X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fio%2FStockholmFile.java;h=9d21a400c6c1920c2560ac0c761e55dbbd5ac100;hb=8d0d8f010041eb2089bfe0bf7e5ad481ceae56d5;hp=669181a3670c5b16c1ff2f783d7e4e86b2e7a89a;hpb=ad20cd92225f2ee8c251d39b00b90555d382a616;p=jalview.git
diff --git a/src/jalview/io/StockholmFile.java b/src/jalview/io/StockholmFile.java
index 669181a..9d21a40 100644
--- a/src/jalview/io/StockholmFile.java
+++ b/src/jalview/io/StockholmFile.java
@@ -1,30 +1,54 @@
/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.8)
- * Copyright (C) 2012 J Procter, AM Waterhouse, LM Lui, J Engelhardt, G Barton, M Clamp, S Searle
+ * 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.
*/
/*
* This extension was written by Benjamin Schuster-Boeckler at sanger.ac.uk
*/
package jalview.io;
-import java.io.*;
-import java.util.*;
+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 com.stevesoft.pat.*;
-import jalview.datamodel.*;
+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.*;
@@ -37,17 +61,34 @@ import jalview.datamodel.*;
* 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;
public StockholmFile()
{
}
+ /**
+ * Creates a new StockholmFile object for output.
+ */
+ public StockholmFile(AlignmentI al)
+ {
+ this.al = al;
+ }
+
public StockholmFile(String inFile, String type) throws IOException
{
super(inFile, type);
@@ -64,6 +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
*
@@ -81,13 +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()))
{
@@ -97,6 +203,7 @@ public class StockholmFile extends AlignFile
else
{
version = r.stringMatched(1);
+
// logger.debug("Stockholm version: " + version);
}
@@ -132,8 +239,24 @@ public class StockholmFile extends AlignFile
if (rend.search(line))
{
// End of the alignment, pass stuff back
-
this.noSeqs = seqs.size();
+
+ 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)
+ {
+ String dbType = getAlignmentProperty("AC").toString();
+ if (pf.search(dbType))
+ {
+ // PFAM Alignment - so references are typically from Uniprot
+ dbsource = "PFAM";
+ }
+ else if (rf.search(dbType))
+ {
+ dbsource = "RFAM";
+ }
+ }
// logger.debug("Number of sequences: " + this.noSeqs);
Enumeration accs = seqs.keys();
while (accs.hasMoreElements())
@@ -185,19 +308,25 @@ public class StockholmFile extends AlignFile
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++)
+ if (accAnnotations != null && accAnnotations.containsKey("AC"))
+ {
+ if (dbsource != null)
{
- AlignmentAnnotation an = (AlignmentAnnotation) v.elementAt(i);
- seqO.addAlignmentAnnotation(an);
- // annotations.add(an);
+ 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
+ guessDatabaseFor(seqO, dbr, dbsource);
+
+ }
}
+ // else - do what ? add the data anyway and prompt the user to
+ // specify what references these are ?
}
Hashtable features = null;
@@ -224,6 +353,24 @@ public class StockholmFile extends AlignFile
// TODO: map coding region to core jalview feature types
String type = i.nextElement().toString();
Hashtable content = (Hashtable) features.remove(type);
+
+ // add alignment annotation for this feature
+ String key = type2id(type);
+ if (key != null)
+ {
+ if (accAnnotations != null
+ && accAnnotations.containsKey(key))
+ {
+ Vector vv = (Vector) accAnnotations.get(key);
+ for (int ii = 0; ii < vv.size(); ii++)
+ {
+ AlignmentAnnotation an = (AlignmentAnnotation) vv
+ .elementAt(ii);
+ seqO.addAlignmentAnnotation(an);
+ }
+ }
+ }
+
Enumeration j = content.keys();
while (j.hasMoreElements())
{
@@ -478,25 +625,24 @@ public class StockholmFile extends AlignFile
ns += seq;
content.put(description, ns);
- if (type.equals("SS"))
+ // if(type.equals("SS")){
+ Hashtable strucAnn;
+ if (seqAnn.containsKey(acc))
{
- Hashtable strucAnn;
- if (seqAnn.containsKey(acc))
- {
- strucAnn = (Hashtable) seqAnn.get(acc);
- }
- else
- {
- strucAnn = new Hashtable();
- }
+ strucAnn = (Hashtable) seqAnn.get(acc);
+ }
+ else
+ {
+ strucAnn = new Hashtable();
+ }
- Vector newStruc = new Vector();
- parseAnnotationRow(newStruc, type, ns);
+ Vector newStruc = new Vector();
+ parseAnnotationRow(newStruc, type, ns);
- strucAnn.put(type, newStruc);
- seqAnn.put(acc, strucAnn);
- }
+ strucAnn.put(type, newStruc);
+ seqAnn.put(acc, strucAnn);
}
+ // }
else
{
System.err
@@ -522,6 +668,114 @@ 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)
+ */
+ 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)
+ {
+ String num, range = sdbac.substring(st + 1);
+ sdbac = sdbac.substring(0, st);
+ if ((p = range.indexOf("-")) > -1)
+ {
+ p++;
+ if (p < range.length())
+ {
+ num = range.substring(p).trim();
+ try
+ {
+ en = Integer.parseInt(num);
+ } catch (NumberFormatException x)
+ {
+ // could warn here that index is invalid
+ en = -1;
+ }
+ }
+ }
+ else
+ {
+ p = range.length();
+ }
+ num = range.substring(0, p).trim();
+ try
+ {
+ st = Integer.parseInt(num);
+ } catch (NumberFormatException x)
+ {
+ // could warn here that index is invalid
+ st = -1;
+ }
+ }
+ if (dbsource.equals("PFAM"))
+ {
+ seqdb = "UNIPROT";
+ 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)
+ {
+ dbrs.add(dbrf);
+ }
+ }
+ 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)
+ {
+ // strip off last subdomain
+ 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)
+ {
+ dbrs.add(dbrf);
+ }
+ }
+ if (st != -1 && en != -1)
+ {
+ 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.datamodel.Mapping mping = new Mapping(mp);
+ d.setMap(mping);
+ }
+ }
+ }
+
protected static AlignmentAnnotation parseAnnotationRow(
Vector annotation, String label, String annots)
{
@@ -538,8 +792,12 @@ public class StockholmFile extends AlignFile
convert2 = closeparen.replaceAll(convert1);
annots = convert2;
- String type = (label.indexOf("_cons") == label.length() - 5) ? label
- .substring(0, label.length() - 5) : label;
+ String type = label;
+ if (label.contains("_cons"))
+ {
+ 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"))
@@ -606,14 +864,211 @@ public class StockholmFile extends AlignFile
return annot;
}
- public static String print(SequenceI[] s)
+ public String print(SequenceI[] s)
{
- return "not yet implemented";
+ // find max length of id
+ int max = 0;
+ int maxid = 0;
+ int in = 0;
+ Hashtable dataRef = null;
+ while ((in < s.length) && (s[in] != null))
+ {
+ String tmp = printId(s[in]);
+ if (s[in].getSequence().length > max)
+ {
+ max = s[in].getSequence().length;
+ }
+
+ if (tmp.length() > maxid)
+ {
+ maxid = tmp.length();
+ }
+ if (s[in].getDBRef() != null)
+ {
+ for (int idb = 0; idb < s[in].getDBRef().length; idb++)
+ {
+ if (dataRef == null)
+ dataRef = new Hashtable();
+
+ String datAs1 = s[in].getDBRef()[idb].getSource().toString()
+ + " ; "
+ + s[in].getDBRef()[idb].getAccessionId().toString();
+ dataRef.put(tmp, datAs1);
+ }
+ }
+ in++;
+ }
+ maxid += 9;
+ int i = 0;
+
+ // output database type
+ if (al.getProperties() != null)
+ {
+ if (!al.getProperties().isEmpty())
+ {
+ Enumeration key = al.getProperties().keys();
+ Enumeration val = al.getProperties().elements();
+ while (key.hasMoreElements())
+ {
+ out.append("#=GF " + key.nextElement() + " " + val.nextElement());
+ out.append(newline);
+ }
+ }
+ }
+
+ // output database accessions
+ if (dataRef != null)
+ {
+ Enumeration en = dataRef.keys();
+ while (en.hasMoreElements())
+ {
+ Object idd = en.nextElement();
+ String type = (String) dataRef.remove(idd);
+ out.append(new Format("%-" + (maxid - 2) + "s").form("#=GS "
+ + idd.toString() + " "));
+ if (type.contains("PFAM") || type.contains("RFAM"))
+ {
+
+ out.append(" AC " + type.substring(type.indexOf(";") + 1));
+ }
+ else
+ {
+ out.append(" DR " + type + " ");
+ }
+ out.append(newline);
+ }
+ }
+
+ // output annotations
+ while (i < s.length && s[i] != null)
+ {
+ if (s[i].getDatasetSequence() != null)
+ {
+ SequenceI ds = s[i].getDatasetSequence();
+ AlignmentAnnotation[] alAnot;
+ Annotation[] ann;
+ Annotation annot;
+ alAnot = s[i].getAnnotation();
+ String feature = "";
+ if (alAnot != null)
+ {
+ for (int j = 0; j < alAnot.length; j++)
+ {
+ if (ds.getSequenceFeatures() != null)
+ {
+ feature = ds.getSequenceFeatures()[0].type;
+ }
+ String key = type2id(feature);
+
+ if (key == null)
+ continue;
+
+ // out.append("#=GR ");
+ out.append(new Format("%-" + maxid + "s").form("#=GR "
+ + printId(s[i]) + " " + key + " "));
+ ann = alAnot[j].annotations;
+ String seq = "";
+ for (int k = 0; k < ann.length; k++)
+ {
+ annot = ann[k];
+ String ch = (annot == null) ? Character.toString(s[i]
+ .getCharAt(k)) : annot.displayCharacter;
+ if (ch.length() == 0)
+ {
+ if (key.equals("SS"))
+ {
+ char ll = annot.secondaryStructure;
+ seq = (Character.toString(ll).equals(" ")) ? seq + "C"
+ : seq + ll;
+ }
+ else
+ {
+ seq += ".";
+ }
+ }
+ else if (ch.length() == 1)
+ {
+ seq += ch;
+ }
+ else if (ch.length() > 1)
+ {
+ seq += ch.charAt(1);
+ }
+ }
+ out.append(seq);
+ out.append(newline);
+ }
+ }
+ }
+
+ out.append(new Format("%-" + maxid + "s").form(printId(s[i]) + " "));
+ out.append(s[i].getSequenceAsString());
+ out.append(newline);
+ i++;
+ }
+
+ // alignment annotation
+ AlignmentAnnotation aa;
+ if (al.getAlignmentAnnotation() != null)
+ {
+ for (int ia = 0; ia < al.getAlignmentAnnotation().length; ia++)
+ {
+ aa = al.getAlignmentAnnotation()[ia];
+ if (aa.autoCalculated || !aa.visible)
+ {
+ continue;
+ }
+ String seq = "";
+ String label;
+
+ if (aa.label.equals("seq"))
+ label = "seq_cons";
+ else
+ label = type2id(aa.label.toLowerCase()) + "_cons";
+
+ if (label == null)
+ label = aa.label;
+
+ out.append(new Format("%-" + maxid + "s").form("#=GC " + label
+ + " "));
+ for (int j = 0; j < aa.annotations.length; j++)
+ {
+ String ch = (aa.annotations[j] == null) ? "-"
+ : aa.annotations[j].displayCharacter;
+ if (ch.length() == 0)
+ {
+ char ll = aa.annotations[j].secondaryStructure;
+ if (Character.toString(ll).equals(" "))
+ seq += "C";
+ else
+ seq += ll;
+ }
+ else if (ch.length() == 1)
+ {
+ seq += ch;
+ }
+ else if (ch.length() > 1)
+ {
+ seq += ch.charAt(1);
+ }
+ }
+ out.append(seq);
+ out.append(newline);
+ }
+ }
+ return out.toString();
}
public String print()
{
- return print(getSeqsAsArray());
+ out = new StringBuffer();
+ out.append("# STOCKHOLM 1.0");
+ out.append(newline);
+ print(getSeqsAsArray());
+
+ out.append("//");
+ out.append(newline);
+ return out.toString();
}
private static Hashtable typeIds = null;
@@ -651,38 +1106,45 @@ public class StockholmFile extends AlignFile
+ id);
return id;
}
+
+ protected static String type2id(String type)
+ {
+ String key = null;
+ Enumeration e = typeIds.keys();
+ while (e.hasMoreElements())
+ {
+ Object ll = e.nextElement();
+ if (typeIds.get(ll).toString().equals(type))
+ {
+ key = (String) ll;
+ break;
+ }
+ }
+ if (key != null)
+ {
+ return (String) key;
+ }
+ System.err.println("Warning : Unknown Stockholm annotation type: "
+ + 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);
- *
- * 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);
+ * make a friendly ID string.
*
- *
- * 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;
+ }
}