From 0812da43d6b8d673aa25d2d7a7c5f65aab1b1642 Mon Sep 17 00:00:00 2001 From: jprocter Date: Mon, 4 Jun 2007 09:54:31 +0000 Subject: [PATCH] fix for 'RF' annotation tags and ensured parser is robust to new/unknown two letter annotation tag codes. --- src/jalview/io/StockholmFile.java | 396 ++++++++++++++++++------------------- 1 file changed, 192 insertions(+), 204 deletions(-) diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index 9104a5f..dedbd44 100644 --- a/src/jalview/io/StockholmFile.java +++ b/src/jalview/io/StockholmFile.java @@ -27,24 +27,23 @@ import java.util.*; import com.stevesoft.pat.*; import jalview.datamodel.*; -//import org.apache.log4j.*; +// import org.apache.log4j.*; /** * This class is supposed to parse a Stockholm format file into Jalview + * * @author bsb at sanger.ac.uk * @version 0.3 */ -public class StockholmFile - extends AlignFile +public class StockholmFile extends AlignFile { - //static Logger logger = Logger.getLogger("jalview.io.StockholmFile"); + // static Logger logger = Logger.getLogger("jalview.io.StockholmFile"); public StockholmFile() { } - public StockholmFile(String inFile, String type) - throws IOException + public StockholmFile(String inFile, String type) throws IOException { super(inFile, type); } @@ -55,42 +54,46 @@ public class StockholmFile } /** - * 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 + * 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 + public void parse() throws IOException { - StringBuffer treeString=new StringBuffer(); + StringBuffer treeString = new StringBuffer(); String treeName = null; // --------------- Variable Definitions ------------------- String line; String version; - // String id; - Hashtable seqAnn = new Hashtable(); // Sequence related annotations + // String id; + Hashtable seqAnn = new Hashtable(); // Sequence related annotations Hashtable seqs = new Hashtable(); Regex p, r, rend, s, x; // ------------------ Parsing File ---------------------- - // First, we have to check that this file has STOCKHOLM format, i.e. the first line must match + // 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'"); + 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); + // logger.debug("Stockholm version: " + version); } -// We define some Regexes here that will be used regularily later + // We define some Regexes here that will be used regularily later rend = new Regex("\\/\\/"); // Find the end of an alignment - p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in id/from/to + p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in + // id/from/to s = new Regex("(\\S+)\\s+(\\w{2})\\s+(.*)"); // Parses annotation subtype r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line - x = new Regex("(\\S+)\\s+(\\S+)"); //split id from sequence + x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence rend.optimize(); p.optimize(); @@ -98,7 +101,7 @@ public class StockholmFile r.optimize(); x.optimize(); - while ( (line = nextLine()) != null) + while ((line = nextLine()) != null) { if (line.length() == 0) { @@ -106,15 +109,15 @@ public class StockholmFile } if (rend.search(line)) { -// End of the alignment, pass stuff back + // End of the alignment, pass stuff back this.noSeqs = seqs.size(); - //logger.debug("Number of sequences: " + this.noSeqs); + // logger.debug("Number of sequences: " + this.noSeqs); Enumeration accs = seqs.keys(); while (accs.hasMoreElements()) { String acc = (String) accs.nextElement(); - //logger.debug("Processing sequence " + acc); + // logger.debug("Processing sequence " + acc); String seq = (String) seqs.get(acc); if (maxLength < seq.length()) { @@ -125,12 +128,12 @@ public class StockholmFile String sid = acc; // Retrieve hash of annotations for this accession Hashtable accAnnotations = null; - - if (seqAnn!=null && seqAnn.containsKey(acc)) + + if (seqAnn != null && seqAnn.containsKey(acc)) { accAnnotations = (Hashtable) seqAnn.get(acc); } - + // Split accession in id and from/to if (p.search(acc)) { @@ -138,24 +141,25 @@ public class StockholmFile start = Integer.parseInt(p.stringMatched(2)); end = Integer.parseInt(p.stringMatched(3)); } - //logger.debug(sid + ", " + start + ", " + end); + // logger.debug(sid + ", " + start + ", " + end); Sequence seqO = new Sequence(sid, seq, start, end); // Add Description (if any) - if (accAnnotations!=null && accAnnotations.containsKey("DE")) + if (accAnnotations != null && accAnnotations.containsKey("DE")) { String desc = (String) accAnnotations.get("DE"); - seqO.setDescription((desc==null)?"" : desc); + seqO.setDescription((desc == null) ? "" : desc); } // Add DB References (if any) - if (accAnnotations!=null && accAnnotations.containsKey("DR")) + if (accAnnotations != null && accAnnotations.containsKey("DR")) { String dbr = (String) accAnnotations.get("DR"); - if (dbr!=null && dbr.indexOf(";")>-1) + if (dbr != null && dbr.indexOf(";") > -1) { String src = dbr.substring(0, dbr.indexOf(";")); - String acn = dbr.substring(dbr.indexOf(";")+1); - DBRefEntry dbref = new DBRefEntry(jalview.util.DBRefUtils.getCanonicalName(src), acn, ""); + String acn = dbr.substring(dbr.indexOf(";") + 1); + DBRefEntry dbref = new DBRefEntry(jalview.util.DBRefUtils + .getCanonicalName(src), acn, ""); seqO.addDBRef(dbref); } } @@ -163,13 +167,12 @@ public class StockholmFile // We need to adjust the positions of all features to account for gaps try { - features = (Hashtable) accAnnotations.get( - "features"); - } - catch (java.lang.NullPointerException e) + features = (Hashtable) accAnnotations.get("features"); + } catch (java.lang.NullPointerException e) { - //loggerwarn("Getting Features for " + acc + ": " + e.getMessage()); - //continue; + // loggerwarn("Getting Features for " + acc + ": " + + // e.getMessage()); + // continue; } // if we have features if (features != null) @@ -177,7 +180,8 @@ public class StockholmFile Enumeration i = features.keys(); while (i.hasMoreElements()) { - // TODO: parse out secondary structure annotation as annotation row + // 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(); @@ -192,13 +196,11 @@ public class StockholmFile for (int k = 0; k < byChar.length; k++) { char c = byChar[k]; - if (! (c == ' ' || c == '_' || - c == '-')) + if (!(c == ' ' || c == '_' || c == '-')) { int new_pos = seqO.findPosition(k); - SequenceFeature feat = - new SequenceFeature(type, - desc, new_pos, new_pos, 0f, null); + SequenceFeature feat = new SequenceFeature(type, desc, + new_pos, new_pos, 0f, null); seqO.addSequenceFeature(feat); } @@ -208,18 +210,19 @@ public class StockholmFile } } - //logger.debug("Adding seq " + acc + " from " + start + " to " + end + ": " + seq); + // logger.debug("Adding seq " + acc + " from " + start + " to " + end + // + ": " + seq); this.seqs.addElement(seqO); } } else if (!r.search(line)) { - //System.err.println("Found sequence line: " + 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); + // 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)); @@ -236,68 +239,62 @@ public class StockholmFile String annType = r.stringMatched(1); String annContent = r.stringMatched(2); - //System.err.println("type:" + annType + " content: " + annContent); + // 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. + /* + * 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... + // 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) + } + else if (an.stringMatched(1).equals("TN")) + { + if (treeString.length() > 0) { - if (treeName==null) + if (treeName == null) { - treeName = "Tree "+(getTreeCount()+1); + treeName = "Tree " + (getTreeCount() + 1); } addNewickTree(treeName, treeString.toString()); } @@ -310,15 +307,12 @@ public class StockholmFile 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.) + /* + * 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)) { @@ -351,25 +345,21 @@ public class StockholmFile if (x.search(annContent)) { // parse out and create alignment annotation directly. - AlignmentAnnotation annotation = parseAnnotationRow(x.stringMatched(1), x.stringMatched(2)); - annotations.addElement(annotation); + 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 + // 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] + * 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)) { @@ -390,12 +380,12 @@ public class StockholmFile // Get an object with all the annotations for this sequence if (seqAnn.containsKey(acc)) { - //logger.debug("Found annotations for " + acc); + // logger.debug("Found annotations for " + acc); ann = (Hashtable) seqAnn.get(acc); } else { - //logger.debug("Creating new annotations holder for " + acc); + // logger.debug("Creating new annotations holder for " + acc); ann = new Hashtable(); seqAnn.put(acc, ann); } @@ -404,12 +394,12 @@ public class StockholmFile // Get an object with all the content for an annotation if (ann.containsKey("features")) { - //logger.debug("Found features for " + acc); + // logger.debug("Found features for " + acc); features = (Hashtable) ann.get("features"); } else { - //logger.debug("Creating new features holder for " + acc); + // logger.debug("Creating new features holder for " + acc); features = new Hashtable(); ann.put("features", features); } @@ -417,12 +407,13 @@ public class StockholmFile Hashtable content; if (features.containsKey(this.id2type(type))) { - //logger.debug("Found content for " + 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)); + // logger.debug("Creating new content holder for " + + // this.id2type(type)); content = new Hashtable(); features.put(this.id2type(type), content); } @@ -441,54 +432,81 @@ public class StockholmFile } else { - throw new IOException("Unknown annotation detected: " + annType + " " + - annContent); + throw new IOException("Unknown annotation detected: " + annType + + " " + annContent); } } } - if (treeString.length()>0) + if (treeString.length() > 0) { - if (treeName==null) + if (treeName == null) { - treeName = "Tree "+(1+getTreeCount()); + treeName = "Tree " + (1 + getTreeCount()); } addNewickTree(treeName, treeString.toString()); } } - private AlignmentAnnotation parseAnnotationRow(String label, String annots) + private AlignmentAnnotation parseAnnotationRow(Vector annotation, + String label, String annots) { - String type = (label.indexOf("_cons")==label.length()-5) ? label.substring(0, label.length()-5) - : label; + String 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; + ss = true; } // decide on secondary structure or not. Annotation[] els = new Annotation[annots.length()]; - for (int i = 0; i