/*\r
- * Jalview - A Sequence Alignment Editor and Viewer\r
- * Copyright (C) 2005 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 2.6)\r
+ * Copyright (C) 2010 J Procter, AM Waterhouse, 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 bsb at sanger.ac.uk\r
+ * This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk\r
*/\r
package jalview.io;\r
+\r
import java.io.*;\r
import java.util.*;\r
-import jalview.datamodel.*;\r
+\r
import com.stevesoft.pat.*;\r
-//import org.apache.log4j.*;\r
+import jalview.datamodel.*;\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
- //static Logger logger = Logger.getLogger("jalview.io.StockholmFile");\r
-\r
- public StockholmFile()\r
+ // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");\r
+\r
+ public StockholmFile()\r
+ {\r
+ }\r
+\r
+ public StockholmFile(String inFile, String type) throws IOException\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
+ }\r
+\r
+ /**\r
+ * Parse a file in Stockholm format into Jalview's data model. The file has to\r
+ * be passed at construction time\r
+ * \r
+ * @throws IOException\r
+ * If there is an error with the input file\r
+ */\r
+ public void parse() throws IOException\r
+ {\r
+ StringBuffer treeString = new StringBuffer();\r
+ String treeName = null;\r
+ // --------------- Variable Definitions -------------------\r
+ String line;\r
+ String version;\r
+ // String id;\r
+ Hashtable seqAnn = new Hashtable(); // Sequence related annotations\r
+ Hashtable seqs = new Hashtable();\r
+ Regex p, r, rend, s, x;\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 = new Regex("# STOCKHOLM ([\\d\\.]+)");\r
+ if (!r.search(nextLine()))\r
{\r
+ throw new IOException(\r
+ "This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");\r
}\r
-\r
-\r
- public StockholmFile(String inFile, String type) throws IOException\r
+ else\r
{\r
- super(inFile, type);\r
+ version = r.stringMatched(1);\r
+ // logger.debug("Stockholm version: " + version);\r
}\r
\r
- public void initData()\r
+ // We define some Regexes here that will be used regularily later\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+(\\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
+ rend.optimize();\r
+ p.optimize();\r
+ s.optimize();\r
+ r.optimize();\r
+ x.optimize();\r
+\r
+ while ((line = nextLine()) != null)\r
{\r
- super.initData();\r
- }\r
+ if (line.length() == 0)\r
+ {\r
+ continue;\r
+ }\r
+ if (rend.search(line))\r
+ {\r
+ // End of the alignment, pass stuff back\r
+\r
+ this.noSeqs = seqs.size();\r
+ // logger.debug("Number of sequences: " + this.noSeqs);\r
+ Enumeration accs = seqs.keys();\r
+ while (accs.hasMoreElements())\r
+ {\r
+ String acc = (String) accs.nextElement();\r
+ // logger.debug("Processing sequence " + acc);\r
+ String seq = (String) seqs.remove(acc);\r
+ if (maxLength < seq.length())\r
+ {\r
+ maxLength = seq.length();\r
+ }\r
+ int start = 1;\r
+ int end = -1;\r
+ String sid = acc;\r
+ // Retrieve hash of annotations for this accession\r
+ Hashtable accAnnotations = null;\r
+\r
+ if (seqAnn != null && seqAnn.containsKey(acc))\r
+ {\r
+ accAnnotations = (Hashtable) seqAnn.remove(acc);\r
+ }\r
+\r
+ // Split accession in id and from/to\r
+ if (p.search(acc))\r
+ {\r
+ sid = p.stringMatched(1);\r
+ start = Integer.parseInt(p.stringMatched(2));\r
+ end = Integer.parseInt(p.stringMatched(3));\r
+ }\r
+ // logger.debug(sid + ", " + start + ", " + end);\r
+\r
+ Sequence seqO = new Sequence(sid, seq, start, end);\r
+ // Add Description (if any)\r
+ if (accAnnotations != null && accAnnotations.containsKey("DE"))\r
+ {\r
+ String desc = (String) accAnnotations.get("DE");\r
+ seqO.setDescription((desc == null) ? "" : desc);\r
+ }\r
+ // Add DB References (if any)\r
+ if (accAnnotations != null && accAnnotations.containsKey("DR"))\r
+ {\r
+ String dbr = (String) accAnnotations.get("DR");\r
+ if (dbr != null && dbr.indexOf(";") > -1)\r
+ {\r
+ String src = dbr.substring(0, dbr.indexOf(";"));\r
+ String acn = dbr.substring(dbr.indexOf(";") + 1);\r
+ jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);\r
+ // seqO.addDBRef(dbref);\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.remove("features");\r
+ } catch (java.lang.NullPointerException e)\r
+ {\r
+ // loggerwarn("Getting Features for " + acc + ": " +\r
+ // e.getMessage());\r
+ // continue;\r
+ }\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 secondary structure annotation as annotation\r
+ // row\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.remove(type);\r
+ Enumeration j = content.keys();\r
+ while (j.hasMoreElements())\r
+ {\r
+ String desc = j.nextElement().toString();\r
+ String ns = content.get(desc).toString();\r
+ char[] byChar = ns.toCharArray();\r
+ for (int k = 0; k < byChar.length; k++)\r
+ {\r
+ char c = byChar[k];\r
+ if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM\r
+ // uses\r
+ // '.'\r
+ // for\r
+ // feature\r
+ // background\r
+ {\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
+ seqO.addSequenceFeature(feat);\r
+ }\r
+ }\r
+ }\r
\r
- /**\r
- * Parse a file in Stockholm format into Jalview's data model. The file has\r
- * to be passed at construction time\r
- * @throws IOException If there is an error with the input file\r
- */\r
- public void parse() throws IOException\r
- {\r
- // --------------- Variable Definitions -------------------\r
- String line;\r
- String version;\r
- // String id;\r
- Hashtable alAnn = new Hashtable(); // Alignment wide annotations\r
- Hashtable seqAnn = new Hashtable(); // Sequence related annotations\r
- Hashtable seqs = new Hashtable();\r
- Regex p, r, rend, s, x;\r
-\r
- // ------------------ Parsing File ----------------------\r
- // First, we have to check that this file has STOCKHOLM format, i.e. the first line must match\r
- r = new Regex("# STOCKHOLM ([\\d\\.]+)");\r
- if(!r.search(nextLine()))\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
+ // System.err.println("Found sequence line: " + line);\r
+\r
+ // Split sequence in sequence and accession parts\r
+ if (!x.search(line))\r
{\r
- throw new IOException("This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");\r
+ // logger.error("Could not parse sequence line: " + line);\r
+ throw new IOException("Could not parse sequence line: " + line);\r
}\r
- else\r
+ String ns = (String) seqs.get(x.stringMatched(1));\r
+ if (ns == null)\r
{\r
- version = r.stringMatched(1);\r
- //logger.debug("Stockholm version: " + version);\r
+ ns = "";\r
}\r
+ ns += x.stringMatched(2);\r
\r
-// We define some Regexes here that will be used regularily later\r
- rend = new Regex("\\/\\/"); // Find the end of an alignment\r
- p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in id/from/to\r
- s = new Regex("(\\S+)\\s+(\\w{2})\\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
+ seqs.put(x.stringMatched(1), ns);\r
+ }\r
+ else\r
+ {\r
+ String annType = r.stringMatched(1);\r
+ String annContent = r.stringMatched(2);\r
\r
- rend.optimize();\r
- p.optimize();\r
- s.optimize();\r
- r.optimize();\r
- x.optimize();\r
+ // System.err.println("type:" + annType + " content: " + annContent);\r
\r
- while ( (line = nextLine()) != null)\r
+ if (annType.equals("GF"))\r
{\r
- if (line.length() == 0) continue;\r
- if(rend.search(line))\r
+ /*\r
+ * Generic per-File annotation, free text Magic features: #=GF NH\r
+ * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier\r
+ * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS\r
+ * \r
+ * Compulsory fields: ------------------\r
+ * \r
+ * AC Accession number: Accession number in form PFxxxxx.version or\r
+ * PBxxxxxx. ID Identification: One word name for family. DE\r
+ * Definition: Short description of family. AU Author: Authors of the\r
+ * entry. SE Source of seed: The source suggesting the seed members\r
+ * belong to one family. GA Gathering method: Search threshold to\r
+ * build the full alignment. TC Trusted Cutoff: Lowest sequence score\r
+ * and domain score of match in the full alignment. NC Noise Cutoff:\r
+ * Highest sequence score and domain score of match not in full\r
+ * alignment. TP Type: Type of family -- presently Family, Domain,\r
+ * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM\r
+ * Alignment Method The order ls and fs hits are aligned to the model\r
+ * to build the full align. // End of alignment.\r
+ * \r
+ * Optional fields: ----------------\r
+ * \r
+ * DC Database Comment: Comment about database reference. DR Database\r
+ * Reference: Reference to external database. RC Reference Comment:\r
+ * Comment about literature reference. RN Reference Number: Reference\r
+ * Number. RM Reference Medline: Eight digit medline UI number. RT\r
+ * Reference Title: Reference Title. RA Reference Author: Reference\r
+ * Author RL Reference Location: Journal location. PI Previous\r
+ * identifier: Record of all previous ID lines. KW Keywords: Keywords.\r
+ * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.\r
+ * NL Location: Location of nested domains - sequence ID, start and\r
+ * end of insert.\r
+ * \r
+ * Obsolete fields: ----------- AL Alignment method of seed: The\r
+ * method used to align the seed members.\r
+ */\r
+ // Let's save the annotations, maybe we'll be able to do something\r
+ // with them later...\r
+ Regex an = new Regex("(\\w+)\\s*(.*)");\r
+ if (an.search(annContent))\r
+ {\r
+ if (an.stringMatched(1).equals("NH"))\r
{\r
-// End of the alignment, pass stuff back\r
-\r
- this.noSeqs = seqs.size();\r
- //logger.debug("Number of sequences: " + this.noSeqs);\r
- Enumeration accs = seqs.keys();\r
- while (accs.hasMoreElements())\r
- {\r
- String acc = (String) accs.nextElement();\r
- //logger.debug("Processing sequence " + acc);\r
- String seq = (String) seqs.get(acc);\r
- if (maxLength < seq.length())\r
- {\r
- maxLength = seq.length();\r
- }\r
- int start = 1;\r
- int end = -1;\r
- String sid = acc;\r
- // Split accession in id and from/to\r
- if (p.search(acc))\r
- {\r
- sid = p.stringMatched(1);\r
- start = Integer.parseInt(p.stringMatched(2));\r
- end = Integer.parseInt(p.stringMatched(3));\r
- }\r
- //logger.debug(sid + ", " + start + ", " + end);\r
-\r
- Sequence seqO = new Sequence(sid, seq, start, end);\r
- Hashtable features = null;\r
- // We need to adjust the positions of all features to account for gaps\r
- try\r
- {\r
- features = (Hashtable) ((Hashtable) seqAnn.get(acc)).get("features");\r
- }\r
- catch (java.lang.NullPointerException e)\r
- {\r
- //loggerwarn("Getting Features for " + acc + ": " + e.getMessage());\r
- //continue;\r
- }\r
- // if we have features\r
- if (features != null)\r
- {\r
- Enumeration i = features.keys();\r
- while(i.hasMoreElements())\r
- {\r
- String type = i.nextElement().toString();\r
- Hashtable content = (Hashtable) features.get(type);\r
-\r
- Enumeration j = content.keys();\r
- while(j.hasMoreElements())\r
- {\r
- String desc = j.nextElement().toString();\r
- String ns = content.get(desc).toString();\r
- char[] byChar = ns.toCharArray();\r
- for (int k = 0; k < byChar.length; k++)\r
- {\r
- char c = byChar[k];\r
- if (! (c == ' ' || c == '_' ||\r
- c == '-'))\r
- {\r
- int new_pos = seqO.findPosition(k);\r
- SequenceFeature feat =\r
- new SequenceFeature(type,\r
- desc, new_pos, new_pos, 0f, null);\r
-\r
- seqO.addSequenceFeature(feat);\r
- }\r
- }\r
- }\r
-\r
- }\r
-\r
- }\r
- //logger.debug("Adding seq " + acc + " from " + start + " to " + end + ": " + seq);\r
- this.seqs.addElement(seqO);\r
- }\r
+ treeString.append(an.stringMatched(2));\r
}\r
- else if (!r.search(line))\r
+ else if (an.stringMatched(1).equals("TN"))\r
{\r
- //System.err.println("Found sequence line: " + line);\r
-\r
- // Split sequence in sequence and accession parts\r
- if(!x.search(line))\r
+ if (treeString.length() > 0)\r
+ {\r
+ if (treeName == null)\r
{\r
- //logger.error("Could not parse sequence line: " + line);\r
- throw new IOException("Could not parse sequence line: " + line);\r
+ treeName = "Tree " + (getTreeCount() + 1);\r
}\r
- String ns = (String) seqs.get(x.stringMatched(1));\r
- if (ns == null) ns = "";\r
- ns += x.stringMatched(2);\r
+ addNewickTree(treeName, treeString.toString());\r
+ }\r
+ treeName = an.stringMatched(2);\r
+ treeString = new StringBuffer();\r
+ }\r
+ setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));\r
+ }\r
+ }\r
+ else if (annType.equals("GS"))\r
+ {\r
+ // Generic per-Sequence annotation, free text\r
+ /*\r
+ * Pfam uses these features: Feature Description ---------------------\r
+ * ----------- AC <accession> ACcession number DE <freetext>\r
+ * DEscription DR <db>; <accession>; Database Reference OS <organism>\r
+ * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)\r
+ * LO <look> Look (Color, etc.)\r
+ */\r
+ if (s.search(annContent))\r
+ {\r
+ String acc = s.stringMatched(1);\r
+ String type = s.stringMatched(2);\r
+ String content = s.stringMatched(3);\r
+ // TODO: store DR in a vector.\r
+ // TODO: store AC according to generic file db annotation.\r
+ Hashtable ann;\r
+ if (seqAnn.containsKey(acc))\r
+ {\r
+ ann = (Hashtable) seqAnn.get(acc);\r
+ }\r
+ else\r
+ {\r
+ ann = new Hashtable();\r
+ }\r
+ ann.put(type, content);\r
+ seqAnn.put(acc, ann);\r
+ }\r
+ else\r
+ {\r
+ throw new IOException("Error parsing " + line);\r
+ }\r
+ }\r
+ else if (annType.equals("GC"))\r
+ {\r
+ // Generic per-Column annotation, exactly 1 char per column\r
+ // always need a label.\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
+ }\r
+ }\r
+ else if (annType.equals("GR"))\r
+ {\r
+ // Generic per-Sequence AND per-Column markup, exactly 1 char per\r
+ // column\r
+ /*\r
+ * Feature Description Markup letters ------- -----------\r
+ * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface\r
+ * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane\r
+ * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;\r
+ * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in\r
+ * or after) [0-2]\r
+ */\r
+ if (s.search(annContent))\r
+ {\r
+ String acc = s.stringMatched(1);\r
+ String type = s.stringMatched(2);\r
+ String seq = new String(s.stringMatched(3));\r
+ String description = null;\r
+ // Check for additional information about the current annotation\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
+ seq = sep.nextToken();\r
+ }\r
+ else\r
+ {\r
+ seq = description;\r
+ description = new String();\r
+ }\r
+ // sequence id with from-to fields\r
\r
- seqs.put(x.stringMatched(1), ns);\r
+ Hashtable ann;\r
+ // Get an object with all the annotations for this sequence\r
+ if (seqAnn.containsKey(acc))\r
+ {\r
+ // logger.debug("Found annotations for " + acc);\r
+ ann = (Hashtable) seqAnn.get(acc);\r
}\r
else\r
{\r
- String annType = r.stringMatched(1);\r
- String annContent = r.stringMatched(2);\r
+ // logger.debug("Creating new annotations holder for " + acc);\r
+ ann = new Hashtable();\r
+ seqAnn.put(acc, ann);\r
+ }\r
\r
- //System.err.println("type:" + annType + " content: " + annContent);\r
+ Hashtable features;\r
+ // Get an object with all the content for an annotation\r
+ if (ann.containsKey("features"))\r
+ {\r
+ // logger.debug("Found features for " + acc);\r
+ features = (Hashtable) ann.get("features");\r
+ }\r
+ else\r
+ {\r
+ // logger.debug("Creating new features holder for " + acc);\r
+ features = new Hashtable();\r
+ ann.put("features", features);\r
+ }\r
\r
- if (annType.equals("GF"))\r
- {\r
- /* Generic per-File annotation, free text\r
- * Magic features:\r
- * #=GF NH <tree in New Hampshire eXtended format>\r
- * #=GF TN <Unique identifier for the next tree>\r
- * Pfam descriptions:\r
- 7. DESCRIPTION OF FIELDS\r
-\r
- Compulsory fields:\r
- ------------------\r
-\r
- AC Accession number: Accession number in form PFxxxxx.version or PBxxxxxx.\r
- ID Identification: One word name for family.\r
- DE Definition: Short description of family.\r
- AU Author: Authors of the entry.\r
- SE Source of seed: The source suggesting the seed members belong to one family.\r
- GA Gathering method: Search threshold to build the full alignment.\r
- TC Trusted Cutoff: Lowest sequence score and domain score of match in the full alignment.\r
- NC Noise Cutoff: Highest sequence score and domain score of match not in full alignment.\r
- TP Type: Type of family -- presently Family, Domain, Motif or Repeat.\r
- SQ Sequence: Number of sequences in alignment.\r
- AM Alignment Method The order ls and fs hits are aligned to the model to build the full align.\r
- // End of alignment.\r
-\r
- Optional fields:\r
- ----------------\r
-\r
- DC Database Comment: Comment about database reference.\r
- DR Database Reference: Reference to external database.\r
- RC Reference Comment: Comment about literature reference.\r
- RN Reference Number: Reference Number.\r
- RM Reference Medline: Eight digit medline UI number.\r
- RT Reference Title: Reference Title.\r
- RA Reference Author: Reference Author\r
- RL Reference Location: Journal location.\r
- PI Previous identifier: Record of all previous ID lines.\r
- KW Keywords: Keywords.\r
- CC Comment: Comments.\r
- NE Pfam accession: Indicates a nested domain.\r
- NL Location: Location of nested domains - sequence ID, start and end of insert.\r
-\r
- Obsolete fields:\r
- -----------\r
- AL Alignment method of seed: The method used to align the seed members.\r
- */\r
- // Let's save the annotations, maybe we'll be able to do something with them later...\r
- Regex an = new Regex("(\\w+)\\s*(.*)");\r
- if (an.search(annContent)) alAnn.put(an.stringMatched(1), an.stringMatched(2));\r
- }\r
- else if(annType.equals("GS"))\r
- {\r
- // Generic per-Sequence annotation, free text\r
- /* Pfam uses these features:\r
- Feature Description\r
- --------------------- -----------\r
- AC <accession> ACcession number\r
- DE <freetext> DEscription\r
- DR <db>; <accession>; Database Reference\r
- OS <organism> OrganiSm (species)\r
- OC <clade> Organism Classification (clade, etc.)\r
- LO <look> Look (Color, etc.)\r
- */\r
- if (s.search(annContent))\r
- {\r
- String acc = s.stringMatched(1);\r
- String type = s.stringMatched(2);\r
- String content = s.stringMatched(3);\r
-\r
- Hashtable ann;\r
- if (seqAnn.containsKey(acc))\r
- {\r
- ann = (Hashtable) seqAnn.get(acc);\r
- }\r
- else\r
- {\r
- ann = new Hashtable();\r
- }\r
- ann.put(type, content);\r
- seqAnn.put(acc, ann);\r
- }\r
- else\r
- {\r
- throw new IOException("Error parsing " + line);\r
- }\r
- }\r
- else if(annType.equals("GC"))\r
- {\r
- // Generic per-Column annotation, exactly 1 char per column\r
- }\r
- else if(annType.equals("GR"))\r
- {\r
- // Generic per-Sequence AND per-Column markup, exactly 1 char per column\r
- /*\r
- Feature Description Markup letters\r
- ------- ----------- --------------\r
- SS Secondary Structure [HGIEBTSCX]\r
- SA Surface Accessibility [0-9X]\r
- (0=0%-10%; ...; 9=90%-100%)\r
- TM TransMembrane [Mio]\r
- PP Posterior Probability [0-9*]\r
- (0=0.00-0.05; 1=0.05-0.15; *=0.95-1.00)\r
- LI LIgand binding [*]\r
- AS Active Site [*]\r
- IN INtron (in or after) [0-2]\r
- */\r
- if (s.search(annContent))\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
- // Check for additional information about the current annotation\r
- if (x.search(seq))\r
- {\r
- description = x.stringMatched(1);\r
- seq = x.stringMatched(2);\r
- }\r
- // sequence id with from-to fields\r
-\r
- Hashtable ann;\r
- // Get an object with all the annotations for this sequence\r
- if (seqAnn.containsKey(acc))\r
- {\r
- //logger.debug("Found annotations for " + acc);\r
- ann = (Hashtable) seqAnn.get(acc);\r
- }\r
- else\r
- {\r
- //logger.debug("Creating new annotations holder for " + acc);\r
- ann = new Hashtable();\r
- seqAnn.put(acc, ann);\r
- }\r
-\r
- Hashtable features;\r
- // Get an object with all the content for an annotation\r
- if (ann.containsKey("features"))\r
- {\r
- //logger.debug("Found features for " + acc);\r
- features = (Hashtable) ann.get("features");\r
- }\r
- else\r
- {\r
- //logger.debug("Creating new features holder for " + acc);\r
- features = new Hashtable();\r
- ann.put("features", features);\r
- }\r
-\r
- Hashtable content;\r
- if (features.containsKey(this.id2type(type)))\r
- {\r
- //logger.debug("Found content for " + this.id2type(type));\r
- content = (Hashtable) features.get(this.id2type(type));\r
- }\r
- else\r
- {\r
- //logger.debug("Creating new content holder for " + this.id2type(type));\r
- content = new Hashtable();\r
- features.put(this.id2type(type), content);\r
- }\r
- String ns = (String) content.get(description);\r
- if (ns == null) ns = "";\r
- ns += seq;\r
- content.put(description, seq);\r
- }\r
- else\r
- {\r
- throw new IOException("Error parsing " + line);\r
- }\r
- }\r
- else\r
- {\r
- throw new IOException("Unknown annotation detected: " + annType + " " + annContent);\r
- }\r
+ Hashtable content;\r
+ if (features.containsKey(this.id2type(type)))\r
+ {\r
+ // logger.debug("Found content for " + this.id2type(type));\r
+ content = (Hashtable) features.get(this.id2type(type));\r
+ }\r
+ else\r
+ {\r
+ // logger.debug("Creating new content holder for " +\r
+ // this.id2type(type));\r
+ content = new Hashtable();\r
+ features.put(this.id2type(type), content);\r
+ }\r
+ String ns = (String) content.get(description);\r
+ if (ns == null)\r
+ {\r
+ ns = "";\r
}\r
+ ns += seq;\r
+ content.put(description, seq);\r
+ }\r
+ else\r
+ {\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
+ {\r
+ throw new IOException("Unknown annotation detected: " + annType\r
+ + " " + annContent);\r
}\r
+ }\r
}\r
-\r
- public static String print(SequenceI[] s)\r
+ if (treeString.length() > 0)\r
{\r
- return "not yet implemented";\r
+ if (treeName == null)\r
+ {\r
+ treeName = "Tree " + (1 + getTreeCount());\r
+ }\r
+ addNewickTree(treeName, treeString.toString());\r
}\r
+ }\r
+\r
+ private AlignmentAnnotation parseAnnotationRow(Vector annotation,\r
+ String label, String annots)\r
+ {\r
+ String type = (label.indexOf("_cons") == label.length() - 5) ? label\r
+ .substring(0, label.length() - 5) : label;\r
+ boolean ss = false;\r
+ type = id2type(type);\r
+ if (type.equals("secondary structure"))\r
+ {\r
+ ss = true;\r
+ }\r
+ // decide on secondary structure or not.\r
+ Annotation[] els = new Annotation[annots.length()];\r
+ for (int i = 0; i < annots.length(); i++)\r
+ {\r
+ String pos = annots.substring(i, i + 1);\r
+ Annotation ann;\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 (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')\r
+ {\r
+ ann.displayCharacter = ""; // null; // " ";\r
+ }\r
+ else\r
+ {\r
+ ann.displayCharacter = " " + ann.displayCharacter;\r
+ }\r
+ }\r
\r
- public String print()\r
+ els[i] = ann;\r
+ }\r
+ AlignmentAnnotation annot = null;\r
+ Enumeration e = annotation.elements();\r
+ while (e.hasMoreElements())\r
+ {\r
+ annot = (AlignmentAnnotation) e.nextElement();\r
+ if (annot.label.equals(type))\r
+ break;\r
+ annot = null;\r
+ }\r
+ if (annot == null)\r
{\r
- return print(getSeqsAsArray());\r
+ annot = new AlignmentAnnotation(type, type, els);\r
+ annotation.addElement(annot);\r
+ }\r
+ else\r
+ {\r
+ Annotation[] anns = new Annotation[annot.annotations.length\r
+ + els.length];\r
+ System.arraycopy(annot.annotations, 0, anns, 0,\r
+ annot.annotations.length);\r
+ System.arraycopy(els, 0, anns, annot.annotations.length, els.length);\r
+ annot.annotations = anns;\r
+ }\r
+ return annot;\r
+ }\r
+\r
+ public static String print(SequenceI[] s)\r
+ {\r
+ return "not yet implemented";\r
+ }\r
+\r
+ public String print()\r
+ {\r
+ return print(getSeqsAsArray());\r
+ }\r
+\r
+ private static Hashtable typeIds = null;\r
+ static\r
+ {\r
+ if (typeIds == null)\r
+ {\r
+ typeIds = new Hashtable();\r
+ typeIds.put("SS", "secondary structure");\r
+ typeIds.put("SA", "surface accessibility");\r
+ typeIds.put("TM", "transmembrane");\r
+ typeIds.put("PP", "posterior probability");\r
+ typeIds.put("LI", "ligand binding");\r
+ typeIds.put("AS", "active site");\r
+ typeIds.put("IN", "intron");\r
+ typeIds.put("IR", "interacting residue");\r
+ typeIds.put("AC", "accession");\r
+ typeIds.put("OS", "organism");\r
+ typeIds.put("CL", "class");\r
+ typeIds.put("DE", "description");\r
+ typeIds.put("DR", "reference");\r
+ typeIds.put("LO", "look");\r
+ typeIds.put("RF", "reference positions");\r
+\r
}\r
+ }\r
\r
- private String id2type(String id)\r
+ private String id2type(String id)\r
+ {\r
+ if (typeIds.containsKey(id))\r
{\r
- // GR ids\r
- if (id.equals("SS")) return "secondary structure";\r
- else if (id.equals("SA")) return "surface accessibility";\r
- else if (id.equals("TM")) return "transmembrane";\r
- else if (id.equals("PP")) return "posterior probability";\r
- else if (id.equals("LI")) return "ligand binding";\r
- else if (id.equals("AS")) return "active site";\r
- else if (id.equals("IN")) return "intron";\r
- else if (id.equals("IR")) return "interacting residue";\r
- // GS ids\r
- else if (id.equals("AC")) return "accession";\r
- else if (id.equals("OS")) return "organism";\r
- else if (id.equals("CL")) return "class";\r
- else if (id.equals("DE")) return "description";\r
- else if (id.equals("DR")) return "reference";\r
- else if (id.equals("LO")) return "look";\r
- else return null;\r
+ return (String) typeIds.get(id);\r
}\r
+ System.err.println("Warning : Unknown Stockholm annotation type code "\r
+ + id);\r
+ return id;\r
+ }\r
}\r
git://source.jalview.org / jalview.git / blobdiff