Library routines to read and write molecule file, including sequences and coordinates. More...

#include "rwmolecule.h"
#include "rwatomprop.h"
#include "mol_transform.h"
#include "mol_util.h"
#include "seq_util.h"
#include "linked_list.h"
#include "utilities.h"
#include "rwmol_star.h"
#include "rwmol_text.h"
#include "rwClustal.h"
#include "rwEMBL.h"
#include "rwFASTA.h"
#include "rwGenBank.h"
#include "rwGROMACS.h"
#include "rwPDB.h"
#include "rwPhylip.h"
#include "rwPIR.h"
#include "rwWAH.h"

Functions
int	molgroup_sequence_check (Bmolgroup *molgroup)

Bmolgroup *	molgroup_init ()
	Initializes and allocates a new molecule group. More...

Bmolecule *	molecule_add (Bmolecule *mol, char name)
	Adds a molecule to a linked list. More...

Bmolecule *	molecule_add (Bmolecule **mol, Bstring &name)

Bresidue *	residue_add (Bresidue *res, const char type)
	Adds a residue to a linked list. More...

Bresidue *	residue_add (Bresidue **res, Bstring &type)

Batom *	atom_add (Batom *atom, const char type)
	Adds an atom to a linked list. More...

Batom *	atom_add (Batom **atom, Bstring &type)

Batom *	atom_copy (Batom *atom)

long	residue_count (Bmolgroup *molgroup)
	Counts the number of residues in a molecule group. More...

long	atom_count (Bmolgroup *molgroup)
	Counts the number of atoms in a molecule group. More...

int	atom_clean_type (Batom atom, const char type)
	Cleans up the type string and assigns an element code to an atom. More...

Bbond *	bond_add (Bbond *bond, Batom atom1, Batom *atom2, double l, double k)
	Adds a bond to a linked list. More...

Bangle *	angle_add (Bangle *angle, Batom atom1, Batom atom2, Batom atom3, double a, double k)
	Adds an angle to a linked list. More...

int	molgroup_list_kill (Bmolgroup *molgroup)
	Destroys a molecule group linked list. More...

int	molgroup_kill (Bmolgroup *molgroup)
	Destroys a molecule group. More...

int	molecule_kill (Bmolecule *mol)
	Destroys a molecule. More...

int	residue_kill (Bresidue *res)
	Destroys a residue. More...

int	bond_kill (Bbond *bond)
	Dealocates a list of bonds. More...

int	angle_kill (Bangle *angle)
	Dealocates a list of angles. More...

Bmolgroup *	molgroup_list_copy (Bmolgroup *molgroup)
	Copies a molecule group list. More...

Bmolgroup *	molgroup_copy (Bmolgroup *molgroup)
	Copies a molecule group. More...

Bmolecule *	molecule_copy (Bmolecule *mol)
	Copies a molecule. More...

Bmolecule *	mol_copy_and_add_to_molgroup (Bmolgroup molgroup, Bmolecule mol)
	Copies a molecule and assign to a new pointer in the molgroup. More...

Bbond *	molgroup_bond_list_copy (Bmolgroup molgroup, Bmolgroup molgroupcopy)
	Copies a bond list. More...

int	molgroup_from_molgroup_list (Bmolgroup *molgroup)
	Converts a molecule group list to a single molecule group. More...

Bmolgroup *	read_molecule (const char filename, const char atom_select, const char *paramfile)
	The generalized function for reading molecular files. More...

Bmolgroup *	read_molecule (Bstring &filename, Bstring &atom_select, Bstring &paramfile)

Bmolgroup *	read_molecule (Bstring *file_list, int set_pbc, Vector3< double > box, Bstring atom_select, Bstring paramfile)
	Reads and catenates multiple molecule files. More...

int	write_molecule (char filename, Bmolgroup molgroup)
	Writes a molecule group. More...

int	write_molecule (Bstring &filename, Bmolgroup *molgroup)

int	molgroup_list_write (Bstring &filename, Bmolgroup *molgroup)
	Writes a molecule group list. More...

long	molgroup_count_molecules (Bmolgroup *molgroup)
	Counts the total number of molecules in a molecule group. More...

long	molgroup_count_residues (Bmolgroup *molgroup)
	Counts the total number of residues in a molecule group. More...

long	mol_count_residues (Bmolecule *mol)
	Counts the total number of residues in a molecule. More...

long	molgroup_count_atoms (Bmolgroup *molgroup)
	Counts the total number of atoms in a molecule group. More...

long	mol_count_atoms (Bmolecule *mol)
	Counts the total number of atoms in a molecule. More...

int	molgroup_consolidate_gaps (Bmolgroup *molgroup)
	Removes redundant gaps from an alignment. More...

long	molgroup_stats (Bmolgroup *molgroup, int show)
	Calculates the statistics of a molecule group. More...

long	molgroup_stats (Bmolgroup *molgroup)

long	mol_stats (Bmolecule *mol, int show)
	Calculates the statistics of a molecule. More...

long	mol_stats (Bmolecule *mol)

int	molecule_update_comment (Bmolgroup molgroup, int n, char *strings)
	Puts a set of strings and time in the main comment of a molecule group. More...

int	molecule_get_masses (Bmolgroup *molgroup, Bstring &paramfile)
	Gets atomic masses from a parameter file. More...

int	bond_exists (Bbond bondlist, Batom atom1, Batom *atom2)

Bbond *	molgroup_bond_list_generate (Bmolgroup *molgroup, double maxlength, int wrap)
	Generates a bond list based on atom separation. More...

Bbond *	mol_bond_list_generate (Bmolgroup *molgroup, double bondlength, int wrap)
	Generates an intramolecular distance-based bond list. More...

int	molecules_to_molgroups (Bmolgroup *molgroup)
	Converts molecules in a molecule group to individual molecule groups. More...

Variables
int	verbose

Detailed Description

Library routines to read and write molecule file, including sequences and coordinates.

Author: Bernard Heymann

Date: Created: 19980822; Modified: 20220427

Function Documentation

◆ angle_add()

Bangle * angle_add	(	Bangle **	angle,
		Batom *	atom1,
		Batom *	atom2,
		Batom *	atom3,
		double	a,
		double	k
	)

Adds an angle to a linked list.

Parameters

**angle	pointer to any angle in the list.
*atom1	atom1 of angle.
*atom2	atom2 of angle (central atom).
*atom3	atom3 of angle.
a	reference angle.
k	angle strength.

Returns

Bangle* new angle.

The function allocates memory for a new angle structure.
If the content of the pointer is null, the new structure is
the first in the list. Otherwise, the end of the list is found
and the new structure added to it.

◆ angle_kill()

int angle_kill ( Bangle * angle )

Dealocates a list of angles.

Parameters

*angle first angle in the list.

Returns

int 0.

All angles downstream are deallocated.

◆ atom_add() [1/2]

Batom * atom_add	(	Batom **	atom,
		Bstring &	type
	)

◆ atom_add() [2/2]

Batom * atom_add	(	Batom **	atom,
		const char *	type
	)

Adds an atom to a linked list.

Parameters

**atom	pointer to any atom in the list.
*type	atom type.

Returns

Batom* new atom.

The function allocates memory for a new atom structure.
If the content of the pointer is null, the new structure is
the first in the list. Otherwise, the end of the list is found
and the new structure added to it.

◆ atom_clean_type()

int atom_clean_type	(	Batom *	atom,
		const char *	type
	)

Cleans up the type string and assigns an element code to an atom.

Parameters

*atom	atom.
*type	atom type.

Returns

int 0.

The first two alphanumeric characters of the type string is used to
determine the element.

◆ atom_copy()

Batom * atom_copy ( Batom * atom )

◆ atom_count()

long atom_count ( Bmolgroup * molgroup )

Counts the number of atoms in a molecule group.

Parameters

*molgroup the molecule group.

Returns: long number of atoms.

◆ bond_add()

Bbond * bond_add	(	Bbond **	bond,
		Batom *	atom1,
		Batom *	atom2,
		double	l,
		double	k
	)

Adds a bond to a linked list.

Parameters

**bond	pointer to any bond in the list.
*atom1	atom1 of bond.
*atom2	atom2 of bond.
l	reference bond length.
k	bond strength.

Returns

Bbond* new bond.

The function allocates memory for a new bond structure.
If the content of the pointer is null, the new structure is
the first in the list. Otherwise, the end of the list is found
and the new structure added to it.

◆ bond_exists()

int bond_exists	(	Bbond *	bondlist,
		Batom *	atom1,
		Batom *	atom2
	)

◆ bond_kill()

int bond_kill ( Bbond * bond )

Dealocates a list of bonds.

Parameters

*bond first bond in the list.

Returns

int 0.

All bonds downstream are deallocated.

◆ mol_bond_list_generate()

Bbond * mol_bond_list_generate	(	Bmolgroup *	molgroup,
		double	bondlength,
		int	wrap
	)

Generates an intramolecular distance-based bond list.

This function defines bonds on distance and within molecules.
If the molecule group already has a bond list, no new bonds are generated.

Parameters

*molgroup	molecule group structure.
bondlength	maximum bond length.
wrap	wrap around periodic boundaries if !=0.

Returns: Bbond* new bond list.

◆ mol_copy_and_add_to_molgroup()

Bmolecule * mol_copy_and_add_to_molgroup	(	Bmolgroup *	molgroup,
		Bmolecule *	mol
	)

Copies a molecule and assign to a new pointer in the molgroup.

Parameters

*molgroup	the molecule group.
*mol	the molecule to be copied.

Returns

Bmolecule* the new molecule, NULL if copy failed.

Adds a new molecule to the molecule group identical to the given
molecule and returns a pointer to the new molecule.

◆ mol_count_atoms()

long mol_count_atoms ( Bmolecule * mol )

Counts the total number of atoms in a molecule.

Parameters

*mol	the molecule.

Returns: long number of atoms.

◆ mol_count_residues()

long mol_count_residues ( Bmolecule * mol )

Counts the total number of residues in a molecule.

Parameters

*mol	the molecule.

Returns: long number of residues.

◆ mol_stats() [1/2]

long mol_stats ( Bmolecule * mol )

◆ mol_stats() [2/2]

long mol_stats	(	Bmolecule *	mol,
		int	show
	)

Calculates the statistics of a molecule.

Parameters

*mol	the molecule.
show	flag to show statistics.

Returns: long number of atoms (<0 if writing failed).

◆ molecule_add() [1/2]

Bmolecule * molecule_add	(	Bmolecule **	mol,
		Bstring &	name
	)

◆ molecule_add() [2/2]

Bmolecule * molecule_add	(	Bmolecule **	mol,
		char *	name
	)

Adds a molecule to a linked list.

Parameters

**mol	pointer to any molecule in the list.
*name	molecule name.

Returns

Bmolecule* new molecule.

The function allocates memory for a new molecule structure.
If the content of the pointer is null, the new structure is
the first in the list. Otherwise, the end of the list is found
and the new structure added to it.

◆ molecule_copy()

Bmolecule * molecule_copy ( Bmolecule * mol )

Copies a molecule.

Parameters

*mol	the molecule to be copied.

Returns

Bmolecule* the new molecule, NULL if copy failed.

Generates a new molecule with the same structure as the given molecule.

◆ molecule_get_masses()

int molecule_get_masses	(	Bmolgroup *	molgroup,
		Bstring &	paramfile
	)

Gets atomic masses from a parameter file.

Parameters

*molgroup	the molecule group.
&paramfile	parameter file name.

Returns: int 0.

◆ molecule_kill()

int molecule_kill ( Bmolecule * mol )

Destroys a molecule.

Parameters

*mol	the molecule.

Returns: int 0.

◆ molecule_update_comment()

int molecule_update_comment	(	Bmolgroup *	molgroup,
		int	n,
		char **	strings
	)

Puts a set of strings and time in the main comment of a molecule group.

This is designed to pack the command line into a string followed by
a second string for the time.

Parameters

*molgroup	the molecule group.
n	the number of strings.
**strings	an array of strings.

Returns: int string length of the new comment.

◆ molecules_to_molgroups()

int molecules_to_molgroups ( Bmolgroup * molgroup )

Converts molecules in a molecule group to individual molecule groups.

A new linked list of molecule groups is created and the links to the
individual molecules set.

Parameters

*molgroup molecule group structure (modified).

Returns: int 0.

◆ molgroup_bond_list_copy()

Bbond * molgroup_bond_list_copy	(	Bmolgroup *	molgroup,
		Bmolgroup *	molgroupcopy
	)

Copies a bond list.

Parameters

*molgroup	molecule group structure.
*molgroupcopy	molecule group structure to copy bonds to.

Returns

Bbond* new bond list.

A copy of the molecule group bond list is generated and returned.

◆ molgroup_bond_list_generate()

Bbond * molgroup_bond_list_generate	(	Bmolgroup *	molgroup,
		double	maxlength,
		int	wrap
	)

Generates a bond list based on atom separation.

Parameters

*molgroup	the molecule group.
maxlength	maximum bond length.
wrap	wrap around periodic boundaries if !=0.

Returns: Bbond* new bond list.

◆ molgroup_consolidate_gaps()

int molgroup_consolidate_gaps ( Bmolgroup * molgroup )

Removes redundant gaps from an alignment.

All positions in an alignment with only gaps are removed.

Parameters

*molgroup the molecule group.

Returns: int 0.

◆ molgroup_copy()

Bmolgroup * molgroup_copy ( Bmolgroup * molgroup )

Copies a molecule group.

Parameters

*molgroup the molecule group.

Returns

Bmolgroup* new molecule group.

All parts of a molecule group are copied to a completely new structure
hierarchy, except sequence flag array.

◆ molgroup_count_atoms()

long molgroup_count_atoms ( Bmolgroup * molgroup )

Counts the total number of atoms in a molecule group.

Parameters

*molgroup the molecule group.

Returns: long number of atoms.

◆ molgroup_count_molecules()

long molgroup_count_molecules ( Bmolgroup * molgroup )

Counts the total number of molecules in a molecule group.

Parameters

*molgroup the molecule group.

Returns: long number of molecules.

◆ molgroup_count_residues()

long molgroup_count_residues ( Bmolgroup * molgroup )

Counts the total number of residues in a molecule group.

Parameters

*molgroup the molecule group.

Returns: long number of residues.

◆ molgroup_from_molgroup_list()

int molgroup_from_molgroup_list ( Bmolgroup * molgroup )

Converts a molecule group list to a single molecule group.

Parameters

*molgroup molecule group list.

Returns

int 0.

The input molecule group list is replace by a single molecule group.

◆ molgroup_init()

Bmolgroup * molgroup_init ( )

Initializes and allocates a new molecule group.

Returns

Bmolgroup* the new molecule group, NULL if initialization failed.

The selection string is set to "all".
The spacegroup is set to 1, the space group string to "P 1".
The point group is set to "C1".
The unit cell is set to 1,1,1,90,90,90.

◆ molgroup_kill()

int molgroup_kill ( Bmolgroup * molgroup )

Destroys a molecule group.

Parameters

*molgroup the molecule group.

Returns: int 0.

◆ molgroup_list_copy()

Bmolgroup * molgroup_list_copy ( Bmolgroup * molgroup )

Copies a molecule group list.

Parameters

*molgroup the molecule group list.

Returns

Bmolgroup* new molecule group list.

All molecule groups are copied to a completely new list.

◆ molgroup_list_kill()

int molgroup_list_kill ( Bmolgroup * molgroup )

Destroys a molecule group linked list.

Parameters

*molgroup the molecule group linked list.

Returns: int 0.

◆ molgroup_list_write()

int molgroup_list_write	(	Bstring &	filename,
		Bmolgroup *	molgroup
	)

Writes a molecule group list.

The output files are numbered if the list constains more than one molecule group.

Parameters

*filename	the file name.
*molgroup	the molecule group.

Returns: int number of molecules written (<0 if writing failed).

◆ molgroup_sequence_check()

int molgroup_sequence_check ( Bmolgroup * molgroup )

◆ molgroup_stats() [1/2]

long molgroup_stats ( Bmolgroup * molgroup )

◆ molgroup_stats() [2/2]

long molgroup_stats	(	Bmolgroup *	molgroup,
		int	show
	)

Calculates the statistics of a molecule group.

Parameters

*molgroup	molecule group.
show	flag to show statistics.

Returns: long number of molecules (<0 if writing failed).

◆ read_molecule() [1/3]

Bmolgroup * read_molecule	(	Bstring &	filename,
		Bstring &	atom_select,
		Bstring &	paramfile
	)

◆ read_molecule() [2/3]

Bmolgroup * read_molecule	(	Bstring *	file_list,
		int	set_pbc,
		Vector3< double >	box,
		Bstring	atom_select,
		Bstring	paramfile
	)

Reads and catenates multiple molecule files.

Parameters

file_list	list of file names.
set_pbc	flag to fit within periodic boundaries.
box	periodic boundary box.
atom_select	atomic selection.
paramfile	atomic parameters.

Returns: Bmolgroup* new molecule group.

◆ read_molecule() [3/3]

Bmolgroup * read_molecule	(	const char *	filename,
		const char *	atom_select,
		const char *	paramfile
	)

The generalized function for reading molecular files.

Parameters

*filename	the file name.
*atom_select	a selection string.
*paramfile	parameter file name.

Returns

Bmolgroup* new molecule group, NULL if reading failed.

All sequence and atomic coordinate information is read from a file into
an internal hierarchy of structures in linked lists:
    Bmolgroup   molecule group or collection of molecules
    Bmolecule   linked list of molecules in the group
    Bresidue    linked list of residues in a molecule
    Batom       linked list of atoms in a residue
    Bbond       linked list of bonds in the molecule group
The selection string is used to select for specific atom types:
    CA          C-alpha atoms only
The parameter file is used to load atomic properties, such as mass
    and charge. The default file is bsoft/parameters/atom_prop.star.
The input format is based on the file name extension.

◆ residue_add() [1/2]

Bresidue * residue_add	(	Bresidue **	res,
		Bstring &	type
	)

◆ residue_add() [2/2]

Bresidue * residue_add	(	Bresidue **	res,
		const char *	type
	)

Adds a residue to a linked list.

Parameters

**res	pointer to any residue in the list.
*type	residue type.

Returns

Bresidue* new residue.

The function allocates memory for a new residue structure.
If the content of the pointer is null, the new structure is
the first in the list. Otherwise, the end of the list is found
and the new structure added to it.

◆ residue_count()

long residue_count ( Bmolgroup * molgroup )

Counts the number of residues in a molecule group.

Parameters

*molgroup the molecule group.

Returns: long number of residues.

◆ residue_kill()

int residue_kill ( Bresidue * res )

Destroys a residue.

Parameters

*res	the residue.

Returns: int 0.

◆ write_molecule() [1/2]

int write_molecule	(	Bstring &	filename,
		Bmolgroup *	molgroup
	)

◆ write_molecule() [2/2]

int write_molecule	(	char *	filename,
		Bmolgroup *	molgroup
	)

Writes a molecule group.

The output format is based on the file name extension.

Parameters

*filename	the file name.
*molgroup	the molecule group.

Returns: int number of molecules written (<0 if writing failed).

Variable Documentation

◆ verbose

int verbose

extern

Functions

Variables

Detailed Description

Function Documentation

◆ angle_add()

◆ angle_kill()

◆ atom_add() [1/2]

◆ atom_add() [2/2]

◆ atom_clean_type()

◆ atom_copy()

◆ atom_count()

◆ bond_add()

◆ bond_exists()

◆ bond_kill()

◆ mol_bond_list_generate()

◆ mol_copy_and_add_to_molgroup()

◆ mol_count_atoms()

◆ mol_count_residues()

◆ mol_stats() [1/2]

◆ mol_stats() [2/2]

◆ molecule_add() [1/2]

◆ molecule_add() [2/2]

◆ molecule_copy()

◆ molecule_get_masses()

◆ molecule_kill()

◆ molecule_update_comment()

◆ molecules_to_molgroups()

◆ molgroup_bond_list_copy()

◆ molgroup_bond_list_generate()

◆ molgroup_consolidate_gaps()

◆ molgroup_copy()

◆ molgroup_count_atoms()

◆ molgroup_count_molecules()

◆ molgroup_count_residues()

◆ molgroup_from_molgroup_list()

◆ molgroup_init()

◆ molgroup_kill()

◆ molgroup_list_copy()

◆ molgroup_list_kill()

◆ molgroup_list_write()

◆ molgroup_sequence_check()

◆ molgroup_stats() [1/2]

◆ molgroup_stats() [2/2]

◆ read_molecule() [1/3]

◆ read_molecule() [2/3]

◆ read_molecule() [3/3]

◆ residue_add() [1/2]

◆ residue_add() [2/2]

◆ residue_count()

◆ residue_kill()

◆ write_molecule() [1/2]

◆ write_molecule() [2/2]

Variable Documentation

◆ verbose