Java Structure.getChains方法代码示例

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
public static void convert(File inFile, File outFile) throws IOException {
			 
       MMcifParser parser = new SimpleMMcifParser();

       SimpleMMcifConsumer consumer = new SimpleMMcifConsumer();       
       parser.addMMcifConsumer(consumer);
       parser.parse(new BufferedReader(new InputStreamReader(new FileInputStream(inFile))));
       
       // now get the protein structure.
       Structure cifStructure = consumer.getStructure();

       // and write it out as PDB format
       PrintWriter pr = new PrintWriter(outFile);
       for (Chain c : cifStructure.getChains()) {
       		// we can override the chain name, the mmCIF chain names might have more than 1 character
       		c.setName(c.getName().substring(0, 1));
       		pr.print(c.toPDB());
       		pr.println("TER");
       }
       
	pr.close();
	

}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
@Test
public void test4letterChains() throws IOException, StructureException, URISyntaxException {
	String filename = "/1hh0_4char.cif.gz";
	URL url = getClass().getResource(filename);
	assumeNotNull("Can't find resource "+filename,url);

	File file = new File(url.toURI());
	assumeNotNull(file);
	assumeTrue(file.exists());

	MMCIFFileReader reader = new MMCIFFileReader();
	Structure s = reader.getStructure(file);

	assertNotNull("Failed to load structure from jar",s);

	List<Chain> chains = s.getChains();
	assertEquals("Wrong number of chains",chains.size(), 1);

	Chain chain = chains.get(0);
	assertEquals("Wrong chain ID",chain.getId(),"ABCD");

	Chain chain2 = s.getPolyChainByPDB("ABCD");
	assertNotNull(chain2);
	assertEquals(chain2, chain);
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * test output essential structure information of input pdb 
 * @param pdbname
 */
void outputPDB(String pdbname){
	try {

		//test "4cof"
           Structure s = StructureIO.getStructure(pdbname);
           
           for(DBRef db : s.getDBRefs()){
           	System.out.println("**");
           	System.out.println(db.getChainId());
           	System.out.println(db.getDatabase());
           	System.out.println(db.getDbAccession());
           	System.out.println(db.getDbIdCode());
           	System.out.println(db.getInsertBegin());
           	System.out.println(db.getInsertEnd());
           	System.out.println(db.getDbSeqBegin());
           	System.out.println(db.getDbSeqEnd());
           	System.out.println(db.getIdbnsBegin());
           	System.out.println(db.getIdbnsEnd());
           	System.out.println(db.getIdCode());
           	System.out.println(db.getId());
           }

           for ( Chain c : s.getChains()) {
           	
           	System.out.println(c.getChainID()+"\t"+c.getAtomLength()+"\t"+c.getAtomSequence().length()+"\t"+c.getSeqResLength());

               // only the observed residues
               System.out.println(c.getAtomSequence());
                             

               // print biological sequence
               System.out.println(c.getSeqResSequence());
           }

       } catch (Exception e) {

           e.printStackTrace();
       } 
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Returns a list of chain ids in the order they are specified in the ATOM
 * records in the asymmetric unit
 * @param asymUnit
 * @return
 */
private List<String> getChainIds(Structure asymUnit) {
	List<String> chainIds = new ArrayList<String>();
	for ( Chain c : asymUnit.getChains()){
		String intChainID = c.getId();
		chainIds.add(intChainID);
	}
	return chainIds;
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Converts a Structure into a List of {@link AtomSite} objects
 * @param s
 * @return
 */
public static List<AtomSite> convertStructureToAtomSites(Structure s) {
	List<AtomSite> list = new ArrayList<AtomSite>();

	for (int m=0;m<s.nrModels();m++) {
		for (Chain c:s.getChains(m)) {
			list.addAll(convertChainToAtomSites(c, m+1, c.getName(), c.getId()));
		}
	}
	return list;
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Count the total number of groups in the structure
 * @param structure the input structure
 * @return the total number of groups
 */
public static int getNumGroups(Structure structure) {
	int count = 0;
	for(int i=0; i<structure.nrModels(); i++) {
		for(Chain chain : structure.getChains(i)){
			count+= chain.getAtomGroups().size();
		}
	}
	return count;
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
@Test
public void test4cup() throws IOException, StructureException {

	AtomCache cache = new AtomCache();
	cache.setUseMmCif(true);
	FileParsingParameters params = cache.getFileParsingParams();

	cache.setFileParsingParams(params);
	StructureIO.setAtomCache(cache);
	// Set the test lists
	String[] asymChainList = {"A","B","C","D","E","F"};
	String[] authChainList = {"A","A","A","A","A","A"};
	String[] asymChainListTest = new String[6];
	String[] authChainListTest = new String[6];
	// Get the structure
	Structure bioJavaStruct = StructureIO.getStructure("4cup");
	List<Chain> chainList = bioJavaStruct.getChains();
	assertEquals(6,chainList.size());
	for(int i=0; i<chainList.size();i++){
		Chain c = chainList.get(i);
		authChainListTest[i] = c.getName();
		asymChainListTest[i] = c.getId();
	}
	// Now check both lists are the same
	assertArrayEquals(authChainListTest, authChainList);
	assertArrayEquals(asymChainListTest, asymChainList);
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Find all of the inter group bonds in a structure
 * @param pdbId the pdb id of the structure to determine
 * @return the number of inter group bonds (double counted) in a structure
 * @throws IOException
 * @throws StructureException
 */
public int getInterBonds(String pdbId) throws IOException, StructureException{
	AtomCache cache = new AtomCache();
	cache.setUseMmCif(true);
	cache.setFetchBehavior(FetchBehavior.FETCH_FILES);
	FileParsingParameters params = cache.getFileParsingParams();
	params.setCreateAtomBonds(true);
	params.setAlignSeqRes(true);
	params.setParseBioAssembly(true);
	DownloadChemCompProvider dcc = new DownloadChemCompProvider();
	ChemCompGroupFactory.setChemCompProvider(dcc);
	dcc.checkDoFirstInstall();
	cache.setFileParsingParams(params);
	StructureIO.setAtomCache(cache);
	int counter =0;
	// Now get the structure
	Structure newStruc = StructureIO.getStructure(pdbId);
	// Now loop through the atoms
	for(Chain c: newStruc.getChains()){
		for(Group g: c.getAtomGroups()){
			List<Atom> theseAtoms = g.getAtoms();
			for(Atom a: theseAtoms){
				List<Bond> theseBonds = a.getBonds();
				if(theseBonds != null){
					for(Bond b: a.getBonds()){
						Atom other = b.getOther(a);
						int indexOther = theseAtoms.indexOf(other);
						// Check if the index is within the group
						if(indexOther<0 || indexOther >= theseAtoms.size()){
							counter++;
						}
					}
				}
			}
		}
	}
	return counter;
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
private void checkChains(Structure s) {
	for (Chain chain:s.getChains()) {
		int seqResLength = chain.getSeqResLength();
		int atomLength = chain.getAtomLength();
		System.out.println("chain "+chain.getId()+", atomLength: "+atomLength+", seqResLength: "+seqResLength);
		//assertTrue("atom length ("+atomLength+") should be smaller than seqResLength ("+seqResLength+")",atomLength<=seqResLength);
		System.out.println("seq res groups size: "+chain.getSeqResGroups().size());
	}
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Scan through SeqResGroups, returns true if any have Atoms.
 * @param s
 * @return
 */
public boolean doSeqResHaveAtoms(Structure s) {
	for (int i = 0; i < s.nrModels(); i++) {
		for (Chain c : s.getChains(i)) {
			for (Group g : c.getSeqResGroups()) {
				if (hasAtoms(g)) return true; // Found some Atoms in a Seqres group.
			}
		}
	}

	return false;
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
public List<ModifiedCompound> testXMLSerialization(String pdbId){
	String xml = null;
	ModifiedCompound currentMC = null;
	List<ModifiedCompound> all = new ArrayList<ModifiedCompound>();
	try {

		Structure struc = TmpAtomCache.cache.getStructure(pdbId);

		ProteinModificationIdentifier parser = new ProteinModificationIdentifier();

		for (Chain c : struc.getChains()) {

			parser.identify(c, ProteinModificationRegistry.allModifications());
			Set<ModifiedCompound> mcs = parser.getIdentifiedModifiedCompound();

			for (ModifiedCompound mc : mcs){
				currentMC = mc;
				xml =  doXMLSerialization(mc) ;
				//logger.info( pdbId + " got XML: " + String.format("%n") + xml);
				ModifiedCompound newMC = getModifiedCompoundFromXML(xml);
				String xml2 = doXMLSerialization(newMC);
				assertEquals(xml,xml2);
				//logger.info(xml2);
				//assertEquals("The two objects are not equal before and after XML serialization" , mc, newMC);
				//logger.info(mc.getDescription());
				//logger.info(newMC.getDescription());
				all.add(mc);
			}
		}
	} catch (Exception e){
		logger.error(e.getMessage(),e);
		logger.error("Error when serializing {}", pdbId);
		logger.error(currentMC.getDescription());
		logger.error(xml, e);
		fail(e.getMessage());
	}
	xml = null;
	currentMC =null;
	return all;
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Pass data from Biojava structure  to another generic output type. Loops through the data 
 * structure and calls all the set functions.
 * @param structure the input {@link Structure} to write
 * @param dataTransferInterface the generic interface that 
 * implements all the set methods.
 */
public MmtfStructureWriter(Structure structure, StructureAdapterInterface dataTransferInterface) {
	this.mmtfDecoderInterface = dataTransferInterface;
	// Reset structure to consider altloc groups with the same residue number but different group names as seperate groups
	MmtfUtils.fixMicroheterogenity(structure);
	// Get the chain name to index map
	MmtfSummaryDataBean mmtfSummaryDataBean = MmtfUtils.getStructureInfo(structure);
	Map<String, Integer> chainIdToIndexMap = mmtfSummaryDataBean.getChainIdToIndexMap();
	List<Atom> allAtoms = mmtfSummaryDataBean.getAllAtoms();
	int numBonds = mmtfSummaryDataBean.getNumBonds();
	List<Chain> allChains = mmtfSummaryDataBean.getAllChains();
	mmtfDecoderInterface.initStructure(numBonds, allAtoms.size(), MmtfUtils.getNumGroups(structure), allChains.size(), structure.nrModels(), structure.getPDBCode());
	// Generate the secondary structure
	MmtfUtils.calculateDsspSecondaryStructure(structure);
	// Get the header and the xtal info.
	PDBHeader pdbHeader = structure.getPDBHeader();
	PDBCrystallographicInfo xtalInfo = pdbHeader.getCrystallographicInfo();
	mmtfDecoderInterface.setHeaderInfo(pdbHeader.getRfree(), pdbHeader.getRwork(), pdbHeader.getResolution(), pdbHeader.getTitle(), MmtfUtils.dateToIsoString(pdbHeader.getDepDate()), 
			MmtfUtils.dateToIsoString(pdbHeader.getRelDate()), MmtfUtils.techniquesToStringArray(pdbHeader.getExperimentalTechniques()));
	mmtfDecoderInterface.setXtalInfo(MmtfUtils.getSpaceGroupAsString(xtalInfo.getSpaceGroup()), MmtfUtils.getUnitCellAsArray(xtalInfo), MmtfUtils.getNcsAsArray(xtalInfo.getNcsOperators()));
	// Store the bioassembly data
	storeBioassemblyInformation(chainIdToIndexMap, pdbHeader.getBioAssemblies());
	// Store the entity data
	storeEntityInformation(allChains, structure.getEntityInfos());
	// Now loop through the data structure
	for (int modelIndex=0; modelIndex<structure.nrModels(); modelIndex++) {
		List<Chain> modelChains = structure.getChains(modelIndex);
		// Set this model
		mmtfDecoderInterface.setModelInfo(modelIndex, modelChains.size());
		for(int chainInModelIndex=0; chainInModelIndex<modelChains.size(); chainInModelIndex++) {
			Chain chain = modelChains.get(chainInModelIndex);
			List<Group> groups = chain.getAtomGroups();
			List<Group> sequenceGroups = chain.getSeqResGroups();
			mmtfDecoderInterface.setChainInfo(chain.getId(), chain.getName(), groups.size());
			for(int groupInChainIndex=0; groupInChainIndex<groups.size(); groupInChainIndex++){
				Group group = groups.get(groupInChainIndex);
				List<Atom> atomsInGroup = MmtfUtils.getAtomsForGroup(group);
				ChemComp chemComp = group.getChemComp();
				Character insCode = group.getResidueNumber().getInsCode();
				if(insCode==null || insCode.equals(' ')){
					insCode=MmtfStructure.UNAVAILABLE_CHAR_VALUE;
				}
				char singleLetterCode = 'X';
				if (chemComp.getOne_letter_code().length()==1){
					singleLetterCode = chemComp.getOne_letter_code().charAt(0);
				}
				mmtfDecoderInterface.setGroupInfo(group.getPDBName(), group.getResidueNumber().getSeqNum(), insCode.charValue(), 
						chemComp.getType().toUpperCase(), atomsInGroup.size(), MmtfUtils.getNumBondsInGroup(atomsInGroup), singleLetterCode,
						sequenceGroups.indexOf(group), MmtfUtils.getSecStructType(group));
				for (Atom atom : atomsInGroup){
					char altLoc = MmtfStructure.UNAVAILABLE_CHAR_VALUE;
					if(atom.getAltLoc()!=null){
						if(atom.getAltLoc().charValue()!=' '){
							altLoc=atom.getAltLoc().charValue();
						}
					}
					mmtfDecoderInterface.setAtomInfo(atom.getName(), atom.getPDBserial(), altLoc, (float) atom.getX(), 
							(float) atom.getY(), (float) atom.getZ(), atom.getOccupancy(), 
							atom.getTempFactor(), atom.getElement().toString(), atom.getCharge());
					addBonds(atom, atomsInGroup, allAtoms);
				}
			}
		}
	}
	mmtfDecoderInterface.finalizeStructure();

}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
/**
 * Function to add the charges to a given structure.
 */
public static void addCharges(Structure structure) {
	// Loop through the models
	for(int i=0; i<structure.nrModels(); i++){
		for(Chain c: structure.getChains(i)){
			for(Group g: c.getAtomGroups()){
				ChemComp thisChemComp = ChemCompGroupFactory.getChemComp(g.getPDBName());
				List<ChemCompAtom> chemAtoms = thisChemComp.getAtoms();
				for(ChemCompAtom chemCompAtom : chemAtoms) {
					Atom atom = g.getAtom(chemCompAtom.getAtom_id());	
					String stringCharge = chemCompAtom.getCharge();
					short shortCharge = 0;
					if (stringCharge!=null){
						if(!stringCharge.equals("?")){
							try{
								shortCharge = Short.parseShort(stringCharge);
							}
							catch(NumberFormatException e){
								logger.warn("Number format exception. Parsing '"+stringCharge+"' to short");
							}
						}
						else{
							logger.warn("? charge on atom "+chemCompAtom.getAtom_id()+" in group "+thisChemComp.getId());
						}
					}
					else{
						logger.warn("Null charge on atom "+chemCompAtom.getAtom_id()+" in group "+thisChemComp.getId());
					}
					if(atom!=null){
						atom.setCharge(shortCharge);
					}
					// Now do the same for alt locs
					for (Group altLoc : g.getAltLocs()) {
						Atom altAtom = altLoc.getAtom(chemCompAtom.getAtom_id());
						if(altAtom!=null){
							altAtom.setCharge(shortCharge);
						}
					}
				}
			}

		}
	}
}
 

import org.biojava.nbio.structure.Structure; //导入方法依赖的package包/类
@Test	
public void testEntityId() throws IOException, StructureException {
	
	// Set up the atom cache to parse on Internal chain id
	AtomCache cache = new AtomCache();
	cache.setUseMmCif(true);
	FileParsingParameters params = cache.getFileParsingParams();

	DownloadChemCompProvider cc = new DownloadChemCompProvider();
	ChemCompGroupFactory.setChemCompProvider(cc);
	cc.checkDoFirstInstall();
	cache.setFileParsingParams(params);
	StructureIO.setAtomCache(cache);
	// This is hte information we want to test against
	String[] typeInformation = new String[] {"POLYMER", "NONPOLYMER", "NONPOLYMER", "NONPOLYMER", "NONPOLYMER", "WATER"};
	String[] descriptionInformation = new String[] {"BROMODOMAIN ADJACENT TO ZINC FINGER DOMAIN PROTEIN 2B","4-Fluorobenzamidoxime",  "METHANOL", "METHANOL", "METHANOL", "water"};	
	
	// Now some other information fields to test this data is collated correctly
	String[] geneSourceSciName = new String[] {"HOMO SAPIENS", null, null, null, null, null};
	String[] geneSourceTaxId = new String[] {"9606", null, null, null, null, null};
	String[] hostOrganismSciName = new String[] {"ESCHERICHIA COLI", null, null, null, null, null};
	String[] hostOrganismTaxId = new String[] {"469008", null, null, null, null, null};		

	
	
	/// TODO GET ALL THE ENTITY INFORMATION REQUIRED FOR 4CUP 
	// Get this structure
	Structure bioJavaStruct = StructureIO.getStructure("4cup");
	String[] testTypeInfo = new String[6];
	String[] testDescInfo = new String[6];
	
	
	String[] testGeneSourceSciName = new String[6];
	String[] testGeneSourceTaxId = new String[6];
	String[] testHostOrganismSciName = new String[6];
	String[] testHostOrganismTaxId = new String[6];

	// Now loop through the structure
	int chainCounter = 0;
	for (Chain c: bioJavaStruct.getChains()) {
		// Now get the entity information we want to test
		EntityInfo thisCmpd = c.getEntityInfo();
		testTypeInfo[chainCounter] = thisCmpd.getType().toString();
		testDescInfo[chainCounter] = thisCmpd.getDescription();
		testGeneSourceSciName[chainCounter] =  thisCmpd.getOrganismScientific();
		testGeneSourceTaxId[chainCounter] = thisCmpd.getOrganismTaxId();
		testHostOrganismSciName[chainCounter] = thisCmpd.getExpressionSystem();
		testHostOrganismTaxId[chainCounter] = thisCmpd.getExpressionSystemTaxId();

		chainCounter++;
	}
	// Now check they're both the same
	assertArrayEquals(descriptionInformation, testDescInfo);
	assertArrayEquals(typeInformation, testTypeInfo);
	// Now check these work too
	assertArrayEquals(geneSourceSciName, testGeneSourceSciName);
	assertArrayEquals(geneSourceTaxId, testGeneSourceTaxId);
	assertArrayEquals(hostOrganismSciName, testHostOrganismSciName);
	assertArrayEquals(hostOrganismTaxId, testHostOrganismTaxId);

	
	
}