pdbreader.java

化学图形处理软件

/* $Revision: 8242 $ $Author: egonw $ $Date: 2007-04-22 22:49:31 +0200 (Sun, 22 Apr 2007) $
 *
 * Copyright (C) 1997-2007  The Chemistry Development Kit (CDK) project
 * 
 * Contact: [e-mail]
 * 
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public License
 * as published by the Free Software Foundation; either version 2.1
 * of the License, or (at your option) any later version.
 * All we ask is that proper credit is given for our work, which includes
 * - but is not limited to - adding the above copyright notice to the beginning
 * of your source code files, and to any copyright notice that you may distribute
 * with programs based on this work.
 * 
 * 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 Lesser General Public License for more details.
 * 
 * You should have received a copy of the GNU Lesser General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *  */
package org.openscience.cdk.io;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.StringReader;
import java.util.Hashtable;
import java.util.Map;

import javax.vecmath.Point3d;

import org.openscience.cdk.CDKConstants;
import org.openscience.cdk.config.AtomTypeFactory;
import org.openscience.cdk.exception.CDKException;
import org.openscience.cdk.exception.NoSuchAtomTypeException;
import org.openscience.cdk.graph.rebond.RebondTool;
import org.openscience.cdk.interfaces.IAtom;
import org.openscience.cdk.interfaces.IAtomType;
import org.openscience.cdk.interfaces.IBioPolymer;
import org.openscience.cdk.interfaces.IChemFile;
import org.openscience.cdk.interfaces.IChemModel;
import org.openscience.cdk.interfaces.IChemObject;
import org.openscience.cdk.interfaces.IChemSequence;
import org.openscience.cdk.interfaces.IMolecule;
import org.openscience.cdk.interfaces.IMoleculeSet;
import org.openscience.cdk.interfaces.IMonomer;
import org.openscience.cdk.interfaces.IStrand;
import org.openscience.cdk.io.formats.IResourceFormat;
import org.openscience.cdk.io.formats.PDBFormat;
import org.openscience.cdk.io.setting.BooleanIOSetting;
import org.openscience.cdk.io.setting.IOSetting;
import org.openscience.cdk.protein.data.PDBAtom;
import org.openscience.cdk.protein.data.PDBMonomer;
import org.openscience.cdk.protein.data.PDBPolymer;
import org.openscience.cdk.protein.data.PDBStrand;
import org.openscience.cdk.protein.data.PDBStructure;
import org.openscience.cdk.tools.LoggingTool;
import org.openscience.cdk.tools.manipulator.AtomTypeManipulator;

/**
 * Reads the contents of a PDBFile.
 *
 * <p>A description can be found at <a href="http://www.rcsb.org/pdb/static.do?p=file_formats/pdb/index.html">
 * http://www.rcsb.org/pdb/static.do?p=file_formats/pdb/index.html</a>.
 *
 * @cdk.module  pdb
 *
 * @author      Edgar Luttmann
 * @author      Bradley Smith <[e-mail]>
 * @author      Martin Eklund <[e-mail]>
 * @author      Ola Spjuth <[e-mail]>
 * @cdk.created 2001-08-06
 * @cdk.keyword file format, PDB
 */
public class PDBReader extends DefaultChemObjectReader {
	
	private LoggingTool logger;
	private BufferedReader _oInput; // The internal used BufferedReader
	private BooleanIOSetting useRebondTool;
	private BooleanIOSetting readConnect;
	
	private Map atomNumberMap;
	
	private static AtomTypeFactory pdbFactory;
	
	/**
	 *
	 * Contructs a new PDBReader that can read Molecules from a given
	 * InputStream.
	 *
	 * @param oIn  The InputStream to read from
	 *
	 */
	public PDBReader(InputStream oIn) {
		this(new InputStreamReader(oIn));
	}
	
	/**
	 *
	 * Contructs a new PDBReader that can read Molecules from a given
	 * Reader.
	 *
	 * @param oIn  The Reader to read from
	 *
	 */
	public PDBReader(Reader oIn) {
		logger = new LoggingTool(this.getClass());
		_oInput = new BufferedReader(oIn);
		initIOSettings();
		pdbFactory = null;
	}
	
	public PDBReader() {
		this(new StringReader(""));
	}
	
	public IResourceFormat getFormat() {
		return PDBFormat.getInstance();
	}
	
	public void setReader(Reader input) throws CDKException {
		if (input instanceof BufferedReader) {
			this._oInput = (BufferedReader)input;
		} else {
			this._oInput = new BufferedReader(input);
		}
	}
	
	public void setReader(InputStream input) throws CDKException {
		setReader(new InputStreamReader(input));
	}
	
	public boolean accepts(Class classObject) {
		Class[] interfaces = classObject.getInterfaces();
		for (int i=0; i<interfaces.length; i++) {
			if (IChemFile.class.equals(interfaces[i])) return true;
		}
		return false;
	}

	/**
	 *
	 * Takes an object which subclasses IChemObject, e.g. Molecule, and will
	 * read this (from file, database, internet etc). If the specific
	 * implementation does not support a specific IChemObject it will throw
	 * an Exception.
	 *
	 * @param oObj  The object that subclasses IChemObject
	 * @return      The IChemObject read  
	 * @exception   CDKException  
	 *
	 */
	public IChemObject read(IChemObject oObj) throws CDKException {
		if (oObj instanceof IChemFile) {
			if (pdbFactory == null) {
				try {
					pdbFactory = AtomTypeFactory.getInstance("org/openscience/cdk/config/data/pdb_atomtypes.xml", 
				    	  ((IChemFile)oObj).getBuilder());
				} catch (Exception exception) {
					logger.debug(exception);
					throw new CDKException("Could not setup list of PDB atom types! " + exception.getMessage());
				}
			}
			return readChemFile((IChemFile)oObj);
		} else {
			throw new CDKException("Only supported is reading of ChemFile objects.");
		}
	}
	
	/**
	 * Read a <code>ChemFile</code> from a file in PDB format. The molecules
	 * in the file are stored as <code>BioPolymer</code>s in the
	 * <code>ChemFile</code>. The residues are the monomers of the
	 * <code>BioPolymer</code>, and their names are the concatenation of the
	 * residue, chain id, and the sequence number. Separate chains (denoted by
	 * TER records) are stored as separate <code>BioPolymer</code> molecules.
	 *
	 * <p>Connectivity information is not currently read.
	 *
	 * @return The ChemFile that was read from the PDB file.
	 */
	private IChemFile readChemFile(IChemFile oFile) 	{
		// initialize all containers
		IChemSequence oSeq = oFile.getBuilder().newChemSequence();
		IChemModel oModel = oFile.getBuilder().newChemModel();
		IMoleculeSet oSet = oFile.getBuilder().newMoleculeSet();
		
		// some variables needed
		String cCol;
		PDBAtom oAtom;
		PDBPolymer oBP = new PDBPolymer();
		IMolecule molecularStructure = oFile.getBuilder().newMolecule();
		StringBuffer cResidue;
		String oObj;
		IMonomer oMonomer;
		String cRead = "";
		char chain = 'A';	// To ensure stringent name giving of monomers
		IStrand oStrand;
		int lineLength = 0;
		
		boolean isProteinStructure = false;
		
		atomNumberMap = new Hashtable();
		
		// do the reading of the Input		
		try {
			do {
				cRead = _oInput.readLine();
				logger.debug("Read line: ", cRead);
				if (cRead != null) {	
					lineLength = cRead.length();
					
					if (lineLength < 80) {
						logger.warn("Line is not of the expected length 80!");
					}
					
					// make sure the record name is 6 characters long
					if (lineLength < 6) {
						cRead = cRead + "      ";
					}
					// check the first column to decide what to do
					cCol = cRead.substring(0,6);
					if ("SEQRES".equalsIgnoreCase(cCol)) {
						isProteinStructure = true;
					} else if ("ATOM  ".equalsIgnoreCase(cCol)) {
						// read an atom record
						oAtom = readAtom(cRead, lineLength);
						
						if (isProteinStructure) {
							// construct a string describing the residue
							cResidue = new StringBuffer(8);
							oObj = oAtom.getResName();
							if (oObj != null) {
								cResidue = cResidue.append(oObj.trim());
							}
							oObj = oAtom.getChainID();
							if (oObj != null) {
								// cResidue = cResidue.append(((String)oObj).trim());
								cResidue = cResidue.append(String.valueOf(chain));
							}
							oObj = oAtom.getResSeq();
							if (oObj != null) {
								cResidue = cResidue.append(oObj.trim());
							}

							// search for an existing strand or create a new one.
							String strandName = oAtom.getChainID();
							if (strandName == null || strandName.length() == 0) {
								strandName = String.valueOf(chain);
							}
							oStrand = oBP.getStrand(strandName);
							if (oStrand == null) {
								oStrand = new PDBStrand();
								oStrand.setStrandName(strandName);
								oStrand.setID(String.valueOf(chain));
							}

							// search for an existing monomer or create a new one.
							oMonomer = oBP.getMonomer(cResidue.toString(), String.valueOf(chain));
							if (oMonomer == null) {
								PDBMonomer monomer = new PDBMonomer();
								monomer.setMonomerName(cResidue.toString());
								monomer.setMonomerType(oAtom.getResName());
								monomer.setChainID(oAtom.getChainID());
								monomer.setICode(oAtom.getICode());
								monomer.setResSeq(oAtom.getResSeq());
								oMonomer = monomer;
							}

							// add the atom
							oBP.addAtom(oAtom, oMonomer, oStrand);
							if (readConnect.isSet() && atomNumberMap.put(new Integer(oAtom.getSerial()), oAtom) != null) {
								logger.warn("Duplicate serial ID found for atom: ", oAtom);
							}
						} else {
							molecularStructure.addAtom(oAtom);
						}
						logger.debug("Added ATOM: ", oAtom);
						
						/** As HETATMs cannot be considered to either belong to a certain monomer or strand,
						 * they are dealt with seperately.*/
					} else if("HETATM".equalsIgnoreCase(cCol))	{
						// read an atom record
						oAtom = readAtom(cRead, lineLength);
						oAtom.setHetAtom(true);
						oBP.addAtom(oAtom);
						if (atomNumberMap.put(new Integer(oAtom.getSerial()), oAtom) != null) {
							logger.warn("Duplicate serial ID found for atom: ", oAtom);
						}
						logger.debug("Added HETATM: ", oAtom);
					} else if ("TER   ".equalsIgnoreCase(cCol)) {
						// start new strand						
						chain++;
						oStrand = new PDBStrand();
						oStrand.setStrandName(String.valueOf(chain));
						logger.debug("Added new STRAND");
					} else if ("END   ".equalsIgnoreCase(cCol)) {
						atomNumberMap.clear();
						if (isProteinStructure) {
							// create bonds and finish the molecule
							if (useRebondTool.isSet()) {
								try {
									if(!createBondsWithRebondTool(oBP))	{
										// Get rid of all potentially created bonds.
										logger.info("Bonds could not be created using the RebondTool when PDB file was read.");								
										oBP.removeAllBonds();								
									}
								} catch (Exception exception) {
									logger.info("Bonds could not be created when PDB file was read.");
									logger.debug(exception);
								}
							}
							oSet.addMolecule(oBP);
						} else {
							oSet.addMolecule(molecularStructure);
						}
					} else if (cCol.equals("MODEL ")) {
						// OK, start a new model and save the current one first *if* it contains atoms