X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FStockholmFile.java;h=9d21a400c6c1920c2560ac0c761e55dbbd5ac100;hb=ad5029edaf36ceaafb4e269f2e00b0e1e0d7ffc4;hp=4566bacbd97ad2e616a34b2d7bd965130940c2bb;hpb=865a855a4ca87eadb3e5ff284ed32ed307d9c34b;p=jalview.git diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java index 4566bac..9d21a40 100644 --- a/src/jalview/io/StockholmFile.java +++ b/src/jalview/io/StockholmFile.java @@ -1,19 +1,21 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.0b1) + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8.2) * Copyright (C) 2014 The Jalview Authors * * 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. + * 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 . + * You should have received a copy of the GNU General Public License + * along with Jalview. If not, see . * The Jalview Authors are detailed in the 'AUTHORS' file. */ /* @@ -21,13 +23,33 @@ */ package jalview.io; -import java.io.*; -import java.util.*; - -import com.stevesoft.pat.*; -import jalview.datamodel.*; +import jalview.datamodel.AlignmentI; +import jalview.datamodel.AlignmentAnnotation; +import jalview.datamodel.AlignmentI; +import jalview.datamodel.Annotation; +import jalview.datamodel.DBRefEntry; +import jalview.datamodel.Mapping; +import jalview.datamodel.Sequence; +import jalview.datamodel.SequenceFeature; +import jalview.datamodel.SequenceI; import jalview.util.Format; +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.List; +import java.util.StringTokenizer; +import java.util.Vector; + +import com.stevesoft.pat.Regex; + +import fr.orsay.lri.varna.exceptions.ExceptionUnmatchedClosingParentheses; +import fr.orsay.lri.varna.factories.RNAFactory; +import fr.orsay.lri.varna.models.rna.RNA; + // import org.apache.log4j.*; /** @@ -39,12 +61,18 @@ import jalview.util.Format; * into Jalview's local representation. * * @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 Anne Menard (Paris, FR) (VARNA parsing of Stockholm file data) * @version 0.3 + jalview mods * */ public class StockholmFile extends AlignFile { // static Logger logger = Logger.getLogger("jalview.io.StockholmFile"); + protected ArrayList result; + StringBuffer out; // output buffer AlignmentI al; @@ -77,6 +105,71 @@ public class StockholmFile extends AlignFile } /** + * Parse a file in Stockholm format into Jalview's data model using VARNA + * + * @throws IOException + * If there is an error with the input file + */ + public void parse_with_VARNA(java.io.File inFile) throws IOException + { + FileReader fr = null; + fr = new FileReader(inFile); + + BufferedReader r = new BufferedReader(fr); + result = null; + try + { + result = RNAFactory.loadSecStrStockholm(r); + } catch (ExceptionUnmatchedClosingParentheses umcp) + { + errormessage = "Unmatched parentheses in annotation. Aborting (" + + umcp.getMessage() + ")"; + throw new IOException(umcp); + } + // DEBUG System.out.println("this is the secondary scructure:" + // +result.size()); + SequenceI[] seqs = new SequenceI[result.size()]; + String id = null; + for (int i = 0; i < result.size(); i++) + { + // DEBUG System.err.println("Processing i'th sequence in Stockholm file") + RNA current = result.get(i); + + String seq = current.getSeq(); + String rna = current.getStructDBN(true); + // DEBUG System.out.println(seq); + // DEBUG System.err.println(rna); + int begin = 0; + int end = seq.length() - 1; + id = safeName(getDataName()); + seqs[i] = new Sequence(id, seq, begin, end); + String[] annot = new String[rna.length()]; + Annotation[] ann = new Annotation[rna.length()]; + for (int j = 0; j < rna.length(); j++) + { + annot[j] = rna.substring(j, j + 1); + + } + + for (int k = 0; k < rna.length(); k++) + { + ann[k] = new Annotation(annot[k], "", + jalview.schemes.ResidueProperties.getRNASecStrucState( + annot[k]).charAt(0), 0f); + + } + AlignmentAnnotation align = new AlignmentAnnotation("Sec. str.", + current.getID(), ann); + + seqs[i].addAlignmentAnnotation(align); + seqs[i].setRNA(result.get(i)); + this.annotations.addElement(align); + } + this.setSeqs(seqs); + + } + + /** * Parse a file in Stockholm format into Jalview's data model. The file has to * be passed at construction time * @@ -94,13 +187,13 @@ public class StockholmFile extends AlignFile 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())) { @@ -110,6 +203,7 @@ public class StockholmFile extends AlignFile else { version = r.stringMatched(1); + // logger.debug("Stockholm version: " + version); } @@ -147,7 +241,7 @@ public class StockholmFile extends AlignFile // 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) @@ -205,7 +299,6 @@ public class StockholmFile extends AlignFile String desc = (String) accAnnotations.get("DE"); seqO.setDescription((desc == null) ? "" : desc); } - // Add DB References (if any) if (accAnnotations != null && accAnnotations.containsKey("DR")) { @@ -225,12 +318,15 @@ public class StockholmFile extends AlignFile 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; @@ -528,6 +624,8 @@ public class StockholmFile extends AlignFile } ns += seq; content.put(description, ns); + + // if(type.equals("SS")){ Hashtable strucAnn; if (seqAnn.containsKey(acc)) { @@ -540,9 +638,11 @@ public class StockholmFile extends AlignFile Vector newStruc = new Vector(); parseAnnotationRow(newStruc, type, ns); + strucAnn.put(type, newStruc); seqAnn.put(acc, strucAnn); } + // } else { System.err @@ -569,40 +669,49 @@ public class StockholmFile extends AlignFile } /** - * 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) + * 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 dbrs=new ArrayList(); - String seqdb="Unknown",sdbac=""+dbr; - int st=-1,en=-1,p; - if ((st=sdbac.indexOf("/"))>-1) + DBRefEntry dbrf = null; + List dbrs = new ArrayList(); + 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-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); } @@ -1009,38 +1128,23 @@ public class StockholmFile extends AlignFile + type); return key; } + /** - * //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); + * make a friendly ID string. * - * 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; } + * @param dataName + * @return truncated dataName to after last '/' */ + private String safeName(String dataName) + { + int b = 0; + 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(); + return dataName; + } }