IMP::multifit Namespace Reference

See IMP.multifit Overview for more information.

Classes
class	AssemblyHeader
	Holds data about the assembly density needed for optimization. More...
class	ComplementarityRestraint
	Compute the complementarity between two molecules. More...
class	ComponentHeader
	Holds data about a component needed for optimization. More...
class	DataPointsAssignment
class	DensityDataPoints
	Stores density voxels as a vector of Array1D. More...
class	FittingSolutionRecord
	A fitting solution record. More...
class	FittingStates
class	ProteinsAnchorsSamplingSpace
	stores the anchors sampling space for each protein More...
class	RadiusOfGyrationRestraint
	Ensure the radius of gyration of particles fits the predicted one. More...
class	RMSDClustering
	RMSD clustering. More...
class	SettingsData
	Holds header data for optimization. More...
class	WeightedExcludedVolumeRestraint
	Calculate score based on fit to EM map. More...

Typedefs
typedef IMP::base::Vector < AlignmentParams >	AlignmentParamsList
typedef IMP::base::Vector < AnchorsData >	AnchorsDataList
typedef std::map< IntPair, int >	CEdges
typedef IMP::base::Vector < ComplementarityParams >	ComplementarityParamsList
typedef IMP::base::Vector < IMP::base::Pointer < ComponentHeader > >	ComponentHeaders
typedef IMP::base::Vector < ConnectivityParams >	ConnectivityParamsList
typedef IMP::algebra::DenseGrid3D < double >	DensGrid
typedef IMP::base::Vector < IMP::base::Pointer < DensityDataPoints > >	DensityDataPointsList
typedef IMP::base::Vector < DominoParams >	DominoParamsList
typedef IMP::base::Vector < IMP::base::Pointer< Ensemble > >	Ensembles
typedef IMP::base::Vector < EVParams >	EVParamsList
typedef IMP::base::Vector < FiltersParams >	FiltersParamsList
typedef IMP::base::Vector < FittingParams >	FittingParamsList
typedef IMP::base::Vector < FittingSolutionRecord >	FittingSolutionRecords
typedef IMP::base::Vector < FragmentsParams >	FragmentsParamsList
typedef IMP::base::Vector < IMP::base::Pointer < ProbabilisticAnchorGraph > >	ProbabilisticAnchorGraphs
typedef IMP::base::Vector < ProteinRecordData >	ProteinRecordDataList
typedef IMP::base::Vector < ProteinsAnchorsSamplingSpace >	ProteinsAnchorsSamplingSpaces
typedef IMP::base::Vector < IMP::base::Pointer < ProteomicsEMAlignmentAtomic > >	ProteomicsEMAlignmentAtomics
typedef IMP::base::Vector < RogParams >	RogParamsList
typedef IMP::base::Vector < IMP::base::Pointer < TransformationClustering > >	TransformationClusterings
typedef IMP::base::Vector < XlinkParams >	XlinkParamsList

Functions
void	add_surface_index (core::Hierarchy mhd, Float apix, FloatKey shell_key=FloatKey("surf_ind"), FloatKey radius_key=core::XYZR::get_radius_key(), FloatKey weight_key=atom::Mass::get_mass_key())
	add shell index to leaves More...
FittingSolutionRecords	convert_em_to_multifit_format (const em::FittingSolutions &em_fits)
algebra::Transformation3Ds	convert_multifit_format_to_transformations (const FittingSolutionRecords &recs)
em::FittingSolutions	convert_multifit_to_em_format (const FittingSolutionRecords &multifit_fits)
FittingSolutionRecords	convert_transformations_to_multifit_format (const algebra::Transformation3Ds &trans)
atom::Hierarchy	create_coarse_molecule_from_density (em::DensityMap *dmap, float dens_threshold, int num_beads, Model *mdl, float bead_radius)
	Coarsen a density map based on voxels clustering. More...
atom::Hierarchy	create_coarse_molecule_from_molecule (const atom::Hierarchy &mh, int num_beads, Model *mdl, float bead_radius, bool add_conn_restraint=false)
	Coarsen a molecule based on atom clustering. More...
atom::Hierarchies	create_coarse_molecules_from_molecules (const atom::Hierarchies &mhs, int frag_len, Model *mdl, float bead_radius, bool add_conn_restraint=false)
	Coarsen molecules based on atom clustering. More...
em::DensityMap *	create_hit_map (core::RigidBody rb, Refiner *rb_ref, const FittingSolutionRecords &sols, em::DensityMap *damp)
IMP::Restraint *	create_weighted_excluded_volume_restraint (core::RigidBody rb1, core::RigidBody rb2, FloatKey shell_key=FloatKey("surf_ind"))
	create a weighted excluded volume restraint between two rigid bodies More...
multifit::FittingSolutionRecords	fft_based_rigid_fitting (atom::Hierarchy mol2fit, em::DensityMap *dmap, double density_threshold, double angle_sampling_interval_rad)
	FFT fit of a molecule in the density. More...
em::FittingSolutions	fitting_clustering (const atom::Hierarchy &mh, const em::FittingSolutions &ts, float spacing, int top_sols, float rmsd)
float	get_actual_radius_of_gyration (ParticlesTemp ps)
IntsList	get_anchor_indices_matching_secondary_structure (const AnchorsData &ad, const atom::SecondaryStructureResidues &ssrs, Float max_rmsd=0.7)
	Get lists of anchors that match a sequence of secondary structures. More...
void	get_anchors_for_density (em::DensityMap *dmap, int number_of_means, float density_threshold, std::string pdb_filename, std::string cmm_filename, std::string seg_filename, std::string txt_filename)
	Generate anchors in several formats for a given density map.
float	get_approximated_radius (int len)
float	get_approximated_radius_of_gyration (int len)
FittingSolutionRecords	get_close_to_point (const FittingSolutionRecords &fit_sols, atom::Hierarchy mh, IMP::Particle *ap, Float dist)
	prune solutions by distance to an anchor point More...
IntsList	get_clustered (Particles ps, const algebra::Transformation3Ds &trans, float max_rmsd, float max_angle_diff_in_rad, float max_displace, int min_cluster_size)
	Cluster transformations. More...
IntsList	get_connected_components (em::DensityMap *dmap, float threshold, float edge_threshold)
	Return connected components based on density values. More...
std::string	get_data_path (std::string file_name)
	Return the full path to installed data. More...
statistics::Histogram	get_density_histogram (const em::DensityMap *dmap, float threshold, int num_bins)
	Get a histogram of density values.
std::string	get_example_path (std::string file_name)
	Return the path to installed example data for this module. More...
ProteinsAnchorsSamplingSpace	get_part_of_sampling_space (const ProteinsAnchorsSamplingSpace &prots_ss, const Strings &prot_names)
	Get the sampling space of few of the proteins.
multifit::SettingsData *	get_partial_assembly_setting_data (multifit::SettingsData *prots_sd, const Strings &prot_names)
	Get the assembly data for a few of the proteins.
ProteomicsData *	get_partial_proteomics_data (const ProteomicsData *pd, const Strings &prot_names)
algebra::Vector3Ds	get_points_close_to_molecule (const atom::Hierarchy &mh, const algebra::Vector3Ds points, Float max_dist)
algebra::Vector3Ds	get_points_far_from_molecule (const atom::Hierarchy &mh, const algebra::Vector3Ds points, Float max_dist)
algebra::Vector3D	get_segment_maximum (const DataPointsAssignment &dpa, em::DensityMap *dmap, int segment_id)
algebra::Vector3D	get_segment_maximum (const DataPointsAssignment &dpa, DensGrid *dmap, int segment_id)
em::DensityMap *	grid2map (const DensGrid &dg, float spacing)
Ensemble *	load_ensemble (multifit::SettingsData *sd, Model *mdl, const ProteinsAnchorsSamplingSpace &mapping_data)
AnchorsData	molecule2anchors (atom::Hierarchy mh, int k)
em::FittingSolutions	pca_based_rigid_fitting (core::RigidBody rb, Refiner *rb_refiner, em::DensityMap *em_map, Float threshold, FloatKey wei_key=atom::Mass::get_mass_key(), algebra::PrincipalComponentAnalysis dens_pca_input=algebra::PrincipalComponentAnalysis())
	Compute fitting scores for a given set of rigid transformations. More...
em::FittingSolutions	pca_based_rigid_fitting (ParticlesTemp ps, em::DensityMap *em_map, Float threshold, FloatKey wei_key=atom::Mass::get_mass_key(), algebra::PrincipalComponentAnalysis dens_pca_input=algebra::PrincipalComponentAnalysis())
	Compute fitting scores for a given set of rigid transformations. More...
AnchorsData	read_anchors_data (const char *txt_filename)
std::pair< algebra::Vector3Ds, CEdges >	read_cmm (const std::string &cmm_filename)
FittingSolutionRecords	read_fitting_solutions (const char *fitting_fn)
	Fitting solutions reader. More...
IntsList	read_paths (const char *txt_filename, int max_paths=INT_MAX)
	Read paths. More...
ProteinsAnchorsSamplingSpace	read_protein_anchors_mapping (multifit::ProteomicsData *prots, const std::string &anchors_prot_map_fn, int max_paths=INT_MAX)
ProteomicsData *	read_proteomics_data (const char *proteomics_fn)
	Proteomics reader. More...
SettingsData *	read_settings (const char *filename)
em::DensityMap *	remove_background (em::DensityMap *dmap, float threshold, float edge_threshold)
	Returns a map containing all density without the background. More...
void	write_chimera (const std::string &chimera_filename, const DataPointsAssignment &dpa)
void	write_cmm (const std::string &cmm_filename, const std::string &marker_set_name, const AnchorsData &dpa)
void	write_connolly_surface (atom::Atoms as, base::TextOutput fn, float density, float probe_radius)
	Write the Connolly surface for a set of atoms to a file. More...
void	write_fitting_solutions (const char *fitting_fn, const FittingSolutionRecords &fit_sols, int num_sols=-1)
	Write fitting solutions to a file. More...
void	write_markers (const algebra::PrincipalComponentAnalysisD< 3 > &pca, std::ostream &out)
void	write_paths (const IntsList &paths, const std::string &txt_filename)
void	write_pdb (const std::string &pdb_filename, const DataPointsAssignment &dpa)
void	write_protein_anchors_mapping (const std::string &anchors_prot_map_fn, const std::string &anchors_fn, const std::vector< std::pair< String, String > > &prot_paths)
void	write_protein_anchors_mapping (const std::string &anchors_prot_map_fn, const ProteinsAnchorsSamplingSpace &pa, const Strings &prot_names)
void	write_segment_as_mrc (em::DensityMap *dmap, const DataPointsAssignment &dpa, int segment_id, Float resolution, Float apix, const std::string &filename)
void	write_segment_as_pdb (const DataPointsAssignment &dpa, int segment_id, const std::string &filename)
void	write_segments_as_mrc (em::DensityMap *dmap, const DataPointsAssignment &dpa, Float resolution, Float apix, Float threshold, const std::string &filename)
	Write segments in MRC format. More...
void	write_segments_as_pdb (const DataPointsAssignment &dpa, const std::string &filename)
void	write_settings (const char *filename, const SettingsData *sd)
void	write_txt (const std::string &txt_filename, const AnchorsData &ad)

Standard module methods
All IMP modules have a set of standard methods to help get information about the module and about files associated with the module.
std::string	get_module_version ()
std::string	get_module_name ()

Typedef Documentation

typedef IMP::base::Vector< AlignmentParams > IMP::multifit::AlignmentParamsList

Pass or store a set of AlignmentParams .

Definition at line 300 of file AlignmentParams.h.

typedef IMP::base::Vector< AnchorsData > IMP::multifit::AnchorsDataList

Pass or store a set of AnchorsData .

Definition at line 88 of file anchors_reader.h.

typedef IMP::base::Vector< ComplementarityParams > IMP::multifit::ComplementarityParamsList

Pass or store a set of ComplementarityParams .

Definition at line 258 of file AlignmentParams.h.

typedef IMP::base::Vector<IMP::base::Pointer< ComponentHeader > > IMP::multifit::ComponentHeaders

Store a set of objects.

Definition at line 71 of file SettingsData.h.

typedef IMP::base::Vector< ConnectivityParams > IMP::multifit::ConnectivityParamsList

Pass or store a set of ConnectivityParams .

Definition at line 94 of file AlignmentParams.h.

typedef IMP::base::Vector<IMP::base::Pointer< DensityDataPoints > > IMP::multifit::DensityDataPointsList

Store a set of objects.

Definition at line 64 of file DensityDataPoints.h.

typedef IMP::base::Vector< DominoParams > IMP::multifit::DominoParamsList

Pass or store a set of DominoParams .

Definition at line 46 of file AlignmentParams.h.

typedef IMP::base::Vector<IMP::base::Pointer< Ensemble > > IMP::multifit::Ensembles

Store a set of objects.

Definition at line 48 of file ensemble_analysis.h.

typedef IMP::base::Vector< EVParams > IMP::multifit::EVParamsList

Pass or store a set of EVParams .

Definition at line 181 of file AlignmentParams.h.

typedef IMP::base::Vector< FiltersParams > IMP::multifit::FiltersParamsList

Pass or store a set of FiltersParams .

Definition at line 202 of file AlignmentParams.h.

typedef IMP::base::Vector< FittingParams > IMP::multifit::FittingParamsList

Pass or store a set of FittingParams .

Definition at line 227 of file AlignmentParams.h.

typedef IMP::base::Vector< FittingSolutionRecord > IMP::multifit::FittingSolutionRecords

Pass or store a set of FittingSolutionRecord .

Definition at line 80 of file FittingSolutionRecord.h.

typedef IMP::base::Vector< FragmentsParams > IMP::multifit::FragmentsParamsList

Pass or store a set of FragmentsParams .

Definition at line 121 of file AlignmentParams.h.

typedef IMP::base::Vector<IMP::base::Pointer< ProbabilisticAnchorGraph > > IMP::multifit::ProbabilisticAnchorGraphs

Store a set of objects.

Definition at line 67 of file anchor_graph.h.

typedef IMP::base::Vector< ProteinRecordData > IMP::multifit::ProteinRecordDataList

Pass or store a set of ProteinRecordData .

Definition at line 69 of file proteomics_reader.h.

typedef IMP::base::Vector< ProteinsAnchorsSamplingSpace > IMP::multifit::ProteinsAnchorsSamplingSpaces

Pass or store a set of ProteinsAnchorsSamplingSpace .

Definition at line 65 of file protein_anchors_mapping_reader.h.

typedef IMP::base::Vector<IMP::base::Pointer< ProteomicsEMAlignmentAtomic > > IMP::multifit::ProteomicsEMAlignmentAtomics

Store a set of objects.

Definition at line 108 of file proteomics_em_alignment_atomic.h.

typedef IMP::base::Vector< RogParams > IMP::multifit::RogParamsList

Pass or store a set of RogParams .

Definition at line 139 of file AlignmentParams.h.

typedef IMP::base::Vector<IMP::base::Pointer< TransformationClustering > > IMP::multifit::TransformationClusterings

Store a set of objects.

Definition at line 71 of file TransformationClustering.h.

typedef IMP::base::Vector< XlinkParams > IMP::multifit::XlinkParamsList

Pass or store a set of XlinkParams .

Definition at line 71 of file AlignmentParams.h.

Function Documentation

void IMP::multifit::add_surface_index	(	core::Hierarchy	mhd,
		Float	apix,
		FloatKey	shell_key = FloatKey("surf_ind"),
		FloatKey	radius_key = core::XYZR::get_radius_key(),
		FloatKey	weight_key = atom::Mass::get_mass_key()
	)

/param[in] apix sets the resolution of the surface /note we assume that the leaves are xyz particles

atom::Hierarchy IMP::multifit::create_coarse_molecule_from_density	(	em::DensityMap *	dmap,
		float	dens_threshold,
		int	num_beads,
		Model *	mdl,
		float	bead_radius
	)

Parameters

[in]	dmap	the density map to coarsen
[in]	dens_threshold	use only voxels above this threshold for clustering
[in]	num_beads	the number of beads
[in]	mdl	model to add the new molecule to
[in]	bead_radius	bead radius

atom::Hierarchy IMP::multifit::create_coarse_molecule_from_molecule	(	const atom::Hierarchy &	mh,
		int	num_beads,
		Model *	mdl,
		float	bead_radius,
		bool	add_conn_restraint = false
	)

Parameters

[in]	mh	the molecule to coarsen
[in]	num_beads	the output number of beads
[in]	mdl	model to add the new molecule to
[in]	bead_radius	bead radius
[in]	add_conn_restraint	if true a connectivity restraint between the particles of the new molecule is added

atom::Hierarchies IMP::multifit::create_coarse_molecules_from_molecules	(	const atom::Hierarchies &	mhs,
		int	frag_len,
		Model *	mdl,
		float	bead_radius,
		bool	add_conn_restraint = false
	)

Parameters

[in]	mhs	the molecules to coarsen
[in]	frag_len	the number of beads for each molecule will be its number of residues / frag_len
[in]	mdl	model to add the new molecule to
[in]	bead_radius	bead radius
[in]	add_conn_restraint	if true a connectivity restraint between the particles of the new molecule is added

IMP::Restraint* IMP::multifit::create_weighted_excluded_volume_restraint	(	core::RigidBody	rb1,
		core::RigidBody	rb2,
		FloatKey	shell_key = FloatKey("surf_ind")
	)

/param[in] rb1 the first rigid body /param[in] rb2 the second rigid body /param[in] shell_key the attribute that stored the particles surface level with respect to its molecule

multifit::FittingSolutionRecords IMP::multifit::fft_based_rigid_fitting	(	atom::Hierarchy	mol2fit,
		em::DensityMap *	dmap,
		double	density_threshold,
		double	angle_sampling_interval_rad
	)

Parameters

[in]	mol2fit	a rigid body molecule to fit
[in]	dmap	the map to fit into
[in]	angle_sampling_interval_rad	sampling internal in radians

em::FittingSolutions IMP::multifit::fitting_clustering	(	const atom::Hierarchy &	mh,
		const em::FittingSolutions &	ts,
		float	spacing,
		int	top_sols,
		float	rmsd
	)

Parameters

[in]	mh	cluster transformations with respect to this protein
[in]	ts	the transformations with respect to the transformation in the PDB
[in]	spacing	transformations with rmsd < spacing*2 are clustered together
[in]	top_sols	cluster no more than this many top solutions
[in]	rmsd	maximum RMSD between transformations in the same cluster

Returns

the clustered transformations

IntsList IMP::multifit::get_anchor_indices_matching_secondary_structure	(	const AnchorsData &	ad,
		const atom::SecondaryStructureResidues &	ssrs,
		Float	max_rmsd = 0.7
	)

Parameters

[in]	ad	The AnchorsData
[in]	sse_ps	The SecondaryStructureResidue particles to match
[in]	min_correlation	SecondaryStructureResidue match must be below this value (0.816 is rmsd of known SSE to random)

FittingSolutionRecords IMP::multifit::get_close_to_point	(	const FittingSolutionRecords &	fit_sols,
		atom::Hierarchy	mh,
		IMP::Particle *	ap,
		Float	dist
	)

Parameters

[in]	fit_sols	initial fitting solutions
[in]	mh	the molecule the fitting solutions apply for
[in]	ap	anchor point for which the transformed mh (fit) should be close to
[in]	dist	all fits such that the distance between ap and the fit center is smaller than dist will be included

Returns

the pruned fitting solutions

IntsList IMP::multifit::get_clustered	(	Particles	ps,
		const algebra::Transformation3Ds &	trans,
		float	max_rmsd,
		float	max_angle_diff_in_rad,
		float	max_displace,
		int	min_cluster_size
	)

Parameters

[in]	ps	Cluster transformation with respect to these particles
[in]	trans	The transformations to cluster
[in]	max_rmsd	Maximum RMSD between transformations within a cluster
[in]	max_angle_diff_in_rad	maximum angle between rotations in a cluster
[in]	max_displace	maximum translation between transformations within a cluster
[in]	min_cluster_size	prune out clusters of size smaller

Returns

representatives of the clustered transformations

Note

This is one possible protocol for clustering. For flexibility use internal clustering functions directly.

IntsList IMP::multifit::get_connected_components	(	em::DensityMap *	dmap,
		float	threshold,
		float	edge_threshold
	)

Parameters

[in]	dmap	the density map to analyze
[in]	threshold	consider only voxels above this threshold
[in]	edge_threshold	an edge is added between two neighboring voxels if their density difference is below this threshold

Returns

List of indexes for each connected component

std::string IMP::multifit::get_data_path

(

std::string

file_name

)

Each module has its own data directory, so be sure to use the version of this function in the correct module. To read the data file "data_library" that was placed in the data directory of module "mymodule", do something like

std::ifstream in(IMP::mymodule::get_data_path("data_library"));

This will ensure that the code works when IMP is installed or used via the tools/imppy.sh script.

std::string IMP::multifit::get_example_path

(

std::string

file_name

)

Each module has its own example directory, so be sure to use the version of this function in the correct module. For example to read the file example_protein.pdb located in the examples directory of the IMP::atom module, do

IMP::atom::read_pdb(IMP::atom::get_example_path("example_protein.pdb", model));

This will ensure that the code works when IMP is installed or used via the tools/imppy.sh script.

algebra::Vector3Ds IMP::multifit::get_points_close_to_molecule	(	const atom::Hierarchy &	mh,
		const algebra::Vector3Ds	points,
		Float	max_dist
	)

Given a molecule and a set of points, return the indexes of the points that are close to the molecule (up to max_dist) and the res

em::FittingSolutions IMP::multifit::pca_based_rigid_fitting	(	core::RigidBody	rb,
		Refiner *	rb_refiner,
		em::DensityMap *	em_map,
		Float	threshold,
		FloatKey	wei_key = atom::Mass::get_mass_key(),
		algebra::PrincipalComponentAnalysis	dens_pca_input = algebra::PrincipalComponentAnalysis()
	)

Fit a protein to its density by principle component matching

Parameters

[in]	rb	The rigid body to be fitted
[in]	rb_refiner	The rigid body refiner
[in]	em_map	The density map to fit to
[in]	threshold	Use voxels above this threshold for PCA calculations
[in]	wei_key	The weight key of the particles in the rigid body
[in]	dens_pca_input	provide precalculated em_map PCA is available

Returns

fitting solutions

Note

the function assumes the density map holds its density

em::FittingSolutions IMP::multifit::pca_based_rigid_fitting	(	ParticlesTemp	ps,
		em::DensityMap *	em_map,
		Float	threshold,
		FloatKey	wei_key = atom::Mass::get_mass_key(),
		algebra::PrincipalComponentAnalysis	dens_pca_input = algebra::PrincipalComponentAnalysis()
	)

Fit a protein to its density by principle component matching

Parameters

[in]	ps	The particles to fit (treated as rigid)
[in]	em_map	The density map to fit to
[in]	threshold	Use voxels above this threshold for PCA calculations
[in]	wei_key	The weight key of the particles in the rigid body
[in]	dens_pca_input	provide precalculated em_map PCA is available

Returns

fitting solutions

Note

the function assumes the density map holds its density

FittingSolutionRecords IMP::multifit::read_fitting_solutions

(

const char *

fitting_fn

)

IntsList IMP::multifit::read_paths	(	const char *	txt_filename,
		int	max_paths = INT_MAX
	)

Note

Notice that for the function to read the last line it should end with

ProteomicsData* IMP::multifit::read_proteomics_data

(

const char *

proteomics_fn

)

em::DensityMap* IMP::multifit::remove_background	(	em::DensityMap *	dmap,
		float	threshold,
		float	edge_threshold
	)

Parameters

[in]	dmap	the density map to segment
[in]	threshold	consider only voxels above this threshold
[in]	edge_threshold	consider only voxels above this threshold

Returns

the segmented map

void IMP::multifit::write_connolly_surface	(	atom::Atoms	as,
		base::TextOutput	fn,
		float	density,
		float	probe_radius
	)

The algorithm is taken from Connolly's original MS program, which is freely distributable and Copyright 1983, Michael Connolly.

M.L. Connolly, "Solvent-accessible surfaces of proteins and nucleic acids", Science, 221, p709-713 (1983).

M.L. Connolly, "Analytical molecular surface calculation", J. Appl. Cryst. 16, p548-558 (1983).

void IMP::multifit::write_fitting_solutions	(	const char *	fitting_fn,
		const FittingSolutionRecords &	fit_sols,
		int	num_sols = -1
	)

Parameters

[in]	fitting_fn	the fitting filename
[in]	fit_sols	the fitting solutions to write to file
[in]	num_sols	optional, only write the first num_sols fits.

void IMP::multifit::write_segments_as_mrc	(	em::DensityMap *	dmap,
		const DataPointsAssignment &	dpa,
		Float	resolution,
		Float	apix,
		Float	threshold,
		const std::string &	filename
	)

Note

segments are written as filename_0.mrc

an additional file filename.cmd is generated for easy loading of all segments