-/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
- * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
- *
- * This file is part of Jalview.
- *
- * Jalview is free software: you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
- *
- * Jalview is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
- * PURPOSE. See the GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
- */
-/*
- * This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk
- */
-package jalview.io;
-
-import java.io.*;
-import java.util.*;
-
-import com.stevesoft.pat.*;
-import jalview.datamodel.*;
-import jalview.util.Format;
-
-// import org.apache.log4j.*;
-
-/**
- * This class is supposed to parse a Stockholm format file into Jalview There
- * are TODOs in this class: we do not know what the database source and version
- * is for the file when parsing the #GS= AC tag which associates accessions with
- * sequences. Database references are also not parsed correctly: a separate
- * reference string parser must be added to parse the database reference form
- * into Jalview's local representation.
- *
- * @author bsb at sanger.ac.uk
- * @version 0.3 + jalview mods
- *
- */
-public class StockholmFile extends AlignFile
-{
- // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");
- StringBuffer out; // output buffer
-
- AlignmentI al;
-
- public StockholmFile()
- {
- }
-
+/*\r
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)\r
+ * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, 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
+package jalview.io;\r
+\r
+import jalview.datamodel.AlignmentI;\r
+import jalview.datamodel.AlignmentAnnotation;\r
+import jalview.datamodel.Annotation;\r
+import jalview.datamodel.DBRefEntry;\r
+import jalview.datamodel.Mapping;\r
+import jalview.datamodel.Sequence;\r
+import jalview.datamodel.SequenceFeature;\r
+import jalview.datamodel.SequenceI;\r
+import jalview.util.Format;\r
+\r
+import java.io.BufferedReader;\r
+import java.io.FileReader;\r
+import java.io.IOException;\r
+import java.util.ArrayList;\r
+import java.util.Enumeration;\r
+import java.util.Hashtable;\r
+import java.util.List;\r
+import java.util.StringTokenizer;\r
+import java.util.Vector;\r
+\r
+import com.stevesoft.pat.Regex;\r
+\r
+import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses;\r
+import fr.orsay.lri.varna.factories.RNAFactory;\r
+import fr.orsay.lri.varna.models.rna.RNA;\r
+\r
+// import org.apache.log4j.*;\r
+\r
+/**\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 + jalview mods\r
+ * \r
+ */\r
+public class StockholmFile extends AlignFile\r
+{\r
+ // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");\r
+ protected ArrayList<RNA> result;\r
+ \r
+ StringBuffer out; // output buffer\r
+\r
+ AlignmentI al;\r
+\r
+ public StockholmFile()\r
+ {\r
+ }\r
+\r
/**
* Creates a new StockholmFile object for output.
*/
this.al = al;
}
- public StockholmFile(String inFile, String type) throws IOException
- {
- super(inFile, type);
- }
-
- public StockholmFile(FileParse source) throws IOException
- {
- super(source);
- }
-
- public void initData()
- {
- super.initData();
- }
-
- /**
- * Parse a file in Stockholm format into Jalview's data model. The file has to
- * be passed at construction time
- *
- * @throws IOException
- * If there is an error with the input file
- */
- public void parse() throws IOException
- {
- StringBuffer treeString = new StringBuffer();
- String treeName = null;
- // --------------- Variable Definitions -------------------
- String line;
- String version;
+ 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;
- Hashtable seqAnn = new Hashtable(); // Sequence related annotations
- Hashtable seqs = new Hashtable();
- Regex p, r, rend, s, x;
-
- // Temporary line for processing RNA annotation
- // String RNAannot = "";
-
- // ------------------ Parsing File ----------------------
- // First, we have to check that this file has STOCKHOLM format, i.e. the
- // first line must match
- r = new Regex("# STOCKHOLM ([\\d\\.]+)");
- if (!r.search(nextLine()))
- {
- throw new IOException(
- "This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");
- }
- else
- {
- version = r.stringMatched(1);
- // logger.debug("Stockholm version: " + version);
- }
-
- // We define some Regexes here that will be used regularily later
- rend = new Regex("^\\s*\\/\\/"); // Find the end of an alignment
- p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in
- // id/from/to
- s = new Regex("(\\S+)\\s+(\\S*)\\s+(.*)"); // Parses annotation subtype
- r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line
- x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence
-
- // Convert all bracket types to parentheses (necessary for passing to VARNA)
- Regex openparen = new Regex("(<|\\[)", "(");
- Regex closeparen = new Regex("(>|\\])", ")");
-
- // Detect if file is RNA by looking for bracket types
- Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))");
-
- rend.optimize();
- p.optimize();
- s.optimize();
- r.optimize();
- x.optimize();
- openparen.optimize();
- closeparen.optimize();
-
- while ((line = nextLine()) != null)
- {
- if (line.length() == 0)
- {
- continue;
- }
- if (rend.search(line))
- {
- // End of the alignment, pass stuff back
+ Hashtable seqAnn = new Hashtable(); // Sequence related annotations\r
+ Hashtable seqs = new Hashtable();\r
+ Regex p, r, rend, s, x;\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
+ 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
+ else\r
+ {\r
+ version = r.stringMatched(1);\r
+ \r
+ // logger.debug("Stockholm version: " + version);\r
+ }\r
+\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
+ // 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
+ if (line.length() == 0)\r
+ {\r
+ continue;\r
+ }\r
+ if (rend.search(line))\r
+ {\r
+ // End of the alignment, pass stuff back\r
this.noSeqs = seqs.size();
-
+ \r
String seqdb,dbsource = null;
Regex pf = new Regex("PF[0-9]{5}(.*)"); // Finds AC for Pfam
Regex rf = new Regex("RF[0-9]{5}(.*)"); // Finds AC for Rfam
dbsource = "RFAM";
}
}
- // logger.debug("Number of sequences: " + this.noSeqs);
- Enumeration accs = seqs.keys();
- while (accs.hasMoreElements())
- {
- String acc = (String) accs.nextElement();
- // logger.debug("Processing sequence " + acc);
- String seq = (String) seqs.remove(acc);
- if (maxLength < seq.length())
- {
- maxLength = seq.length();
- }
- int start = 1;
- int end = -1;
- String sid = acc;
- /*
+ // 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
+ /*\r
* Retrieve hash of annotations for this accession Associate
* Annotation with accession
- */
- Hashtable accAnnotations = null;
-
- if (seqAnn != null && seqAnn.containsKey(acc))
- {
- accAnnotations = (Hashtable) seqAnn.remove(acc);
- // TODO: add structures to sequence
- }
-
- // Split accession in id and from/to
- if (p.search(acc))
- {
- sid = p.stringMatched(1);
- start = Integer.parseInt(p.stringMatched(2));
- end = Integer.parseInt(p.stringMatched(3));
- }
- // logger.debug(sid + ", " + start + ", " + end);
-
- Sequence seqO = new Sequence(sid, seq, start, end);
- // Add Description (if any)
- if (accAnnotations != null && accAnnotations.containsKey("DE"))
- {
- String desc = (String) accAnnotations.get("DE");
- seqO.setDescription((desc == null) ? "" : desc);
- }
-
- // Add DB References (if any)
- if (accAnnotations != null && accAnnotations.containsKey("DR"))
- {
- String dbr = (String) accAnnotations.get("DR");
- if (dbr != null && dbr.indexOf(";") > -1)
- {
- String src = dbr.substring(0, dbr.indexOf(";"));
- String acn = dbr.substring(dbr.indexOf(";") + 1);
- jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn);
- }
- }
+ */\r
+ Hashtable accAnnotations = null;\r
+ \r
+ if (seqAnn != null && seqAnn.containsKey(acc))\r
+ {\r
+ accAnnotations = (Hashtable) seqAnn.remove(acc);\r
+ //TODO: add structures to sequence\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
+ }\r
+ } \r
if (accAnnotations != null && accAnnotations.containsKey("AC"))
{
{
String dbr = (String) accAnnotations.get("AC");
if (dbr != null)
- {
+ {\r
// we could get very clever here - but for now - just try to guess accession type from source of alignment plus structure of accession
guessDatabaseFor(seqO, dbr, dbsource);
-
- }
- }
+ \r
+ }\r
+ }\r
// else - do what ? add the data anyway and prompt the user to specify what references these are ?
}
-
- Hashtable features = null;
- // We need to adjust the positions of all features to account for gaps
- try
- {
- features = (Hashtable) accAnnotations.remove("features");
- } catch (java.lang.NullPointerException e)
- {
- // loggerwarn("Getting Features for " + acc + ": " +
- // e.getMessage());
- // continue;
- }
- // if we have features
- if (features != null)
- {
- int posmap[] = seqO.findPositionMap();
- Enumeration i = features.keys();
- while (i.hasMoreElements())
- {
- // TODO: parse out secondary structure annotation as annotation
- // row
- // TODO: parse out scores as annotation row
- // TODO: map coding region to core jalview feature types
- String type = i.nextElement().toString();
- Hashtable content = (Hashtable) features.remove(type);
+ \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
// add alignment annotation for this feature
String key = type2id(type);
}
}
- Enumeration j = content.keys();
- while (j.hasMoreElements())
- {
- String desc = j.nextElement().toString();
- String ns = content.get(desc).toString();
- char[] byChar = ns.toCharArray();
- for (int k = 0; k < byChar.length; k++)
- {
- char c = byChar[k];
- if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM
- // uses
- // '.'
- // for
- // feature
- // background
- {
- 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);
-
- seqO.addSequenceFeature(feat);
- }
- }
- }
-
- }
-
- }
- // garbage collect
-
- // logger.debug("Adding seq " + acc + " from " + start + " to " + end
- // + ": " + seq);
- this.seqs.addElement(seqO);
- }
- return; // finished parsing this segment of source
- }
- else if (!r.search(line))
- {
- // System.err.println("Found sequence line: " + line);
-
- // Split sequence in sequence and accession parts
- if (!x.search(line))
- {
- // logger.error("Could not parse sequence line: " + line);
- throw new IOException("Could not parse sequence line: " + line);
- }
- String ns = (String) seqs.get(x.stringMatched(1));
- if (ns == null)
- {
- ns = "";
- }
- ns += x.stringMatched(2);
-
- seqs.put(x.stringMatched(1), ns);
- }
- else
- {
- String annType = r.stringMatched(1);
- String annContent = r.stringMatched(2);
-
- // System.err.println("type:" + annType + " content: " + annContent);
-
- if (annType.equals("GF"))
- {
- /*
- * Generic per-File annotation, free text Magic features: #=GF NH
- * <tree in New Hampshire eXtended format> #=GF TN <Unique identifier
- * for the next tree> Pfam descriptions: 7. DESCRIPTION OF FIELDS
- *
- * Compulsory fields: ------------------
- *
- * AC Accession number: Accession number in form PFxxxxx.version or
- * PBxxxxxx. ID Identification: One word name for family. DE
- * Definition: Short description of family. AU Author: Authors of the
- * entry. SE Source of seed: The source suggesting the seed members
- * belong to one family. GA Gathering method: Search threshold to
- * build the full alignment. TC Trusted Cutoff: Lowest sequence score
- * and domain score of match in the full alignment. NC Noise Cutoff:
- * Highest sequence score and domain score of match not in full
- * alignment. TP Type: Type of family -- presently Family, Domain,
- * Motif or Repeat. SQ Sequence: Number of sequences in alignment. AM
- * Alignment Method The order ls and fs hits are aligned to the model
- * to build the full align. // End of alignment.
- *
- * Optional fields: ----------------
- *
- * DC Database Comment: Comment about database reference. DR Database
- * Reference: Reference to external database. RC Reference Comment:
- * Comment about literature reference. RN Reference Number: Reference
- * Number. RM Reference Medline: Eight digit medline UI number. RT
- * Reference Title: Reference Title. RA Reference Author: Reference
- * Author RL Reference Location: Journal location. PI Previous
- * identifier: Record of all previous ID lines. KW Keywords: Keywords.
- * CC Comment: Comments. NE Pfam accession: Indicates a nested domain.
- * NL Location: Location of nested domains - sequence ID, start and
- * end of insert.
- *
- * Obsolete fields: ----------- AL Alignment method of seed: The
- * method used to align the seed members.
- */
- // Let's save the annotations, maybe we'll be able to do something
- // with them later...
- Regex an = new Regex("(\\w+)\\s*(.*)");
- if (an.search(annContent))
- {
- if (an.stringMatched(1).equals("NH"))
- {
- treeString.append(an.stringMatched(2));
- }
- else if (an.stringMatched(1).equals("TN"))
- {
- if (treeString.length() > 0)
- {
- if (treeName == null)
- {
- treeName = "Tree " + (getTreeCount() + 1);
- }
- addNewickTree(treeName, treeString.toString());
- }
- treeName = an.stringMatched(2);
- treeString = new StringBuffer();
- }
- setAlignmentProperty(an.stringMatched(1), an.stringMatched(2));
- }
- }
- else if (annType.equals("GS"))
- {
- // Generic per-Sequence annotation, free text
- /*
- * Pfam uses these features: Feature Description ---------------------
- * ----------- AC <accession> ACcession number DE <freetext>
- * DEscription DR <db>; <accession>; Database Reference OS <organism>
- * OrganiSm (species) OC <clade> Organism Classification (clade, etc.)
- * LO <look> Look (Color, etc.)
- */
- if (s.search(annContent))
- {
- String acc = s.stringMatched(1);
- String type = s.stringMatched(2);
- String content = s.stringMatched(3);
- // TODO: store DR in a vector.
- // TODO: store AC according to generic file db annotation.
- Hashtable ann;
- if (seqAnn.containsKey(acc))
- {
- ann = (Hashtable) seqAnn.get(acc);
- }
- else
- {
- ann = new Hashtable();
- }
- ann.put(type, content);
- seqAnn.put(acc, ann);
- }
- else
- {
- throw new IOException("Error parsing " + line);
- }
- }
- else if (annType.equals("GC"))
- {
- // Generic per-Column annotation, exactly 1 char per column
- // always need a label.
- if (x.search(annContent))
- {
- // parse out and create alignment annotation directly.
- parseAnnotationRow(annotations, x.stringMatched(1),
- x.stringMatched(2));
- }
- }
- else if (annType.equals("GR"))
- {
- // Generic per-Sequence AND per-Column markup, exactly 1 char per
- // column
- /*
- * Feature Description Markup letters ------- -----------
- * -------------- SS Secondary Structure [HGIEBTSCX] SA Surface
- * Accessibility [0-9X] (0=0%-10%; ...; 9=90%-100%) TM TransMembrane
- * [Mio] PP Posterior Probability [0-9*] (0=0.00-0.05; 1=0.05-0.15;
- * *=0.95-1.00) LI LIgand binding [*] AS Active Site [*] IN INtron (in
- * or after) [0-2]
- */
- if (s.search(annContent))
- {
- 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
-
- Hashtable ann;
- // Get an object with all the annotations for this sequence
- if (seqAnn.containsKey(acc))
- {
- // logger.debug("Found annotations for " + acc);
- ann = (Hashtable) seqAnn.get(acc);
- }
- else
- {
- // logger.debug("Creating new annotations holder for " + acc);
- ann = new Hashtable();
- seqAnn.put(acc, ann);
- }
+ 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
+ \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
+ // logger.error("Could not parse sequence line: " + line);\r
+ throw new IOException("Could not parse sequence line: " + line);\r
+ }\r
+ String ns = (String) seqs.get(x.stringMatched(1));\r
+ if (ns == null)\r
+ {\r
+ ns = "";\r
+ }\r
+ ns += x.stringMatched(2);\r
+ \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
+ // System.err.println("type:" + annType + " content: " + annContent);\r
+ \r
+ if (annType.equals("GF"))\r
+ {\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
+ treeString.append(an.stringMatched(2));\r
+ }\r
+ else if (an.stringMatched(1).equals("TN"))\r
+ {\r
+ if (treeString.length() > 0)\r
+ {\r
+ if (treeName == null)\r
+ {\r
+ treeName = "Tree " + (getTreeCount() + 1);\r
+ }\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),\r
+ x.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
+ 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
// 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"))
- {
- // logger.debug("Found features for " + acc);
- features = (Hashtable) ann.get("features");
- }
- else
- {
- // logger.debug("Creating new features holder for " + acc);
- features = new Hashtable();
- ann.put("features", features);
- }
-
- Hashtable content;
- if (features.containsKey(this.id2type(type)))
- {
- // logger.debug("Found content for " + this.id2type(type));
- content = (Hashtable) features.get(this.id2type(type));
- }
- else
- {
- // logger.debug("Creating new content holder for " +
- // this.id2type(type));
- content = new Hashtable();
- features.put(this.id2type(type), content);
- }
- String ns = (String) content.get(description);
- if (ns == null)
- {
- ns = "";
- }
- ns += seq;
- content.put(description, ns);
- Hashtable strucAnn;
- if (seqAnn.containsKey(acc))
- {
- strucAnn = (Hashtable) seqAnn.get(acc);
- }
- else
- {
- strucAnn = new Hashtable();
- }
-
- Vector newStruc = new Vector();
- parseAnnotationRow(newStruc, type, ns);
- strucAnn.put(type, newStruc);
- seqAnn.put(acc, strucAnn);
- }
- else
- {
- System.err
- .println("Warning - couldn't parse sequence annotation row line:\n"
- + line);
- // throw new IOException("Error parsing " + line);
- }
- }
- else
- {
- throw new IOException("Unknown annotation detected: " + annType
- + " " + annContent);
- }
- }
- }
- if (treeString.length() > 0)
- {
- if (treeName == null)
- {
- treeName = "Tree " + (1 + getTreeCount());
- }
- addNewickTree(treeName, treeString.toString());
- }
- }
-
- /**
- * Demangle an accession string and guess the originating sequence database for a given sequence
- * @param seqO sequence to be annotated
- * @param dbr Accession string for sequence
- * @param dbsource source database for alignment (PFAM or RFAM)
- */
- private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)
- {
- DBRefEntry dbrf=null;
- List<DBRefEntry> dbrs=new ArrayList<DBRefEntry>();
- String seqdb="Unknown",sdbac=""+dbr;
- int st=-1,en=-1,p;
- if ((st=sdbac.indexOf("/"))>-1)
- {
- String num,range=sdbac.substring(st+1);
- sdbac = sdbac.substring(0,st);
- if ((p=range.indexOf("-"))>-1)
- {
- p++;
- if (p<range.length())
- {
- num = range.substring(p).trim();
- try {
- en = Integer.parseInt(num);
- } catch (NumberFormatException x)
- {
- // could warn here that index is invalid
- en = -1;
- }
- }
- } else {
- p=range.length();
- }
- num=range.substring(0,p).trim();
- try {
- st = Integer.parseInt(num);
- } catch (NumberFormatException x)
- {
- // could warn here that index is invalid
- st = -1;
- }
- }
- if (dbsource.equals("PFAM")) {
- seqdb = "UNIPROT";
- if (sdbac.indexOf(".")>-1)
- {
- // strip of last subdomain
- sdbac = sdbac.substring(0,sdbac.indexOf("."));
- dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);
- if (dbrf!=null)
- {
- dbrs.add(dbrf);
- }
- }
- dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);
- if (dbr!=null)
- {
- dbrs.add(dbrf);
- }
- } else {
- seqdb = "EMBL"; // total guess - could be ENA, or something else these days
- if (sdbac.indexOf(".")>-1)
- {
- // strip off last subdomain
- sdbac = sdbac.substring(0,sdbac.indexOf("."));
- dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);
- if (dbrf!=null)
- {
- dbrs.add(dbrf);
- }
- }
-
- dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);
- if (dbrf!=null)
- {
- dbrs.add(dbrf);
- }
- }
- if (st!=-1 && en!=-1)
- {
- 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.datamodel.Mapping mping = new Mapping(mp);
- d.setMap(mping);
- }
- }
- }
-
- protected static AlignmentAnnotation parseAnnotationRow(
- Vector 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;
-
- String type = label;
- if (label.contains("_cons"))
- {
- type = (label.indexOf("_cons") == label.length() - 5) ? label
- .substring(0, label.length() - 5) : label;
- }
- boolean ss = false;
- type = id2type(type);
- if (type.equals("secondary structure"))
- {
- ss = true;
- }
- // decide on secondary structure or not.
- Annotation[] els = new Annotation[annots.length()];
- for (int i = 0; i < annots.length(); i++)
- {
- String pos = annots.substring(i, i + 1);
- Annotation ann;
- ann = new Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
- // be written out
- if (ss)
- {
- if (detectbrackets.search(pos))
- {
- ann.secondaryStructure = jalview.schemes.ResidueProperties
- .getRNASecStrucState(pos).charAt(0);
- }
- else
- {
- ann.secondaryStructure = jalview.schemes.ResidueProperties
- .getDssp3state(pos).charAt(0);
- }
-
- if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0) == 'C')
- {
- ann.displayCharacter = ""; // null; // " ";
- }
- else
- {
- ann.displayCharacter = " " + ann.displayCharacter;
- }
- }
-
- els[i] = ann;
- }
- AlignmentAnnotation annot = null;
- Enumeration e = annotation.elements();
- while (e.hasMoreElements())
- {
- annot = (AlignmentAnnotation) e.nextElement();
- if (annot.label.equals(type))
- break;
- annot = null;
- }
- if (annot == null)
- {
- annot = new AlignmentAnnotation(type, type, els);
- annotation.addElement(annot);
- }
- else
- {
- Annotation[] anns = new Annotation[annot.annotations.length
- + els.length];
- System.arraycopy(annot.annotations, 0, anns, 0,
- annot.annotations.length);
- System.arraycopy(els, 0, anns, annot.annotations.length, els.length);
- annot.annotations = anns;
- // System.out.println("else: ");
- }
- return annot;
- }
-
+ 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 " +\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, 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
+ 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
+ if (treeString.length() > 0)\r
+ {\r
+ if (treeName == null)\r
+ {\r
+ treeName = "Tree " + (1 + getTreeCount());\r
+ }\r
+ addNewickTree(treeName, treeString.toString());\r
+ }\r
+ }\r
+\r
+/**\r
+ * Demangle an accession string and guess the originating sequence database for a given sequence\r
+ * @param seqO sequence to be annotated\r
+ * @param dbr Accession string for sequence\r
+ * @param dbsource source database for alignment (PFAM or RFAM)\r
+ */\r
+ private void guessDatabaseFor(Sequence seqO, String dbr, String dbsource)\r
+ {\r
+ DBRefEntry dbrf=null;\r
+ List<DBRefEntry> dbrs=new ArrayList<DBRefEntry>();\r
+ String seqdb="Unknown",sdbac=""+dbr;\r
+ int st=-1,en=-1,p;\r
+ if ((st=sdbac.indexOf("/"))>-1)\r
+ {\r
+ String num,range=sdbac.substring(st+1);\r
+ sdbac = sdbac.substring(0,st);\r
+ if ((p=range.indexOf("-"))>-1)\r
+ {\r
+ p++;\r
+ if (p<range.length())\r
+ {\r
+ num = range.substring(p).trim();\r
+ try {\r
+ en = Integer.parseInt(num);\r
+ } catch (NumberFormatException x)\r
+ {\r
+ // could warn here that index is invalid\r
+ en = -1;\r
+ }\r
+ }\r
+ } else {\r
+ p=range.length();\r
+ }\r
+ num=range.substring(0,p).trim();\r
+ try {\r
+ st = Integer.parseInt(num);\r
+ } catch (NumberFormatException x)\r
+ {\r
+ // could warn here that index is invalid\r
+ st = -1;\r
+ }\r
+ }\r
+ if (dbsource.equals("PFAM")) {\r
+ seqdb = "UNIPROT";\r
+ if (sdbac.indexOf(".")>-1)\r
+ {\r
+ // strip of last subdomain\r
+ sdbac = sdbac.substring(0,sdbac.indexOf("."));\r
+ dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);\r
+ if (dbrf!=null)\r
+ {\r
+ dbrs.add(dbrf);\r
+ }\r
+ }\r
+ dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);\r
+ if (dbr!=null)\r
+ {\r
+ dbrs.add(dbrf);\r
+ }\r
+ } else {\r
+ seqdb = "EMBL"; // total guess - could be ENA, or something else these days\r
+ if (sdbac.indexOf(".")>-1)\r
+ {\r
+ // strip off last subdomain\r
+ sdbac = sdbac.substring(0,sdbac.indexOf("."));\r
+ dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, seqdb, dbsource, sdbac);\r
+ if (dbrf!=null)\r
+ {\r
+ dbrs.add(dbrf);\r
+ }\r
+ }\r
+ \r
+ dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource, dbr);\r
+ if (dbrf!=null)\r
+ {\r
+ dbrs.add(dbrf);\r
+ }\r
+ }\r
+ if (st!=-1 && en!=-1)\r
+ {\r
+ for (DBRefEntry d:dbrs)\r
+ {\r
+ jalview.util.MapList mp = new jalview.util.MapList(new int[] { seqO.getStart(),seqO.getEnd()},new int[] { st,en},1,1);\r
+ jalview.datamodel.Mapping mping = new Mapping(mp);\r
+ d.setMap(mping);\r
+ }\r
+ }\r
+ }\r
+\r
+\r
+ /**\r
+ * Parse a file in Stockholm format into Jalview's data model using VARNA\r
+ * \r
+ * @throws IOException\r
+ * If there is an error with the input file\r
+ */\r
+ public void parse_with_VARNA() throws IOException\r
+ {\r
+ FileReader fr = null;\r
+ fr = new FileReader(inFile);\r
+\r
+ BufferedReader r = new BufferedReader(fr);\r
+ result = null;\r
+ try\r
+ {\r
+ result = RNAFactory.loadSecStrStockholm(r);\r
+ } catch (ExceptionUnmatchedClosingParentheses umcp)\r
+ {\r
+ errormessage = "Unmatched parentheses in annotation. Aborting ("\r
+ + umcp.getMessage() + ")";\r
+ throw new IOException(umcp);\r
+ }\r
+ // DEBUG System.out.println("this is the secondary scructure:"\r
+ // +result.size());\r
+ SequenceI[] seqs = new SequenceI[result.size()];\r
+ String id=null;\r
+ for (int i = 0; i < result.size(); i++)\r
+ {\r
+ // DEBUG System.err.println("Processing i'th sequence in Stockholm file")\r
+ RNA current = result.get(i);\r
+\r
+ String seq = current.getSeq();\r
+ String rna = current.getStructDBN(true);\r
+ // DEBUG System.out.println(seq);\r
+ // DEBUG System.err.println(rna);\r
+ int begin = 0;\r
+ int end = seq.length() - 1;\r
+ id = safeName(getDataName());\r
+ seqs[i] = new Sequence(id, seq, begin, end);\r
+ String[] annot = new String[rna.length()];\r
+ Annotation[] ann = new Annotation[rna.length()];\r
+ for (int j = 0; j < rna.length(); j++)\r
+ {\r
+ annot[j] = rna.substring(j, j + 1);\r
+\r
+ }\r
+\r
+ for (int k = 0; k < rna.length(); k++)\r
+ {\r
+ ann[k] = new Annotation(annot[k], "",\r
+ jalview.schemes.ResidueProperties.getRNASecStrucState(\r
+ annot[k]).charAt(0), 0f);\r
+\r
+ }\r
+ AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.",\r
+ current.getID(), ann);\r
+\r
+ seqs[i].addAlignmentAnnotation(align);\r
+ seqs[i].setRNA(result.get(i));\r
+ this.annotations.addElement(align);\r
+ }\r
+ this.setSeqs(seqs);\r
+\r
+ }\r
+\r
+ protected static AlignmentAnnotation parseAnnotationRow(\r
+ Vector annotation, 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;\r
+ if (label.contains("_cons"))\r
+ {\r
+ type = (label.indexOf("_cons") == label.length() - 5) ? label\r
+ .substring(0, label.length() - 5) : label;\r
+ }\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
+ 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 = ""; // null; // " ";\r
+ }\r
+ else\r
+ {\r
+ ann.displayCharacter = " " + ann.displayCharacter;\r
+ }\r
+ }\r
+\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
+ 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
+ // System.out.println("else: ");\r
+ }\r
+ return annot;\r
+ }\r
+\r
public String print(SequenceI[] s)
{
// find max length of id
seq += ch;
}
else if (ch.length() > 1)
- {
+ {\r
seq += ch.charAt(1);
}
}
}
}
return out.toString();
- }
-
- public String print()
- {
+ }\r
+\r
+ public String print()\r
+ {\r
out = new StringBuffer();
out.append("# STOCKHOLM 1.0");
out.append(newline);
out.append("//");
out.append(newline);
return out.toString();
- }
-
- private static Hashtable typeIds = null;
- static
- {
- if (typeIds == null)
- {
- typeIds = new Hashtable();
- typeIds.put("SS", "secondary structure");
- typeIds.put("SA", "surface accessibility");
- typeIds.put("TM", "transmembrane");
- typeIds.put("PP", "posterior probability");
- typeIds.put("LI", "ligand binding");
- typeIds.put("AS", "active site");
- typeIds.put("IN", "intron");
- typeIds.put("IR", "interacting residue");
- typeIds.put("AC", "accession");
- typeIds.put("OS", "organism");
- typeIds.put("CL", "class");
- typeIds.put("DE", "description");
- typeIds.put("DR", "reference");
- typeIds.put("LO", "look");
- typeIds.put("RF", "reference positions");
-
- }
- }
-
- protected static String id2type(String id)
- {
- if (typeIds.containsKey(id))
- {
- return (String) typeIds.get(id);
- }
- System.err.println("Warning : Unknown Stockholm annotation type code "
- + id);
- return id;
- }
+ }\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
+ protected static String id2type(String id)\r
+ {\r
+ if (typeIds.containsKey(id))\r
+ {\r
+ return (String) typeIds.get(id);\r
+ }\r
+ System.err.println("Warning : Unknown Stockholm annotation type code "\r
+ + id);\r
+ return id;\r
+ }\r
protected static String type2id(String type)
{
+ type);
return key;
}
- /**
- * //ssline is complete secondary structure line private AlignmentAnnotation
- * addHelices(Vector annotation, String label, String ssline) {
- *
- * // decide on secondary structure or not. Annotation[] els = new
- * Annotation[ssline.length()]; for (int i = 0; i < ssline.length(); i++) {
- * String pos = ssline.substring(i, i + 1); Annotation ann; ann = new
- * Annotation(pos, "", ' ', 0f); // 0f is 'valid' null - will not
- *
- * ann.secondaryStructure =
- * jalview.schemes.ResidueProperties.getRNAssState(pos).charAt(0);
- *
- * ann.displayCharacter = "x" + ann.displayCharacter;
- *
- * System.out.println(ann.displayCharacter);
- *
- * els[i] = ann; } AlignmentAnnotation helicesAnnot = null; Enumeration e =
- * annotation.elements(); while (e.hasMoreElements()) { helicesAnnot =
- * (AlignmentAnnotation) e.nextElement(); if (helicesAnnot.label.equals(type))
- * break; helicesAnnot = null; } if (helicesAnnot == null) { helicesAnnot =
- * new AlignmentAnnotation(type, type, els);
- * annotation.addElement(helicesAnnot); } else { Annotation[] anns = new
- * Annotation[helicesAnnot.annotations.length + els.length];
- * System.arraycopy(helicesAnnot.annotations, 0, anns, 0,
- * helicesAnnot.annotations.length); System.arraycopy(els, 0, anns,
- * helicesAnnot.annotations.length, els.length); helicesAnnot.annotations =
- * anns; }
- *
- * helicesAnnot.features = Rna.GetBasePairs(ssline);
- * Rna.HelixMap(helicesAnnot.features);
- *
- *
- * return helicesAnnot; }
- */
-}
+ /**\r
+ * make a friendly ID string.\r
+ * \r
+ * @param dataName\r
+ * @return truncated dataName to after last '/'\r
+ */\r
+ private String safeName(String dataName)\r
+ {\r
+ int b = 0;\r
+ while ((b = dataName.indexOf("/")) > -1 && b < dataName.length())\r
+ {\r
+ dataName = dataName.substring(b + 1).trim();\r
+\r
+ }\r
+ int e = (dataName.length() - dataName.indexOf(".")) + 1;\r
+ dataName = dataName.substring(1, e).trim();\r
+ return dataName;\r
+ }\r
+}\r
git://source.jalview.org / jalview.git / blobdiff