/*\r
- * Jalview - A Sequence Alignment Editor and Viewer\r
- * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
- *\r
- * This program is free software; you can redistribute it and/or\r
- * modify it under the terms of the GNU General Public License\r
- * as published by the Free Software Foundation; either version 2\r
- * of the License, or (at your option) any later version.\r
- *\r
- * This program is distributed in the hope that it will be useful,\r
- * but WITHOUT ANY WARRANTY; without even the implied warranty of\r
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
- * GNU General Public License for more details.\r
- *\r
- * You should have received a copy of the GNU General Public License\r
- * along with this program; if not, write to the Free Software\r
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)\r
+ * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle\r
+ * \r
+ * This file is part of Jalview.\r
+ * \r
+ * Jalview is free software: you can redistribute it and/or\r
+ * modify it under the terms of the GNU General Public License \r
+ * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.\r
+ * \r
+ * Jalview is distributed in the hope that it will be useful, but \r
+ * WITHOUT ANY WARRANTY; without even the implied warranty \r
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR \r
+ * PURPOSE. See the GNU General Public License for more details.\r
+ * \r
+ * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.\r
*/\r
/*\r
* This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk\r
\r
import com.stevesoft.pat.*;\r
import jalview.datamodel.*;\r
+import jalview.analysis.Rna;\r
\r
// import org.apache.log4j.*;\r
\r
/**\r
- * This class is supposed to parse a Stockholm format file into Jalview\r
+ * This class is supposed to parse a Stockholm format file into Jalview There\r
+ * are TODOs in this class: we do not know what the database source and version\r
+ * is for the file when parsing the #GS= AC tag which associates accessions with\r
+ * sequences. Database references are also not parsed correctly: a separate\r
+ * reference string parser must be added to parse the database reference form\r
+ * into Jalview's local representation.\r
* \r
* @author bsb at sanger.ac.uk\r
- * @version 0.3\r
+ * @version 0.3 + jalview mods\r
+ * \r
*/\r
public class StockholmFile extends AlignFile\r
{\r
super(inFile, type);\r
}\r
\r
+ public StockholmFile(FileParse source) throws IOException\r
+ {\r
+ super(source);\r
+ }\r
+\r
public void initData()\r
{\r
super.initData();\r
Hashtable seqs = new Hashtable();\r
Regex p, r, rend, s, x;\r
\r
+ // Temporary line for processing RNA annotation\r
+ // String RNAannot = "";\r
+\r
// ------------------ Parsing File ----------------------\r
// First, we have to check that this file has STOCKHOLM format, i.e. the\r
// first line must match\r
}\r
\r
// We define some Regexes here that will be used regularily later\r
- rend = new Regex("\\/\\/"); // Find the end of an alignment\r
+ rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment\r
p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in\r
- // id/from/to\r
- s = new Regex("(\\S+)\\s+(\\w{2})\\s+(.*)"); // Parses annotation subtype\r
+ // id/from/to\r
+ s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype\r
r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line\r
x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence\r
\r
+ // Convert all bracket types to parentheses (necessary for passing to VARNA)\r
+ Regex openparen = new Regex("(<|\\[)", "(");\r
+ Regex closeparen = new Regex("(>|\\])", ")");\r
+\r
+ // Detect if file is RNA by looking for bracket types\r
+ Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");\r
+\r
rend.optimize();\r
p.optimize();\r
s.optimize();\r
r.optimize();\r
x.optimize();\r
+ openparen.optimize();\r
+ closeparen.optimize();\r
\r
while ((line = nextLine()) != null)\r
{\r
{\r
String acc = (String) accs.nextElement();\r
// logger.debug("Processing sequence " + acc);\r
- String seq = (String) seqs.get(acc);\r
+ String seq = (String) seqs.remove(acc);\r
if (maxLength < seq.length())\r
{\r
maxLength = seq.length();\r
int start = 1;\r
int end = -1;\r
String sid = acc;\r
- // Retrieve hash of annotations for this accession\r
+ /*\r
+ * Retrieve hash of annotations for this accession\r
+ * Associate Annotation with accession\r
+ */\r
Hashtable accAnnotations = null;\r
\r
if (seqAnn != null && seqAnn.containsKey(acc))\r
{\r
- accAnnotations = (Hashtable) seqAnn.get(acc);\r
+ accAnnotations = (Hashtable) seqAnn.remove(acc);\r
+ //TODO: add structures to sequence\r
}\r
\r
// Split accession in id and from/to\r
{\r
String src = dbr.substring(0, dbr.indexOf(";"));\r
String acn = dbr.substring(dbr.indexOf(";") + 1);\r
- DBRefEntry dbref = new DBRefEntry(jalview.util.DBRefUtils\r
- .getCanonicalName(src), acn, "");\r
- seqO.addDBRef(dbref);\r
+ jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);\r
+ // seqO.addDBRef(dbref);\r
}\r
+ } \r
+ if (accAnnotations != null && accAnnotations.containsKey("SS"))\r
+ {\r
+ Vector v = (Vector) accAnnotations.get("SS");\r
+ \r
+ for (int i = 0; i < v.size(); i++)\r
+ {\r
+ AlignmentAnnotation an = (AlignmentAnnotation) v.elementAt(i);\r
+ seqO.addAlignmentAnnotation(an);\r
+ //annotations.add(an);\r
+ }\r
}\r
+ \r
Hashtable features = null;\r
// We need to adjust the positions of all features to account for gaps\r
try\r
{\r
- features = (Hashtable) accAnnotations.get("features");\r
+ features = (Hashtable) accAnnotations.remove("features");\r
} catch (java.lang.NullPointerException e)\r
{\r
// loggerwarn("Getting Features for " + acc + ": " +\r
// if we have features\r
if (features != null)\r
{\r
+ int posmap[] = seqO.findPositionMap();\r
Enumeration i = features.keys();\r
while (i.hasMoreElements())\r
{\r
// TODO: parse out scores as annotation row\r
// TODO: map coding region to core jalview feature types\r
String type = i.nextElement().toString();\r
- Hashtable content = (Hashtable) features.get(type);\r
-\r
+ Hashtable content = (Hashtable) features.remove(type);\r
Enumeration j = content.keys();\r
while (j.hasMoreElements())\r
{\r
for (int k = 0; k < byChar.length; k++)\r
{\r
char c = byChar[k];\r
- if (!(c == ' ' || c == '_' || c == '-'))\r
+ if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM\r
+ // uses\r
+ // '.'\r
+ // for\r
+ // feature\r
+ // background\r
{\r
- int new_pos = seqO.findPosition(k);\r
+ int new_pos = posmap[k]; // look up nearest seqeunce\r
+ // position to this column\r
SequenceFeature feat = new SequenceFeature(type, desc,\r
new_pos, new_pos, 0f, null);\r
\r
}\r
\r
}\r
+ // garbage collect\r
+\r
// logger.debug("Adding seq " + acc + " from " + start + " to " + end\r
// + ": " + seq);\r
this.seqs.addElement(seqO);\r
}\r
+ return; // finished parsing this segment of source\r
}\r
else if (!r.search(line))\r
{\r
if (x.search(annContent))\r
{\r
// parse out and create alignment annotation directly.\r
- parseAnnotationRow(annotations, x.stringMatched(1), x\r
- .stringMatched(2));\r
+ parseAnnotationRow(annotations, x.stringMatched(1),\r
+ x.stringMatched(2));\r
}\r
}\r
else if (annType.equals("GR"))\r
{\r
String acc = s.stringMatched(1);\r
String type = s.stringMatched(2);\r
- String seq = s.stringMatched(3);\r
- String description = new String();\r
-\r
+ String seq = new String(s.stringMatched(3));\r
+ String description = null;\r
// Check for additional information about the current annotation\r
- if (x.search(seq))\r
+ // We use a simple string tokenizer here for speed\r
+ StringTokenizer sep = new StringTokenizer(seq, " \t");\r
+ description = sep.nextToken();\r
+ if (sep.hasMoreTokens())\r
{\r
- description = x.stringMatched(1);\r
- seq = x.stringMatched(2);\r
+ seq = sep.nextToken();\r
+ }\r
+ else\r
+ {\r
+ seq = description;\r
+ description = new String();\r
}\r
// sequence id with from-to fields\r
\r
ann = new Hashtable();\r
seqAnn.put(acc, ann);\r
}\r
-\r
+ //TODO test structure, call parseAnnotationRow with vector from hashtable for specific sequence\r
Hashtable features;\r
// Get an object with all the content for an annotation\r
if (ann.containsKey("features"))\r
ns = "";\r
}\r
ns += seq;\r
- content.put(description, seq);\r
+ content.put(description, ns);\r
+
+ if(type.equals("SS")){\r
+ Hashtable strucAnn;\r
+ if (seqAnn.containsKey(acc))\r
+ {\r
+ strucAnn = (Hashtable) seqAnn.get(acc);\r
+ }\r
+ else\r
+ {\r
+ strucAnn = new Hashtable();\r
+ }\r
+ \r
+ Vector newStruc=new Vector();\r
+ parseAnnotationRow(newStruc, type,ns);\r
+ \r
+ strucAnn.put(type, newStruc);\r
+ seqAnn.put(acc, strucAnn);\r
+ }\r
}\r
else\r
{\r
- throw new IOException("Error parsing " + line);\r
+ System.err\r
+ .println("Warning - couldn't parse sequence annotation row line:\n"\r
+ + line);\r
+ // throw new IOException("Error parsing " + line);\r
}\r
}\r
else\r
private AlignmentAnnotation parseAnnotationRow(Vector annotation,\r
String label, String annots)\r
{\r
+ String convert1, convert2 = null;\r
+\r
+ // Convert all bracket types to parentheses\r
+ Regex openparen = new Regex("(<|\\[)", "(");\r
+ Regex closeparen = new Regex("(>|\\])", ")");\r
+\r
+ // Detect if file is RNA by looking for bracket types\r
+ Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");\r
+\r
+ convert1 = openparen.replaceAll(annots);\r
+ convert2 = closeparen.replaceAll(convert1);\r
+ annots = convert2;\r
+\r
String type = (label.indexOf("_cons") == label.length() - 5) ? label\r
.substring(0, label.length() - 5) : label;\r
boolean ss = false;\r
{\r
String pos = annots.substring(i, i + 1);\r
Annotation ann;\r
- ann = new Annotation(pos, "", ' ', Float.NaN);\r
+ ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not\r
+ // be written out\r
if (ss)\r
{\r
- ann.secondaryStructure = jalview.schemes.ResidueProperties\r
- .getDssp3state(pos).charAt(0);\r
+ if (detectbrackets.search(pos))\r
+ {\r
+ ann.secondaryStructure = jalview.schemes.ResidueProperties\r
+ .getRNASecStrucState(pos).charAt(0);\r
+ }\r
+ else\r
+ {\r
+ ann.secondaryStructure = jalview.schemes.ResidueProperties\r
+ .getDssp3state(pos).charAt(0);\r
+ }\r
+\r
if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')\r
{\r
- ann.displayCharacter = "";\r
+ ann.displayCharacter = ""; // null; // " ";\r
}\r
else\r
{\r
- ann.displayCharacter += " ";\r
+ ann.displayCharacter = " " + ann.displayCharacter;\r
}\r
}\r
\r
annot.annotations.length);\r
System.arraycopy(els, 0, anns, annot.annotations.length, els.length);\r
annot.annotations = anns;\r
+ //System.out.println("else: ");\r
}\r
return annot;\r
}\r
+ id);\r
return id;\r
}\r
+ /**\r
+ * //ssline is complete secondary structure line private AlignmentAnnotation\r
+ * addHelices(Vector annotation, String label, String ssline) {\r
+ * \r
+ * // decide on secondary structure or not. Annotation[] els = new\r
+ * Annotation[ssline.length()]; for (int i = 0; i < ssline.length(); i++) {\r
+ * String pos = ssline.substring(i, i + 1); Annotation ann; ann = new\r
+ * Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not\r
+ * \r
+ * ann.secondaryStructure =\r
+ * jalview.schemes.ResidueProperties.getRNAssState(pos).charAt(0);\r
+ * \r
+ * ann.displayCharacter = "x" + ann.displayCharacter;\r
+ * \r
+ * System.out.println(ann.displayCharacter);\r
+ * \r
+ * els[i] = ann; } AlignmentAnnotation helicesAnnot = null; Enumeration e =\r
+ * annotation.elements(); while (e.hasMoreElements()) { helicesAnnot =\r
+ * (AlignmentAnnotation) e.nextElement(); if (helicesAnnot.label.equals(type))\r
+ * break; helicesAnnot = null; } if (helicesAnnot == null) { helicesAnnot =\r
+ * new AlignmentAnnotation(type, type, els);\r
+ * annotation.addElement(helicesAnnot); } else { Annotation[] anns = new\r
+ * Annotation[helicesAnnot.annotations.length + els.length];\r
+ * System.arraycopy(helicesAnnot.annotations, 0, anns, 0,\r
+ * helicesAnnot.annotations.length); System.arraycopy(els, 0, anns,\r
+ * helicesAnnot.annotations.length, els.length); helicesAnnot.annotations =\r
+ * anns; }\r
+ * \r
+ * helicesAnnot.features = Rna.GetBasePairs(ssline);\r
+ * Rna.HelixMap(helicesAnnot.features);\r
+ * \r
+ * \r
+ * return helicesAnnot; }\r
+ */\r
}\r
git://source.jalview.org / jalview.git / blobdiff