From: jprocter Date: Tue, 4 Dec 2012 16:15:04 +0000 (+0000) Subject: JAL-1140 - handled VARNA specific RNA exceptions within the IO class - which should... X-Git-Tag: Jalview_2_9~256 X-Git-Url: http://source.jalview.org/gitweb/?a=commitdiff_plain;h=2a7ae58b8b7d619b73e8a25654fa3a12414cfd9a;p=jalview.git JAL-1140 - handled VARNA specific RNA exceptions within the IO class - which should only raise IOExceptions JAL-1199 JAL-1207 - THIS COMMIT IS A REGRESSION! Overwrites existing stockholm parsing code in favour of VARNA code which supports reliable pseudoknot parsing (JAL-1081) --- diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index 07a5c80..b0d3c8b 100644 --- a/src/jalview/io/StockholmFile.java +++ b/src/jalview/io/StockholmFile.java @@ -20,23 +20,24 @@ */ package jalview.io; -import java.io.*; -import java.util.*; +import jalview.datamodel.AlignmentAnnotation; +import jalview.datamodel.Annotation; +import jalview.datamodel.Sequence; +import jalview.datamodel.SequenceI; -import javax.xml.parsers.ParserConfigurationException; +import java.io.BufferedReader; +import java.io.FileReader; +import java.io.IOException; +import java.util.ArrayList; +import java.util.Enumeration; +import java.util.Hashtable; +import java.util.Vector; -import org.xml.sax.SAXException; +import com.stevesoft.pat.Regex; -import com.stevesoft.pat.*; - -import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax; -import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed; -import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied; import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses; import fr.orsay.lri.varna.factories.RNAFactory; import fr.orsay.lri.varna.models.rna.RNA; -import jalview.datamodel.*; -import jalview.analysis.Rna; // import org.apache.log4j.*; @@ -56,18 +57,19 @@ public class StockholmFile extends AlignFile { // static Logger logger = Logger.getLogger("jalview.io.StockholmFile"); protected ArrayList result; + public String id; - + public StockholmFile() { } - public StockholmFile(String inFile, String type) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses + public StockholmFile(String inFile, String type) throws IOException { super(inFile, type); } - public StockholmFile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed, InterruptedException, ExceptionUnmatchedClosingParentheses + public StockholmFile(FileParse source) throws IOException { super(source); } @@ -83,489 +85,67 @@ public class StockholmFile extends AlignFile * * @throws IOException * If there is an error with the input file - * @throws ExceptionUnmatchedClosingParentheses */ - public void parse() throws IOException, ExceptionUnmatchedClosingParentheses + public void parse() throws IOException { - FileReader fr = null; - fr = new FileReader(inFile); - - BufferedReader r = new BufferedReader (fr); - result = RNAFactory.loadSecStrStockholm(r); - System.out.println("this is the secondary scructure:" +result.size()); - SequenceI[] seqs = new SequenceI[result.size()]; - System.out.println(type); //the type is "File" - System.out.println(inFile );//inFile is the path - for(int i=0;i|\\])", ")"); -// -// // 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(); -// // 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); -// // seqO.addDBRef(dbref); -// } -// } -// if (accAnnotations != null && accAnnotations.containsKey("SS")) -// { -// Vector v = (Vector) accAnnotations.get("SS"); -// -// for (int i = 0; i < v.size(); i++) -// { -// AlignmentAnnotation an = (AlignmentAnnotation) v.elementAt(i); -// seqO.addAlignmentAnnotation(an); -// //annotations.add(an); -// } -// } -// -// 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); -// 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 -// * #=GF TN 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 number DE -// * DEscription DR ; ; Database Reference OS -// * OrganiSm (species) OC Organism Classification (clade, etc.) -// * LO 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()); -// } -// } -// - protected static AlignmentAnnotation parseAnnotationRow(Vector annotation, - String label, String annots) + + protected static AlignmentAnnotation parseAnnotationRow( + Vector annotation, String label, String annots) { String convert1, convert2 = null; @@ -573,7 +153,7 @@ public class StockholmFile extends AlignFile Regex openparen = new Regex("(<|\\[)", "("); Regex closeparen = new Regex("(>|\\])", ")"); - // Detect if file is RNA by looking for bracket types + // Detect if file is RNA by looking for bracket types Regex detectbrackets = new Regex("(<|>|\\[|\\]|\\(|\\))"); convert1 = openparen.replaceAll(annots); @@ -601,7 +181,7 @@ public class StockholmFile extends AlignFile if (detectbrackets.search(pos)) { ann.secondaryStructure = jalview.schemes.ResidueProperties - .getRNASecStrucState(pos).charAt(0); + .getRNASecStrucState(pos).charAt(0); } else { @@ -614,14 +194,14 @@ public class StockholmFile extends AlignFile ann.displayCharacter = ""; // null; // " "; } else - { + { ann.displayCharacter = " " + ann.displayCharacter; } } els[i] = ann; } - AlignmentAnnotation annot = null; + AlignmentAnnotation annot = null; Enumeration e = annotation.elements(); while (e.hasMoreElements()) { @@ -636,16 +216,16 @@ public class StockholmFile extends AlignFile 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(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; + // System.out.println("else: "); + } + return annot; } public static String print(SequenceI[] s) @@ -694,41 +274,6 @@ public class StockholmFile extends AlignFile return id; } /** - * //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; } - * - */ - /** * make a friendly ID string. * * @param dataName @@ -737,13 +282,13 @@ public class StockholmFile extends AlignFile private String safeName(String dataName) { int b = 0; - while ((b = dataName.indexOf("/")) > -1 && b < dataName.length() ) - { - dataName = dataName.substring(b + 1).trim(); - + while ((b = dataName.indexOf("/")) > -1 && b < dataName.length()) + { + dataName = dataName.substring(b + 1).trim(); + } - int e = (dataName.length() - dataName.indexOf("."))+1; - dataName = dataName.substring(1,e).trim(); + int e = (dataName.length() - dataName.indexOf(".")) + 1; + dataName = dataName.substring(1, e).trim(); return dataName; } } \ No newline at end of file