import com.stevesoft.pat.*;\r
import jalview.datamodel.*;\r
\r
-//import org.apache.log4j.*;\r
+// import org.apache.log4j.*;\r
\r
/**\r
* This class is supposed to parse a Stockholm format file into Jalview\r
+ * \r
* @author bsb at sanger.ac.uk\r
* @version 0.3\r
*/\r
-public class StockholmFile\r
- extends AlignFile\r
+public class StockholmFile extends AlignFile\r
{\r
- //static Logger logger = Logger.getLogger("jalview.io.StockholmFile");\r
+ // static Logger logger = Logger.getLogger("jalview.io.StockholmFile");\r
\r
public StockholmFile()\r
{\r
}\r
\r
- public StockholmFile(String inFile, String type)\r
- throws IOException\r
+ public StockholmFile(String inFile, String type) throws IOException\r
{\r
super(inFile, type);\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
+ * 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()\r
- throws IOException\r
+ public void parse() throws IOException\r
{\r
- StringBuffer treeString=new StringBuffer();\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
+ // 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 first line must match\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("This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");\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
- //logger.debug("Stockholm version: " + version);\r
+ // logger.debug("Stockholm version: " + version);\r
}\r
\r
-// We define some Regexes here that will be used regularily later\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
+ p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in\r
+ // id/from/to\r
s = new Regex("(\\S+)\\s+(\\w{2})\\s+(.*)"); // Parses annotation subtype\r
r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line\r
- x = new Regex("(\\S+)\\s+(\\S+)"); //split id from sequence\r
+ x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence\r
\r
rend.optimize();\r
p.optimize();\r
r.optimize();\r
x.optimize();\r
\r
- while ( (line = nextLine()) != null)\r
+ while ((line = nextLine()) != null)\r
{\r
if (line.length() == 0)\r
{\r
}\r
if (rend.search(line))\r
{\r
-// End of the alignment, pass stuff back\r
+ // End of the alignment, pass stuff back\r
\r
this.noSeqs = seqs.size();\r
- //logger.debug("Number of sequences: " + this.noSeqs);\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
+ // logger.debug("Processing sequence " + acc);\r
String seq = (String) seqs.get(acc);\r
if (maxLength < seq.length())\r
{\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
+ if (seqAnn != null && seqAnn.containsKey(acc))\r
{\r
accAnnotations = (Hashtable) seqAnn.get(acc);\r
}\r
- \r
+\r
// Split accession in id and from/to\r
if (p.search(acc))\r
{\r
start = Integer.parseInt(p.stringMatched(2));\r
end = Integer.parseInt(p.stringMatched(3));\r
}\r
- //logger.debug(sid + ", " + start + ", " + end);\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
+ if (accAnnotations != null && accAnnotations.containsKey("DE"))\r
{\r
String desc = (String) accAnnotations.get("DE");\r
- seqO.setDescription((desc==null)?"" : desc);\r
+ seqO.setDescription((desc == null) ? "" : desc);\r
}\r
// Add DB References (if any)\r
- if (accAnnotations!=null && accAnnotations.containsKey("DR"))\r
+ if (accAnnotations != null && accAnnotations.containsKey("DR"))\r
{\r
String dbr = (String) accAnnotations.get("DR");\r
- if (dbr!=null && dbr.indexOf(";")>-1)\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
- DBRefEntry dbref = new DBRefEntry(jalview.util.DBRefUtils.getCanonicalName(src), acn, "");\r
+ String acn = dbr.substring(dbr.indexOf(";") + 1);\r
+ DBRefEntry dbref = new DBRefEntry(jalview.util.DBRefUtils\r
+ .getCanonicalName(src), acn, "");\r
seqO.addDBRef(dbref);\r
}\r
}\r
// We need to adjust the positions of all features to account for gaps\r
try\r
{\r
- features = (Hashtable) accAnnotations.get(\r
- "features");\r
- }\r
- catch (java.lang.NullPointerException e)\r
+ features = (Hashtable) accAnnotations.get("features");\r
+ } catch (java.lang.NullPointerException e)\r
{\r
- //loggerwarn("Getting Features for " + acc + ": " + e.getMessage());\r
- //continue;\r
+ // loggerwarn("Getting Features for " + acc + ": " +\r
+ // e.getMessage());\r
+ // continue;\r
}\r
// if we have features\r
if (features != null)\r
Enumeration i = features.keys();\r
while (i.hasMoreElements())\r
{\r
- // TODO: parse out secondary structure annotation as annotation row\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
for (int k = 0; k < byChar.length; k++)\r
{\r
char c = byChar[k];\r
- if (! (c == ' ' || c == '_' ||\r
- c == '-'))\r
+ if (!(c == ' ' || c == '_' || 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
+ SequenceFeature feat = new SequenceFeature(type, desc,\r
+ new_pos, new_pos, 0f, null);\r
\r
seqO.addSequenceFeature(feat);\r
}\r
}\r
\r
}\r
- //logger.debug("Adding seq " + acc + " from " + start + " to " + end + ": " + seq);\r
+ // logger.debug("Adding seq " + acc + " from " + start + " to " + end\r
+ // + ": " + seq);\r
this.seqs.addElement(seqO);\r
}\r
}\r
else if (!r.search(line))\r
{\r
- //System.err.println("Found sequence line: " + line);\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
+ // 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
String annType = r.stringMatched(1);\r
String annContent = r.stringMatched(2);\r
\r
- //System.err.println("type:" + annType + " content: " + annContent);\r
+ // System.err.println("type:" + annType + " content: " + annContent);\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
+ * 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 with them later...\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
- } else \r
- if (an.stringMatched(1).equals("TN")) {\r
- if (treeString.length()>0)\r
+ }\r
+ else if (an.stringMatched(1).equals("TN"))\r
+ {\r
+ if (treeString.length() > 0)\r
{\r
- if (treeName==null)\r
+ if (treeName == null)\r
{\r
- treeName = "Tree "+(getTreeCount()+1);\r
+ treeName = "Tree " + (getTreeCount() + 1);\r
}\r
addNewickTree(treeName, treeString.toString());\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
+ * 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
if (x.search(annContent))\r
{\r
// parse out and create alignment annotation directly.\r
- AlignmentAnnotation annotation = parseAnnotationRow(x.stringMatched(1), x.stringMatched(2));\r
- annotations.addElement(annotation);\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 column\r
+ // Generic per-Sequence AND per-Column markup, exactly 1 char per\r
+ // 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
+ * 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
// Get an object with all the annotations for this sequence\r
if (seqAnn.containsKey(acc))\r
{\r
- //logger.debug("Found annotations for " + acc);\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
+ // logger.debug("Creating new annotations holder for " + acc);\r
ann = new Hashtable();\r
seqAnn.put(acc, ann);\r
}\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
+ // 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
+ // logger.debug("Creating new features holder for " + acc);\r
features = new Hashtable();\r
ann.put("features", features);\r
}\r
Hashtable content;\r
if (features.containsKey(this.id2type(type)))\r
{\r
- //logger.debug("Found content for " + this.id2type(type));\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
+ // logger.debug("Creating new content holder for " +\r
+ // this.id2type(type));\r
content = new Hashtable();\r
features.put(this.id2type(type), content);\r
}\r
}\r
else\r
{\r
- throw new IOException("Unknown annotation detected: " + annType + " " +\r
- annContent);\r
+ throw new IOException("Unknown annotation detected: " + annType\r
+ + " " + annContent);\r
}\r
}\r
}\r
- if (treeString.length()>0)\r
+ if (treeString.length() > 0)\r
{\r
- if (treeName==null)\r
+ if (treeName == null)\r
{\r
- treeName = "Tree "+(1+getTreeCount());\r
+ treeName = "Tree " + (1 + getTreeCount());\r
}\r
addNewickTree(treeName, treeString.toString());\r
}\r
}\r
\r
- private AlignmentAnnotation parseAnnotationRow(String label, String annots)\r
+ private AlignmentAnnotation parseAnnotationRow(Vector annotation,\r
+ String label, String annots)\r
{\r
- String type = (label.indexOf("_cons")==label.length()-5) ? label.substring(0, label.length()-5)\r
- : label;\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
+ 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
+ for (int i = 0; i < annots.length(); i++)\r
{\r
- String pos = annots.substring(i,i+1);\r
+ String pos = annots.substring(i, i + 1);\r
Annotation ann;\r
ann = new Annotation(pos, "", ' ', Float.NaN);\r
if (ss)\r
{\r
- ann.secondaryStructure = jalview.schemes.ResidueProperties.getDssp3state(pos).charAt(0);\r
- if (ann.secondaryStructure == pos.charAt(0) || pos.charAt(0)=='C')\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 = "";\r
- } else {\r
+ }\r
+ else\r
+ {\r
ann.displayCharacter += " ";\r
}\r
}\r
- \r
+\r
els[i] = ann;\r
}\r
- return new AlignmentAnnotation(label, label, els);\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.add(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
+\r
public static String print(SequenceI[] s)\r
{\r
return "not yet implemented";\r
return print(getSeqsAsArray());\r
}\r
\r
- private String id2type(String id)\r
+ private static Hashtable typeIds = null;\r
+ static\r
{\r
- // GR ids\r
- if (id.equals("SS"))\r
- {\r
- return "secondary structure";\r
- }\r
- else if (id.equals("SA"))\r
- {\r
- return "surface accessibility";\r
- }\r
- else if (id.equals("TM"))\r
- {\r
- return "transmembrane";\r
- }\r
- else if (id.equals("PP"))\r
+ if (typeIds == null)\r
{\r
- return "posterior probability";\r
- }\r
- else if (id.equals("LI"))\r
- {\r
- return "ligand binding";\r
- }\r
- else if (id.equals("AS"))\r
- {\r
- return "active site";\r
- }\r
- else if (id.equals("IN"))\r
- {\r
- return "intron";\r
- }\r
- else if (id.equals("IR"))\r
- {\r
- return "interacting residue";\r
- }\r
- // GS ids\r
- else if (id.equals("AC"))\r
- {\r
- return "accession";\r
- }\r
- else if (id.equals("OS"))\r
- {\r
- return "organism";\r
- }\r
- else if (id.equals("CL"))\r
- {\r
- return "class";\r
- }\r
- else if (id.equals("DE"))\r
- {\r
- return "description";\r
- }\r
- else if (id.equals("DR"))\r
- {\r
- return "reference";\r
- }\r
- else if (id.equals("LO"))\r
- {\r
- return "look";\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
- else\r
+ }\r
+\r
+ private String id2type(String id)\r
+ {\r
+ if (typeIds.containsKey(id))\r
{\r
- 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 / commitdiff