/*
- * Jalview - A Sequence Alignment Editor and Viewer (Development Version 2.4.1)
- * Copyright (C) 2009 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle
+ * 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
*
- * 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 file is part of Jalview.
*
- * 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.
+ * 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 this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
+ * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
*/
package MCview;
import java.awt.*;
+import jalview.analysis.AlignSeq;
import jalview.datamodel.*;
+import jalview.ext.jmol.PDBFileWithJmol;
import jalview.io.FileParse;
+import jalview.ws.jws1.Annotate3D;
public class PDBfile extends jalview.io.AlignFile
{
public void parse() throws IOException
{
- // TODO set the filename sensibly
- id = (inFile == null || inFile.getName()==null || inFile.getName().length()==0) ? "PDBFILE" : inFile.getName();
- try
- {
- chains = new Vector();
+ // TODO set the filename sensibly - try using data source name.
+ id = safeName(getDataName());
- PDBChain tmpchain;
- String line;
- boolean modelFlag = false;
- boolean terFlag = false;
- String lastID="";
+ chains = new Vector();
+ ArrayList<SequenceI> rna=new ArrayList<SequenceI>(), prot=new ArrayList<SequenceI>();
+ PDBChain tmpchain;
+ String line = null;
+ boolean modelFlag = false;
+ boolean terFlag = false;
+ String lastID = "";
- int index = 0;
- String atomnam=null;
+ int index = 0;
+ String atomnam = null;
+ try
+ {
while ((line = nextLine()) != null)
{
if (line.indexOf("HEADER") == 0)
{
- if (line.length()>62)
+ if (line.length() > 62)
{
String tid;
- if (line.length()>67) {
+ if (line.length() > 67)
+ {
tid = line.substring(62, 67).trim();
- } else {
- tid=line.substring(62).trim();
}
- if (tid.length()>0)
+ else
+ {
+ tid = line.substring(62).trim();
+ }
+ if (tid.length() > 0)
{
id = tid;
}
{
if (tmpatom.resNumIns.trim().equals(lastID))
{
- // phosphorylated protein - seen both CA and P..
+ // phosphorylated protein - seen both CA and P..
continue;
}
tmpchain.atoms.addElement(tmpatom);
dataset.setName(id + "|" + dataset.getName());
PDBEntry entry = new PDBEntry();
entry.setId(id);
+ entry.setProperty(new Hashtable());
+ if (((PDBChain)chains.elementAt(i)).id!=null) {
+ entry.getProperty().put("CHAIN", ((PDBChain)chains.elementAt(i)).id);
+ }
if (inFile != null)
{
entry.setFile(inFile.getAbsolutePath());
}
+ else
+ {
+ // TODO: decide if we should dump the datasource to disk
+ entry.setFile(getDataName());
+ }
dataset.addPDBId(entry);
SequenceI chainseq = dataset.deriveSequence(); // PDBChain objects
- // maintain reference to
- // dataset
+ // maintain reference to
+ // dataset
seqs.addElement(chainseq);
+ if(isRNA(chainseq)==true)
+ {
+ rna.add(chainseq);
+ } else {
+ prot.add(chainseq);
+ }
+
AlignmentAnnotation[] chainannot = chainseq.getAnnotation();
+
if (chainannot != null)
{
for (int ai = 0; ai < chainannot.length; ai++)
{
+
chainannot[ai].visible = VisibleChainAnnotation;
annotations.addElement(chainannot[ai]);
}
}
}
+ if (rna.size()>0)
+ try {
+ processPdbFileWithAnnotate3d(rna);
+ } catch (Exception x)
+ {
+ System.err.println("Exceptions when dealing with RNA in pdb file");
+ x.printStackTrace();
+
+ };
+ if (prot.size()>0)
+ try {
+ processPdbFileWithJmol(prot);
+ } catch (Exception x)
+ {
+ System.err.println("Exceptions when dealing with RNA in pdb file");
+ x.printStackTrace();
+
+ };
+ if (prot.size()>0)
+ try {
+ processPdbFileWithJmol(prot);
+ } catch (Exception x)
+ {
+ System.err.println("Exceptions when dealing with RNA in pdb file");
+ x.printStackTrace();
+
+ };
} catch (OutOfMemoryError er)
{
System.out.println("OUT OF MEMORY LOADING PDB FILE");
throw new IOException("Out of memory loading PDB File");
+ } catch (NumberFormatException ex)
+ {
+ if (line != null)
+ {
+ System.err.println("Couldn't read number from line:");
+ System.err.println(line);
+ }
}
}
+ private void processPdbFileWithJmol(ArrayList<SequenceI> prot) throws Exception
+ {
+ PDBFileWithJmol jmf = new PDBFileWithJmol(new FileParse(getDataName(),type));
+ Alignment al = new Alignment(jmf.getSeqsAsArray());
+ jmf.addAnnotations(al);
+ replaceMatchingSeqsWith(prot, al, AlignSeq.PEP);
+ }
+ private void processPdbFileWithAnnotate3d(ArrayList<SequenceI> rna) throws Exception {
+// System.out.println("this is a PDB format and RNA sequence");
+ Annotate3D an3d = new Annotate3D();
+ // TODO: use the PDB ID of the structure if one is available, to save bandwidth and avoid uploading the whole structure to the service
+ AlignmentI al = an3d.getRNAMLFor(new FileParse(getDataName(),type));
+ replaceMatchingSeqsWith(rna, al, AlignSeq.DNA);
+ }
+ private void replaceMatchingSeqsWith(ArrayList<SequenceI> ochains, AlignmentI al, String dnaOrProtein)
+ {
+ if (al!=null && al.getHeight()>0)
+ {
+ ArrayList<SequenceI> matches=new ArrayList<SequenceI>();
+ ArrayList<AlignSeq> aligns=new ArrayList<AlignSeq>();
+
+ for (SequenceI sq:ochains)
+ {
+ SequenceI bestm=null;
+ AlignSeq bestaseq=null;
+ int bestscore=0;
+ for (SequenceI msq:al.getSequences())
+ {
+ AlignSeq aseq = AlignSeq.doGlobalNWAlignment(msq, sq, dnaOrProtein);
+ if (bestm==null || aseq.getMaxScore()>bestscore)
+ {
+ bestscore=aseq.getMaxScore();
+ bestaseq= aseq;
+ bestm=msq;
+ }
+ }
+ System.out.println("Best Score for "+(matches.size()+1)+" :"+bestscore);
+ matches.add(bestm);
+ aligns.add(bestaseq);
+ al.deleteSequence(bestm);
+ }
+ for (int p=0,pSize=seqs.size();p<pSize;p++)
+ {
+ SequenceI sq,sp=seqs.get(p);
+ int q;
+ if ((q=ochains.indexOf(sp))>-1)
+ {
+ seqs.set(p, sq=matches.get(q));
+ sq.setName(sp.getName());
+ sq.setDescription(sp.getDescription());
+ sq.transferAnnotation(sp, aligns.get(q).getMappingFromS1(false));
+ int inspos=-1;
+ for (int ap=0;ap<annotations.size();)
+ {
+ if (((AlignmentAnnotation)annotations.get(ap)).sequenceRef==sp) {
+ if (inspos==-1)
+ {
+ inspos=ap;
+ }
+ annotations.remove(ap);
+ } else {
+ ap++;
+ }
+ }
+ if (sq.getAnnotation()!=null) {
+ annotations.addAll(inspos, Arrays.asList(sq.getAnnotation()));
+ }
+ }
+ }
+ }
+ }
+ /**
+ * make a friendly ID string.
+ *
+ * @param dataName
+ * @return truncated dataName to after last '/'
+ */
+ private String safeName(String dataName)
+ {
+ int p = 0;
+ while ((p = dataName.indexOf("/")) > -1 && p < dataName.length())
+ {
+ dataName = dataName.substring(p + 1);
+ }
+ return dataName;
+ }
public void makeResidueList()
{
1.0f / (float) i, .4f, 1.0f));
}
}
+ public boolean isRNA(SequenceI seqs)
+ {
+ for (int i=0;i<seqs.getLength();i++){
+ if((seqs.getCharAt(i)!='A') &&(seqs.getCharAt(i)!='C')&&(seqs.getCharAt(i)!='G')&&(seqs.getCharAt(i)!='U'))
+ {
+ return false;
+ }
+ }
+
+ return true;
+
+
+ }
}