X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FStockholmFile.java;h=8d340f2fe7eec06b31ed717e19c17688a1b495b0;hb=d2e495268df6f50286b972f1145f302ad181da00;hp=a47e1ea3c19a77e4c7f2cc873e863ec9e4271fdd;hpb=db1b28364c2034ea432c0668100c1ec9e0d17523;p=jalview.git diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index a47e1ea..8d340f2 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; @@ -78,8 +78,8 @@ public class StockholmFile extends AlignFile 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 @@ -195,7 +195,7 @@ public class StockholmFile extends AlignFile String version; // String id; Hashtable seqAnn = new Hashtable(); // Sequence related annotations - LinkedHashMap seqs = new LinkedHashMap(); + LinkedHashMap seqs = new LinkedHashMap<>(); Regex p, r, rend, s, x; // Temporary line for processing RNA annotation // String RNAannot = ""; @@ -366,6 +366,11 @@ 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 +379,7 @@ 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 +392,11 @@ public class StockholmFile extends AlignFile while (j.hasMoreElements()) { String desc = j.nextElement().toString(); + if ("annotations".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++) @@ -572,22 +583,11 @@ 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 +602,12 @@ 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 +635,18 @@ 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)) { @@ -650,13 +657,14 @@ public class StockholmFile extends AlignFile strucAnn = new Hashtable(); } - Vector newStruc = new Vector(); + Vector newStruc = new Vector<>(); parseAnnotationRow(newStruc, type, ns); for (AlignmentAnnotation alan : newStruc) { alan.visible = false; } - // annotations.addAll(newStruc); + // new annotation overwrites any existing annotation... + strucAnn.put(type, newStruc); seqAnn.put(acc, strucAnn); } @@ -701,7 +709,7 @@ public class StockholmFile extends AlignFile private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource) { DBRefEntry dbrf = null; - List dbrs = new ArrayList(); + List dbrs = new ArrayList<>(); String seqdb = "Unknown", sdbac = "" + dbr; int st = -1, en = -1, p; if ((st = sdbac.indexOf("/")) > -1) @@ -810,12 +818,16 @@ public class StockholmFile extends AlignFile 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++) @@ -831,12 +843,12 @@ 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)) { @@ -846,9 +858,29 @@ public class StockholmFile extends AlignFile { ann.displayCharacter = " " + ann.displayCharacter; } + } } } + 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) + { + val = 10; + } + } + ann.value = val; + } els[i] = ann; } @@ -884,6 +916,13 @@ public class StockholmFile extends AlignFile @Override public String print(SequenceI[] s, boolean jvSuffix) { + String string = print(s, jvSuffix, false); + return string; + } + + public String print(SequenceI[] s, boolean jvSuffix, + boolean removeAnnotations) + { out = new StringBuffer(); out.append("# STOCKHOLM 1.0"); out.append(newline); @@ -963,19 +1002,14 @@ public class StockholmFile extends AlignFile } } - // output annotations - while (i < s.length && s[i] != null) - { - if (s[i].getDatasetSequence() != null) + + // output annotations + while (i < s.length && s[i] != null) { - SequenceI ds = s[i].getDatasetSequence(); - AlignmentAnnotation[] alAnot; - Annotation[] ann; - Annotation annot; - alAnot = s[i].getAnnotation(); - String feature = ""; - if (alAnot != null) + AlignmentAnnotation[] alAnot = s[i].getAnnotation(); + if (alAnot != null && !removeAnnotations) { + Annotation[] ann; for (int j = 0; j < alAnot.length; j++) { @@ -995,8 +1029,8 @@ public class StockholmFile extends AlignFile } // out.append("#=GR "); - out.append(new Format("%-" + maxid + "s").form("#=GR " - + printId(s[i], jvSuffix) + " " + key + " ")); + 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++) @@ -1007,60 +1041,62 @@ public class StockholmFile extends AlignFile out.append(newline); } } - } - out.append(new Format("%-" + maxid + "s") - .form(printId(s[i], jvSuffix) + " ")); - out.append(s[i].getSequenceAsString()); - out.append(newline); - i++; - } + out.append(new Format("%-" + maxid + "s") + .form(printId(s[i], jvSuffix) + " ")); + out.append(s[i].getSequenceAsString()); + out.append(newline); + i++; + } - // alignment annotation - AlignmentAnnotation aa; - if (al.getAlignmentAnnotation() != null) + if (!removeAnnotations) { - for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++) + // alignment annotation + AlignmentAnnotation aa; + if (al.getAlignmentAnnotation() != null) { - aa = al.getAlignmentAnnotation()[ia]; - if (aa.autoCalculated || !aa.visible || aa.sequenceRef != null) + for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++) { - continue; - } - String seq = ""; - String label; - String key = ""; - if (aa.label.equals("seq")) - { - label = "seq_cons"; - } - else - { - key = type2id(aa.label.toLowerCase()); - if (key == null) + aa = al.getAlignmentAnnotation()[ia]; + if (aa.autoCalculated || !aa.visible || aa.sequenceRef != null) { - label = aa.label; + continue; + } + String seq = ""; + String label; + String key = ""; + if (aa.label.equals("seq")) + { + label = "seq_cons"; } else { - label = key + "_cons"; + key = type2id(aa.label.toLowerCase()); + if (key == null) + { + label = aa.label; + } + else + { + label = key + "_cons"; + } + } + if (label == null) + { + label = aa.label; } - } - if (label == null) - { - label = aa.label; - } - label = label.replace(" ", "_"); + label = label.replace(" ", "_"); - out.append(new Format("%-" + maxid + "s").form("#=GC " + label - + " ")); - boolean isrna = aa.isValidStruc(); - for (int j = 0; j < aa.annotations.length; j++) - { - seq += outputCharacter(key, j, isrna, aa.annotations, null); + out.append(new Format("%-" + maxid + "s") + .form("#=GC " + label + " ")); + boolean isrna = aa.isValidStruc(); + for (int j = 0; j < aa.annotations.length; j++) + { + seq += outputCharacter(key, j, isrna, aa.annotations, null); + } + out.append(seq); + out.append(newline); } - out.append(seq); - out.append(newline); } } @@ -1091,8 +1127,8 @@ public class StockholmFile extends AlignFile { 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 { @@ -1126,7 +1162,6 @@ public class StockholmFile extends AlignFile out.append(newline); print(getSeqsAsArray(), false); - out.append("//"); out.append(newline); return out.toString(); } @@ -1138,10 +1173,10 @@ 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"); @@ -1152,7 +1187,7 @@ 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"); } } @@ -1175,7 +1210,7 @@ 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;