X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;ds=sidebyside;f=src%2Fjalview%2Fio%2FStockholmFile.java;h=34ce3bf99db93a2bdc75743c6ef4c5da66361096;hb=a95b88b05400d7e841f9523d4c4228c678307654;hp=9104a5fceff177a6d620d40520ed37c26fb859a4;hpb=70cb8184fe397a90f60ecc06d419ff2f7fbbb433;p=jalview.git diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index 9104a5f..34ce3bf 100644 --- a/src/jalview/io/StockholmFile.java +++ b/src/jalview/io/StockholmFile.java @@ -1,20 +1,19 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer - * Copyright (C) 2007 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle - * - * This program 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 2 - * of the License, or (at your option) any later version. - * - * This program 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 this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.6) + * Copyright (C) 2010 J Procter, AM Waterhouse, 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 . */ /* * This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk @@ -27,70 +26,84 @@ 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 + * 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 + * @version 0.3 + jalview mods + * */ -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); } + 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 + * 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 - rend = new Regex("\\/\\/"); // Find the end of an alignment - p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in id/from/to - s = new Regex("(\\S+)\\s+(\\w{2})\\s+(.*)"); // Parses annotation subtype + // 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 + x = new Regex("(\\S+)\\s+(\\S+)"); // split id from sequence rend.optimize(); p.optimize(); @@ -98,7 +111,7 @@ public class StockholmFile r.optimize(); x.optimize(); - while ( (line = nextLine()) != null) + while ((line = nextLine()) != null) { if (line.length() == 0) { @@ -106,16 +119,16 @@ 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); - String seq = (String) seqs.get(acc); + // logger.debug("Processing sequence " + acc); + String seq = (String) seqs.remove(acc); if (maxLength < seq.length()) { maxLength = seq.length(); @@ -125,12 +138,12 @@ 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); + accAnnotations = (Hashtable) seqAnn.remove(acc); } - + // Split accession in id and from/to if (p.search(acc)) { @@ -138,51 +151,51 @@ 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, ""); - seqO.addDBRef(dbref); + String acn = dbr.substring(dbr.indexOf(";") + 1); + jalview.util.DBRefUtils.parseToDbRef(seqO, src, "0", acn); + // seqO.addDBRef(dbref); } } Hashtable features = null; // 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.remove("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) { + int posmap[] = seqO.findPositionMap(); 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(); - Hashtable content = (Hashtable) features.get(type); - + Hashtable content = (Hashtable) features.remove(type); Enumeration j = content.keys(); while (j.hasMoreElements()) { @@ -192,13 +205,17 @@ public class StockholmFile for (int k = 0; k < byChar.length; k++) { char c = byChar[k]; - if (! (c == ' ' || c == '_' || - c == '-')) + if (!(c == ' ' || c == '_' || c == '-' || c == '.')) // PFAM + // uses + // '.' + // for + // feature + // background { - int new_pos = seqO.findPosition(k); - SequenceFeature feat = - new SequenceFeature(type, - desc, new_pos, new_pos, 0f, null); + 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); } @@ -208,18 +225,22 @@ public class StockholmFile } } - //logger.debug("Adding seq " + acc + " from " + start + " to " + end + ": " + seq); + // 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); + // 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 +257,62 @@ 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 +325,12 @@ 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)) { @@ -351,38 +363,40 @@ 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)) { String acc = s.stringMatched(1); String type = s.stringMatched(2); - String seq = s.stringMatched(3); - String description = new String(); - + String seq = new String(s.stringMatched(3)); + String description = null; // Check for additional information about the current annotation - if (x.search(seq)) + // 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 { - description = x.stringMatched(1); - seq = x.stringMatched(2); + seq = description; + description = new String(); } // sequence id with from-to fields @@ -390,12 +404,12 @@ 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 +418,12 @@ 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 +431,13 @@ 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); } @@ -436,59 +451,90 @@ public class StockholmFile } else { - throw new IOException("Error parsing " + line); + 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); + 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