org.biojava.nbio.structure.io.FileConvert Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of biojava-structure Show documentation
Show all versions of biojava-structure Show documentation
The protein structure modules of BioJava.
/*
* This code may be freely distributed and modified under the
* terms of the GNU Lesser General Public Licence. This should
* be distributed with the code. If you do not have a copy,
* see:
*
* http://www.gnu.org/copyleft/lesser.html
*
* Copyright for this code is held jointly by the individual
* authors. These should be listed in @author doc comments.
*
* For more information on the BioJava project and its aims,
* or to join the biojava-l mailing list, visit the home page
* at:
*
* http://www.biojava.org/
*
* Created on 26.04.2004
* @author Andreas Prlic
*
*/
package org.biojava.nbio.structure.io;
import java.io.IOException;
import java.text.DateFormat;
import java.text.DecimalFormat;
import java.text.NumberFormat;
import java.text.SimpleDateFormat;
import java.util.List;
import java.util.Locale;
import org.biojava.nbio.core.util.XMLWriter;
import org.biojava.nbio.structure.Atom;
import org.biojava.nbio.structure.Bond;
import org.biojava.nbio.structure.Chain;
import org.biojava.nbio.structure.DBRef;
import org.biojava.nbio.structure.Element;
import org.biojava.nbio.structure.Group;
import org.biojava.nbio.structure.GroupType;
import org.biojava.nbio.structure.PDBHeader;
import org.biojava.nbio.structure.Site;
import org.biojava.nbio.structure.Structure;
import org.biojava.nbio.structure.io.cif.CifStructureConverter;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* Methods to convert a structure object into different file formats.
* @author Andreas Prlic
* @since 1.4
*/
public class FileConvert {
private static final Logger logger = LoggerFactory.getLogger(FileConvert.class);
private Structure structure ;
private boolean printConnections;
// Locale should be english, e.g. in DE separator is "," -> PDB files have "." !
public static DecimalFormat d3 = (DecimalFormat)NumberFormat.getInstance(Locale.US);
static {
d3.setMaximumIntegerDigits(4);
d3.setMinimumFractionDigits(3);
d3.setMaximumFractionDigits(3);
d3.setGroupingUsed(false);
}
public static DecimalFormat d2 = (DecimalFormat)NumberFormat.getInstance(Locale.US);
static {
d2.setMaximumIntegerDigits(3);
d2.setMinimumFractionDigits(2);
d2.setMaximumFractionDigits(2);
d2.setGroupingUsed(false);
}
private static final String newline = System.getProperty("line.separator");
/**
* Constructs a FileConvert object.
*
* @param struc a Structure object
*/
public FileConvert(Structure struc) {
structure = struc ;
printConnections = true;
}
/**
* Returns if the Connections should be added
* default is true;
* @return if the printConnections flag is set
*/
public boolean doPrintConnections() {
return printConnections;
}
/** enable/disable printing of connections
* connections are sometimes buggy in PDB files
* so there are some cases where one might turn this off.
* @param printConnections
*/
public void setPrintConnections(boolean printConnections) {
this.printConnections = printConnections;
}
/**
* Prints the connections in PDB style
*
* Rewritten since 5.0 to use {@link Bond}s
* Will produce strictly one CONECT record per bond (won't group several bonds in one line)
*/
private String printPDBConnections(){
StringBuilder str = new StringBuilder();
for (Chain c:structure.getChains()) {
for (Group g:c.getAtomGroups()) {
for (Atom a:g.getAtoms()) {
if (a.getBonds()!=null) {
for (Bond b:a.getBonds()) { //7890123456789012345678901234567890123456789012345678901234567890
str.append(String.format("CONECT%5d%5d "+newline, b.getAtomA().getPDBserial(), b.getAtomB().getPDBserial()));
}
}
}
}
}
return str.toString();
}
/** Convert a structure into a PDB file.
* @return a String representing a PDB file.
*/
public String toPDB() {
StringBuffer str = new StringBuffer();
//int i = 0 ;
// TODO: print all the PDB header informaton in PDB style
// some objects (PDBHeader, Compound) are still missing
//
PDBHeader header = structure.getPDBHeader();
header.toPDB(str);
//REMARK 800
if (!structure.getSites().isEmpty()) {
str.append("REMARK 800 ").append(newline);
str.append("REMARK 800 SITE ").append(newline);
for (Site site : structure.getSites()) {
site.remark800toPDB(str);
}
}
//DBREF
for (DBRef dbref : structure.getDBRefs()){
dbref.toPDB(str);
str.append(newline);
}
//SSBOND
List ssbonds = SSBondImpl.getSsBondListFromBondList(structure.getSSBonds());
for (SSBondImpl ssbond : ssbonds){
ssbond.toPDB(str);
str.append(newline);
}
//SITE
for (Site site : structure.getSites()) {
try {
site.toPDB(str);
} catch (Exception e){
e.printStackTrace();
}
}
//
// print the atom records
//
// do for all models
int nrModels = structure.nrModels() ;
if ( structure.isNmr()) {
str.append("EXPDTA NMR, "+ nrModels+" STRUCTURES"+newline) ;
}
for (int m = 0 ; m < nrModels ; m++) {
if ( nrModels>1 ) {
str.append("MODEL " + (m+1)+ newline);
}
List polyChains = structure.getPolyChains(m);
List nonPolyChains = structure.getNonPolyChains(m);
List waterChains = structure.getWaterChains(m);
for (Chain chain : polyChains) {
// do for all groups
int nrGroups = chain.getAtomLength();
for ( int h=0; h 0) str.append(String.format("%-80s","TER")).append(newline);
}
boolean nonPolyGroupsExist = false;
for (Chain chain : nonPolyChains) {
// do for all groups
int nrGroups = chain.getAtomLength();
for ( int h=0; h1) {
str.append(String.format("%-80s","ENDMDL")).append(newline);
}
}
if ( doPrintConnections() )
str.append(printPDBConnections());
return str.toString() ;
}
private static void toPDB(Group g, StringBuffer str) {
// iterate over all atoms ...
// format output ...
int groupsize = g.size();
for ( int atompos = 0 ; atompos < groupsize; atompos++) {
Atom a = null ;
a = g.getAtom(atompos);
if ( a == null)
continue ;
toPDB(a, str);
//line = record + serial + " " + fullname +altLoc
//+ leftResName + " " + chainID + resseq
//+ " " + x+y+z
//+ occupancy + tempfactor;
//str.append(line + newline);
//System.out.println(line);
}
if ( g.hasAltLoc()){
for (Group alt : g.getAltLocs() ) {
toPDB(alt,str);
}
}
}
/** Prints the content of an Atom object as a PDB formatted line.
*
* @param a
* @return
*/
public static String toPDB(Atom a){
StringBuffer w = new StringBuffer();
toPDB(a,w);
return w.toString();
}
public static String toPDB(Atom a, String chainId) {
StringBuffer w = new StringBuffer();
toPDB(a,w, chainId);
return w.toString();
}
/**
* Convert a Chain object to PDB representation
*
* @param chain
* @return
*/
public static String toPDB(Chain chain){
StringBuffer w = new StringBuffer();
int nrGroups = chain.getAtomLength();
for ( int h=0; h
* ATOM 1 N ASP A 15 110.964 24.941 59.191 1.00 83.44 N
*
* COLUMNS DATA TYPE FIELD DEFINITION
* ---------------------------------------------------------------------------------
* 1 - 6 Record name "ATOM "
* 7 - 11 Integer serial Atom serial number.
* 13 - 16 Atom name Atom name.
* 17 Character altLoc Alternate location indicator.
* 18 - 20 Residue name resName Residue name.
* 22 Character chainID Chain identifier.
* 23 - 26 Integer resSeq Residue sequence number.
* 27 AChar iCode Code for insertion of residues.
* 31 - 38 Real(8.3) x Orthogonal coordinates for X in
* Angstroms.
* 39 - 46 Real(8.3) y Orthogonal coordinates for Y in
* Angstroms.
* 47 - 54 Real(8.3) z Orthogonal coordinates for Z in
* Angstroms.
* 55 - 60 Real(6.2) occupancy Occupancy.
* 61 - 66 Real(6.2) tempFactor Temperature factor.
* 73 - 76 LString(4) segID Segment identifier, left-justified.
* 77 - 78 LString(2) element Element symbol, right-justified.
* 79 - 80 LString(2) charge Charge on the atom.
*