X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FStockholmFile.java;fp=src%2Fjalview%2Fio%2FStockholmFile.java;h=f5b517728c85ce77ad785c9030e7b7e475ed2046;hb=9f70ff4b6d193b340031997634c9e3602486bc8e;hp=2061f293a2e45452bf89f16b7004ec3f16625b84;hpb=76844c43faeeeba369deaf42f1998ca0fb33d956;p=jalview.git diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index 2061f29..f5b5177 100644 --- a/src/jalview/io/StockholmFile.java +++ b/src/jalview/io/StockholmFile.java @@ -33,6 +33,7 @@ import jalview.datamodel.Sequence; import jalview.datamodel.SequenceFeature; import jalview.datamodel.SequenceI; import jalview.schemes.ResidueProperties; +import jalview.util.Comparison; import jalview.util.Format; import jalview.util.MessageManager; @@ -45,7 +46,6 @@ import java.util.Hashtable; import java.util.LinkedHashMap; import java.util.List; import java.util.Map; -import java.util.StringTokenizer; import java.util.Vector; import com.stevesoft.pat.Regex; @@ -74,12 +74,14 @@ import fr.orsay.lri.varna.models.rna.RNA; */ public class StockholmFile extends AlignFile { + private static final String ANNOTATION = "annotation"; + private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "("); private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")"); - private static final Regex DETECT_BRACKETS = new Regex( - "(<|>|\\[|\\]|\\(|\\))"); + public static final Regex DETECT_BRACKETS = new Regex( + "(<|>|\\[|\\]|\\(|\\)|\\{|\\})"); StringBuffer out; // output buffer @@ -163,8 +165,8 @@ public class StockholmFile extends AlignFile for (int k = 0; k < rna.length(); k++) { - ann[k] = new Annotation(annot[k], "", Rna.getRNASecStrucState( - annot[k]).charAt(0), 0f); + ann[k] = new Annotation(annot[k], "", + Rna.getRNASecStrucState(annot[k]).charAt(0), 0f); } AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.", @@ -207,9 +209,8 @@ public class StockholmFile extends AlignFile r = new Regex("# STOCKHOLM ([\\d\\.]+)"); if (!r.search(nextLine())) { - throw new IOException( - MessageManager - .getString("exception.stockholm_invalid_format")); + throw new IOException(MessageManager + .getString("exception.stockholm_invalid_format")); } else { @@ -366,6 +367,11 @@ public class StockholmFile extends AlignFile // add alignment annotation for this feature String key = type2id(type); + + /* + * have we added annotation rows for this type ? + */ + boolean annotsAdded = false; if (key != null) { if (accAnnotations != null @@ -374,6 +380,7 @@ public class StockholmFile extends AlignFile Vector vv = (Vector) accAnnotations.get(key); for (int ii = 0; ii < vv.size(); ii++) { + annotsAdded = true; AlignmentAnnotation an = (AlignmentAnnotation) vv .elementAt(ii); seqO.addAlignmentAnnotation(an); @@ -386,6 +393,11 @@ public class StockholmFile extends AlignFile while (j.hasMoreElements()) { String desc = j.nextElement().toString(); + if (ANNOTATION.equals(desc) && annotsAdded) + { + // don't add features if we already added an annotation row + continue; + } String ns = content.get(desc).toString(); char[] byChar = ns.toCharArray(); for (int k = 0; k < byChar.length; k++) @@ -401,7 +413,7 @@ public class StockholmFile extends AlignFile int new_pos = posmap[k]; // look up nearest seqeunce // position to this column SequenceFeature feat = new SequenceFeature(type, desc, - new_pos, new_pos, 0f, null); + new_pos, new_pos, null); seqO.addSequenceFeature(feat); } @@ -428,8 +440,8 @@ public class StockholmFile extends AlignFile { // logger.error("Could not parse sequence line: " + line); throw new IOException(MessageManager.formatMessage( - "exception.couldnt_parse_sequence_line", - new String[] { line })); + "exception.couldnt_parse_sequence_line", new String[] + { line })); } String ns = seqs.get(x.stringMatched(1)); if (ns == null) @@ -572,22 +584,11 @@ public class StockholmFile extends AlignFile { String acc = s.stringMatched(1); String type = s.stringMatched(2); - String seq = new String(s.stringMatched(3)); - String description = null; - // Check for additional information about the current annotation - // We use a simple string tokenizer here for speed - StringTokenizer sep = new StringTokenizer(seq, " \t"); - description = sep.nextToken(); - if (sep.hasMoreTokens()) - { - seq = sep.nextToken(); - } - else - { - seq = description; - description = new String(); - } - // sequence id with from-to fields + String oseq = s.stringMatched(3); + /* + * copy of annotation field that may be processed into whitespace chunks + */ + String seq = new String(oseq); Hashtable ann; // Get an object with all the annotations for this sequence @@ -602,8 +603,12 @@ public class StockholmFile extends AlignFile ann = new Hashtable(); seqAnn.put(acc, ann); } + + // // start of block for appending annotation lines for wrapped + // stokchholm file // TODO test structure, call parseAnnotationRow with vector from // hashtable for specific sequence + Hashtable features; // Get an object with all the content for an annotation if (ann.containsKey("features")) @@ -631,15 +636,18 @@ public class StockholmFile extends AlignFile content = new Hashtable(); features.put(this.id2type(type), content); } - String ns = (String) content.get(description); + String ns = (String) content.get(ANNOTATION); + if (ns == null) { ns = ""; } + // finally, append the annotation line ns += seq; - content.put(description, ns); + content.put(ANNOTATION, ns); + // // end of wrapped annotation block. + // // Now a new row is created with the current set of data - // if(type.equals("SS")){ Hashtable strucAnn; if (seqAnn.containsKey(acc)) { @@ -656,15 +664,16 @@ public class StockholmFile extends AlignFile { alan.visible = false; } - // annotations.addAll(newStruc); + // new annotation overwrites any existing annotation... + strucAnn.put(type, newStruc); seqAnn.put(acc, strucAnn); } // } else { - System.err - .println("Warning - couldn't parse sequence annotation row line:\n" + System.err.println( + "Warning - couldn't parse sequence annotation row line:\n" + line); // throw new IOException("Error parsing " + line); } @@ -672,8 +681,8 @@ public class StockholmFile extends AlignFile else { throw new IOException(MessageManager.formatMessage( - "exception.unknown_annotation_detected", new String[] { - annType, annContent })); + "exception.unknown_annotation_detected", new String[] + { annType, annContent })); } } } @@ -786,8 +795,10 @@ public class StockholmFile extends AlignFile { for (DBRefEntry d : dbrs) { - jalview.util.MapList mp = new jalview.util.MapList(new int[] { - seqO.getStart(), seqO.getEnd() }, new int[] { st, en }, 1, 1); + jalview.util.MapList mp = new jalview.util.MapList( + new int[] + { seqO.getStart(), seqO.getEnd() }, new int[] { st, en }, 1, + 1); jalview.datamodel.Mapping mping = new Mapping(mp); d.setMap(mping); } @@ -800,22 +811,27 @@ public class StockholmFile extends AlignFile { String convert1, convert2 = null; - convert1 = OPEN_PAREN.replaceAll(annots); - convert2 = CLOSE_PAREN.replaceAll(convert1); - annots = convert2; + // convert1 = OPEN_PAREN.replaceAll(annots); + // convert2 = CLOSE_PAREN.replaceAll(convert1); + // annots = convert2; String type = label; if (label.contains("_cons")) { - type = (label.indexOf("_cons") == label.length() - 5) ? label - .substring(0, label.length() - 5) : label; + type = (label.indexOf("_cons") == label.length() - 5) + ? label.substring(0, label.length() - 5) + : label; } - boolean ss = false; + boolean ss = false, posterior = false; type = id2type(type); - if (type.equals("secondary structure")) + if (type.equalsIgnoreCase("secondary structure")) { ss = true; } + if (type.equalsIgnoreCase("posterior probability")) + { + posterior = true; + } // decide on secondary structure or not. Annotation[] els = new Annotation[annots.length()]; for (int i = 0; i < annots.length(); i++) @@ -831,23 +847,43 @@ public class StockholmFile extends AlignFile if (DETECT_BRACKETS.search(pos)) { ann.secondaryStructure = Rna.getRNASecStrucState(pos).charAt(0); + ann.displayCharacter = "" + pos.charAt(0); } else { ann.secondaryStructure = ResidueProperties.getDssp3state(pos) .charAt(0); - } - if (ann.secondaryStructure == pos.charAt(0)) - { - ann.displayCharacter = ""; // null; // " "; + if (ann.secondaryStructure == pos.charAt(0)) + { + ann.displayCharacter = ""; // null; // " "; + } + else + { + ann.displayCharacter = " " + ann.displayCharacter; + } } - else + } + + } + if (posterior && !ann.isWhitespace() + && !Comparison.isGap(pos.charAt(0))) + { + float val = 0; + // symbol encodes values - 0..*==0..10 + if (pos.charAt(0) == '*') + { + val = 10; + } + else + { + val = pos.charAt(0) - '0'; + if (val > 9) { - ann.displayCharacter = " " + ann.displayCharacter; + val = 10; } } - + ann.value = val; } els[i] = ann; @@ -896,10 +932,7 @@ public class StockholmFile extends AlignFile while ((in < s.length) && (s[in] != null)) { String tmp = printId(s[in], jvSuffix); - if (s[in].getSequence().length > max) - { - max = s[in].getSequence().length; - } + max = Math.max(max, s[in].getLength()); if (tmp.length() > maxid) { @@ -948,8 +981,8 @@ public class StockholmFile extends AlignFile { Object idd = en.nextElement(); String type = (String) dataRef.remove(idd); - out.append(new Format("%-" + (maxid - 2) + "s").form("#=GS " - + idd.toString() + " ")); + out.append(new Format("%-" + (maxid - 2) + "s") + .form("#=GS " + idd.toString() + " ")); if (type.contains("PFAM") || type.contains("RFAM")) { @@ -966,43 +999,39 @@ public class StockholmFile extends AlignFile // output annotations while (i < s.length && s[i] != null) { - if (s[i].getDatasetSequence() != null) + AlignmentAnnotation[] alAnot = s[i].getAnnotation(); + if (alAnot != null) { - SequenceI ds = s[i].getDatasetSequence(); - AlignmentAnnotation[] alAnot; Annotation[] ann; - Annotation annot; - alAnot = s[i].getAnnotation(); - String feature = ""; - if (alAnot != null) + for (int j = 0; j < alAnot.length; j++) { - for (int j = 0; j < alAnot.length; j++) + + String key = type2id(alAnot[j].label); + boolean isrna = alAnot[j].isValidStruc(); + + if (isrna) + { + // hardwire to secondary structure if there is RNA secondary + // structure on the annotation + key = "SS"; + } + if (key == null) { - if (ds.getSequenceFeatures() != null) - { - feature = ds.getSequenceFeatures()[0].type; - } - // ?bug - feature may still have previous loop value - String key = type2id(feature); - if (key == null) - { - continue; - } + continue; + } - // out.append("#=GR "); - out.append(new Format("%-" + maxid + "s").form("#=GR " - + printId(s[i], jvSuffix) + " " + key + " ")); - ann = alAnot[j].annotations; - boolean isrna = alAnot[j].isValidStruc(); - String seq = ""; - for (int k = 0; k < ann.length; k++) - { - seq += outputCharacter(key, k, isrna, ann, s[i]); - } - out.append(seq); - out.append(newline); + // out.append("#=GR "); + out.append(new Format("%-" + maxid + "s").form( + "#=GR " + printId(s[i], jvSuffix) + " " + key + " ")); + ann = alAnot[j].annotations; + String seq = ""; + for (int k = 0; k < ann.length; k++) + { + seq += outputCharacter(key, k, isrna, ann, s[i]); } + out.append(seq); + out.append(newline); } } @@ -1049,8 +1078,8 @@ public class StockholmFile extends AlignFile } label = label.replace(" ", "_"); - out.append(new Format("%-" + maxid + "s").form("#=GC " + label - + " ")); + out.append( + new Format("%-" + maxid + "s").form("#=GC " + label + " ")); boolean isrna = aa.isValidStruc(); for (int j = 0; j < aa.annotations.length; j++) { @@ -1082,14 +1111,16 @@ public class StockholmFile extends AlignFile { char seq = ' '; Annotation annot = ann[k]; - String ch = (annot == null) ? ((sequenceI == null) ? "-" : Character - .toString(sequenceI.getCharAt(k))) : annot.displayCharacter; + String ch = (annot == null) + ? ((sequenceI == null) ? "-" + : Character.toString(sequenceI.getCharAt(k))) + : annot.displayCharacter; if (key != null && key.equals("SS")) { if (annot == null) { - // sensible gap character if one is available or make one up - return sequenceI == null ? '-' : sequenceI.getCharAt(k); + // sensible gap character + return ' '; } else { @@ -1135,10 +1166,10 @@ public class StockholmFile extends AlignFile if (typeIds == null) { typeIds = new Hashtable(); - typeIds.put("SS", "secondary structure"); - typeIds.put("SA", "surface accessibility"); + typeIds.put("SS", "Secondary Structure"); + typeIds.put("SA", "Surface Accessibility"); typeIds.put("TM", "transmembrane"); - typeIds.put("PP", "posterior probability"); + typeIds.put("PP", "Posterior Probability"); typeIds.put("LI", "ligand binding"); typeIds.put("AS", "active site"); typeIds.put("IN", "intron"); @@ -1149,7 +1180,7 @@ public class StockholmFile extends AlignFile typeIds.put("DE", "description"); typeIds.put("DR", "reference"); typeIds.put("LO", "look"); - typeIds.put("RF", "reference positions"); + typeIds.put("RF", "Reference Positions"); } } @@ -1160,8 +1191,8 @@ public class StockholmFile extends AlignFile { return (String) typeIds.get(id); } - System.err.println("Warning : Unknown Stockholm annotation type code " - + id); + System.err.println( + "Warning : Unknown Stockholm annotation type code " + id); return id; } @@ -1172,7 +1203,7 @@ public class StockholmFile extends AlignFile while (e.hasMoreElements()) { Object ll = e.nextElement(); - if (typeIds.get(ll).toString().equals(type)) + if (typeIds.get(ll).toString().equalsIgnoreCase(type)) { key = (String) ll; break; @@ -1182,8 +1213,8 @@ public class StockholmFile extends AlignFile { return key; } - System.err.println("Warning : Unknown Stockholm annotation type: " - + type); + System.err.println( + "Warning : Unknown Stockholm annotation type: " + type); return key; }