*
* @author bsb at sanger.ac.uk
* @author Natasha Shersnev (Dundee, UK) (Stockholm file writer)
- * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as stockholm)
+ * @author Lauren Lui (UCSC, USA) (RNA secondary structure annotation import as
+ * stockholm)
* @author Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data)
* @version 0.3 + jalview mods
*
{
// static Logger logger = Logger.getLogger("jalview.io.StockholmFile");
protected ArrayList<RNA> result;
+
StringBuffer out; // output buffer
AlignmentI al;
{
super.initData();
}
+
/**
* Parse a file in Stockholm format into Jalview's data model using VARNA
*
// DEBUG System.out.println("this is the secondary scructure:"
// +result.size());
SequenceI[] seqs = new SequenceI[result.size()];
- String id=null;
+ String id = null;
for (int i = 0; i < result.size(); i++)
{
// DEBUG System.err.println("Processing i'th sequence in Stockholm file")
}
-
/**
* Parse a file in Stockholm format into Jalview's data model. The file has to
* be passed at construction time
*/
public void parse() throws IOException
{
- StringBuffer treeString = new StringBuffer();
- String treeName = null;
- // --------------- Variable Definitions -------------------
- String line;
- String version;
+ StringBuffer treeString = new StringBuffer();
+ String treeName = null;
+ // --------------- Variable Definitions -------------------
+ String line;
+ String version;
// 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
+ 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
this.noSeqs = seqs.size();
-
- String seqdb,dbsource = null;
+
+ 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
if (getAlignmentProperty("AC") != null)
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);
+ 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;
+ /*
* 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);
- }
- }
+ */
+ 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);
+ }
+ }
if (accAnnotations != null && accAnnotations.containsKey("AC"))
{
{
String dbr = (String) accAnnotations.get("AC");
if (dbr != null)
- {
- // we could get very clever here - but for now - just try to guess accession type from source of alignment plus structure of accession
+ {
+ // 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);
-
- }
- }
- // else - do what ? add the data anyway and prompt the user to specify what references these are ?
+
+ }
+ }
+ // 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);
+
+ 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);
// 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();
+ 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);
+ }
// 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);
-
-// if(type.equals("SS")){
- 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());
- }
- }
+ 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);
+ }
-/**
- * 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)
+ 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);
+
+ // if(type.equals("SS")){
+ 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)
+ 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)
+ 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)
+ if (p < range.length())
{
- // could warn here that index is invalid
- en = -1;
- }
+ 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 {
+ else
+ {
+ p = range.length();
+ }
+ num = range.substring(0, p).trim();
+ try
+ {
st = Integer.parseInt(num);
} catch (NumberFormatException x)
{
st = -1;
}
}
- if (dbsource.equals("PFAM")) {
+ if (dbsource.equals("PFAM"))
+ {
seqdb = "UNIPROT";
- if (sdbac.indexOf(".")>-1)
+ 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)
+ 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)
+ 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)
+ }
+ 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)
+ 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)
+
+ dbrf = jalview.util.DBRefUtils.parseToDbRef(seqO, dbsource, dbsource,
+ dbr);
+ if (dbrf != null)
{
dbrs.add(dbrf);
}
}
- if (st!=-1 && en!=-1)
+ if (st != -1 && en != -1)
{
- for (DBRefEntry d:dbrs)
+ 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);
}
seq += ch;
}
else if (ch.length() > 1)
- {
+ {
seq += ch.charAt(1);
}
}
+ type);
return key;
}
+
/**
* make a friendly ID string.
*
git://source.jalview.org / jalview.git / blobdiff