Clover icon

Coverage Report

  1. Project Clover database Mon Sep 2 2024 17:57:51 BST
  2. Package jalview.io

File StockholmFile.java

 

Coverage histogram

../../img/srcFileCovDistChart8.png
21% of files have more coverage

Code metrics

250
481
17
1
1,321
949
177
0.37
28.29
17
10.41

Classes

Class Line # Actions
StockholmFile 75 481 177
0.7633689676.3%
 

Contributing tests

This file is covered by 24 tests. .

Source view

1    /*
2    * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3    * Copyright (C) $$Year-Rel$$ The Jalview Authors
4    *
5    * This file is part of Jalview.
6    *
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.
11    *
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.
16    *
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.
20    */
21    /*
22    * This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk
23    */
24    package jalview.io;
25   
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;
34    import java.util.Locale;
35    import java.util.Map;
36    import java.util.Vector;
37   
38    import com.stevesoft.pat.Regex;
39   
40    import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;
41    import fr.orsay.lri.varna.factories.RNAFactory;
42    import fr.orsay.lri.varna.models.rna.RNA;
43    import jalview.analysis.Rna;
44    import jalview.datamodel.AlignmentAnnotation;
45    import jalview.datamodel.AlignmentI;
46    import jalview.datamodel.Annotation;
47    import jalview.datamodel.DBRefEntry;
48    import jalview.datamodel.DBRefSource;
49    import jalview.datamodel.Mapping;
50    import jalview.datamodel.Sequence;
51    import jalview.datamodel.SequenceFeature;
52    import jalview.datamodel.SequenceI;
53    import jalview.schemes.ResidueProperties;
54    import jalview.util.Comparison;
55    import jalview.util.DBRefUtils;
56    import jalview.util.Format;
57    import jalview.util.MessageManager;
58   
59    /**
60    * This class is supposed to parse a Stockholm format file into Jalview There
61    * are TODOs in this class: we do not know what the database source and version
62    * is for the file when parsing the #GS= AC tag which associates accessions with
63    * sequences. Database references are also not parsed correctly: a separate
64    * reference string parser must be added to parse the database reference form
65    * into Jalview's local representation.
66    *
67    * @author bsb at sanger.ac.uk
68    * @author Natasha Shersnev (Dundee, UK) (Stockholm file writer)
69    * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as
70    * stockholm)
71    * @author Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data)
72    * @version 0.3 + jalview mods
73    *
74    */
 
75    public class StockholmFile extends AlignFile
76    {
77    private static final String ANNOTATION = "annotation";
78   
79    // private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "(");
80    //
81    // private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")");
82   
83    public static final Regex DETECT_BRACKETS = new Regex(
84    "(<|>|\\[|\\]|\\(|\\)|\\{|\\})");
85   
86    // WUSS extended symbols. Avoid ambiguity with protein SS annotations by using
87    // NOT_RNASS first.
88    public static final String RNASS_BRACKETS = "<>[](){}AaBbCcDdEeFfGgHhIiJjKkLlMmNnOoPpQqRrSsTtUuVvWwXxYyZz";
89   
90    // use the following regex to decide an annotations (whole) line is NOT an RNA
91    // SS (it contains only E,H,e,h and other non-brace/non-alpha chars)
92    private static final Regex NOT_RNASS = new Regex(
93    "^[^<>[\\](){}ADFJ-RUVWYZadfj-ruvwyz]*$");
94   
95    StringBuffer out; // output buffer
96   
97    AlignmentI al;
98   
 
99  0 toggle public StockholmFile()
100    {
101    }
102   
103    /**
104    * Creates a new StockholmFile object for output.
105    */
 
106  60 toggle public StockholmFile(AlignmentI al)
107    {
108  60 this.al = al;
109    }
110   
 
111  0 toggle public StockholmFile(String inFile, DataSourceType type)
112    throws IOException
113    {
114  0 super(inFile, type);
115    }
116   
 
117  45 toggle public StockholmFile(FileParse source) throws IOException
118    {
119  45 super(source);
120    }
121   
 
122  105 toggle @Override
123    public void initData()
124    {
125  105 super.initData();
126    }
127   
128    /**
129    * Parse a file in Stockholm format into Jalview's data model using VARNA
130    *
131    * @throws IOException
132    * If there is an error with the input file
133    */
 
134  0 toggle public void parse_with_VARNA(java.io.File inFile) throws IOException
135    {
136  0 FileReader fr = null;
137  0 fr = new FileReader(inFile);
138   
139  0 BufferedReader r = new BufferedReader(fr);
140  0 List<RNA> result = null;
141  0 try
142    {
143  0 result = RNAFactory.loadSecStrStockholm(r);
144    } catch (ExceptionUnmatchedClosingParentheses umcp)
145    {
146  0 errormessage = "Unmatched parentheses in annotation. Aborting ("
147    + umcp.getMessage() + ")";
148  0 throw new IOException(umcp);
149    }
150    // DEBUG jalview.bin.Console.outPrintln("this is the secondary scructure:"
151    // +result.size());
152  0 SequenceI[] seqs = new SequenceI[result.size()];
153  0 String id = null;
154  0 for (int i = 0; i < result.size(); i++)
155    {
156    // DEBUG jalview.bin.Console.errPrintln("Processing i'th sequence in
157    // Stockholm file")
158  0 RNA current = result.get(i);
159   
160  0 String seq = current.getSeq();
161  0 String rna = current.getStructDBN(true);
162    // DEBUG jalview.bin.Console.outPrintln(seq);
163    // DEBUG jalview.bin.Console.errPrintln(rna);
164  0 int begin = 0;
165  0 int end = seq.length() - 1;
166  0 id = safeName(getDataName());
167  0 seqs[i] = new Sequence(id, seq, begin, end);
168  0 String[] annot = new String[rna.length()];
169  0 Annotation[] ann = new Annotation[rna.length()];
170  0 for (int j = 0; j < rna.length(); j++)
171    {
172  0 annot[j] = rna.substring(j, j + 1);
173   
174    }
175   
176  0 for (int k = 0; k < rna.length(); k++)
177    {
178  0 ann[k] = new Annotation(annot[k], "",
179    Rna.getRNASecStrucState(annot[k]).charAt(0), 0f);
180   
181    }
182  0 AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.",
183    current.getID(), ann);
184   
185  0 seqs[i].addAlignmentAnnotation(align);
186  0 seqs[i].setRNA(result.get(i));
187  0 this.annotations.addElement(align);
188    }
189  0 this.setSeqs(seqs);
190   
191    }
192   
193    /**
194    * Parse a file in Stockholm format into Jalview's data model. The file has to
195    * be passed at construction time
196    *
197    * @throws IOException
198    * If there is an error with the input file
199    */
 
200  45 toggle @Override
201    public void parse() throws IOException
202    {
203  45 StringBuffer treeString = new StringBuffer();
204  45 String treeName = null;
205    // --------------- Variable Definitions -------------------
206  45 String line;
207  45 String version;
208    // String id;
209  45 Hashtable seqAnn = new Hashtable(); // Sequence related annotations
210  45 LinkedHashMap<String, String> seqs = new LinkedHashMap<>();
211  45 Regex p, r, rend, s, x;
212    // Temporary line for processing RNA annotation
213    // String RNAannot = "";
214   
215    // ------------------ Parsing File ----------------------
216    // First, we have to check that this file has STOCKHOLM format, i.e. the
217    // first line must match
218   
219  45 r = new Regex("# STOCKHOLM ([\\d\\.]+)");
220  45 if (!r.search(nextLine()))
221    {
222  0 throw new IOException(
223    MessageManager.getString("exception.stockholm_invalid_format")
224    + " (" + r + ")");
225    }
226    else
227    {
228  45 version = r.stringMatched(1);
229   
230    // logger.debug("Stockholm version: " + version);
231    }
232   
233    // We define some Regexes here that will be used regularily later
234  45 rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
235  45 p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
236    // id/from/to
237  45 s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
238  45 r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
239  45 x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
240   
241    // Convert all bracket types to parentheses (necessary for passing to VARNA)
242  45 Regex openparen = new Regex("(<|\\[)", "(");
243  45 Regex closeparen = new Regex("(>|\\])", ")");
244   
245    // // Detect if file is RNA by looking for bracket types
246    // Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
247   
248  45 rend.optimize();
249  45 p.optimize();
250  45 s.optimize();
251  45 r.optimize();
252  45 x.optimize();
253  45 openparen.optimize();
254  45 closeparen.optimize();
255   
256  ? while ((line = nextLine()) != null)
257    {
258  2512 if (line.length() == 0)
259    {
260  6 continue;
261    }
262  2506 if (rend.search(line))
263    {
264    // End of the alignment, pass stuff back
265  45 this.noSeqs = seqs.size();
266   
267  45 String dbsource = null;
268  45 Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
269  45 Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
270  45 if (getAlignmentProperty("AC") != null)
271    {
272  6 String dbType = getAlignmentProperty("AC").toString();
273  6 if (pf.search(dbType))
274    {
275    // PFAM Alignment - so references are typically from Uniprot
276  3 dbsource = "PFAM";
277    }
278  3 else if (rf.search(dbType))
279    {
280  3 dbsource = "RFAM";
281    }
282    }
283    // logger.debug("Number of sequences: " + this.noSeqs);
284  45 for (Map.Entry<String, String> skey : seqs.entrySet())
285    {
286    // logger.debug("Processing sequence " + acc);
287  917 String acc = skey.getKey();
288  917 String seq = skey.getValue();
289  917 if (maxLength < seq.length())
290    {
291  45 maxLength = seq.length();
292    }
293  917 int start = 1;
294  917 int end = -1;
295  917 String sid = acc;
296    /*
297    * Retrieve hash of annotations for this accession Associate
298    * Annotation with accession
299    */
300  917 Hashtable accAnnotations = null;
301   
302  917 if (seqAnn != null && seqAnn.containsKey(acc))
303    {
304  916 accAnnotations = (Hashtable) seqAnn.remove(acc);
305    // TODO: add structures to sequence
306    }
307   
308    // Split accession in id and from/to
309  917 if (p.search(acc))
310    {
311  684 sid = p.stringMatched(1);
312  684 start = Integer.parseInt(p.stringMatched(2));
313  684 end = Integer.parseInt(p.stringMatched(3));
314    }
315    // logger.debug(sid + ", " + start + ", " + end);
316   
317  917 Sequence seqO = new Sequence(sid, seq, start, end);
318    // Add Description (if any)
319  917 if (accAnnotations != null && accAnnotations.containsKey("DE"))
320    {
321  16 String desc = (String) accAnnotations.get("DE");
322  16 seqO.setDescription((desc == null) ? "" : desc);
323    }
324    // Add DB References (if any)
325  917 if (accAnnotations != null && accAnnotations.containsKey("DR"))
326    {
327  26 String dbr = (String) accAnnotations.get("DR");
328  26 if (dbr != null && dbr.indexOf(";") > -1)
329    {
330  26 String src = dbr.substring(0, dbr.indexOf(";"));
331  26 String acn = dbr.substring(dbr.indexOf(";") + 1);
332  26 jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);
333    }
334    }
335   
336  917 if (accAnnotations != null && accAnnotations.containsKey("AC"))
337    {
338  895 String dbr = (String) accAnnotations.get("AC");
339  895 if (dbr != null)
340    {
341    // we could get very clever here - but for now - just try to
342    // guess accession type from type of sequence, source of alignment
343    // plus
344    // structure
345    // of accession
346  895 guessDatabaseFor(seqO, dbr, dbsource);
347    }
348    // else - do what ? add the data anyway and prompt the user to
349    // specify what references these are ?
350    }
351   
352  917 Hashtable features = null;
353    // We need to adjust the positions of all features to account for gaps
354  917 try
355    {
356  917 features = (Hashtable) accAnnotations.remove("features");
357    } catch (java.lang.NullPointerException e)
358    {
359    // loggerwarn("Getting Features for " + acc + ": " +
360    // e.getMessage());
361    // continue;
362    }
363    // if we have features
364  917 if (features != null)
365    {
366  320 int posmap[] = seqO.findPositionMap();
367  320 Enumeration i = features.keys();
368  640 while (i.hasMoreElements())
369    {
370    // TODO: parse out secondary structure annotation as annotation
371    // row
372    // TODO: parse out scores as annotation row
373    // TODO: map coding region to core jalview feature types
374  320 String type = i.nextElement().toString();
375  320 Hashtable content = (Hashtable) features.remove(type);
376   
377    // add alignment annotation for this feature
378  320 String key = type2id(type);
379   
380    /*
381    * have we added annotation rows for this type ?
382    */
383  320 boolean annotsAdded = false;
384  320 if (key != null)
385    {
386  320 if (accAnnotations != null
387    && accAnnotations.containsKey(key))
388    {
389  320 Vector vv = (Vector) accAnnotations.get(key);
390  640 for (int ii = 0; ii < vv.size(); ii++)
391    {
392  320 annotsAdded = true;
393  320 AlignmentAnnotation an = (AlignmentAnnotation) vv
394    .elementAt(ii);
395  320 seqO.addAlignmentAnnotation(an);
396  320 annotations.add(an);
397    }
398    }
399    }
400   
401  320 Enumeration j = content.keys();
402  640 while (j.hasMoreElements())
403    {
404  320 String desc = j.nextElement().toString();
405  320 if (ANNOTATION.equals(desc) && annotsAdded)
406    {
407    // don't add features if we already added an annotation row
408  320 continue;
409    }
410  0 String ns = content.get(desc).toString();
411  0 char[] byChar = ns.toCharArray();
412  0 for (int k = 0; k < byChar.length; k++)
413    {
414  0 char c = byChar[k];
415  0 if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM
416    // uses
417    // '.'
418    // for
419    // feature
420    // background
421    {
422  0 int new_pos = posmap[k]; // look up nearest seqeunce
423    // position to this column
424  0 SequenceFeature feat = new SequenceFeature(type, desc,
425    new_pos, new_pos, null);
426   
427  0 seqO.addSequenceFeature(feat);
428    }
429    }
430    }
431   
432    }
433   
434    }
435    // garbage collect
436   
437    // logger.debug("Adding seq " + acc + " from " + start + " to " + end
438    // + ": " + seq);
439  917 this.seqs.addElement(seqO);
440    }
441  45 return; // finished parsing this segment of source
442    }
443  2461 else if (!r.search(line))
444    {
445    // jalview.bin.Console.errPrintln("Found sequence line: " + line);
446   
447    // Split sequence in sequence and accession parts
448  917 if (!x.search(line))
449    {
450    // logger.error("Could not parse sequence line: " + line);
451  0 throw new IOException(MessageManager.formatMessage(
452    "exception.couldnt_parse_sequence_line", new String[]
453    { line }));
454    }
455  917 String ns = seqs.get(x.stringMatched(1));
456  917 if (ns == null)
457    {
458  917 ns = "";
459    }
460  917 ns += x.stringMatched(2);
461   
462  917 seqs.put(x.stringMatched(1), ns);
463    }
464    else
465    {
466  1544 String annType = r.stringMatched(1);
467  1544 String annContent = r.stringMatched(2);
468   
469    // jalview.bin.Console.errPrintln("type:" + annType + " content: " +
470    // annContent);
471   
472  1544 if (annType.equals("GF"))
473    {
474    /*
475    * Generic per-File annotation, free text Magic features: #=GF NH
476    * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier
477    * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS
478    *
479    * Compulsory fields: ------------------
480    *
481    * AC Accession number: Accession number in form PFxxxxx.version or
482    * PBxxxxxx. ID Identification: One word name for family. DE
483    * Definition: Short description of family. AU Author: Authors of the
484    * entry. SE Source of seed: The source suggesting the seed members
485    * belong to one family. GA Gathering method: Search threshold to
486    * build the full alignment. TC Trusted Cutoff: Lowest sequence score
487    * and domain score of match in the full alignment. NC Noise Cutoff:
488    * Highest sequence score and domain score of match not in full
489    * alignment. TP Type: Type of family -- presently Family, Domain,
490    * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM
491    * Alignment Method The order ls and fs hits are aligned to the model
492    * to build the full align. // End of alignment.
493    *
494    * Optional fields: ----------------
495    *
496    * DC Database Comment: Comment about database reference. DR Database
497    * Reference: Reference to external database. RC Reference Comment:
498    * Comment about literature reference. RN Reference Number: Reference
499    * Number. RM Reference Medline: Eight digit medline UI number. RT
500    * Reference Title: Reference Title. RA Reference Author: Reference
501    * Author RL Reference Location: Journal location. PI Previous
502    * identifier: Record of all previous ID lines. KW Keywords: Keywords.
503    * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.
504    * NL Location: Location of nested domains - sequence ID, start and
505    * end of insert.
506    *
507    * Obsolete fields: ----------- AL Alignment method of seed: The
508    * method used to align the seed members.
509    */
510    // Let's save the annotations, maybe we'll be able to do something
511    // with them later...
512  152 Regex an = new Regex("(\\w+)\\s*(.*)");
513  152 if (an.search(annContent))
514    {
515  152 if (an.stringMatched(1).equals("NH"))
516    {
517  0 treeString.append(an.stringMatched(2));
518    }
519  152 else if (an.stringMatched(1).equals("TN"))
520    {
521  0 if (treeString.length() > 0)
522    {
523  0 if (treeName == null)
524    {
525  0 treeName = "Tree " + (getTreeCount() + 1);
526    }
527  0 addNewickTree(treeName, treeString.toString());
528    }
529  0 treeName = an.stringMatched(2);
530  0 treeString = new StringBuffer();
531    }
532    // TODO: JAL-3532 - this is where GF comments and database
533    // references are lost
534    // suggest overriding this method for Stockholm files to catch and
535    // properly
536    // process CC, DR etc into multivalued properties
537  152 setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
538    }
539    }
540  1392 else if (annType.equals("GS"))
541    {
542    // Generic per-Sequence annotation, free text
543    /*
544    * Pfam uses these features: Feature Description ---------------------
545    * ----------- AC <accession> ACcession number DE <freetext>
546    * DEscription DR <db>; <accession>; Database Reference OS <organism>
547    * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)
548    * LO <look> Look (Color, etc.)
549    */
550  1059 if (s.search(annContent))
551    {
552  1059 String acc = s.stringMatched(1);
553  1059 String type = s.stringMatched(2);
554  1059 String content = s.stringMatched(3);
555    // TODO: store DR in a vector.
556    // TODO: store AC according to generic file db annotation.
557  1059 Hashtable ann;
558  1059 if (seqAnn.containsKey(acc))
559    {
560  148 ann = (Hashtable) seqAnn.get(acc);
561    }
562    else
563    {
564  911 ann = new Hashtable();
565    }
566  1059 ann.put(type, content);
567  1059 seqAnn.put(acc, ann);
568    }
569    else
570    {
571    // throw new IOException("Error parsing " + line);
572  0 jalview.bin.Console
573    .errPrintln(">> missing annotation: " + line);
574    }
575    }
576  333 else if (annType.equals("GC"))
577    {
578    // Generic per-Column annotation, exactly 1 char per column
579    // always need a label.
580  13 if (x.search(annContent))
581    {
582    // parse out and create alignment annotation directly.
583  13 parseAnnotationRow(annotations, x.stringMatched(1),
584    x.stringMatched(2));
585    }
586    }
587  320 else if (annType.equals("GR"))
588    {
589    // Generic per-Sequence AND per-Column markup, exactly 1 char per
590    // column
591    /*
592    * Feature Description Markup letters ------- -----------
593    * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface
594    * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane
595    * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;
596    * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in
597    * or after) [0-2]
598    */
599  320 if (s.search(annContent))
600    {
601  320 String acc = s.stringMatched(1);
602  320 String type = s.stringMatched(2);
603  320 String oseq = s.stringMatched(3);
604    /*
605    * copy of annotation field that may be processed into whitespace chunks
606    */
607  320 String seq = new String(oseq);
608   
609  320 Hashtable ann;
610    // Get an object with all the annotations for this sequence
611  320 if (seqAnn.containsKey(acc))
612    {
613    // logger.debug("Found annotations for " + acc);
614  315 ann = (Hashtable) seqAnn.get(acc);
615    }
616    else
617    {
618    // logger.debug("Creating new annotations holder for " + acc);
619  5 ann = new Hashtable();
620  5 seqAnn.put(acc, ann);
621    }
622   
623    // // start of block for appending annotation lines for wrapped
624    // stokchholm file
625    // TODO test structure, call parseAnnotationRow with vector from
626    // hashtable for specific sequence
627   
628  320 Hashtable features;
629    // Get an object with all the content for an annotation
630  320 if (ann.containsKey("features"))
631    {
632    // logger.debug("Found features for " + acc);
633  0 features = (Hashtable) ann.get("features");
634    }
635    else
636    {
637    // logger.debug("Creating new features holder for " + acc);
638  320 features = new Hashtable();
639  320 ann.put("features", features);
640    }
641   
642  320 Hashtable content;
643  320 if (features.containsKey(this.id2type(type)))
644    {
645    // logger.debug("Found content for " + this.id2type(type));
646  0 content = (Hashtable) features.get(this.id2type(type));
647    }
648    else
649    {
650    // logger.debug("Creating new content holder for " +
651    // this.id2type(type));
652  320 content = new Hashtable();
653  320 features.put(this.id2type(type), content);
654    }
655  320 String ns = (String) content.get(ANNOTATION);
656   
657  320 if (ns == null)
658    {
659  320 ns = "";
660    }
661    // finally, append the annotation line
662  320 ns += seq;
663  320 content.put(ANNOTATION, ns);
664    // // end of wrapped annotation block.
665    // // Now a new row is created with the current set of data
666   
667  320 Hashtable strucAnn;
668  320 if (seqAnn.containsKey(acc))
669    {
670  320 strucAnn = (Hashtable) seqAnn.get(acc);
671    }
672    else
673    {
674  0 strucAnn = new Hashtable();
675    }
676   
677  320 Vector<AlignmentAnnotation> newStruc = new Vector<>();
678  320 parseAnnotationRow(newStruc, type, ns);
679  320 for (AlignmentAnnotation alan : newStruc)
680    {
681  320 alan.visible = false;
682    }
683    // new annotation overwrites any existing annotation...
684   
685  320 strucAnn.put(type, newStruc);
686  320 seqAnn.put(acc, strucAnn);
687    }
688    // }
689    else
690    {
691  0 jalview.bin.Console.errPrintln(
692    "Warning - couldn't parse sequence annotation row line:\n"
693    + line);
694    // throw new IOException("Error parsing " + line);
695    }
696    }
697    else
698    {
699  0 throw new IOException(MessageManager.formatMessage(
700    "exception.unknown_annotation_detected", new String[]
701    { annType, annContent }));
702    }
703    }
704    }
705  0 if (treeString.length() > 0)
706    {
707  0 if (treeName == null)
708    {
709  0 treeName = "Tree " + (1 + getTreeCount());
710    }
711  0 addNewickTree(treeName, treeString.toString());
712    }
713    }
714   
715    /**
716    * Demangle an accession string and guess the originating sequence database
717    * for a given sequence
718    *
719    * @param seqO
720    * sequence to be annotated
721    * @param dbr
722    * Accession string for sequence
723    * @param dbsource
724    * source database for alignment (PFAM or RFAM)
725    */
 
726  895 toggle private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)
727    {
728  895 DBRefEntry dbrf = null;
729  895 List<DBRefEntry> dbrs = new ArrayList<>();
730  895 String seqdb = "Unknown", sdbac = "" + dbr;
731  895 int st = -1, en = -1, p;
732  ? if ((st = sdbac.indexOf("/")) > -1)
733    {
734  215 String num, range = sdbac.substring(st + 1);
735  215 sdbac = sdbac.substring(0, st);
736  ? if ((p = range.indexOf("-")) > -1)
737    {
738  215 p++;
739  215 if (p < range.length())
740    {
741  215 num = range.substring(p).trim();
742  215 try
743    {
744  215 en = Integer.parseInt(num);
745    } catch (NumberFormatException x)
746    {
747    // could warn here that index is invalid
748  0 en = -1;
749    }
750    }
751    }
752    else
753    {
754  0 p = range.length();
755    }
756  215 num = range.substring(0, p).trim();
757  215 try
758    {
759  215 st = Integer.parseInt(num);
760    } catch (NumberFormatException x)
761    {
762    // could warn here that index is invalid
763  215 st = -1;
764    }
765    }
766  895 if (dbsource == null)
767    {
768    // make up an origin based on whether the sequence looks like it is
769    // nucleotide
770    // or protein
771  94 dbsource = (seqO.isProtein()) ? "PFAM" : "RFAM";
772    }
773  895 if (dbsource.equals("PFAM"))
774    {
775  619 seqdb = "UNIPROT";
776  619 if (sdbac.indexOf(".") > -1)
777    {
778    // strip of last subdomain
779  412 sdbac = sdbac.substring(0, sdbac.indexOf("."));
780  412 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource,
781    sdbac);
782  412 if (dbrf != null)
783    {
784  412 dbrs.add(dbrf);
785    }
786    }
787  619 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
788    dbr);
789  619 if (dbr != null)
790    {
791  619 dbrs.add(dbrf);
792    }
793    }
794    else
795    {
796  276 seqdb = "EMBL"; // total guess - could be ENA, or something else these
797    // days
798  276 if (sdbac.indexOf(".") > -1)
799    {
800    // strip off last subdomain
801  215 sdbac = sdbac.substring(0, sdbac.indexOf("."));
802  215 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource,
803    sdbac);
804  215 if (dbrf != null)
805    {
806  215 dbrs.add(dbrf);
807    }
808    }
809   
810  276 dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
811    dbr);
812  276 if (dbrf != null)
813    {
814  276 dbrs.add(dbrf);
815    }
816    }
817  895 if (st != -1 && en != -1)
818    {
819  0 for (DBRefEntry d : dbrs)
820    {
821  0 jalview.util.MapList mp = new jalview.util.MapList(
822    new int[]
823    { seqO.getStart(), seqO.getEnd() }, new int[] { st, en }, 1,
824    1);
825  0 jalview.datamodel.Mapping mping = new Mapping(mp);
826  0 d.setMap(mping);
827    }
828    }
829    }
830   
 
831  333 toggle protected static AlignmentAnnotation parseAnnotationRow(
832    Vector<AlignmentAnnotation> annotation, String label,
833    String annots)
834    {
835  333 String convert1, convert2 = null;
836   
837    // convert1 = OPEN_PAREN.replaceAll(annots);
838    // convert2 = CLOSE_PAREN.replaceAll(convert1);
839    // annots = convert2;
840   
841  333 String type = label;
842  333 if (label.contains("_cons"))
843    {
844  11 type = (label.indexOf("_cons") == label.length() - 5)
845    ? label.substring(0, label.length() - 5)
846    : label;
847    }
848  333 boolean ss = false, posterior = false;
849  333 type = id2type(type);
850   
851  333 boolean isrnass = false;
852  333 if (type.equalsIgnoreCase("secondary structure"))
853    {
854  327 ss = true;
855  327 isrnass = !NOT_RNASS.search(annots); // sorry about the double negative
856    // here (it's easier for dealing with
857    // other non-alpha-non-brace chars)
858    }
859  333 if (type.equalsIgnoreCase("posterior probability"))
860    {
861  0 posterior = true;
862    }
863    // decide on secondary structure or not.
864  333 Annotation[] els = new Annotation[annots.length()];
865  25982 for (int i = 0; i < annots.length(); i++)
866    {
867  25649 String pos = annots.substring(i, i + 1);
868  25649 Annotation ann;
869  25649 ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
870    // be written out
871  25649 if (ss)
872    {
873    // if (" .-_".indexOf(pos) == -1)
874    {
875  24998 if (isrnass && RNASS_BRACKETS.indexOf(pos) >= 0)
876    {
877  8020 ann.secondaryStructure = Rna.getRNASecStrucState(pos).charAt(0);
878  8020 ann.displayCharacter = "" + pos.charAt(0);
879    }
880    else
881    {
882  16978 ann.secondaryStructure = ResidueProperties.getDssp3state(pos)
883    .charAt(0);
884   
885  16978 if (ann.secondaryStructure == pos.charAt(0))
886    {
887  1766 ann.displayCharacter = ""; // null; // " ";
888    }
889    else
890    {
891  15212 ann.displayCharacter = " " + ann.displayCharacter;
892    }
893    }
894    }
895   
896    }
897  25649 if (posterior && !ann.isWhitespace()
898    && !Comparison.isGap(pos.charAt(0)))
899    {
900  0 float val = 0;
901    // symbol encodes values - 0..*==0..10
902  0 if (pos.charAt(0) == '*')
903    {
904  0 val = 10;
905    }
906    else
907    {
908  0 val = pos.charAt(0) - '0';
909  0 if (val > 9)
910    {
911  0 val = 10;
912    }
913    }
914  0 ann.value = val;
915    }
916   
917  25649 els[i] = ann;
918    }
919  333 AlignmentAnnotation annot = null;
920  333 Enumeration<AlignmentAnnotation> e = annotation.elements();
921  339 while (e.hasMoreElements())
922    {
923  6 annot = e.nextElement();
924  6 if (annot.label.equals(type))
925    {
926  0 break;
927    }
928  6 annot = null;
929    }
930  333 if (annot == null)
931    {
932  333 annot = new AlignmentAnnotation(type, type, els);
933  333 annotation.addElement(annot);
934    }
935    else
936    {
937  0 Annotation[] anns = new Annotation[annot.annotations.length
938    + els.length];
939  0 System.arraycopy(annot.annotations, 0, anns, 0,
940    annot.annotations.length);
941  0 System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
942  0 annot.annotations = anns;
943    // jalview.bin.Console.outPrintln("else: ");
944    }
945  333 return annot;
946    }
947   
 
948  281 toggle private String dbref_to_ac_record(DBRefEntry ref)
949    {
950  281 return ref.getSource().toString() + " ; "
951    + ref.getAccessionId().toString();
952    }
953   
 
954  60 toggle @Override
955    public String print(SequenceI[] s, boolean jvSuffix)
956    {
957  60 out = new StringBuffer();
958  60 out.append("# STOCKHOLM 1.0");
959  60 out.append(newline);
960   
961    // find max length of id
962  60 int max = 0;
963  60 int maxid = 0;
964  60 int in = 0;
965  60 int slen = s.length;
966  60 SequenceI seq;
967  60 Hashtable<String, String> dataRef = null;
968  60 boolean isAA = s[in].isProtein();
969  ? while ((in < slen) && ((seq = s[in]) != null))
970    {
971  344 String tmp = printId(seq, jvSuffix);
972  344 max = Math.max(max, seq.getLength());
973   
974  344 if (tmp.length() > maxid)
975    {
976  65 maxid = tmp.length();
977    }
978  344 List<DBRefEntry> seqrefs = seq.getDBRefs();
979  344 int ndb;
980  ? if (seqrefs != null && (ndb = seqrefs.size()) > 0)
981    {
982  268 if (dataRef == null)
983    {
984  3 dataRef = new Hashtable<>();
985    }
986  268 List<DBRefEntry> primrefs = seq.getPrimaryDBRefs();
987  268 if (primrefs.size() >= 1)
988    {
989  1 dataRef.put(tmp, dbref_to_ac_record(primrefs.get(0)));
990    }
991    else
992    {
993  280 for (int idb = 0; idb < seq.getDBRefs().size(); idb++)
994    {
995  280 DBRefEntry dbref = seq.getDBRefs().get(idb);
996  280 dataRef.put(tmp, dbref_to_ac_record(dbref));
997    // if we put in a uniprot or EMBL record then we're done:
998  280 if (isAA && DBRefSource.UNIPROT
999    .equals(DBRefUtils.getCanonicalName(dbref.getSource())))
1000    {
1001  206 break;
1002    }
1003  74 if (!isAA && DBRefSource.EMBL
1004    .equals(DBRefUtils.getCanonicalName(dbref.getSource())))
1005    {
1006  61 break;
1007    }
1008    }
1009    }
1010    }
1011  344 in++;
1012    }
1013  60 maxid += 9;
1014  60 int i = 0;
1015   
1016    // output database type
1017  60 if (al.getProperties() != null)
1018    {
1019  3 if (!al.getProperties().isEmpty())
1020    {
1021  3 Enumeration key = al.getProperties().keys();
1022  3 Enumeration val = al.getProperties().elements();
1023  41 while (key.hasMoreElements())
1024    {
1025  38 out.append("#=GF " + key.nextElement() + " " + val.nextElement());
1026  38 out.append(newline);
1027    }
1028    }
1029    }
1030   
1031    // output database accessions
1032  60 if (dataRef != null)
1033    {
1034  3 Enumeration<String> en = dataRef.keys();
1035  271 while (en.hasMoreElements())
1036    {
1037  268 Object idd = en.nextElement();
1038  268 String type = dataRef.remove(idd);
1039  268 out.append(new Format("%-" + (maxid - 2) + "s")
1040    .form("#=GS " + idd.toString() + " "));
1041  268 if (isAA && type.contains("UNIPROT")
1042    || (!isAA && type.contains("EMBL")))
1043    {
1044   
1045  268 out.append(" AC " + type.substring(type.indexOf(";") + 1));
1046    }
1047    else
1048    {
1049  0 out.append(" DR " + type + " ");
1050    }
1051  268 out.append(newline);
1052    }
1053    }
1054   
1055    // output description and annotations
1056   
1057  ? while (i < slen && (seq = s[i]) != null)
1058    {
1059  344 if (seq.getDescription() != null)
1060    {
1061    // out.append("#=GR ");
1062  16 out.append(new Format("%-" + maxid + "s").form("#=GS "
1063    + printId(seq, jvSuffix) + " DE " + seq.getDescription()));
1064  16 out.append(newline);
1065    }
1066   
1067  344 AlignmentAnnotation[] alAnot = seq.getAnnotation();
1068  344 if (alAnot != null)
1069    {
1070  83 Annotation[] ann;
1071  166 for (int j = 0, nj = alAnot.length; j < nj; j++)
1072    {
1073   
1074  83 String key = type2id(alAnot[j].label);
1075  83 boolean isrna = alAnot[j].isValidStruc();
1076   
1077  83 if (isrna)
1078    {
1079    // hardwire to secondary structure if there is RNA secondary
1080    // structure on the annotation
1081  66 key = "SS";
1082    }
1083  83 if (key == null)
1084    {
1085   
1086  4 continue;
1087    }
1088   
1089    // out.append("#=GR ");
1090  79 out.append(new Format("%-" + maxid + "s").form(
1091    "#=GR " + printId(seq, jvSuffix) + " " + key + " "));
1092  79 ann = alAnot[j].annotations;
1093  79 String sseq = "";
1094  7982 for (int k = 0, nk = ann.length; k < nk; k++)
1095    {
1096  7903 sseq += outputCharacter(key, k, isrna, ann, seq);
1097    }
1098  79 out.append(sseq);
1099  79 out.append(newline);
1100    }
1101    }
1102   
1103  344 out.append(new Format("%-" + maxid + "s")
1104    .form(printId(seq, jvSuffix) + " "));
1105  344 out.append(seq.getSequenceAsString());
1106  344 out.append(newline);
1107  344 i++;
1108    }
1109   
1110    // alignment annotation
1111  60 AlignmentAnnotation aa;
1112  60 AlignmentAnnotation[] an = al.getAlignmentAnnotation();
1113  60 if (an != null)
1114    {
1115  272 for (int ia = 0, na = an.length; ia < na; ia++)
1116    {
1117  216 aa = an[ia];
1118  216 if (aa.autoCalculated || !aa.visible || aa.sequenceRef != null)
1119    {
1120  211 continue;
1121    }
1122  5 String sseq = "";
1123  5 String label;
1124  5 String key = "";
1125  5 if (aa.label.equals("seq"))
1126    {
1127  1 label = "seq_cons";
1128    }
1129    else
1130    {
1131  4 key = type2id(aa.label.toLowerCase(Locale.ROOT));
1132  4 if (key == null)
1133    {
1134  0 label = aa.label;
1135    }
1136    else
1137    {
1138  4 label = key + "_cons";
1139    }
1140    }
1141  5 if (label == null)
1142    {
1143  0 label = aa.label;
1144    }
1145  5 label = label.replace(" ", "_");
1146   
1147  5 out.append(
1148    new Format("%-" + maxid + "s").form("#=GC " + label + " "));
1149  5 boolean isrna = aa.isValidStruc();
1150  453 for (int j = 0, nj = aa.annotations.length; j < nj; j++)
1151    {
1152  448 sseq += outputCharacter(key, j, isrna, aa.annotations, null);
1153    }
1154  5 out.append(sseq);
1155  5 out.append(newline);
1156    }
1157    }
1158   
1159  60 out.append("//");
1160  60 out.append(newline);
1161   
1162  60 return out.toString();
1163    }
1164   
1165    /**
1166    * add an annotation character to the output row
1167    *
1168    * @param seq
1169    * @param key
1170    * @param k
1171    * @param isrna
1172    * @param ann
1173    * @param sequenceI
1174    */
 
1175  8351 toggle private char outputCharacter(String key, int k, boolean isrna,
1176    Annotation[] ann, SequenceI sequenceI)
1177    {
1178  8351 char seq = ' ';
1179  8351 Annotation annot = ann[k];
1180  8351 String ch = (annot == null)
1181  2440 ? ((sequenceI == null) ? "-"
1182    : Character.toString(sequenceI.getCharAt(k)))
1183  5911 : (annot.displayCharacter == null
1184    ? String.valueOf(annot.secondaryStructure)
1185    : annot.displayCharacter);
1186  8351 if (ch == null)
1187    {
1188  0 ch = " ";
1189    }
1190  8351 if (key != null && key.equals("SS"))
1191    {
1192  8134 char ssannotchar = ' ';
1193  8134 boolean charset = false;
1194  8134 if (annot == null)
1195    {
1196    // sensible gap character
1197  2440 ssannotchar = ' ';
1198  2440 charset = true;
1199    }
1200    else
1201    {
1202    // valid secondary structure AND no alternative label (e.g. ' B')
1203  5694 if (annot.secondaryStructure > ' ' && ch.length() < 2)
1204    {
1205  3074 ssannotchar = annot.secondaryStructure;
1206  3074 charset = true;
1207    }
1208    }
1209  8134 if (charset)
1210    {
1211  5514 return (ssannotchar == ' ' && isrna) ? '.' : ssannotchar;
1212    }
1213    }
1214   
1215  2837 if (ch.length() == 0)
1216    {
1217  0 seq = '.';
1218    }
1219  2837 else if (ch.length() == 1)
1220    {
1221  454 seq = ch.charAt(0);
1222    }
1223  2383 else if (ch.length() > 1)
1224    {
1225  2383 seq = ch.charAt(1);
1226    }
1227   
1228  2837 return (seq == ' ' && key != null && key.equals("SS") && isrna) ? '.'
1229    : seq;
1230    }
1231   
 
1232  0 toggle public String print()
1233    {
1234  0 out = new StringBuffer();
1235  0 out.append("# STOCKHOLM 1.0");
1236  0 out.append(newline);
1237  0 print(getSeqsAsArray(), false);
1238   
1239  0 out.append("//");
1240  0 out.append(newline);
1241  0 return out.toString();
1242    }
1243   
1244    private static Hashtable typeIds = null;
1245   
 
1246  1 toggle static
1247    {
1248  1 if (typeIds == null)
1249    {
1250  1 typeIds = new Hashtable();
1251  1 typeIds.put("SS", "Secondary Structure");
1252  1 typeIds.put("SA", "Surface Accessibility");
1253  1 typeIds.put("TM", "transmembrane");
1254  1 typeIds.put("PP", "Posterior Probability");
1255  1 typeIds.put("LI", "ligand binding");
1256  1 typeIds.put("AS", "active site");
1257  1 typeIds.put("IN", "intron");
1258  1 typeIds.put("IR", "interacting residue");
1259  1 typeIds.put("AC", "accession");
1260  1 typeIds.put("OS", "organism");
1261  1 typeIds.put("CL", "class");
1262  1 typeIds.put("DE", "description");
1263  1 typeIds.put("DR", "reference");
1264  1 typeIds.put("LO", "look");
1265  1 typeIds.put("RF", "Reference Positions");
1266   
1267    }
1268    }
1269   
 
1270  973 toggle protected static String id2type(String id)
1271    {
1272  973 if (typeIds.containsKey(id))
1273    {
1274  970 return (String) typeIds.get(id);
1275    }
1276  3 jalview.bin.Console.errPrintln(
1277    "Warning : Unknown Stockholm annotation type code " + id);
1278  3 return id;
1279    }
1280   
 
1281  407 toggle protected static String type2id(String type)
1282    {
1283  407 String key = null;
1284  407 Enumeration e = typeIds.keys();
1285  4494 while (e.hasMoreElements())
1286    {
1287  4490 Object ll = e.nextElement();
1288  4490 if (typeIds.get(ll).toString().equalsIgnoreCase(type))
1289    {
1290  403 key = (String) ll;
1291  403 break;
1292    }
1293    }
1294  407 if (key != null)
1295    {
1296  403 return key;
1297    }
1298  4 jalview.bin.Console.errPrintln(
1299    "Warning : Unknown Stockholm annotation type: " + type);
1300  4 return key;
1301    }
1302   
1303    /**
1304    * make a friendly ID string.
1305    *
1306    * @param dataName
1307    * @return truncated dataName to after last '/'
1308    */
 
1309  0 toggle private String safeName(String dataName)
1310    {
1311  0 int b = 0;
1312  0 while ((b = dataName.indexOf("/")) > -1 && b < dataName.length())
1313    {
1314  0 dataName = dataName.substring(b + 1).trim();
1315   
1316    }
1317  0 int e = (dataName.length() - dataName.indexOf(".")) + 1;
1318  0 dataName = dataName.substring(1, e).trim();
1319  0 return dataName;
1320    }
1321    }
  • Report generated by OpenClover v 4.4.1 on Mon Sep 2 2024 18:05:00 BST using coverage data from Mon Sep 2 2024 18:04:45 BST.
  • OpenClover is free and open-source software.