int main () {
//PDBFile pdb ("quartz_100_short.pdb");
PDBFile pdb ("beta-cristobalite.pdb");
// create the quartz unitcell
Molecule * uc = pdb.Molecules(0);
//make copies of the quartz unitcell and shift them around
//VecR x_shift (4.91, 0.0, 0.0);
VecR x_shift (10.0, 0.0, 0.0);
VecR y_shift (0.0, 10.0, 0.0);
VecR z_shift (0.0, 0.0, 0.0);
// Create the slab by creating and shifting copies of the unit cell
Mol_ptr_vec mols = UnitCellToSlab(uc, x_shift, y_shift, z_shift);
Molecule * mol = MakeSingleMolecule (mols);
//AddDanglingHydrogens (mol);
// Take care of renaming the atoms and the residue before printing it out
FixSingleMoleculeNaming (mol);
PrintMoleculePDB (mol);
return 0;
}
int main () {
PDBFile pdb ("temp.pdb");
Molecule * mol = pdb.Molecules(0);
mol->Name("qtz");
std::vector<Atom *> atoms = mol->Atoms();
/* cycle through each atom in order of the pdb file */
RUN (atoms)
{
Atom * atom = atoms[i];
atom->Residue("qtz");
VecR pos = atom->Position();
/* find the surface Oxygens */
if (atom->Name().find("O") != string::npos && pos[z] > -7.9)
{
/* add H's to the surface */
Atom * h = new Atom ("H", pos + VecR (0.0, 0.0, 1.1));
mol->AddAtom(h);
}
}
std::vector<Molecule *> mols;
mols.push_back(mol);
PDBFile::WritePDB(mols);
}
static void dumpStreamData(ScopedPrinter &P, PDBFile &File) {
uint32_t StreamCount = File.getNumStreams();
StringRef DumpStreamStr = opts::DumpStreamData;
uint32_t DumpStreamNum;
if (DumpStreamStr.getAsInteger(/*Radix=*/0U, DumpStreamNum) ||
DumpStreamNum >= StreamCount)
return;
uint32_t StreamBytesRead = 0;
uint32_t StreamSize = File.getStreamByteSize(DumpStreamNum);
auto StreamBlocks = File.getStreamBlockList(DumpStreamNum);
for (uint32_t StreamBlockAddr : StreamBlocks) {
uint32_t BytesLeftToReadInStream = StreamSize - StreamBytesRead;
if (BytesLeftToReadInStream == 0)
break;
uint32_t BytesToReadInBlock = std::min(
BytesLeftToReadInStream, static_cast<uint32_t>(File.getBlockSize()));
auto StreamBlockData =
File.getBlockData(StreamBlockAddr, BytesToReadInBlock);
outs() << StreamBlockData;
StreamBytesRead += StreamBlockData.size();
}
}
static bool diffAndPrint(StringRef Label, PDBFile &File1, PDBFile &File2, T V1,
T V2) {
if (V1 == V2) {
outs() << formatv(" {0}: No differences detected!\n", Label);
return false;
}
outs().indent(2) << Label << "\n";
outs().indent(4) << formatv("{0}: {1}\n", File1.getFilePath(), V1);
outs().indent(4) << formatv("{0}: {1}\n", File2.getFilePath(), V2);
return true;
}
static void dumpStreamSizes(ScopedPrinter &P, PDBFile &File) {
if (!opts::DumpStreamSizes)
return;
ListScope L(P, "StreamSizes");
uint32_t StreamCount = File.getNumStreams();
for (uint32_t StreamIdx = 0; StreamIdx < StreamCount; ++StreamIdx) {
std::string Name("Stream ");
Name += to_string(StreamIdx);
P.printNumber(Name, File.getStreamByteSize(StreamIdx));
}
}
static void dumpStreamBlocks(ScopedPrinter &P, PDBFile &File) {
if (!opts::DumpStreamBlocks)
return;
ListScope L(P, "StreamBlocks");
uint32_t StreamCount = File.getNumStreams();
for (uint32_t StreamIdx = 0; StreamIdx < StreamCount; ++StreamIdx) {
std::string Name("Stream ");
Name += to_string(StreamIdx);
auto StreamBlocks = File.getStreamBlockList(StreamIdx);
P.printList(Name, StreamBlocks);
}
}
static bool diffAndPrint(StringRef Label, PDBFile &File1, PDBFile &File2,
ArrayRef<T> V1, ArrayRef<T> V2) {
if (V1 == V2) {
outs() << formatv(" {0}: No differences detected!\n", Label);
return false;
}
outs().indent(2) << Label << "\n";
outs().indent(4) << formatv("{0}: {1}\n", File1.getFilePath(),
make_range(V1.begin(), V1.end()));
outs().indent(4) << formatv("{0}: {1}\n", File2.getFilePath(),
make_range(V2.begin(), V2.end()));
return true;
}
static void dumpNamedStream(ScopedPrinter &P, PDBFile &File, StringRef Stream) {
InfoStream &IS = File.getPDBInfoStream();
uint32_t NameStreamIndex = IS.getNamedStreamIndex(Stream);
if (NameStreamIndex != 0) {
std::string Name("Stream '");
Name += Stream;
Name += "'";
DictScope D(P, Name);
P.printNumber("Index", NameStreamIndex);
MappedBlockStream NameStream(NameStreamIndex, File);
StreamReader Reader(NameStream);
NameHashTable NameTable;
NameTable.load(Reader);
P.printHex("Signature", NameTable.getSignature());
P.printNumber("Version", NameTable.getHashVersion());
P.printNumber("Name Count", NameTable.getNameCount());
ListScope L(P, "Names");
for (uint32_t ID : NameTable.name_ids()) {
StringRef Str = NameTable.getStringForID(ID);
if (!Str.empty())
P.printString(Str);
}
}
}
static void dumpInfoStream(ScopedPrinter &P, PDBFile &File) {
InfoStream &IS = File.getPDBInfoStream();
DictScope D(P, "PDB Stream");
P.printNumber("Version", IS.getVersion());
P.printHex("Signature", IS.getSignature());
P.printNumber("Age", IS.getAge());
P.printObject("Guid", IS.getGuid());
}
static void dumpFileHeaders(ScopedPrinter &P, PDBFile &File) {
if (!opts::DumpHeaders)
return;
DictScope D(P, "FileHeaders");
P.printNumber("BlockSize", File.getBlockSize());
P.printNumber("Unknown0", File.getUnknown0());
P.printNumber("NumBlocks", File.getBlockCount());
P.printNumber("NumDirectoryBytes", File.getNumDirectoryBytes());
P.printNumber("Unknown1", File.getUnknown1());
P.printNumber("BlockMapAddr", File.getBlockMapIndex());
P.printNumber("NumDirectoryBlocks", File.getNumDirectoryBlocks());
P.printNumber("BlockMapOffset", File.getBlockMapOffset());
// The directory is not contiguous. Instead, the block map contains a
// contiguous list of block numbers whose contents, when concatenated in
// order, make up the directory.
P.printList("DirectoryBlocks", File.getDirectoryBlockArray());
P.printNumber("NumStreams", File.getNumStreams());
}
static bool printSymmetricDifferences(PDBFile &File1, PDBFile &File2,
T &&OnlyRange1, T &&OnlyRange2,
StringRef Label) {
bool HasDiff = false;
if (!OnlyRange1.empty()) {
HasDiff = true;
outs() << formatv(" {0} {1}(s) only in ({2})\n", OnlyRange1.size(), Label,
File1.getFilePath());
for (const auto &Item : OnlyRange1)
outs() << formatv(" {0}\n", Label, Item);
}
if (!OnlyRange2.empty()) {
HasDiff = true;
outs() << formatv(" {0} {1}(s) only in ({2})\n", OnlyRange2.size(),
File2.getFilePath());
for (const auto &Item : OnlyRange2)
outs() << formatv(" {0}\n", Item);
}
return HasDiff;
}
int main () {
// The unitcell's PDB file - must have a "TER" after the residue
PDBFile pdb ("octadecane.pdb");
string name = "odn";
double spacing = 5.528; // inter-chain spacing
GridParams params (pdb.Molecules(0), name, spacing, 7, 1, 6);
// Create the slab by creating and shifting copies of the unit cell
Mol_ptr_vec mols = UnitCellToSlab(params);
//Molecule * mol = MakeSingleMolecule (params);
//AddDanglingHydrogens (params);
// Take care of renaming the atoms and the residue before printing it out
//FixSingleMoleculeNaming (params);
PrintMoleculesPDB (mols);
return 0;
}
int main () {
PDBFile pdb ("octadecane.pdb");
//MDSystem::Dimensions(VecR(29.868, 100.0, 27.792));
Atom_ptr_vec& atoms = pdb.Atoms();
printf ("!entry.xxx.unit.connectivity table int atom1x int atom2x int flags\n");
/* cycle through each atom in order of the pdb file */
for (int i = 0; i != atoms.size() - 1; i++)
{
for (int j = i+1; j != atoms.size(); j++)
{
//double distance = MDSystem::Distance(atoms[i],atoms[j]).Magnitude();
double distance = (atoms[i]->Position() - atoms[j]->Position()).Magnitude();
if (distance < 1.7)
{
printf (" %d %d 1\n", i+1, j+1);
}
}
}
return 0;
}
static void dumpDbiStream(ScopedPrinter &P, PDBFile &File) {
DbiStream &DS = File.getPDBDbiStream();
DictScope D(P, "DBI Stream");
P.printNumber("Dbi Version", DS.getDbiVersion());
P.printNumber("Age", DS.getAge());
P.printBoolean("Incremental Linking", DS.isIncrementallyLinked());
P.printBoolean("Has CTypes", DS.hasCTypes());
P.printBoolean("Is Stripped", DS.isStripped());
P.printObject("Machine Type", DS.getMachineType());
P.printNumber("Number of Symbols", DS.getNumberOfSymbols());
uint16_t Major = DS.getBuildMajorVersion();
uint16_t Minor = DS.getBuildMinorVersion();
P.printVersion("Toolchain Version", Major, Minor);
std::string DllName;
raw_string_ostream DllStream(DllName);
DllStream << "mspdb" << Major << Minor << ".dll version";
DllStream.flush();
P.printVersion(DllName, Major, Minor, DS.getPdbDllVersion());
ListScope L(P, "Modules");
for (auto &Modi : DS.modules()) {
DictScope DD(P);
P.printString("Name", Modi.Info.getModuleName());
P.printNumber("Debug Stream Index", Modi.Info.getModuleStreamIndex());
P.printString("Object File Name", Modi.Info.getObjFileName());
P.printNumber("Num Files", Modi.Info.getNumberOfFiles());
P.printNumber("Source File Name Idx", Modi.Info.getSourceFileNameIndex());
P.printNumber("Pdb File Name Idx", Modi.Info.getPdbFilePathNameIndex());
P.printNumber("Line Info Byte Size", Modi.Info.getLineInfoByteSize());
P.printNumber("C13 Line Info Byte Size",
Modi.Info.getC13LineInfoByteSize());
P.printNumber("Symbol Byte Size", Modi.Info.getSymbolDebugInfoByteSize());
P.printNumber("Type Server Index", Modi.Info.getTypeServerIndex());
P.printBoolean("Has EC Info", Modi.Info.hasECInfo());
std::string FileListName =
to_string(Modi.SourceFiles.size()) + " Contributing Source Files";
ListScope LL(P, FileListName);
for (auto File : Modi.SourceFiles)
P.printString(File);
}
}
static void dumpTpiStream(ScopedPrinter &P, PDBFile &File) {
if (!opts::DumpTypeStream)
return;
DictScope D(P, "Type Info Stream");
TpiStream &Tpi = File.getPDBTpiStream();
P.printNumber("TPI Version", Tpi.getTpiVersion());
P.printNumber("Record count", Tpi.NumTypeRecords());
if (!opts::DumpTpiRecordBytes)
return;
ListScope L(P, "Records");
for (auto &Type : Tpi.types()) {
DictScope DD(P, "");
P.printHex("Kind", unsigned(Type.Leaf));
P.printBinaryBlock("Bytes", Type.LeafData);
}
}
Expected<std::unique_ptr<DbiStream>>
DbiStreamBuilder::build(PDBFile &File, const msf::WritableStream &Buffer) {
if (!VerHeader.hasValue())
return make_error<RawError>(raw_error_code::unspecified,
"Missing DBI Stream Version");
if (auto EC = finalize())
return std::move(EC);
auto StreamData = MappedBlockStream::createIndexedStream(File.getMsfLayout(),
Buffer, StreamDBI);
auto Dbi = llvm::make_unique<DbiStream>(File, std::move(StreamData));
Dbi->Header = Header;
Dbi->FileInfoSubstream = ReadableStreamRef(FileInfoBuffer);
Dbi->ModInfoSubstream = ReadableStreamRef(ModInfoBuffer);
if (auto EC = Dbi->initializeModInfoArray())
return std::move(EC);
if (auto EC = Dbi->initializeFileInfo())
return std::move(EC);
return std::move(Dbi);
}
Expected<std::unique_ptr<TpiStream>>
TpiStreamBuilder::build(PDBFile &File, const msf::WritableStream &Buffer) {
if (!VerHeader.hasValue())
return make_error<RawError>(raw_error_code::unspecified,
"Missing TPI Stream Version");
if (auto EC = finalize())
return std::move(EC);
auto StreamData =
MappedBlockStream::createIndexedStream(File.getMsfLayout(), Buffer, Idx);
auto Tpi = llvm::make_unique<TpiStream>(File, std::move(StreamData));
Tpi->Header = Header;
Tpi->TypeRecords = VarStreamArray<codeview::CVType>(TypeRecordStream);
if (HashValueStream) {
Tpi->HashStream = std::move(HashValueStream);
StreamReader HSR(*Tpi->HashStream);
if (auto EC = HSR.readArray(Tpi->HashValues, TypeRecords.size()))
return std::move(EC);
}
return std::move(Tpi);
}
YAMLOutputStyle::YAMLOutputStyle(PDBFile &File)
: File(File), Out(outs()), Obj(File.getAllocator()) {}
int main(int argc, char** argv)
{
if (argc != 3)
{
Log << "Usage:" << argv[0] << " <PDB infile> <PDB outfile> [<amber parameter file>]" << endl;
return 1;
}
System system;
PDBFile f;
f.open(argv[1]);
if (f.bad())
{
Log.error() << "cannot read PDB file " << argv[1] << endl;
return 2;
}
f >> system;
f.close();
FragmentDB db("");
// ResidueChecker check(db);
// system.apply(check);
db.normalize_names.setNamingStandard("Amber");
system.apply(db.normalize_names);
system.apply(db.build_bonds);
Size cyx_counter = 0;
Size hip_counter = 0;
ResidueIterator it = system.beginResidue();
for (; +it; ++it)
{
if (it->getFullName() == "CYS-S")
{
it->setName("CYX");
cyx_counter++;
}
if (it->getFullName() == "HIS")
{
it->setName("HIP");
hip_counter++;
}
}
if (cyx_counter > 0)
{
Log.info() << "Renamed " << cyx_counter << " residues from CYS-S to CYX"
<< endl;
}
if (hip_counter > 0)
{
Log.info() << "Renamed " << hip_counter << " residues from HIS to HIP"
<< endl;
}
PDBFile g;
g.open(argv[2], ios::out);
if (g.bad())
{
Log.error() << "cannot write PDB file " << argv[2] << endl;
return 2;
}
g << system;
g.close();
Log.info()
<< endl
<< "Conversion to AMBER naming scheme done. Please note that you might"
<< endl
<< "have to edit the resulting file by hand (if there are HIS or CYS"
<< endl
<< "residues in the original file, e. g.)"
<< endl
<< endl
<< "Good luck."
<< endl;
}
int main (int argc, char **argv)
{
// instantiate CommandlineParser object supplying
// - tool name
// - short description
// - version string
// - build date
// - category
CommandlineParser parpars("DockPoseClustering", "clusters docking poses ", VERSION, String(__DATE__), "Docking");
// we register an input file parameter
// - CLI switch
// - description
// - Inputfile
parpars.registerMandatoryInputFile("i_pdb", "input pdb-file");
parpars.registerOptionalInputFile("i_dcd", "input dcd-file");
///TODO: offer the alternatives in a more elegant way!
parpars.registerOptionalInputFile("i_trans", "or input transformation file for rigid rmsd clustering ");
// we register an output file parameter
// - CLI switch
// - description
// - parameter type
// - required
// - default value
// - hidden in galaxy
parpars.registerMandatoryOutputFile("o_index_list", "output file name for the index list ");
parpars.setParameterAsHidden("o_index_list");
parpars.registerOptionalOutputFile("o_score_matrix", "output file name for scoring matrix ");
parpars.setParameterAsHidden("o_score_matrix");
parpars.registerOptionalOutputFile("o_dcd", "output file name for the first cluster dcd file ");
parpars.setParameterAsHidden("o_dcd");
parpars.registerOptionalGalaxyOutputId("o_dcd_id", "output id ", "$o_dcd.id");
// need to be hidden in command line mode
parpars.setParameterAsAdvanced("o_dcd_id");
parpars.setParameterAsHidden("o_dcd_id");
parpars.registerOptionalGalaxyOutputFolder("o_dcd_dir", "output directory for 2nd to last cluster dcd file (if needed) ", "$__new_file_path__");
// need to be hidden in command line mode
parpars.setParameterAsAdvanced("o_dcd_dir");
parpars.setParameterAsHidden("o_dcd_dir");
// register String parameter for supplying minimal rmsd between clusters
parpars.registerOptionalDoubleParameter("rmsd_cutoff", "minimal rmsd between the final clusters (default 5.0) ", 5.0);
parpars.setParameterRestrictions("rmsd_cutoff", 0, 100);
// choice of cluster algorithm
parpars.registerOptionalStringParameter("alg", "algorithm used for clustering (CLINK_DEFAYS, CLINK_ALTHAUS, NEAREST_NEIGHBOR_CHAIN_WARD, SLINK_SIBSON, TRIVIAL_COMPLETE_LINKAGE) ", "CLINK_DEFAYS");
list<String> cluster_algs;
cluster_algs.push_back("CLINK_DEFAYS");
cluster_algs.push_back("CLINK_ALTHAUS");
cluster_algs.push_back("TRIVIAL_COMPLETE_LINKAGE");
cluster_algs.push_back("NEAREST_NEIGHBOR_CHAIN_WARD");
cluster_algs.push_back("SLINK_SIBSON");
parpars.setParameterRestrictions("alg", cluster_algs);
// choice of atom rmsd scope
parpars.registerOptionalStringParameter("scope", "atoms to be considered for scoreing a pose (C_ALPHA, BACKBONE, ALL_ATOMS) ", "C_ALPHA");
list<String> rmsd_levels;
rmsd_levels.push_back("C_ALPHA");
//rmsd_levels.push_back("HEAVY_ATOMS"); //TODO
rmsd_levels.push_back("BACKBONE");
rmsd_levels.push_back("ALL_ATOMS");
parpars.setParameterRestrictions("scope", rmsd_levels);
// choice of rmsd type
parpars.registerOptionalStringParameter("rmsd_type", "rmsd type used for clustering (SNAPSHOT_RMSD, RIGID_RMSD, CENTER_OF_MASS_DISTANCE) ", "SNAPSHOT_RMSD");
list<String> rmsd_types;
rmsd_types.push_back("SNAPSHOT_RMSD");
rmsd_types.push_back("RIGID_RMSD");
rmsd_types.push_back("CENTER_OF_MASS_DISTANCE");
parpars.setParameterRestrictions("rmsd_type", rmsd_types);
// further optional output parameters
parpars.registerOptionalOutputFile("o_red_dcd", "output file for the reduced cluster set (dcd with one structure per final cluster) ");
// write the final cluster tree in boost::serialize format, if it was computed
parpars.registerOptionalOutputFile("o_cluster_tree", "output file containing the cluster tree in boost::serialize format (if the tree was computed) ");
// register bool parameter for using pre-clustering
parpars.registerFlag("use_refinement", "Apply a second clustering run with different options (-refine_alg <string>, -refine_rmsd_type <string>, and -refine_rmsd_scope <string>)", false, true);
// refinement algorithm
parpars.registerOptionalStringParameter("refine_alg", "algorithm used for second clustering run (CLINK_DEFAYS, NEAREST_NEIGHBOR_CHAIN_WARD, SLINK_SIBSON, TRIVIAL_COMPLETE_LINKAGE) ", "CLINK_DEFAYS");
parpars.setParameterAsHidden("refine_alg");
parpars.setParameterRestrictions("refine_alg", cluster_algs);
// refinement rmsd type
parpars.registerOptionalStringParameter("refine_rmsd_type", "rmsd type used for second clustering run (SNAPSHOT_RMSD, RIGID_RMSD, CENTER_OF_MASS_DISTANCE) ", "SNAPSHOT_RMSD");
parpars.setParameterAsHidden("refine_rmsd_type");
parpars.setParameterRestrictions("refine_rmsd_type", rmsd_types);
// refinement rmsd scope
parpars.registerOptionalStringParameter("refine_rmsd_scope", "atoms to be considered for rmsd score in second clustering run (C_ALPHA, BACKBONE, ALL_ATOMS) ", "C_ALPHA");
parpars.setParameterAsHidden("refine_rmsd_scope");
parpars.setParameterRestrictions("refine_rmsd_scope", rmsd_levels);
// force serial execution, even if the algorithm supports parallel runs
parpars.registerFlag("run_serial", "force serial excecution, even if parallel execution would be supported by the algorithm", false, true);
// the manual
String man = "This tool computes clusters of docking poses given as conformation set or a list of rigid transformations.\n\nParameters are either the input ConformationSet (-i_dcd) and one corresponding pdb file (-i_pdb), or a transformation file (-i_trans). Output can be a cluster index list (-o_index_list), a cluster scoring matrix (-o_score_matrix), or dcd files per cluster (-o_dcd). Optional parameters are the algorithm (-alg), the minimal rmsd between the final clusters (-rmsd_cutoff), the rmsd type (-rmsd_type), and the type of atoms used for scoring a pose (-scope). The optional parameter -o_red_dcd sets the output file for the reduced cluster set (one representative per cluster). The optional parameter -o_cluster_tree specifies the output file for storing the cluster tree.\n\nOutput of this tool depends in the choice of the output parameters.";
parpars.setToolManual(man);
// here we set the types of I/O files
parpars.setSupportedFormats("i_dcd","dcd");
parpars.setSupportedFormats("i_pdb","pdb");
parpars.setSupportedFormats("i_trans","txt");
parpars.setSupportedFormats("o_index_list","txt");
parpars.setSupportedFormats("o_score_matrix","txt");
parpars.setSupportedFormats("o_dcd","dcd");
parpars.setSupportedFormats("o_red_dcd","dcd");
parpars.setSupportedFormats("o_cluster_tree","dat");
parpars.parse(argc, argv);
//////////////////////////////////////////////////
if (parpars.has("o_dcd"))
{
if (!parpars.has("o_dcd_dir") || !parpars.has("o_dcd_id"))
{
Log << "Output type \"dcd\" requires setting the options \"o_dir\" \"o_id\"! Abort!" << endl;
return 1;
}
}
if ( parpars.has("o_cluster_tree")
&& (!parpars.has("alg") || parpars.get("alg") != "NEAREST_NEIGHBOR_CHAIN_WARD"))
{
Log << "Output of cluster tree requires Ward algorithm! Abort!" << endl;
return 1;
}
// read the input
PDBFile pdb;
pdb.open(parpars.get("i_pdb"));
System sys;
pdb.read(sys);
ConformationSet cs;
cs.setup(sys);
if (parpars.has("i_dcd"))
{
cs.readDCDFile(parpars.get("i_dcd"));
}
cs.resetScoring();
PoseClustering pc;
if (parpars.has("i_trans"))
{
pc.setBaseSystemAndTransformations(sys, parpars.get("i_trans"));
}
if (parpars.has("rmsd_cutoff"))
{
float rmsd = parpars.get("rmsd_cutoff").toInt();
pc.options.setReal(PoseClustering::Option::DISTANCE_THRESHOLD, rmsd);
}
if (parpars.has("scope"))
{
String scope = parpars.get("scope");
if (scope == "C_ALPHA")
pc.options.set(PoseClustering::Option::RMSD_LEVEL_OF_DETAIL, PoseClustering::C_ALPHA);
else if (scope == "BACKBONE")
pc.options.set(PoseClustering::Option::RMSD_LEVEL_OF_DETAIL, PoseClustering::BACKBONE);
else if (scope == "ALL_ATOMS")
pc.options.set(PoseClustering::Option::RMSD_LEVEL_OF_DETAIL, PoseClustering::ALL_ATOMS);
else
Log.info() << "Unknown value " << scope << " for option scope." << endl;
}
if (parpars.has("alg"))
{
String alg = parpars.get("alg");
if (alg == "CLINK_DEFAYS")
pc.options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::CLINK_DEFAYS);
else if (alg == "CLINK_ALTHAUS")
pc.options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::CLINK_ALTHAUS);
else if (alg == "SLINK_SIBSON")
pc.options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::SLINK_SIBSON);
else if (alg == "TRIVIAL_COMPLETE_LINKAGE")
pc.options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::TRIVIAL_COMPLETE_LINKAGE);
else if (alg == "NEAREST_NEIGHBOR_CHAIN_WARD")
pc.options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::NEAREST_NEIGHBOR_CHAIN_WARD);
else
Log.info() << "Unknown value " << alg << " for option alg." << endl;
}
if (parpars.has("rmsd_type"))
{
String type = parpars.get("rmsd_type");
if (type == "SNAPSHOT_RMSD")
pc.options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::SNAPSHOT_RMSD);
else if (type == "RIGID_RMSD")
pc.options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::RIGID_RMSD);
else if (type == "CENTER_OF_MASS_DISTANCE")
{
pc.options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::CENTER_OF_MASS_DISTANCE);
Log << "Parameter scope will be ignored!" << endl;
}
else
Log.info() << "Unknown value " << type << " for option rmsd_type." << endl;
}
if (parpars.has("run_serial"))
{
pc.options.set(PoseClustering::Option::RUN_PARALLEL, false);
}
else
{
pc.options.set(PoseClustering::Option::RUN_PARALLEL, true);
}
if (parpars.has("i_dcd"))
{
pc.setConformationSet(&cs);
}
pc.compute();
// do we need a second clustering run?
if (parpars.has("use_refinement"))
{
// get the options
Options refine_options = pc.options;
if (parpars.has("refine_rmsd_scope"))
{
String scope = parpars.get("refine_rmsd_scope");
if (scope == "C_ALPHA")
refine_options.set(PoseClustering::Option::RMSD_LEVEL_OF_DETAIL, PoseClustering::C_ALPHA);
else if (scope == "BACKBONE")
refine_options.set(PoseClustering::Option::RMSD_LEVEL_OF_DETAIL, PoseClustering::BACKBONE);
else if (scope == "ALL_ATOMS")
refine_options.set(PoseClustering::Option::RMSD_LEVEL_OF_DETAIL, PoseClustering::ALL_ATOMS);
else
Log.info() << "Unknown value " << scope << " for option refine_rmsd_scope." << endl;
}
if (parpars.has("refine_alg"))
{
String alg = parpars.get("refine_alg");
if (alg == "CLINK_DEFAYS")
refine_options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::CLINK_DEFAYS);
else if (alg == "CLINK_ALTHAUS")
refine_options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::CLINK_ALTHAUS);
else if (alg == "SLINK_SIBSON")
refine_options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::SLINK_SIBSON);
else if (alg == "TRIVIAL_COMPLETE_LINKAGE")
refine_options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::TRIVIAL_COMPLETE_LINKAGE);
else if (alg == "NEAREST_NEIGHBOR_CHAIN_WARD")
refine_options.set(PoseClustering::Option::CLUSTER_METHOD, PoseClustering::NEAREST_NEIGHBOR_CHAIN_WARD);
else
Log.info() << "Unknown value " << alg << " for option refine_alg." << endl;
}
if (parpars.has("refine_rmsd_type"))
{
String type = parpars.get("refine_rmsd_type");
if (type == "SNAPSHOT_RMSD")
refine_options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::SNAPSHOT_RMSD);
else if (type == "RIGID_RMSD")
refine_options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::RIGID_RMSD);
else if (type == "CENTER_OF_MASS_DISTANCE")
{
refine_options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::CENTER_OF_MASS_DISTANCE);
Log << "Parameter scope will be ignored!" << endl;
}
else
Log.info() << "Unknown value " << type << " for option refine_rmsd_type." << endl;
}
pc.refineClustering(refine_options);
}
Size num_clusters = pc.getNumberOfClusters();
Log << "Computed " << num_clusters << " clusters, start writing..." << endl;
if (parpars.has("o_dcd"))
{
for (Size i = 0; i < num_clusters; i++)
{
Log << " Cluster " << i << " has " << pc.getClusterSize(i) << " members." << endl;
boost::shared_ptr<ConformationSet> new_cs = pc.getClusterConformationSet(i);
String outfile_name = (i == 0) ? String(parpars.get("o_dcd"))
: String(parpars.get("o_dcd_dir")) + "/primary_"
+ String(parpars.get("o_dcd_id")) + "_cluster" + String(i)
+ "_visible_dcd";
//Log << " Writing solution " << String(i) << " as " << outfile_name << endl;
new_cs->writeDCDFile(outfile_name);
}
}
if (parpars.has("o_index_list"))
{
String outfile_name = String(parpars.get("o_index_list"));
File cluster_outfile(outfile_name, std::ios::out);
pc.printClusters(cluster_outfile);
}
if (parpars.has("o_score_matrix"))
{
String outfile_name = String(parpars.get("o_score_matrix"));
File cluster_outfile(outfile_name, std::ios::out);
pc.printClusterScores(cluster_outfile);
}
// print
pc.printClusters();
pc.printClusterScores();
if (parpars.has("o_cluster_tree"))
{
File cluster_out(parpars.get("o_cluster_tree"), std::ios::out);
pc.serializeWardClusterTree(cluster_out, true);
cluster_out.close();
}
if (parpars.has("o_red_dcd"))
{
String outfile_name = String(parpars.get("o_red_dcd"));
boost::shared_ptr<ConformationSet> cs = pc.getReducedConformationSet();
cs->writeDCDFile(outfile_name);
}
Log << "done." << endl;
return 0;
}
int main(int argc, char* argv[])
{
FDPB fdpb;
// instantiate CommandlineParser object
CommandlineParser parpars("CalculateSolvationFreeEnergy", "calculate solvation free energy of a protein using AMBER ", VERSION, String(__DATE__), "ForceFields");
parpars.registerParameter("pdb", "input pdb file ", INFILE, true);
parpars.registerParameter("epsilon_medium", "dielectric constant in medium", DOUBLE, false, fdpb.options.getReal(FDPB::Option::SOLVENT_DC));
parpars.registerParameter("epsilon_vacuum", "dielectric constant in vacuum", DOUBLE, false, 1);
// the manual
String man = String("This tool computes the solvation free energy of a pdb file using the Jackson-Sternberg approach (bonded energy using a force field and a non bonded energy (electrostatics only) by solving the Poisson-Boltzmann equation. Parameters are the dielectric constants for the medium (-epsilon_medium) and the vacuum (-epsilon_vacuum).");
parpars.setToolManual(man);
parpars.setSupportedFormats("pdb", "pdb");
// parse the command line
parpars.parse(argc, argv);
PDBFile pdb;
pdb.open(parpars.get("pdb"), std::ios::in);
if (!pdb)
{
// if file does not exist: complain and abort
Log.error() << "error opening " << parpars.get("pdb") << " for input." << std::endl;
exit(2);
}
System sys;
pdb >> sys;
pdb.close();
// normalize the names and build all bonds
FragmentDB db("");
sys.apply(db.normalize_names);
sys.apply(db.build_bonds);
// TODO: Ask ResidueChecker if everything is ok! see tool CalculateEnergy
// create an AMBER force field without non-bonded interactions
AmberFF FF(sys);
// calculate the total energy
float total_energy = FF.updateEnergy();
//Log << FF.getResults() << std::endl;
//Log << " total energy using force field evaluation: " << total_energy << " kJ/mol" << std::endl;
//Log << "removing non bonded energy terms ..." << std::endl;
FF.removeComponent("Amber NonBonded");
// calculate the internal energy (neglecting internal VdW interactions)
float internal_energy = FF.updateEnergy();
//Log << FF.getResults() << std::endl;
Log << " internal energy: " << internal_energy << " kJ/mol" << std::endl;
// assign atom radii
AssignRadiusProcessor radius_processor("radii/PARSE.siz");
sys.apply(radius_processor);
// calculate the electrostatic part of the solvation energy
//FDPB fdpb;
float dielectric_const = fdpb.options.getReal(FDPB::Option::SOLVENT_DC);
if (parpars.has("epsilon_medium"))
dielectric_const = parpars.get("epsilon_medium").toFloat();
fdpb.options[FDPB::Option::SOLVENT_DC] = dielectric_const;
Log << "... using dielectric constant in medium: " << fdpb.options[FDPB::Option::SOLVENT_DC].toFloat() << std::endl;
fdpb.setup(sys);
fdpb.solve();
float solvent_energy = fdpb.getEnergy();
dielectric_const = 1.0;
if (parpars.has("epsilon_vacuum"))
dielectric_const = parpars.get("epsilon_vacuum").toFloat();
fdpb.options[FDPB::Option::SOLVENT_DC] = dielectric_const;
Log << "... using dielectric constant in vacuum: " << fdpb.options[FDPB::Option::SOLVENT_DC].toFloat() << std::endl;
fdpb.setup(sys);
fdpb.solve();
float vacuum_energy = fdpb.getEnergy();
Log << "\n electrostatic solvation free energy: " << solvent_energy - vacuum_energy << std::endl;
Log << "\n total energy using a combination of force field and FDPB evaluation: "
<< internal_energy - vacuum_energy + solvent_energy << " kJ/mol" << std::endl;
return 0;
}
int main(int argc, char* argv[])
{
// instantiate CommandlineParser object
CommandlineParser parpars("CalculateEnergy", "calculate free energy of a protein ", VERSION, String(__DATE__), "ForceFields");
parpars.registerMandatoryInputFile("pdb", "input pdb file ");
// TODO: offer upload of a distinguished fragDB file?
// choice of force field
parpars.registerOptionalStringParameter("force_field", "force field (AMBER, MMFF94)", "AMBER");
list<String> force_fields;
force_fields.push_back("AMBER");
force_fields.push_back("MMFF94");
// TODO: shall we offer CHARM as well?
parpars.setParameterRestrictions("force_field", force_fields);
// TODO: shall we offer a force field parameter file upload?
// TODO: check the naming!
parpars.registerOptionalDoubleParameter("non_bond_cutoff", "cutoff radius in calculations of nonbonded interactions", 20.0);
parpars.registerOptionalDoubleParameter("elec_stat_cuton", "electrostatic cuton", 13.0);
parpars.registerOptionalDoubleParameter("elec_stat_cutoff", "electrostatic cutoff", 15.0);
parpars.registerFlag("dist_dep_dielec", "apply distance dependent dielectric constant", false);
// NOTE: assign is the default
//parpars.registerFlag("assign_typenames","automatically assign type names to the system", false);
//parpars.registerFlag("assign_types","automatically assign types to the system if missing", false);
//parpars.registerFlag("assign_charges", "automatically assign charges to the system if missing", false);
// TODO: if we only allow PDBFile to upload then from where do we get stuff to overwrite??
parpars.registerFlag("overwrite_types", "overwrite even non-empty type names", false);
parpars.registerFlag("overwrite_charges","overwrite even non-zero charges", false);
// the manual
String man = String("This tool computes the free energy of a pdb file using a specified force field (-force_field) and force field parameters (-non_bond_cutoff, -elec_stat_cuton ... ).");
parpars.setToolManual(man);
parpars.setSupportedFormats("pdb", "pdb");
// parse the command line
parpars.parse(argc, argv);
PDBFile pdb;
pdb.open(parpars.get("pdb"), std::ios::in);
if (!pdb)
{
// if file does not exist: complain and abort
Log.error() << "error opening " << parpars.get("pdb") << " for input." << std::endl;
exit(2);
}
System sys;
pdb >> sys;
pdb.close();
// normalize the names and build all bonds
FragmentDB db("");
sys.apply(db.normalize_names);
sys.apply(db.build_bonds);
// check the structure
Log.info() << " checking residues..." << std::endl;
ResidueChecker rc(db);
sys.apply(rc);
if (!rc.getStatus())
{
Log.error() << "There are errors in the given structure. Use the ResidueChecker tool for further investigation." << std::endl;
exit(2);
}
// create a force field
AmberFF* amber_force_field = NULL;
MMFF94* mmff_force_field = NULL;
ForceField* force_field = NULL;
if (parpars.has("force_field"))
{
String penalty_table = parpars.get("force_field");
if (penalty_table == "AMBER")
{
amber_force_field = new AmberFF();
force_field = amber_force_field;
Log << " using the amber force field" << std::endl;
}
else if (penalty_table == "MMFF94")
{
mmff_force_field = new MMFF94();
force_field = mmff_force_field;
Log << " using the MMFF94 force field" << std::endl;
}
else
{
Log.error() << "Unknown force field " << parpars.get("force_field") << " Abort." << std::endl;
exit(2);
}
}
if (!amber_force_field && !mmff_force_field)
{
Log.error() << "Invalid force field. Abort." << std::endl;
exit(2);
}
// set the ff options according the parameters
float non_bonded_cutoff = 0;
if (parpars.has("non_bond_cutoff"))
{
non_bonded_cutoff = parpars.get("non_bond_cutoff").toFloat();
if (amber_force_field)
{
//TODO: something wents awfully wrong with the FF default options!
// cout << "non_bond_cutoff " << amber_force_field->options.getReal(AmberFF::Option::NONBONDED_CUTOFF) << " "<< amber_force_field->options.getReal(AmberFF::Default::NONBONDED_CUTOFF) << endl;
amber_force_field->options[AmberFF::Option::NONBONDED_CUTOFF] = non_bonded_cutoff;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::NONBONDED_CUTOFF] = non_bonded_cutoff;
}
Log << " used non bonded cutoff: " << non_bonded_cutoff << std::endl;
}
float elec_stat_cuton = 0;
if (parpars.has("elec_stat_cuton"))
{
elec_stat_cuton = parpars.get("elec_stat_cuton").toFloat();
if (amber_force_field)
{
// cout << "elec_stat_cuton" << force_field->options[AmberFF::Option::ELECTROSTATIC_CUTON] << endl;
amber_force_field->options[AmberFF::Option::ELECTROSTATIC_CUTON] = elec_stat_cuton;
}
else if (mmff_force_field)
{
// cout << "elec_stat_cuton" << force_field->options[MMFF94::Option::ELECTROSTATIC_CUTON] << endl;
mmff_force_field->options[MMFF94::Option::ELECTROSTATIC_CUTON] = elec_stat_cuton;
}
Log << " used electrostatic cuton: " << elec_stat_cuton << std::endl;
}
float elec_stat_cutoff = 0;
if (parpars.has("elec_stat_cutoff"))
{
elec_stat_cutoff = parpars.get("elec_stat_cutoff").toFloat();
if (amber_force_field)
{
amber_force_field->options[AmberFF::Option::ELECTROSTATIC_CUTOFF] = elec_stat_cutoff;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::ELECTROSTATIC_CUTOFF] = elec_stat_cutoff;
}
Log << " used electrostatic cutoff: " << elec_stat_cutoff << std::endl;
}
bool dist_dep_dielectric = true;
if (parpars.has("dist_dep_dielec"))
{
dist_dep_dielectric = parpars.get("dist_dep_dielec").toBool();
if (amber_force_field)
{
amber_force_field->options[AmberFF::Option::DISTANCE_DEPENDENT_DIELECTRIC] = dist_dep_dielectric;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::DISTANCE_DEPENDENT_DIELECTRIC] = dist_dep_dielectric;
}
}
Log << " distance dependent dielectric constant " << (dist_dep_dielectric ? "on" : "off") << std::endl;
// we handle ASSIGN_TYPES and ASSIGN_TYPENAMES together
bool assign_types = true;
if (parpars.has("assign_types"))
{
assign_types = parpars.get("assign_types").toBool();
if (amber_force_field)
{
amber_force_field->options[AmberFF::Option::ASSIGN_TYPENAMES] = assign_types;
amber_force_field->options[AmberFF::Option::ASSIGN_TYPES] = assign_types;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::ASSIGN_TYPENAMES] = assign_types;
mmff_force_field->options[MMFF94::Option::ASSIGN_TYPES] = assign_types;
}
}
Log << " assignment of missing types " << (assign_types ? "on" : "off") << std::endl;
bool overwrite_types = true;
if (parpars.has("overwrite_types"))
{
overwrite_types = parpars.get("overwrite_types").toBool();
if (amber_force_field)
{
amber_force_field->options[AmberFF::Option::OVERWRITE_TYPENAMES] = overwrite_types;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::OVERWRITE_TYPENAMES] = overwrite_types;
}
}
Log << " overwrite types " << (overwrite_types ? "on" : "off") << std::endl;
bool assign_charges = true;
if (parpars.has("assign_charges"))
{
assign_charges = parpars.get("assign_charges").toBool();
if (amber_force_field)
{
amber_force_field->options[AmberFF::Option::ASSIGN_CHARGES] = assign_charges;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::ASSIGN_CHARGES] = assign_charges;
}
}
Log << " assignment of missing charges " << (assign_charges ? "on" : "off") << std::endl;
bool overwrite_charges = true;
if (parpars.has("overwrite_charges"))
{
overwrite_charges = parpars.get("overwrite_charges").toBool();
if (amber_force_field)
{
amber_force_field->options[AmberFF::Option::OVERWRITE_CHARGES] = overwrite_charges;
}
else if (mmff_force_field)
{
mmff_force_field->options[MMFF94::Option::OVERWRITE_CHARGES] = overwrite_charges;
}
}
Log << " overwrite charges " << (overwrite_charges ? "on" : "off") << std::endl;
// setup the force field
Log.info() << " setting up the force field..." << endl;
force_field->setup(sys);
// setup successful?
if ( (force_field->getUnassignedAtoms().size() > 0)
|| !force_field->isValid())
{
Log.error() << "There are parameterless atoms in the structure. Use the ResidueChecker tool for further investigation." << std::endl;
exit(2);
}
// trigger the energy computations
force_field->updateEnergy();
// print the result
Log.info() << force_field->getResults() << endl;
return 0;
}
int main(int argc, char** argv)
{
CommandlineParser parpars("PoseIndices2PDB", "converts pose indices into PDB files ", VERSION, String(__DATE__), "Convert, combine and store");
parpars.registerMandatoryInputFile("i_clust", "input cluster index file");
parpars.registerMandatoryInputFile("i_trans", "input tranformation file");
parpars.registerMandatoryInputFile("i_pdb", "input reference pdb file");
parpars.registerMandatoryOutputFile("o", "output file name prefix for resulting pdb files");
parpars.setParameterAsHidden("o");
// parameters for galaxy for handling multiple output files
parpars.registerOptionalGalaxyOutputId("o_id", "output file name prefix for 2nd to last pdb file", "$o.id");
// need to be hidden in command line mode
parpars.setParameterAsHidden("o_id");
parpars.setParameterAsAdvanced("o_id");
// parameters for galaxy for handling multiple output files
parpars.registerOptionalGalaxyOutputFolder("o_dir", "output directory for 2nd to last pdb file", "$__new_file_path__");
// need to be hidden in command line mode
parpars.setParameterAsHidden("o_dir");
parpars.setParameterAsAdvanced("o_dir");
// the manual
String man = "This tool converts all pose indices from a given transformation file and the corresponding reference PDBFile into separate PDBFiles.\n\nParameters are the input pose index file (-i_clust), the original transformation file (-i_trans), the corresponding reference pdb file (-i_pdb) and a naming schema for the resulting pdb files (-o). \n\nOutput of this tool is a set of PDBFiles representing the docking poses belonging to the given input cluster.";
parpars.setToolManual(man);
// here we set the types of I/O files
parpars.setSupportedFormats("i_clust","txt");
parpars.setSupportedFormats("i_trans","dcd");
parpars.setSupportedFormats("i_pdb","pdb");
parpars.setSupportedFormats("o","pdb");
parpars.parse(argc, argv);
//////////////////////////////////////////////////
// read the input
PDBFile pdb;
pdb.open(parpars.get("i_pdb"));
System sys;
pdb.read(sys);
PoseClustering pc;
if (parpars.has("i_trans"))
{
pc.options.set(PoseClustering::Option::RMSD_TYPE, PoseClustering::RIGID_RMSD);
pc.setBaseSystemAndTransformations(sys, parpars.get("i_trans"));
}
//std::vector< std::set<Index> > clusters;
LineBasedFile file(parpars.get("i_clust"), std::ios::in);
vector<String> fields;
String cluster_id = -1;
String pose_id = -1;
// called as command line or e.g. via galaxy?
bool is_cmd = !parpars.has("env")
|| ((parpars.has("env") && parpars.get("env")=="cmdline"));
bool first_sol = true;
while (file.LineBasedFile::readLine())
{
// get the line
String current_cluster = file.getLine();
if (current_cluster.getField(1) == "cluster")
{
cluster_id = current_cluster.getField(2);
pose_id = -1;
if (file.LineBasedFile::readLine())
{
current_cluster = file.getLine();
fields.clear();
current_cluster.split(fields);
for (Size i=0; i < fields.size(); i++)
{
System new_pose_sys(sys);
pose_id = fields[i];
pc.applyTransformation2System(pose_id.toInt(), new_pose_sys);
// create the output name
String outfile_name = String(parpars.get("o"))
+ "_clust_" + cluster_id
+ "_pose_" + String(pose_id) + ".pdb";
if (parpars.has("o_dir") && is_cmd && (parpars.get("o_dir") != "$__new_file_path__"))
{
outfile_name = String(parpars.get("o_dir")) + "/" + outfile_name;
}
// NOTE: Galaxy requires this strange naming convention
// including the fact, that zero-th element has a different name
if (!is_cmd)
{
outfile_name = (first_sol) ? String(parpars.get("o"))
: String(parpars.get("o_dir")) + "/primary_"
+ String(parpars.get("o_id")) + "_clust_" + cluster_id
+ "_pose_" + String(pose_id)
+ "_visible_pdb";
}
PDBFile file(outfile_name, ios::out);
if (file.bad())
{
Log.error() << "cannot write file " << outfile_name << endl;
return 2;
}
file << new_pose_sys;
file.close();
// needed for galaxy output
if (first_sol)
first_sol = false;
Log << "wrote file " << outfile_name << endl;
}
}
}
}
Log << "done." << endl;
return 0;
}
