/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2)
- * Copyright (C) 2014 The Jalview Authors
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
*
* This file is part of Jalview.
*
*/
package jalview.io;
+import jalview.analysis.Rna;
import jalview.datamodel.AlignmentAnnotation;
import jalview.datamodel.AlignmentI;
import jalview.datamodel.Annotation;
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;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.Hashtable;
+import java.util.LinkedHashMap;
import java.util.List;
-import java.util.StringTokenizer;
+import java.util.Map;
import java.util.Vector;
import com.stevesoft.pat.Regex;
*/
public class StockholmFile extends AlignFile
{
- // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");
- protected ArrayList<RNA> result;
+ private static final String ANNOTATION = "annotation";
+
+ private static final Regex OPEN_PAREN = new Regex("(<|\\[)", "(");
+
+ private static final Regex CLOSE_PAREN = new Regex("(>|\\])", ")");
+
+ public static final Regex DETECT_BRACKETS = new Regex(
+ "(<|>|\\[|\\]|\\(|\\)|\\{|\\})");
StringBuffer out; // output buffer
this.al = al;
}
- public StockholmFile(String inFile, String type) throws IOException
+ public StockholmFile(String inFile, DataSourceType type)
+ throws IOException
{
super(inFile, type);
}
super(source);
}
+ @Override
public void initData()
{
super.initData();
fr = new FileReader(inFile);
BufferedReader r = new BufferedReader(fr);
- result = null;
+ List<RNA> result = null;
try
{
result = RNAFactory.loadSecStrStockholm(r);
for (int k = 0; k < rna.length(); k++)
{
- ann[k] = new Annotation(annot[k], "",
- jalview.schemes.ResidueProperties.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.",
* @throws IOException
* If there is an error with the input file
*/
+ @Override
public void parse() throws IOException
{
StringBuffer treeString = new StringBuffer();
String version;
// String id;
Hashtable seqAnn = new Hashtable(); // Sequence related annotations
- Hashtable seqs = new Hashtable();
+ LinkedHashMap<String, String> seqs = new LinkedHashMap<String, String>();
Regex p, r, rend, s, x;
// Temporary line for processing RNA annotation
// String RNAannot = "";
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
{
}
}
// logger.debug("Number of sequences: " + this.noSeqs);
- Enumeration accs = seqs.keys();
- while (accs.hasMoreElements())
+ for (Map.Entry<String, String> skey : seqs.entrySet())
{
- String acc = (String) accs.nextElement();
// logger.debug("Processing sequence " + acc);
- String seq = (String) seqs.remove(acc);
+ String acc = skey.getKey();
+ String seq = skey.getValue();
if (maxLength < seq.length())
{
maxLength = seq.length();
// 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
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);
+ annotations.add(an);
}
}
}
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++)
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);
}
if (!x.search(line))
{
// logger.error("Could not parse sequence line: " + line);
- throw new IOException(MessageManager.formatMessage("exception.couldnt_parse_sequence_line", new String[]{line}));
+ throw new IOException(MessageManager.formatMessage(
+ "exception.couldnt_parse_sequence_line",
+ new String[] { line }));
}
- String ns = (String) seqs.get(x.stringMatched(1));
+ String ns = seqs.get(x.stringMatched(1));
if (ns == null)
{
ns = "";
}
else
{
- throw new IOException(MessageManager.formatMessage("exception.error_parsing_line", new String[]{line}));
+ // throw new IOException("Error parsing " + line);
+ System.err.println(">> missing annotation: " + line);
}
}
else if (annType.equals("GC"))
{
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
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"))
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))
{
strucAnn = new Hashtable();
}
- Vector newStruc = new Vector();
+ Vector<AlignmentAnnotation> newStruc = new Vector<AlignmentAnnotation>();
parseAnnotationRow(newStruc, type, ns);
+ for (AlignmentAnnotation alan : newStruc)
+ {
+ alan.visible = false;
+ }
+ // new annotation overwrites any existing annotation...
strucAnn.put(type, newStruc);
seqAnn.put(acc, strucAnn);
}
else
{
- throw new IOException(MessageManager.formatMessage("exception.unknown_annotation_detected", new String[]{annType,annContent}));
+ throw new IOException(MessageManager.formatMessage(
+ "exception.unknown_annotation_detected", new String[] {
+ annType, annContent }));
}
}
}
{
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);
}
}
protected static AlignmentAnnotation parseAnnotationRow(
- Vector annotation, String label, String annots)
+ Vector<AlignmentAnnotation> annotation, String label,
+ String annots)
{
String convert1, convert2 = null;
- // Convert all bracket types to parentheses
- Regex openparen = new Regex("(<|\\[)", "(");
- Regex closeparen = new Regex("(>|\\])", ")");
-
- // Detect if file is RNA by looking for bracket types
- Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
-
- convert1 = openparen.replaceAll(annots);
- convert2 = closeparen.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;
}
- 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++)
// be written out
if (ss)
{
- if (detectbrackets.search(pos))
+ // if (" .-_".indexOf(pos) == -1)
{
- ann.secondaryStructure = jalview.schemes.ResidueProperties
- .getRNASecStrucState(pos).charAt(0);
- }
- else
- {
- ann.secondaryStructure = jalview.schemes.ResidueProperties
- .getDssp3state(pos).charAt(0);
+ 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; // " ";
+ }
+ else
+ {
+ ann.displayCharacter = " " + ann.displayCharacter;
+ }
+ }
}
- if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')
+ }
+ if (posterior && !ann.isWhitespace()
+ && !Comparison.isGap(pos.charAt(0)))
+ {
+ float val = 0;
+ // symbol encodes values - 0..*==0..10
+ if (pos.charAt(0) == '*')
{
- ann.displayCharacter = ""; // null; // " ";
+ val = 10;
}
else
{
- ann.displayCharacter = " " + ann.displayCharacter;
+ val = pos.charAt(0) - '0';
+ if (val > 9)
+ {
+ val = 10;
+ }
}
+ ann.value = val;
}
els[i] = ann;
}
AlignmentAnnotation annot = null;
- Enumeration e = annotation.elements();
+ Enumeration<AlignmentAnnotation> e = annotation.elements();
while (e.hasMoreElements())
{
- annot = (AlignmentAnnotation) e.nextElement();
+ annot = e.nextElement();
if (annot.label.equals(type))
{
break;
return annot;
}
- public String print(SequenceI[] s)
+ @Override
+ public String print(SequenceI[] s, boolean jvSuffix)
{
+ out = new StringBuffer();
+ out.append("# STOCKHOLM 1.0");
+ out.append(newline);
+
// find max length of id
int max = 0;
int maxid = 0;
Hashtable dataRef = null;
while ((in < s.length) && (s[in] != null))
{
- String tmp = printId(s[in]);
+ String tmp = printId(s[in], jvSuffix);
if (s[in].getSequence().length > max)
{
max = s[in].getSequence().length;
{
maxid = tmp.length();
}
- if (s[in].getDBRef() != null)
+ if (s[in].getDBRefs() != null)
{
- for (int idb = 0; idb < s[in].getDBRef().length; idb++)
+ for (int idb = 0; idb < s[in].getDBRefs().length; idb++)
{
if (dataRef == null)
{
dataRef = new Hashtable();
}
- String datAs1 = s[in].getDBRef()[idb].getSource().toString()
+ String datAs1 = s[in].getDBRefs()[idb].getSource().toString()
+ " ; "
- + s[in].getDBRef()[idb].getAccessionId().toString();
+ + s[in].getDBRefs()[idb].getAccessionId().toString();
dataRef.put(tmp, datAs1);
}
}
// 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;
- }
- String key = type2id(feature);
- if (key == null)
- {
- continue;
- }
+ continue;
+ }
- // out.append("#=GR ");
- out.append(new Format("%-" + maxid + "s").form("#=GR "
- + printId(s[i]) + " " + key + " "));
- ann = alAnot[j].annotations;
- String seq = "";
- for (int k = 0; k < ann.length; k++)
- {
- annot = ann[k];
- String ch = (annot == null) ? Character.toString(s[i]
- .getCharAt(k)) : annot.displayCharacter;
- if (ch.length() == 0)
- {
- if (key.equals("SS"))
- {
- char ll = annot.secondaryStructure;
- seq = (Character.toString(ll).equals(" ")) ? seq + "C"
- : seq + ll;
- }
- else
- {
- seq += ".";
- }
- }
- else if (ch.length() == 1)
- {
- seq += ch;
- }
- else if (ch.length() > 1)
- {
- seq += ch.charAt(1);
- }
- }
- 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);
}
}
- out.append(new Format("%-" + maxid + "s").form(printId(s[i]) + " "));
+ out.append(new Format("%-" + maxid + "s")
+ .form(printId(s[i], jvSuffix) + " "));
out.append(s[i].getSequenceAsString());
out.append(newline);
i++;
for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++)
{
aa = al.getAlignmentAnnotation()[ia];
- if (aa.autoCalculated || !aa.visible)
+ if (aa.autoCalculated || !aa.visible || aa.sequenceRef != null)
{
continue;
}
String seq = "";
String label;
-
+ String key = "";
if (aa.label.equals("seq"))
{
label = "seq_cons";
}
else
{
- label = type2id(aa.label.toLowerCase()) + "_cons";
+ key = type2id(aa.label.toLowerCase());
+ if (key == null)
+ {
+ label = aa.label;
+ }
+ else
+ {
+ label = key + "_cons";
+ }
}
-
if (label == null)
{
label = aa.label;
}
+ 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++)
{
- String ch = (aa.annotations[j] == null) ? "-"
- : aa.annotations[j].displayCharacter;
- if (ch.length() == 0)
- {
- char ll = aa.annotations[j].secondaryStructure;
- if (Character.toString(ll).equals(" "))
- {
- seq += "C";
- }
- else
- {
- seq += ll;
- }
- }
- else if (ch.length() == 1)
- {
- seq += ch;
- }
- else if (ch.length() > 1)
- {
- seq += ch.charAt(1);
- }
+ seq += outputCharacter(key, j, isrna, aa.annotations, null);
}
out.append(seq);
out.append(newline);
}
}
+
+ out.append("//");
+ out.append(newline);
+
return out.toString();
}
+ /**
+ * add an annotation character to the output row
+ *
+ * @param seq
+ * @param key
+ * @param k
+ * @param isrna
+ * @param ann
+ * @param sequenceI
+ */
+ private char outputCharacter(String key, int k, boolean isrna,
+ Annotation[] ann, SequenceI sequenceI)
+ {
+ char seq = ' ';
+ Annotation annot = ann[k];
+ 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
+ return ' ';
+ }
+ else
+ {
+ // valid secondary structure AND no alternative label (e.g. ' B')
+ if (annot.secondaryStructure > ' ' && ch.length() < 2)
+ {
+ return annot.secondaryStructure;
+ }
+ }
+ }
+
+ if (ch.length() == 0)
+ {
+ seq = '.';
+ }
+ else if (ch.length() == 1)
+ {
+ seq = ch.charAt(0);
+ }
+ else if (ch.length() > 1)
+ {
+ seq = ch.charAt(1);
+ }
+ return seq;
+ }
+
public String print()
{
out = new StringBuffer();
out.append("# STOCKHOLM 1.0");
out.append(newline);
- print(getSeqsAsArray());
+ print(getSeqsAsArray(), false);
out.append("//");
out.append(newline);
}
private static Hashtable typeIds = null;
+
static
{
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");
typeIds.put("DE", "description");
typeIds.put("DR", "reference");
typeIds.put("LO", "look");
- typeIds.put("RF", "reference positions");
+ typeIds.put("RF", "Reference Positions");
}
}
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;