// from biojava structure, convert to own user model
public void createUserModel(Structure struc) {
// read default MMFFtypes for atoms
if (modelList == null) modelList = new ArrayList<Model>();
Model model = null;
for (int i = 0; i < struc.nrModels(); i++) {
// for each model, create and add to model list
model = new Model();
model.setModelName("Model" + (i + 1));
model.setMolecule(struc.getModel(i)); // set the model
modelList.add(model);
}
}
public void loadStructureIO() {
try {
Structure s1 = StructureIO.getStructure("1gav");
System.out.println(s1.getPDBCode() + " asym unit has nr atoms:");
System.out.println(StructureTools.getNrAtoms(s1));
Structure s2 = StructureIO.getBiologicalAssembly("1gav");
System.out.println(s2.getPDBCode() + " biological assembly has nr atoms:");
System.out.println(StructureTools.getNrAtoms(s2));
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* Identify a set of modifications in a structure.
*
* @param structure query {@link Structure}.
* @param potentialModifications query {@link ProteinModification}s.
*/
public void identify(
final Structure structure, final Set<ProteinModification> potentialModifications) {
if (structure == null) {
throw new IllegalArgumentException("Null structure.");
}
identify(structure.getChains(), potentialModifications);
}
public void basicLoad() {
try {
PDBFileReader reader = new PDBFileReader();
// the path to the local PDB installation
reader.setPath("/tmp");
// are all files in one directory, or are the files split,
// as on the PDB ftp servers?
reader.setPdbDirectorySplit(true);
// should a missing PDB id be fetched automatically from the FTP servers?
reader.setAutoFetch(true);
// configure the parameters of file parsing
FileParsingParameters params = new FileParsingParameters();
// should the ATOM and SEQRES residues be aligned when creating the internal data model?
params.setAlignSeqRes(true);
// should secondary structure get parsed from the file
params.setParseSecStruc(false);
reader.setFileParsingParameters(params);
Structure structure = reader.getStructureById("4hhb");
System.out.println(structure);
Chain c = structure.getChainByPDB("C");
System.out.print(c);
System.out.println(c.getHeader());
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String[] args) {
try {
FileParsingParameters params = new FileParsingParameters();
params.setParseSecStruc(true);
AtomCache cache = new AtomCache();
cache.setFileParsingParams(params);
Structure s = cache.getStructure("4hhb");
for (Chain c : s.getChains()) {
for (Group g : c.getAtomGroups()) {
if (g instanceof AminoAcid) {
AminoAcid aa = (AminoAcid) g;
Map<String, String> sec = aa.getSecStruc();
System.out.println(
c.getChainID()
+ " "
+ g.getResidueNumber()
+ " "
+ g.getPDBName()
+ " "
+ " "
+ sec);
}
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
private void runSCOPTests() {
ScopDatabase scop = ScopFactory.getSCOP();
List<ScopDomain> domains = scop.getDomainsForPDB("4HHB");
assertTrue(domains.size() == 4);
// test case sensitivity;
List<ScopDomain> domains2 = scop.getDomainsForPDB("4hhb");
assertTrue(domains2.size() == domains.size());
// System.out.println(domains);
String scop1m02 =
"d1m02a_ 1m02 A: k.36.1.1 74353 cl=58788,cf=75796,sf=75797,fa=75798,dm=75799,sp=75800,px=74353";
List<ScopDomain> domains1m02 = scop.getDomainsForPDB("1m02");
assertTrue(domains1m02.size() == 1);
ScopDomain d1 = domains1m02.get(0);
assertNotNull(d1);
assertEquals(
"The toString() methods for ScopDomains don't match the scop display",
d1.toString(),
scop1m02);
List<ScopDomain> domains1cdg = scop.getDomainsForPDB("1CDG");
assertTrue(domains1cdg.size() == 4);
ScopDomain d2 = domains1cdg.get(0);
AtomCache cache = new AtomCache();
try {
Structure s = cache.getStructureForDomain(d2);
// checkRange(s,"A:496-581");
// now with ligands!
checkRange(s, "A:496-692");
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
// check a domain with multiple ranges
List<ScopDomain> domains1xzp = scop.getDomainsForPDB("1xzp");
assertTrue(domains1xzp.size() == 4);
try {
Structure s = cache.getStructureForDomain(domains1xzp.get(0));
Chain a = s.getChainByPDB("A");
// now with ligands...
assertEquals(a.getAtomGroups().size(), 176);
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
// check insertion codes
List<ScopDomain> domains2bq6 = scop.getDomainsForPDB("2bq6");
assertTrue(domains2bq6.size() == 2);
ScopDomain target = scop.getDomainByScopID("d2bq6a1");
assertNotNull(target);
try {
Structure s = cache.getStructureForDomain(target);
Chain a = s.getChainByPDB("A");
assertEquals(a.getAtomGroups().size(), 52);
checkRange(s, "A:1A-49");
} catch (Exception e) {
e.printStackTrace();
fail(e.getMessage());
}
}
/**
* Identify a set of modifications in a a list of chains.
*
* @param chains query {@link Chain}s.
* @param potentialModifications query {@link ProteinModification}s.
*/
public void identify(
final List<Chain> chains, final Set<ProteinModification> potentialModifications) {
if (chains == null) {
throw new IllegalArgumentException("Null structure.");
}
if (potentialModifications == null) {
throw new IllegalArgumentException("Null potentialModifications.");
}
reset();
if (potentialModifications.isEmpty()) {
return;
}
Map<String, Chain> mapChainIdChain = new HashMap<String, Chain>(chains.size());
residues = new ArrayList<Group>();
List<Group> ligands = new ArrayList<Group>();
Map<Component, Set<Group>> mapCompGroups = new HashMap<Component, Set<Group>>();
for (Chain chain : chains) {
mapChainIdChain.put(chain.getChainID(), chain);
List<Group> ress = StructureUtil.getAminoAcids(chain);
// List<Group> ligs = chain.getAtomLigands();
List<Group> ligs = StructureTools.filterLigands(chain.getAtomGroups());
residues.addAll(ress);
residues.removeAll(ligs);
ligands.addAll(ligs);
addModificationGroups(potentialModifications, ress, ligs, mapCompGroups);
}
if (residues.isEmpty()) {
String pdbId = "?";
if (chains.size() > 0) {
Structure struc = chains.get(0).getParent();
if (struc != null) pdbId = struc.getPDBCode();
}
System.err.println(
"WARNING: no amino acids found for "
+ pdbId
+ ". Either you did not parse the PDB file with alignSEQRES records, or this record does not contain any amino acids.");
}
List<ModifiedCompound> modComps = new ArrayList<ModifiedCompound>();
for (ProteinModification mod : potentialModifications) {
ModificationCondition condition = mod.getCondition();
List<Component> components = condition.getComponents();
if (!mapCompGroups.keySet().containsAll(components)) {
// not all components exist for this mod.
continue;
}
int sizeComps = components.size();
if (sizeComps == 1) {
processCrosslink1(mapCompGroups, modComps, mod, components);
} else {
processMultiCrosslink(mapCompGroups, modComps, mod, condition);
}
}
if (recordAdditionalAttachments) {
// identify additional groups that are not directly attached to amino acids.
for (ModifiedCompound mc : modComps) {
identifyAdditionalAttachments(mc, ligands, mapChainIdChain);
}
}
mergeModComps(modComps);
identifiedModifiedCompounds.addAll(modComps);
// record unidentifiable linkage
if (recordUnidentifiableModifiedCompounds) {
recordUnidentifiableAtomLinkages(modComps, ligands);
recordUnidentifiableModifiedResidues(modComps);
}
}