alignment Method The order ls and fs hits are aligned to the model
458 * to build the full align. // End of alignment.
460 * Optional fields: ----------------
462 * DC Database Comment: Comment about database reference. DR Database
463 * Reference: Reference to external database. RC Reference Comment:
464 * Comment about literature reference. RN Reference Number: Reference
465 * Number. RM Reference Medline: Eight digit medline UI number. RT
466 * Reference Title: Reference Title. RA Reference Author: Reference
467 * Author RL Reference Location: Journal location. PI Previous
468 * identifier: Record of all previous ID lines. KW Keywords: Keywords.
469 * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.
470 * NL Location: Location of nested domains - sequence ID, start and
473 * Obsolete fields: ----------- AL Alignment method of seed: The
474 * method used to align the seed members.
476 // Let's save the annotations, maybe we'll be able to do something
477 // with them later...
478 Regex an = new Regex("(\\w+)\\s*(.*)");
479 if (an.search(annContent))
481 if (an.stringMatched(1).equals("NH"))
483 treeString.append(an.stringMatched(2));
485 else if (an.stringMatched(1).equals("TN"))
487 if (treeString.length() > 0)
489 if (treeName == null)
491 treeName = "Tree " + (getTreeCount() + 1);
493 addNewickTree(treeName, treeString.toString());
495 treeName = an.stringMatched(2);
496 treeString = new StringBuffer();
498 setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
501 else if (annType.equals("GS"))
503 // Generic per-Sequence annotation, free text
505 * Pfam uses these features: Feature Description ---------------------
506 * ----------- AC <accession> ACcession number DE <freetext>
507 * DEscription DR <db>; <accession>; Database Reference OS <organism>
508 * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)
509 * LO <look> Look (Color, etc.)
511 if (s.search(annContent))
513 String acc = s.stringMatched(1);
514 String type = s.stringMatched(2);
515 String content = s.stringMatched(3);
516 // TODO: store DR in a vector.
517 // TODO: store AC according to generic file db annotation.
519 if (seqAnn.containsKey(acc))
521 ann = (Hashtable) seqAnn.get(acc);
525 ann = new Hashtable();
527 ann.put(type, content);
528 seqAnn.put(acc, ann);
532 throw new IOException(MessageManager.formatMessage("exception.error_parsing_line", new String[]{line}));
535 else if (annType.equals("GC"))
537 // Generic per-Column annotation, exactly 1 char per column
538 // always need a label.
539 if (x.search(annContent))
541 // parse out and create alignment annotation directly.
542 parseAnnotationRow(annotations, x.stringMatched(1),
546 else if (annType.equals("GR"))
548 // Generic per-Sequence AND per-Column markup, exactly 1 char per
551 * Feature Description Markup letters ------- -----------
552 * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface
553 * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane
554 * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;
555 * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in
558 if (s.search(annContent))
560 String acc = s.stringMatched(1);
561 String type = s.stringMatched(2);
562 String seq = new String(s.stringMatched(3));
563 String description = null;
564 // Check for additional information about the current annotation
565 // We use a simple string tokenizer here for speed
566 StringTokenizer sep = new StringTokenizer(seq, " \t");
567 description = sep.nextToken();
568 if (sep.hasMoreTokens())
570 seq = sep.nextToken();
575 description = new String();
577 // sequence id with from-to fields
580 // Get an object with all the annotations for this sequence
581 if (seqAnn.containsKey(acc))
583 // logger.debug("Found annotations for " + acc);
584 ann = (Hashtable) seqAnn.get(acc);
588 // logger.debug("Creating new annotations holder for " + acc);
589 ann = new Hashtable();
590 seqAnn.put(acc, ann);
592 // TODO test structure, call parseAnnotationRow with vector from
593 // hashtable for specific sequence
595 // Get an object with all the content for an annotation
596 if (ann.containsKey("features"))
598 // logger.debug("Found features for " + acc);
599 features = (Hashtable) ann.get("features");
603 // logger.debug("Creating new features holder for " + acc);
604 features = new Hashtable();
605 ann.put("features", features);
609 if (features.containsKey(this.id2type(type)))
611 // logger.debug("Found content for " + this.id2type(type));
612 content = (Hashtable) features.get(this.id2type(type));
616 // logger.debug("Creating new content holder for " +
617 // this.id2type(type));
618 content = new Hashtable();
619 features.put(this.id2type(type), content);
621 String ns = (String) content.get(description);
627 content.put(description, ns);
629 // if(type.equals("SS")){
631 if (seqAnn.containsKey(acc))
633 strucAnn = (Hashtable) seqAnn.get(acc);
637 strucAnn = new Hashtable();
640 Vector<AlignmentAnnotation> newStruc = new Vector<AlignmentAnnotation>();
641 parseAnnotationRow(newStruc, type, ns);
642 for (AlignmentAnnotation alan : newStruc)
644 alan.visible = false;
646 // annotations.addAll(newStruc);
647 strucAnn.put(type, newStruc);
648 seqAnn.put(acc, strucAnn);
654 .println("Warning - couldn't parse sequence annotation row line:\n"
656 // throw new IOException("Error parsing " + line);
661 throw new IOException(MessageManager.formatMessage("exception.unknown_annotation_detected", new String[]{annType,annContent}));
665 if (treeString.length() > 0)
667 if (treeName == null)
669 treeName = "Tree " + (1 + getTreeCount());
671 addNewickTree(treeName, treeString.toString());
676 * Demangle an accession string and guess the originating sequence database
677 * for a given sequence
680 * sequence to be annotated
682 * Accession string for sequence
684 * source database for alignment (PFAM or RFAM)
686 private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)
688 DBRefEntry dbrf = null;
689 List<DBRefEntry> dbrs = new ArrayList<DBRefEntry>();
690 String seqdb = "Unknown", sdbac = "" + dbr;
691 int st = -1, en = -1, p;
692 if ((st = sdbac.indexOf("/")) > -1)
694 String num, range = sdbac.substring(st + 1);
695 sdbac = sdbac.substring(0, st);
696 if ((p = range.indexOf("-")) > -1)
699 if (p < range.length())
701 num = range.substring(p).trim();
704 en = Integer.parseInt(num);
705 } catch (NumberFormatException x)
707 // could warn here that index is invalid
716 num = range.substring(0, p).trim();
719 st = Integer.parseInt(num);
720 } catch (NumberFormatException x)
722 // could warn here that index is invalid
726 if (dbsource.equals("PFAM"))
729 if (sdbac.indexOf(".") > -1)
731 // strip of last subdomain
732 sdbac = sdbac.substring(0, sdbac.indexOf("."));
733 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource,
740 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
749 seqdb = "EMBL"; // total guess - could be ENA, or something else these
751 if (sdbac.indexOf(".") > -1)
753 // strip off last subdomain
754 sdbac = sdbac.substring(0, sdbac.indexOf("."));
755 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource,
763 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
770 if (st != -1 && en != -1)
772 for (DBRefEntry d : dbrs)
774 jalview.util.MapList mp = new jalview.util.MapList(new int[]
775 { seqO.getStart(), seqO.getEnd() }, new int[]
777 jalview.datamodel.Mapping mping = new Mapping(mp);
783 protected static AlignmentAnnotation parseAnnotationRow(
784 Vector annotation, String label, String annots)
786 String convert1, convert2 = null;
788 // Convert all bracket types to parentheses
789 Regex openparen = new Regex("(<|\\[)", "(");
790 Regex closeparen = new Regex("(>|\\])", ")");
792 // Detect if file is RNA by looking for bracket types
793 Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
795 convert1 = openparen.replaceAll(annots);
796 convert2 = closeparen.replaceAll(convert1);
800 if (label.contains("_cons"))
802 type = (label.indexOf("_cons") == label.length() - 5) ? label
803 .substring(0, label.length() - 5) : label;
806 type = id2type(type);
807 if (type.equals("secondary structure"))
811 // decide on secondary structure or not.
812 Annotation[] els = new Annotation[annots.length()];
813 for (int i = 0; i < annots.length(); i++)
815 String pos = annots.substring(i, i + 1);
817 ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
821 if (detectbrackets.search(pos))
823 ann.secondaryStructure = jalview.schemes.ResidueProperties
824 .getRNASecStrucState(pos).charAt(0);
828 ann.secondaryStructure = jalview.schemes.ResidueProperties
829 .getDssp3state(pos).charAt(0);
832 if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')
834 ann.displayCharacter = ""; // null; // " ";
838 ann.displayCharacter = " " + ann.displayCharacter;
844 AlignmentAnnotation annot = null;
845 Enumeration e = annotation.elements();
846 while (e.hasMoreElements())
848 annot = (AlignmentAnnotation) e.nextElement();
849 if (annot.label.equals(type))
857 annot = new AlignmentAnnotation(type, type, els);
858 annotation.addElement(annot);
862 Annotation[] anns = new Annotation[annot.annotations.length
864 System.arraycopy(annot.annotations, 0, anns, 0,
865 annot.annotations.length);
866 System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
867 annot.annotations = anns;
868 // System.out.println("else: ");
873 public String print(SequenceI[] s)
875 // find max length of id
879 Hashtable dataRef = null;
880 while ((in < s.length) && (s[in] != null))
882 String tmp = printId(s[in]);
883 if (s[in].getSequence().length > max)
885 max = s[in].getSequence().length;
888 if (tmp.length() > maxid)
890 maxid = tmp.length();
892 if (s[in].getDBRef() != null)
894 for (int idb = 0; idb < s[in].getDBRef().length; idb++)
898 dataRef = new Hashtable();
901 String datAs1 = s[in].getDBRef()[idb].getSource().toString()
903 + s[in].getDBRef()[idb].getAccessionId().toString();
904 dataRef.put(tmp, datAs1);
912 // output database type
913 if (al.getProperties() != null)
915 if (!al.getProperties().isEmpty())
917 Enumeration key = al.getProperties().keys();
918 Enumeration val = al.getProperties().elements();
919 while (key.hasMoreElements())
921 out.append("#=GF " + key.nextElement() + " " + val.nextElement());
927 // output database accessions
930 Enumeration en = dataRef.keys();
931 while (en.hasMoreElements())
933 Object idd = en.nextElement();
934 String type = (String) dataRef.remove(idd);
935 out.append(new Format("%-" + (maxid - 2) + "s").form("#=GS "
936 + idd.toString() + " "));
937 if (type.contains("PFAM") || type.contains("RFAM"))
940 out.append(" AC " + type.substring(type.indexOf(";") + 1));
944 out.append(" DR " + type + " ");
950 // output annotations
951 while (i < s.length && s[i] != null)
953 if (s[i].getDatasetSequence() != null)
955 SequenceI ds = s[i].getDatasetSequence();
956 AlignmentAnnotation[] alAnot;
959 alAnot = s[i].getAnnotation();
963 for (int j = 0; j < alAnot.length; j++)
965 if (ds.getSequenceFeatures() != null)
967 feature = ds.getSequenceFeatures()[0].type;
969 String key = type2id(feature);
976 // out.append("#=GR ");
977 out.append(new Format("%-" + maxid + "s").form("#=GR "
978 + printId(s[i]) + " " + key + " "));
979 ann = alAnot[j].annotations;
981 for (int k = 0; k < ann.length; k++)
984 String ch = (annot == null) ? Character.toString(s[i]
985 .getCharAt(k)) : annot.displayCharacter;
986 if (ch.length() == 0)
988 if (key.equals("SS"))
990 char ll = annot.secondaryStructure;
991 seq = (Character.toString(ll).equals(" ")) ? seq + "C"
999 else if (ch.length() == 1)
1003 else if (ch.length() > 1)
1005 seq += ch.charAt(1);
1009 out.append(newline);
1014 out.append(new Format("%-" + maxid + "s").form(printId(s[i]) + " "));
1015 out.append(s[i].getSequenceAsString());
1016 out.append(newline);
1020 // alignment annotation
1021 AlignmentAnnotation aa;
1022 if (al.getAlignmentAnnotation() != null)
1024 for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++)
1026 aa = al.getAlignmentAnnotation()[ia];
1027 if (aa.autoCalculated || !aa.visible)
1034 if (aa.label.equals("seq"))
1040 label = type2id(aa.label.toLowerCase()) + "_cons";
1048 out.append(new Format("%-" + maxid + "s").form("#=GC " + label
1050 boolean isrna = aa.isValidStruc();
1051 for (int j = 0; j < aa.annotations.length; j++)
1053 String ch = (aa.annotations[j] == null) ? "-"
1054 : aa.annotations[j].displayCharacter;
1055 if (ch.length() == 0 || isrna)
1057 char ll = aa.annotations[j].secondaryStructure;
1058 if (Character.toString(ll).equals(" "))
1067 else if (ch.length() == 1)
1071 else if (ch.length() > 1)
1073 seq += ch.charAt(1);
1077 out.append(newline);
1080 return out.toString();
1083 public String print()
1085 out = new StringBuffer();
1086 out.append("# STOCKHOLM 1.0");
1087 out.append(newline);
1088 print(getSeqsAsArray());
1091 out.append(newline);
1092 return out.toString();
1095 private static Hashtable typeIds = null;
1098 if (typeIds == null)
1100 typeIds = new Hashtable();
1101 typeIds.put("SS", "secondary structure");
1102 typeIds.put("SA", "surface accessibility");
1103 typeIds.put("TM", "transmembrane");
1104 typeIds.put("PP", "posterior probability");
1105 typeIds.put("LI", "ligand binding");
1106 typeIds.put("AS", "active site");
1107 typeIds.put("IN", "intron");
1108 typeIds.put("IR", "interacting residue");
1109 typeIds.put("AC", "accession");
1110 typeIds.put("OS", "organism");
1111 typeIds.put("CL", "class");
1112 typeIds.put("DE", "description");
1113 typeIds.put("DR", "reference");
1114 typeIds.put("LO", "look");
1115 typeIds.put("RF", "reference positions");
1120 protected static String id2type(String id)
1122 if (typeIds.containsKey(id))
1124 return (String) typeIds.get(id);
1126 System.err.println("Warning : Unknown Stockholm annotation type code "
1131 protected static String type2id(String type)
1134 Enumeration e = typeIds.keys();
1135 while (e.hasMoreElements())
1137 Object ll = e.nextElement();
1138 if (typeIds.get(ll).toString().equals(type))
1148 System.err.println("Warning : Unknown Stockholm annotation type: "
1154 * make a friendly ID string.
1157 * @return truncated dataName to after last '/'
1159 private String safeName(String dataName)
1162 while ((b = dataName.indexOf("/")) > -1 && b < dataName.length())
1164 dataName = dataName.substring(b + 1).trim();
1167 int e = (dataName.length() - dataName.indexOf(".")) + 1;
1168 dataName = dataName.substring(1, e).trim();